技术领域Technical Field
本申请涉及移动通信技术领域，尤其涉及一种基于交互关系的用户识别方法、装置及电子设备。The present application relates to the field of mobile communication technology, and in particular to a user identification method, device and electronic device based on interactive relationship.
背景技术Background technique
随着通信技术的发展，移动用户之间的通信交互量激增，同时也为骚扰电话、垃圾短信、诈骗电话等违规行为的治理带来了巨大的挑战。在相关技术中，通过识别用户的可信度来判断违规用户，但是现有的判断用户的可信度的方案的准确度较低，所以难以准确识别违规用户。With the development of communication technology, the communication interaction between mobile users has increased sharply, which also brings great challenges to the governance of illegal behaviors such as harassing calls, spam text messages, fraudulent calls, etc. In related technologies, illegal users are judged by identifying the credibility of users, but the accuracy of existing solutions for judging the credibility of users is low, so it is difficult to accurately identify illegal users.
发明内容Summary of the invention
为了解决上述问题，本申请提供了一种基于交互关系的用户识别方法、装置及电子设备。In order to solve the above problems, the present application provides a user identification method, device and electronic device based on interaction relationship.
根据本申请的第一方面，提供了一种基于交互关系的用户识别方法，其特征在于，包括：获取在预设时间段内的通信交互数据、个人用户的用户信息、与所述个人用户通信交互的企业用户的用户信息；其中，所述通信交互数据包括在所述预设时间段内个人用户之间第一通信交互数据、所述个人用户与所述企业用户之间的第二通信交互数据和所述个人用户与物联网设备之间的第三通信交互数据；根据所述个人用户的用户信息和所述第一通信交互数据，确定所述个人用户的第一可信度信息；根据所述企业用户的用户信息和所述第二通信交互数据，确定所述个人用户的第二可信度信息；基于预设的物联网设备的影响力分值，根据所述第三通信交互数据，确定所述个人用户的第三可信度信息；根据所述第一可信度信息、所述第二可信度信息和所述第三可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。According to a first aspect of the present application, a user identification method based on an interactive relationship is provided, characterized in that it includes: obtaining communication interaction data, user information of personal users, and user information of corporate users who communicate and interact with the personal users within a preset time period; wherein the communication interaction data includes first communication interaction data between personal users within the preset time period, second communication interaction data between the personal user and the corporate user, and third communication interaction data between the personal user and an Internet of Things device; determining first credibility information of the personal user based on the user information of the personal user and the first communication interaction data; determining second credibility information of the personal user based on the user information of the corporate user and the second communication interaction data; determining third credibility information of the personal user based on the third communication interaction data based on an influence score of a preset Internet of Things device; and identifying whether the personal user is a violating user within the preset time period based on the first credibility information, the second credibility information, and the third credibility information.
根据本申请的第二方面，提供了一种基于交互关系的用户识别方法，包括：获取在预设时间段内的通信交互数据、个人用户的用户信息和与所述个人用户通信交互的企业用户的用户信息；其中，所述通信交互数据包括在所述预设时间段内个人用户之间第一通信交互数据，以及所述个人用户与所述企业用户之间的第二通信交互数据；根据所述个人用户的用户信息和所述第一通信交互数据，确定所述个人用户的第一可信度信息；根据所述企业用户的用户信息和所述第二通信交互数据，确定所述个人用户的第二可信度信息；根据所述第一可信度信息和所述第二可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。According to a second aspect of the present application, a user identification method based on interactive relationships is provided, comprising: acquiring communication interaction data within a preset time period, user information of a personal user, and user information of a corporate user who communicates and interacts with the personal user; wherein the communication interaction data comprises first communication interaction data between personal users within the preset time period, and second communication interaction data between the personal user and the corporate user; determining first credibility information of the personal user based on the user information of the personal user and the first communication interaction data; determining second credibility information of the personal user based on the user information of the corporate user and the second communication interaction data; and identifying whether the personal user is a violating user within the preset time period based on the first credibility information and the second credibility information.
根据本申请的第三方面，提供了一种基于交互关系的用户识别方法，包括：获取在预设时间段内的通信交互数据和个人用户的用户信息；其中，所述通信交互数据包括在所述预设时间段内所述个人用户之间第一通信交互数据，以及所述个人用户与物联网设备之间的第三通信交互数据；根据所述个人用户的用户信息和所述第一通信交互数据，确定所述个人用户的第一可信度信息；基于预设的物联网设备的影响力分值，根据所述第三通信交互数据，确定所述个人用户的第三可信度信息；根据所述第一可信度信息和所述第三可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。According to a third aspect of the present application, a user identification method based on interactive relationships is provided, comprising: obtaining communication interaction data and user information of individual users within a preset time period; wherein the communication interaction data comprises first communication interaction data between the individual users within the preset time period, and third communication interaction data between the individual user and an Internet of Things device; determining first credibility information of the individual user based on the user information of the individual user and the first communication interaction data; determining third credibility information of the individual user based on the third communication interaction data and an influence score of a preset Internet of Things device; and identifying whether the individual user is a violating user within the preset time period based on the first credibility information and the third credibility information.
根据本申请的第四方面，提供了一种基于交互关系的用户识别方法，包括：获取在预设时间段内个人用户之间第一通信交互数据和所述个人用户的用户信息；根据所述用户信息，确定所述个人用户的初始可信度信息；根据所述第一通信交互数据，确定所述个人用户作为主叫用户时与每个被叫用户的交互次数；根据所述个人用户作为主叫用户时与每个被叫用户的交互次数和所述初始可信度信息进行迭代运算，获得所述个人用户的第一可信度信息；根据所述第一可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。According to the fourth aspect of the present application, a user identification method based on interactive relationships is provided, including: obtaining first communication interaction data between individual users within a preset time period and user information of the individual users; determining initial credibility information of the individual users based on the user information; determining the number of interactions between the individual user as a calling user and each called user based on the first communication interaction data; performing iterative operations based on the number of interactions between the individual user as a calling user and each called user and the initial credibility information to obtain first credibility information of the individual user; and identifying whether the individual user is an illegal user within the preset time period based on the first credibility information.
根据本申请的第五方面，提供了一种基于交互关系的用户识别装置，包括：获取模块，用于获取在预设时间段内的通信交互数据、个人用户的用户信息、与所述个人用户通信交互的企业用户的用户信息；其中，所述通信交互数据包括在所述预设时间段内个人用户之间第一通信交互数据、所述个人用户与所述企业用户之间的第二通信交互数据和所述个人用户与物联网设备之间的第三通信交互数据；第一确定模块，用于根据所述个人用户的用户信息和所述第一通信交互数据，确定所述个人用户的第一可信度信息；第二确定模块，用于根据所述企业用户的用户信息和所述第二通信交互数据，确定所述个人用户的第二可信度信息；第三确定模块，用于基于预设的物联网设备的影响力分值，根据所述第三通信交互数据，确定所述个人用户的第三可信度信息；识别模块，用于根据所述第一可信度信息、所述第二可信度信息和所述第三可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。According to a fifth aspect of the present application, a user identification device based on an interactive relationship is provided, comprising: an acquisition module, used to acquire communication interaction data, user information of personal users, and user information of corporate users who communicate and interact with the personal users within a preset time period; wherein the communication interaction data includes first communication interaction data between personal users within the preset time period, second communication interaction data between the personal user and the corporate user, and third communication interaction data between the personal user and an Internet of Things device; a first determination module, used to determine first credibility information of the personal user based on the user information of the personal user and the first communication interaction data; a second determination module, used to determine second credibility information of the personal user based on the user information of the corporate user and the second communication interaction data; a third determination module, used to determine third credibility information of the personal user based on the influence score of a preset Internet of Things device and the third communication interaction data; an identification module, used to identify whether the personal user is a violating user within the preset time period based on the first credibility information, the second credibility information, and the third credibility information.
根据本申请的第六方面，提供了一种基于交互关系的用户识别装置，包括：获取模块，用于获取在预设时间段内的通信交互数据、个人用户的用户信息和与所述个人用户通信交互的企业用户的用户信息；其中，所述通信交互数据包括在所述预设时间段内个人用户之间第一通信交互数据，以及所述个人用户与所述企业用户之间的第二通信交互数据；第一确定模块，用于根据所述个人用户的用户信息和所述第一通信交互数据，确定所述个人用户的第一可信度信息；According to a sixth aspect of the present application, there is provided a user identification device based on an interactive relationship, comprising: an acquisition module, configured to acquire communication interaction data, user information of an individual user, and user information of an enterprise user who communicates and interacts with the individual user within a preset time period; wherein the communication interaction data comprises first communication interaction data between individual users within the preset time period, and second communication interaction data between the individual user and the enterprise user; a first determination module, configured to determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data;
第二确定模块，用于根据所述企业用户的用户信息和所述第二通信交互数据，确定所述个人用户的第二可信度信息；识别模块，用于根据所述第一可信度信息和所述第二可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。A second determination module is used to determine the second credibility information of the individual user based on the user information of the enterprise user and the second communication interaction data; an identification module is used to identify whether the individual user is an illegal user within the preset time period based on the first credibility information and the second credibility information.
根据本申请的第七方面，提供了一种基于交互关系的用户识别装置，包括：获取模块，用于获取在预设时间段内的通信交互数据和个人用户的用户信息；其中，所述通信交互数据包括在所述预设时间段内所述个人用户之间第一通信交互数据，以及所述个人用户与物联网设备之间的第三通信交互数据；第一确定模块，用于根据所述个人用户的用户信息和所述第一通信交互数据，确定所述个人用户的第一可信度信息；第三确定模块，用于基于预设的物联网设备的影响力分值，根据所述第三通信交互数据，确定所述个人用户的第三可信度信息；识别模块，用于根据所述第一可信度信息和所述第三可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。According to the seventh aspect of the present application, a user identification device based on an interactive relationship is provided, comprising: an acquisition module, used to acquire communication interaction data and user information of an individual user within a preset time period; wherein the communication interaction data includes first communication interaction data between the individual users within the preset time period, and third communication interaction data between the individual user and an Internet of Things device; a first determination module, used to determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data; a third determination module, used to determine third credibility information of the individual user based on the third communication interaction data and based on an influence score of a preset Internet of Things device; an identification module, used to identify whether the individual user is an illegal user within the preset time period based on the first credibility information and the third credibility information.
根据本申请的第八方面，提供了一种基于交互关系的用户识别装置，包括：第一获取模块，用于获取在预设时间段内个人用户之间第一通信交互数据和所述个人用户的用户信息；第一确定模块，用于根据所述用户信息，确定所述个人用户的初始可信度信息；第二确定模块，用于根据所述第一通信交互数据，确定所述个人用户作为主叫用户时与每个被叫用户的交互次数；第二获取模块，用于根据所述个人用户作为主叫用户时与每个被叫用户的交互次数和所述初始可信度信息进行迭代运算，获得所述个人用户的第一可信度信息；识别模块，用于根据所述第一可信度信息，识别所述个人用户在所述预设时间段内是否为违规用户。According to the eighth aspect of the present application, a user identification device based on interactive relationship is provided, including: a first acquisition module, used to acquire first communication interaction data between personal users and user information of the personal users within a preset time period; a first determination module, used to determine the initial credibility information of the personal user based on the user information; a second determination module, used to determine the number of interactions between the personal user as a calling user and each called user based on the first communication interaction data; the second acquisition module, used to perform iterative operations based on the number of interactions between the personal user as a calling user and each called user and the initial credibility information to obtain the first credibility information of the personal user; an identification module, used to identify whether the personal user is an illegal user within the preset time period based on the first credibility information.
根据本申请的第九方面，提供了一种电子设备，包括：处理器；用于存储所述处理器的可执行指令的存储器；其中，所述处理器被配置为执行所述指令，以实现上述第一方面所述的基于交互关系的用户识别方法，或者，实现上述第二方面所述的基于交互关系的用户识别方法，或者，实现上述第三方面所述的基于交互关系的用户识别方法，或者，实现上述第四方面所述的基于交互关系的用户识别方法。According to the ninth aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the user identification method based on interactive relationship described in the first aspect above, or to implement the user identification method based on interactive relationship described in the second aspect above, or to implement the user identification method based on interactive relationship described in the third aspect above, or to implement the user identification method based on interactive relationship described in the fourth aspect above.
根据本申请的第十方面，提供了一种计算机可读存储介质，当所述计算机可读存储介质中的指令由电子设备的处理器执行时，使得电子设备能够执行上述第一方面所述的基于交互关系的用户识别方法，或者，执行上述第二方面所述的基于交互关系的用户识别方法，或者，执行上述第三方面所述的基于交互关系的用户识别方法，或者，执行上述第四方面所述的基于交互关系的用户识别方法。According to the tenth aspect of the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of an electronic device, the electronic device is enabled to execute the user identification method based on interactive relationship described in the first aspect above, or execute the user identification method based on interactive relationship described in the second aspect above, or execute the user identification method based on interactive relationship described in the third aspect above, or execute the user identification method based on interactive relationship described in the fourth aspect above.
根据本申请的技术方案，基于个人用户与个人用户之间的通信交互、个人用户与企业用户之间的通信交互，以及个人用户与物联网设备之间的通信交互来确定个人用户的可信度信息，可以充分考虑与个人用户存在交互关系的所有交互对象对个人用户的可信度信息的影响，将企业用户和物联网设备均应用到个人用户的识别过程中，不仅可以提升个人用户可信度信息的准确性，同时也可以提升用户识别的准确性，为移动通信领域违规行为的治理提供了可靠的依据。According to the technical solution of the present application, the credibility information of individual users is determined based on the communication interactions between individual users, the communication interactions between individual users and corporate users, and the communication interactions between individual users and IoT devices. The influence of all interaction objects that have an interactive relationship with the individual user on the credibility information of the individual user can be fully considered. Both corporate users and IoT devices are applied to the identification process of individual users, which can not only improve the accuracy of the credibility information of individual users, but also improve the accuracy of user identification, providing a reliable basis for the governance of violations in the field of mobile communications.
本申请附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本申请的实践了解到。Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
本申请上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：The above and/or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
图1为本申请实施例所提供的一种基于交互关系的用户识别方法的流程图；FIG1 is a flow chart of a user identification method based on interactive relationship provided in an embodiment of the present application;
图2为本申请实施例中的一种确定个人用户的第一可信度信息的实现过程的流程图；FIG2 is a flowchart of an implementation process of determining first credibility information of an individual user in an embodiment of the present application;
图3为本申请实施例中的一种确定个人用户的第二可信度信息的流程图；FIG3 is a flow chart of determining second credibility information of an individual user in an embodiment of the present application;
图4为本申请实施例中的一种确定个人用户受企业用户影响的总分值的流程图；FIG4 is a flow chart of determining the total score of an individual user influenced by an enterprise user in an embodiment of the present application;
图5为本申请实施例中的一种确定个人用户受每个企业用户影响的分值的流程图；FIG5 is a flow chart of determining the score of an individual user influenced by each enterprise user in an embodiment of the present application;
图6为本申请实施例中的一种确定个人用户受每个第二类企业用户影响的分值的流程图；FIG6 is a flow chart of determining the score of an individual user influenced by each second-category enterprise user in an embodiment of the present application;
图7为本申请实施例中的一种确定个人用户的第三可信度信息的流程图；FIG7 is a flow chart of determining third credibility information of an individual user in an embodiment of the present application;
图8为本申请实施例中的一种确定个人用户受物联网设备影响的总分值的流程图；FIG8 is a flow chart of determining a total score of an individual user affected by an IoT device in an embodiment of the present application;
图9为本申请实施例所提供的另一种基于交互关系的用户识别方法的流程图；FIG9 is a flow chart of another method for identifying a user based on an interactive relationship provided in an embodiment of the present application;
图10为本申请实施例所提供的又一种基于交互关系的用户识别方法的流程图；FIG10 is a flowchart of another method for identifying a user based on an interactive relationship provided in an embodiment of the present application;
图11为本申请实施例所提供的又一种基于交互关系的用户识别方法的流程图；FIG11 is a flowchart of another method for identifying a user based on an interactive relationship provided in an embodiment of the present application;
图12为本申请实施例所提供的一种基于交互关系的用户识别装置的结构框图；FIG12 is a structural block diagram of a user identification device based on interactive relationship provided in an embodiment of the present application;
图13为本申请实施例所提供的另一种基于交互关系的用户识别装置的结构框图；FIG13 is a structural block diagram of another user identification device based on interactive relationship provided in an embodiment of the present application;
图14为本申请实施例所提供的又一种基于交互关系的用户识别装置的结构框图；FIG14 is a structural block diagram of another interactive relationship-based user identification device provided in an embodiment of the present application;
图15为本申请实施例所提供的又一种基于交互关系的用户识别装置的结构框图；FIG15 is a structural block diagram of another interactive relationship-based user identification device provided in an embodiment of the present application;
图16为本申请实施例所提供的一种电子设备的结构框图。FIG16 is a structural block diagram of an electronic device provided in an embodiment of the present application.
具体实施方式Detailed ways
下面详细描述本申请的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本申请，而不能理解为对本申请的限制。The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
随着通信技术的发展，移动用户之间的通信交互量激增，同时也为骚扰电话、垃圾短信、诈骗电话等违规行为的治理带来了巨大的挑战。With the development of communication technology, the amount of communication interactions between mobile users has increased dramatically, which has also brought huge challenges to the governance of illegal behaviors such as harassing calls, spam text messages, and fraudulent calls.
在相关技术中，通过对用户的通信交互行为来判断用户的可信度，从而针对不同可信度的用户采用不同的治理策略。其中，判断用户的可信度的方法主要包括：(1)利用用户自身的特征，如用户年龄、套餐信息、话费信息等，采用机器学习算法如随机森林等基于用户特征数据进行建模，并预测用户的评分。(2)基于社交网络传播理论，其主要思想为一个用户的价值可通过交互行为传递给其他用户，被其他高质量用户大量引用的用户其价值也应较高。这种方法一般使用图计算算法，对用户交互矩阵进行迭代求解，最终得到用户在交互网络中的影响力或重要程度。但是由于判断用户的可信度结果的准确度较低，所以难以实现对违规用户的识别。In related technologies, the credibility of users is judged by their communication and interaction behaviors, so that different governance strategies are adopted for users with different credibility. Among them, the methods for judging the credibility of users mainly include: (1) using the user's own characteristics, such as user age, package information, call fee information, etc., using machine learning algorithms such as random forests to model based on user feature data and predict the user's score. (2) Based on social network communication theory, its main idea is that the value of a user can be transmitted to other users through interactive behaviors, and the value of users who are widely cited by other high-quality users should also be high. This method generally uses a graph computing algorithm to iteratively solve the user interaction matrix, and finally obtains the user's influence or importance in the interactive network. However, due to the low accuracy of the results of judging the user's credibility, it is difficult to identify illegal users.
为了解决上述问题，本申请提出了一种基于交互关系的用户识别方法、装置及电子设备。In order to solve the above problems, the present application proposes a user identification method, device and electronic device based on interaction relationship.
本申请的技术方案中，所涉及的用户个人信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。所涉及的用户个人信息是在争得用户同意的情况下获取、存储和应用的。In the technical solution of this application, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good customs. The user personal information involved is acquired, stored and applied with the user's consent.
图1为本申请实施例所提供的一种基于交互关系的用户识别方法的流程图。需要说明的是，本申请实施例所提供的基于交互关系的用户识别方法可以用于本申请实施例中的基于交互关系的用户识别装置，且本申请实施例中的基于交互关系的用户识别装置可配置于电子设备中。如图1所示，该方法可以包括以下步骤：FIG1 is a flow chart of a user identification method based on interactive relationship provided in an embodiment of the present application. It should be noted that the user identification method based on interactive relationship provided in an embodiment of the present application can be used in a user identification device based on interactive relationship in an embodiment of the present application, and the user identification device based on interactive relationship in an embodiment of the present application can be configured in an electronic device. As shown in FIG1 , the method may include the following steps:
步骤101，获取在预设时间段内的通信交互数据、个人用户的用户信息、与个人用户通信交互的企业用户的用户信息；其中，通信交互数据包括在预设时间段内个人用户之间第一通信交互数据、个人用户与企业用户之间的第二通信交互数据和个人用户与物联网设备之间的第三通信交互数据。Step 101, obtaining communication interaction data within a preset time period, user information of individual users, and user information of corporate users who communicate and interact with individual users; wherein the communication interaction data includes first communication interaction data between individual users within the preset time period, second communication interaction data between individual users and corporate users, and third communication interaction data between individual users and IoT devices.
在本申请的一些实施例中，预设时间段可以为包括当前时刻及当前时刻之前一定时间范围的时间段。由于通信交互数据是随时间一直变化的，所以可以以当前时刻之前的一段时间内的通信交互数据作为判断在这段时间内用户是否违规的数据。需要说明的是，本申请实施例的基于交互关系的用户识别方法可以是每间隔预设时间段执行一次。In some embodiments of the present application, the preset time period may be a time period including the current moment and a certain time range before the current moment. Since the communication interaction data changes over time, the communication interaction data within a period of time before the current moment may be used as data for determining whether the user violates the rules during this period of time. It should be noted that the user identification method based on the interaction relationship in the embodiment of the present application may be executed once every preset time period.
其中，个人用户是指以个人身份开通账号的用户，企业用户是指以企业身份所开通账号的用户。此处的个人用户可以为多个，比如某个城市的个人用户、某个区域内的个人用户。个人用户的用户信息即为每个个人用户的用户信息，可以包括用户级别、身份证信息、客户标识、级别编码、城市、性别等相关信息。企业用户的用户信息可以包括企业用户所覆盖的用户数量，企业用户所发送的消息量等相关信息。Among them, individual users refer to users who open an account as individuals, and corporate users refer to users who open an account as companies. There can be multiple individual users here, such as individual users in a certain city or individual users in a certain area. The user information of individual users is the user information of each individual user, which may include user level, ID card information, customer identification, level code, city, gender and other related information. The user information of corporate users may include the number of users covered by the corporate users, the number of messages sent by the corporate users and other related information.
在本申请的一些实施例中，第一通信交互数据是指个人用户与个人用户之间通信交互的数据，其中通信交互的方式可以为电话、短信、5G消息、视频通话等，在实际应用中可以针对不同应用场景选择对应的通信交互方式所对应的数据。第二通信交互数据是指个人用户与企业用户之间通信交互的数据，个人用户与企业用户之间的通信交互方式可以包括短信消息、5G信息、电话、5G视频通话、问卷调查、语音留言等。In some embodiments of the present application, the first communication interaction data refers to the data of communication interaction between individual users, where the communication interaction method can be phone calls, text messages, 5G messages, video calls, etc. In actual applications, the data corresponding to the corresponding communication interaction method can be selected for different application scenarios. The second communication interaction data refers to the data of communication interaction between individual users and corporate users, where the communication interaction method between individual users and corporate users can include text messages, 5G messages, phone calls, 5G video calls, questionnaires, voice messages, etc.
在本申请的一些实施例中，物联网设备可以为物联网电表、物联网水表等设备，还可以为智能家居家电，比如空调、扫地机器人、门锁等，还可以为应用于工业生产领域的物联网终端设备，比如手持终端设备等。第三通信交互数据可以为个人用户缴费时的交互数据、物联网设备所发送的提醒类消息，个人用户向物联网设备所发出的控制指令数据等。In some embodiments of the present application, the IoT device may be an IoT electric meter, an IoT water meter, or other device, or may be a smart home appliance, such as an air conditioner, a sweeping robot, a door lock, or an IoT terminal device used in the field of industrial production, such as a handheld terminal device, etc. The third communication interaction data may be interaction data when an individual user pays, reminder messages sent by an IoT device, control instruction data sent by an individual user to an IoT device, etc.
步骤102，根据个人用户的用户信息和第一通信交互数据，确定个人用户的第一可信度信息。Step 102: Determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data.
其中，第一可信度信息可以为用于基于个人用户的用户信息和个人用户之间的交互所确定的可信度分值。The first credibility information may be a credibility score determined based on user information of individual users and interactions between individual users.
作为一种示例，根据个人用户的用户信息和第一通信交互数据，确定个人用户的第一可信度信息的实现过程可以包括：基于预设的机器学习模型，根据每个个人用户的用户信息，获取每个个人用户的初始可信度分值；根据第一通信交互数据，可以确定个人用户之间的交互关系，基于社交传播算法，根据每个个人用户的初始可信度分值和个人用户之间的交互关系，确定每个个人用户的第一可信度信息。As an example, the implementation process of determining the first credibility information of an individual user based on the user information of the individual user and the first communication interaction data may include: based on a preset machine learning model, obtaining the initial credibility score of each individual user according to the user information of each individual user; based on the first communication interaction data, the interaction relationship between the individual users can be determined, and based on the social communication algorithm, the first credibility information of each individual user is determined according to the initial credibility score of each individual user and the interaction relationship between the individual users.
需要说明的是，针对不同应用场景可以选择不同的个人用户交互方式的通信交互数据。比如，针对骚扰电话违规用户治理场景，第一通信交互数据主要考虑个人用户间的电话交互数据，其他的交互方式所对应的通信交互数据可能带来不必要的干扰；针对垃圾短信违规用户治理场景，第一通信交互数据可以选择基于个人用户间短信交互数据。It should be noted that communication interaction data of different personal user interaction modes can be selected for different application scenarios. For example, for the scenario of managing users who violate the rules of nuisance calls, the first communication interaction data mainly considers the telephone interaction data between personal users, and the communication interaction data corresponding to other interaction modes may bring unnecessary interference; for the scenario of managing users who violate the rules of spam text messages, the first communication interaction data can be selected based on the text message interaction data between personal users.
步骤103，根据企业用户的用户信息和第二通信交互数据，确定个人用户的第二可信度信息。Step 103: Determine the second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data.
可以理解，由于一些企业用户例如大型企业、学校在发送信息时只会给企业职工、学生、教师等其它特定人群发送，同时一些违规号码一般仅用于拨打骚扰电话等行为，而与企业用户交互较少，所以根据个人用户与企业用户的交互信息对于评价个人用户的可信度具有重要作用。It is understandable that some corporate users, such as large enterprises and schools, will only send messages to employees, students, teachers and other specific groups. At the same time, some illegal numbers are generally only used to make harassing calls and have less interaction with corporate users. Therefore, the interaction information between individual users and corporate users plays an important role in evaluating the credibility of individual users.
其中，个人用户的第二可信度信息可以是基于企业用户的影响所确定的个人用户的可信度分值。The second credibility information of the individual user may be a credibility score of the individual user determined based on the influence of the enterprise user.
作为一种实施例方式，根据企业用户的用户信息和第二通信交互数据，确定个人用户的第二可信度信息可以包括：针对每个个人用户，若与该个人用户存在通信交互的企业用户为至少一个，则可以根据每个企业用户的用户信息，确定每个企业用户的影响力信息；根据第二通信交互数据，可以确定每个企业用户与该个人用户之间的交互次数和交互关系；根据每个企业用户与该个人用户之间的交互次数和交互关系，确定该个人用户受每个企业用户影响的影响力系数；根据该个人用户受每个企业用户影响的影响力系数，将每个企业用户的影响力信息进行加权求和，得到该个人用户的第二可信度信息；若与该个人用户存在通信交互的企业用户为0个，则该个人用户的第二可信度信息为空。As an embodiment, determining the second credibility information of an individual user based on the user information of the enterprise user and the second communication interaction data may include: for each individual user, if there is at least one enterprise user that has communication interaction with the individual user, the influence information of each enterprise user can be determined based on the user information of each enterprise user; the number of interactions and the interaction relationship between each enterprise user and the individual user can be determined based on the second communication interaction data; the influence coefficient of the individual user affected by each enterprise user is determined based on the number of interactions and the interaction relationship between each enterprise user and the individual user; based on the influence coefficient of the individual user affected by each enterprise user, the influence information of each enterprise user is weightedly summed to obtain the second credibility information of the individual user; if there are 0 enterprise users that have communication interaction with the individual user, the second credibility information of the individual user is empty.
步骤104，基于预设的物联网设备的影响力分值，根据第三通信交互数据，确定个人用户的第三可信度信息。Step 104: Based on the influence score of the preset IoT device and the third communication interaction data, determine the third credibility information of the individual user.
可以理解，随着5G技术的不断普及与发展，越来越多的物联网设备加入到了通信网络中，个人用户与物联网设备间的交互也越来越频繁，同时对于违规用户通常与物联网设备间的交互较少，所以在确定个人用户的可信度信息时可以将个人用户与物联网设备之间的通信交互数据考虑进来。It is understandable that with the continuous popularization and development of 5G technology, more and more IoT devices are added to the communication network, and the interaction between individual users and IoT devices is becoming more and more frequent. At the same time, illegal users usually have less interaction with IoT devices, so the communication interaction data between individual users and IoT devices can be taken into account when determining the credibility information of individual users.
其中，物联网设备的影响力分值为基于不同的物联网设备对于判断个人用户的可信度的影响力大小，物联网设备的影响力分值可以为0-1之间的值。通常比如物联网电表、物联网水表，或者工业生产领域的物联网设备的影响力分值较高，而智能家居家电等物联网设备的影响力分值较低。The influence score of an IoT device is based on the influence of different IoT devices on the credibility of individual users, and the influence score of an IoT device can be between 0 and 1. Generally, the influence score of IoT devices such as IoT electricity meters, IoT water meters, or IoT devices in the industrial production field is higher, while the influence score of IoT devices such as smart home appliances is lower.
在本申请的一些实施例中，基于预设的物联网设备的影响力分值，根据第三通信交互数据，确定个人用户的第三可信度信息的实现方式可以包括：针对每个个人用户，根据第三通信交互数据，可以确定与该个人用户存在通信交互的物联网设备；若与该个人用户存在通信交互的物联网设备为一个或者多个，可以将以上多个物联网设备的影响力分值进行求和，得到该个人用户的第三可信度信息；若没有与该个人用户存在通信交互的物联网设备，则该个人用户的点可信度信息为空。In some embodiments of the present application, based on the influence score of a preset IoT device and according to the third communication interaction data, an implementation method for determining the third credibility information of an individual user may include: for each individual user, based on the third communication interaction data, the IoT device with which the individual user has communication interaction can be determined; if there is one or more IoT devices with which the individual user has communication interaction, the influence scores of the above multiple IoT devices can be summed to obtain the third credibility information of the individual user; if there is no IoT device with which the individual user has communication interaction, the point credibility information of the individual user is empty.
步骤105，根据第一可信度信息、第二可信度信息和第三可信度信息，识别个人用户在预设时间段内是否为违规用户。Step 105: Identify whether the individual user is an illegal user within a preset time period based on the first credibility information, the second credibility information, and the third credibility information.
在本申请的一些实施例中，根据第一可信度信息、第二可信度信息和第三可信度信息，识别个人用户在预设时间段内是否为违规用户的实现方式可以包括：根据第一可信度信息、第二可信度信息和第三可信度信息，确定个人用户的可信度信息；根据个人用户的可信度信息，识别个人用户在预设时间段内是否为违规用户。In some embodiments of the present application, an implementation method for identifying whether an individual user is a violating user within a preset time period based on the first credibility information, the second credibility information, and the third credibility information may include: determining the credibility information of the individual user based on the first credibility information, the second credibility information, and the third credibility information; and identifying whether the individual user is a violating user within a preset time period based on the credibility information of the individual user.
作为一种示例，可以针对每个个人用户，将该个人用户的第一可信度信息、第二可信度信息和第三可信度信息进行加权求和，并将加权求和结果确定为该个人用户的可信度信息；若可信度信息为用于表示个人用户可信度的可信度分值，则可以预先设定可信度分值阈值，将该个人用户的可信度分值与可信度分值阈值进行比对，若该个人用户的可信度分值小于可信度分值阈值，则识别该个人用户在预设时间段内为违规用户，否则识别该个人用户在预设时间段内非违规用户。As an example, for each individual user, the first credibility information, the second credibility information and the third credibility information of the individual user may be weightedly summed, and the weighted sum result may be determined as the credibility information of the individual user; if the credibility information is a credibility score used to represent the credibility of the individual user, a credibility score threshold may be set in advance, and the credibility score of the individual user may be compared with the credibility score threshold; if the credibility score of the individual user is less than the credibility score threshold, the individual user is identified as a violating user within a preset time period; otherwise, the individual user is identified as a non-violating user within the preset time period.
根据本申请实施例的基于交互关系的用户识别方法，基于个人用户与个人用户之间的通信交互、个人用户与企业用户之间的通信交互，以及个人用户与物联网设备之间的通信交互来确定个人用户的可信度信息，可以充分考虑与个人用户存在交互关系的所有交互对象对个人用户的可信度信息的影响，将企业用户和物联网设备均应用到个人用户的识别过程中，不仅可以提升个人用户可信度信息的准确性，同时也可以提升用户识别的准确性，为移动通信领域违规行为的治理提供了可靠的依据。According to the interactive relationship-based user identification method of the embodiment of the present application, the credibility information of individual users is determined based on the communication interactions between individual users and individual users, the communication interactions between individual users and enterprise users, and the communication interactions between individual users and Internet of Things devices. The influence of all interactive objects that have an interactive relationship with the individual user on the credibility information of the individual user can be fully considered. Both enterprise users and Internet of Things devices are applied to the identification process of individual users, which can not only improve the accuracy of the credibility information of individual users, but also improve the accuracy of user identification, providing a reliable basis for the governance of illegal behaviors in the field of mobile communications.
接下来，将针对确定个人用户的第一可信度信息的实现过程进行介绍。Next, the implementation process of determining the first credibility information of an individual user will be introduced.
图2为本申请实施例中的一种确定个人用户的第一可信度信息的实现过程的流程图。如图2所示，基于上述实施例中图1的步骤102的实现过程可以包括：FIG2 is a flowchart of an implementation process of determining the first credibility information of an individual user in an embodiment of the present application. As shown in FIG2, the implementation process based on step 102 of FIG1 in the above embodiment may include:
步骤201，根据个人用户的用户信息，确定个人用户的初始可信度信息。Step 201, determining initial credibility information of an individual user based on the user information of the individual user.
可以理解，由于个人用户的用户信息中可以包含用户可信度的相关信息，可以基于个人用户的用户信息，先确定个人用户的初始可信度信息。其中，初始可信度信息可以为基于个人用户的用户信息所确定的初始可信度分值。It is understandable that, since the user information of an individual user may include information related to the user's credibility, the initial credibility information of the individual user may be determined based on the user information of the individual user, wherein the initial credibility information may be an initial credibility score determined based on the user information of the individual user.
作为一种示例，可以预先设定用户信息中不同字段所对应的权重值，同时设定每个字段中不同的值所对应的分值，所以可以根据每个个人用户的用户信息，确定每个个人用户的用户信息中每个字段的内容所对应的分值，在基于各自对应的权重值，进行加权求和，得到每个个人用户的初始可信度分值。As an example, the weight values corresponding to different fields in the user information can be set in advance, and the scores corresponding to different values in each field can be set at the same time. Therefore, based on the user information of each individual user, the score corresponding to the content of each field in the user information of each individual user can be determined, and then a weighted sum is performed based on the corresponding weight values to obtain the initial credibility score of each individual user.
作为另一种示例，根据个人用户的用户信息，确定个人用户的初始可信度信息的实现过程可以包括：根据个人用户的用户信息，确定个人用户的用户特征信息，其中，用户特征信息包括用户属性特征信息、用户级别特征信息和用户地域特征信息；将用户特征信息输入至预设的初始评分机器学习模型，获得初始可信度信息；其中，初始评分机器学习模块已学习得到个人用户的用户特征信息与初始可信度信息的映射关系。其中，用户特征信息可以为基于用户信息所确定的特征向量。用户属性特征信息可以包括个人用户的性别、年龄、教育程度、电话、职业、证件等信息。用户级别特征信息可以包括个人用户的星级、星级评定时间、是否实名等信息。用户地域特征信息可以包括城市等信息。As another example, the implementation process of determining the initial credibility information of an individual user based on the user information of the individual user may include: determining the user characteristic information of the individual user based on the user information of the individual user, wherein the user characteristic information includes user attribute characteristic information, user level characteristic information and user regional characteristic information; inputting the user characteristic information into a preset initial scoring machine learning model to obtain initial credibility information; wherein the initial scoring machine learning module has learned the mapping relationship between the user characteristic information of the individual user and the initial credibility information. Among them, the user characteristic information may be a feature vector determined based on the user information. The user attribute characteristic information may include the individual user's gender, age, education level, telephone number, occupation, certificate and other information. The user level characteristic information may include the individual user's star rating, star rating time, whether it is real-name and other information. The user regional characteristic information may include information such as the city.
步骤202，根据第一通信交互数据，确定个人用户作为主叫用户时与每个被叫用户的交互次数。Step 202: Determine the number of interactions between the individual user as a calling user and each called user based on the first communication interaction data.
也就是说，针对每个个人用户，在第一通信交互数据中，判断是否存在该用户作为主叫用户的通信交互数据，若存在该个人用户作为主机用户的通信交互数据，则基于该通信交互数据，确定该个人用户作为主叫用户时，与每个被叫用户之间的交互次数。That is to say, for each individual user, in the first communication interaction data, it is determined whether there is communication interaction data of the individual user as a calling user. If there is communication interaction data of the individual user as a host user, then based on the communication interaction data, the number of interactions between the individual user as a calling user and each called user is determined.
步骤203，根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代运算，获得个人用户的第一可信度信息。Step 203: performing an iterative calculation based on the number of interactions between the individual user as a calling user and each called user and the initial credibility information to obtain the first credibility information of the individual user.
可以理解，某人个人用户与越多的个人用户交互，则说明该个人用户越重要，同时主叫用户重要性越高，被叫用户的重要性也会提高。在相关技术中，同一个主叫用户对所有被叫用户的影响程度是相同的，并未考虑交互次数的影响。比如在一段时间内，与主叫用户通信次数较多的用户其与主叫用户联系更紧密，而与主叫用户通信次数较低的用户，其与主叫用户联系紧密度更低，所以个人用户之间的交互次数对每个个人用户之间的影响是不同的，在基于交互数据进行迭代计算时，需要考虑交互次数。It can be understood that the more individual users a certain individual user interacts with, the more important the individual user is. At the same time, the more important the calling user is, the more important the called user is. In the related art, the same calling user has the same influence on all called users, and the influence of the number of interactions is not considered. For example, within a period of time, users who communicate with the calling user more times have a closer connection with the calling user, while users who communicate with the calling user less times have a lower degree of connection with the calling user. Therefore, the number of interactions between individual users has different effects on each individual user. When performing iterative calculations based on interaction data, the number of interactions needs to be considered.
在本申请的一些实施例中，根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代运算，获得个人用户的第一可信度信息的实现过程可以包括：根据个人用户作为主叫用户时与每个被叫用户的交互次数，确定个人用户作为主叫用户时与每个被叫用户之间的交互占比；基于网页排名Pagerank算法，根据个人用户作为主叫用户时与每个被叫用户之间的交互占比和初始可信度信息进行迭代运算，获取第一可信度信息。In some embodiments of the present application, an iterative operation is performed based on the number of interactions between the individual user as a calling user and each called user and the initial credibility information to obtain the first credibility information of the individual user, which may include: determining the interaction ratio between the individual user as a calling user and each called user based on the number of interactions between the individual user as a calling user and each called user; based on the Pagerank algorithm, iterative operation is performed based on the interaction ratio between the individual user as a calling user and each called user and the initial credibility information to obtain the first credibility information.
作为一种示例，若个人用户A作为主叫用户时与被叫用户B、被叫用户C和被叫用户D存在交互，与被叫用户B的交互次数为RAB，与被叫用户C的交互次数为RAC，与被叫用户D的交互次数为RAD，则个人用户A与被叫用户B之间的交互占比＝RAB/(RAB+RAC+RAD),个人用户A与被叫用户C之间的交互占比＝RAC/(RAB+RAC+RAD),个人用户A与被叫用户D之间的交互占比＝RAD/(RAB+RAC+RAD)。As an example, if personal user A, as a calling user, interacts with called user B, called user C and called user D, the number of interactions with called user B is RAB , the number of interactions with called user C is RAC , and the number of interactions with called user D is RAD , then the interaction ratio between personal user A and called user B = RAB /(RAB +RAC +RAD ), the interaction ratio between personal user A and called user C = RAC /(RAB +RAC +RAD ), and the interaction ratio between personal user A and called user D = RAD /(RAB +RAC +RAD ).
以个人用户u举例而言，在根据个人用户作为主叫用户时与每个被叫用户之间的交互占比和初始可信度信息进行迭代运算中，对于个人用户u在每个迭代过程可以通过以下公式来表达：Taking individual user u as an example, in performing iterative calculations based on the interaction ratio and initial credibility information between the individual user as a calling user and each called user, the individual user u can be expressed by the following formula in each iteration process:
其中，V表示与个人用户u存在通信交互的主叫用户的集合；Vi表示第i个与个人用户u存在通信交互的主叫用户；n为与个人用户u存在通信交互的主叫用户的数量；为Vi作为主叫用户时与个人用户u之间的交互占比，其中，为Vi作为主叫用户时与个人用户u的交互次数，表示Vi作为主叫用户时与所有被叫用户的交互次数；表示主叫用户Vi的在当前迭代过程中的可信度信息迭代值；Cu表示个人用户u在经过当前迭代计算得到的可信度信息迭代值。Wherein, V represents the set of calling users that have communication interaction with individual user u;Vi represents the i-th calling user that has communication interaction with individual user u; n is the number of calling users that have communication interaction with individual user u; is the proportion of interactions between Vi and individual user u when Viis the calling user, where is the number of interactions between Vi and individual user u when Viis the calling user, Indicates the number of interactions betweenVi as the calling user and all called users; represents the iteration value of the credibility information of the calling user Vi in the current iteration process; Cu represents the iteration value of the credibility information of the individual user u calculated after the current iteration.
为了更加清楚的表达以上迭代过程，可以通过举例的方式进行说明。假如共有4个个人用户，分别为个人用户u、个人用户v、个人用户w和个人用户x，通过以下表1来表示主叫用户与每个被叫用户之间的交互次数。如表1所示，Rvu表示个人用户v作为主叫用户时，与被叫用户u之间的交互次数，以此类推。In order to express the above iterative process more clearly, an example can be given. Assuming there are 4 individual users, namely individual user u, individual user v, individual user w and individual user x, the number of interactions between the calling user and each called user is represented by the following Table 1. As shown in Table 1, Rvu represents the number of interactions between individual user v as the calling user and called user u, and so on.
表1个人用户之间的交互关系表Table 1 Interaction relationship table between individual users
若个人用户u的初始可信度信息为Cu0，个人用户v的初始可信度信息为Cv0，个人用户w的初始可信度信息为Cw0，个人用户x的初始可信度信息为Cx0，则第一步迭代过程可以如下式(2)-式(5)所示：If the initial credibility information of individual user u is Cu0 , the initial credibility information of individual user v is Cv0 , the initial credibility information of individual user w is Cw0 , and the initial credibility information of individual user x is Cx0 , then the first iteration process can be shown as follows:
其中，Cu1为个人用户u经过第一轮迭代后的可信度信息；Cv1为个人用户v经过第一轮迭代后的可信度信息；Cw1为个人用户w经过第一轮迭代后的可信度信息；Cx1为个人用户x经过第一轮迭代后的可信度信息。基于第一次迭代过程以此类推，进行多轮迭代，直至两次迭代后的可信度信息的变化满足预设范围，迭代结束，得到每个个人用户的第一可信度信息。Among them, Cu1 is the credibility information of individual user u after the first round of iteration; Cv1 is the credibility information of individual user v after the first round of iteration; Cw1 is the credibility information of individual user w after the first round of iteration; Cx1 is the credibility information of individual user x after the first round of iteration. Based on the first iteration process, multiple rounds of iterations are performed until the change of the credibility information after two iterations meets the preset range, the iteration ends, and the first credibility information of each individual user is obtained.
根据本申请实施例的基于交互关系的用户识别方法，通过基于个人用户的用于信息，确定个人用户的初始可信度信息，并根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代运算，得到个人用户的第一可信度信息。本方案在迭代计算的过程中引入了交互次数，将交互次数作为用户联系紧密度的依据，所以得到的结果相比相关技术准确度更高，从而可以提升用户识别的准确性。According to the user identification method based on interactive relationship of the embodiment of the present application, the initial credibility information of the individual user is determined based on the personal user's usage information, and the first credibility information of the individual user is obtained by performing iterative calculations based on the number of interactions between the individual user and each called user when the individual user is a calling user and the initial credibility information. This solution introduces the number of interactions in the iterative calculation process and uses the number of interactions as the basis for the closeness of user contact, so the result obtained is more accurate than the related technology, thereby improving the accuracy of user identification.
图3为本申请实施例中的一种确定个人用户的第二可信度信息的流程图。如图3所示，基于上述实施例，图1中的步骤103的实现过程可以包括以下步骤：FIG3 is a flow chart of determining the second credibility information of an individual user in an embodiment of the present application. As shown in FIG3 , based on the above embodiment, the implementation process of step 103 in FIG1 may include the following steps:
步骤301，根据企业用户的用户信息和第二通信交互数据，确定个人用户受企业用户影响的总分值。Step 301: Determine the total score of the individual user influenced by the enterprise user according to the user information of the enterprise user and the second communication interaction data.
可以理解，由于企业用户通常会与特定的用户群体进行交互，而违规用户一般仅用于拨打骚然电话或者发送骚然短信等，其与企业用户的交互较少，所以通过企业用户的用户信息和第二通信交互数据对评价个人用户的可信度有重要的作用。It is understandable that since corporate users usually interact with specific user groups, and illegal users are generally only used to make unreasonable calls or send unreasonable text messages, etc., they have less interaction with corporate users. Therefore, the user information of corporate users and the second communication interaction data play an important role in evaluating the credibility of individual users.
在本申请的一些实施例中，可以根据企业用户的用户信息，确定企业用户的影响力分值，再根据第二通信交互数据，确定个人用户与企业用户之间的交互次数，并根据个人用户与企业用于的交互次数，确定个人用户与企业用户之间的紧密度，根据企业用户的影响力分值和个人用户与企业用户之间的紧密度来确定个人用户受企业用户影响的总分值。In some embodiments of the present application, the influence score of the enterprise user can be determined based on the user information of the enterprise user, and the number of interactions between the personal user and the enterprise user can be determined based on the second communication interaction data, and the closeness between the personal user and the enterprise user can be determined based on the number of interactions between the personal user and the enterprise user, and the total score of the personal user influenced by the enterprise user can be determined based on the influence score of the enterprise user and the closeness between the personal user and the enterprise user.
步骤302，将个人用户受企业用户影响的总分值进行排序，并根据排序结果确定个人用户的第二可信度信息。Step 302: sort the total scores of the influence of the enterprise users on the individual users, and determine the second credibility information of the individual users according to the sorting result.
在本申请的一些实施例中，可以将每个个人用户受企业用户影响的总分值组成集合M，集合M中的元素数量为n，其中，n为个人用户的数量。将M中的元素从小到大进行排序，根据排序后M中各个元素的位置，来确定个人用户的第二可信度信息。In some embodiments of the present application, the total score of each individual user influenced by the enterprise user can be formed into a set M, and the number of elements in the set M is n, where n is the number of individual users. The elements in M are sorted from small to large, and the second credibility information of the individual user is determined according to the position of each element in M after sorting.
作为一种示例，个人用户的第二可信度信息可以为百分位数，如公式(6)所示。若排序后，个人用户u受企业用户影响的总分值在集合M中最大，则个人用户u的第二可信度信息为1；若排序后个人用户u受企业用户影响的总分值为集合M中的75％分位数，则个人用户u的第二可信度信息为0.75。As an example, the second credibility information of an individual user may be a percentile, as shown in formula (6). If after sorting, the total score of the individual user u influenced by the enterprise user is the largest in the set M, the second credibility information of the individual user u is 1; if after sorting, the total score of the individual user u influenced by the enterprise user is the 75% percentile in the set M, the second credibility information of the individual user u is 0.75.
Bu＝percentile(M，Mu) (6)Bu＝percentile(M,Mu) (6)
其中，Bu为个人用户u的第二可信度信息；M为每个个人用户受企业用户影响的总分值组成集合；Mu为个人用户u受企业用户的总影响分值。Among them, Bu is the second credibility information of individual user u; M is the set of total scores of each individual user affected by enterprise users; Mu is the total influence score of individual user u affected by enterprise users.
根据本申请实施例的基于交互关系的用户识别方法，根据企业用户的用户信息和第二通信交互数据，确定个人用户受企业用户影响的总分值，将个人用户受企业用户影响的总分值进行排序，并根据排序结果确定个人用户的第二可信度信息。本方案引入了个人用户与企业用户的通信交互数据，基于企业用户的用户信息和交互信息来进一步确定个人用户的可信度分值，从而可以更加全面的评估个人用户的可信度，进而可以提升用户识别的准确性。According to the interactive relationship-based user identification method of the embodiment of the present application, the total score of the influence of the individual user on the enterprise user is determined based on the user information of the enterprise user and the second communication interaction data, the total score of the influence of the individual user on the enterprise user is sorted, and the second credibility information of the individual user is determined based on the sorting result. This solution introduces the communication interaction data between the individual user and the enterprise user, and further determines the credibility score of the individual user based on the user information and interaction information of the enterprise user, so that the credibility of the individual user can be more comprehensively evaluated, thereby improving the accuracy of user identification.
图4为本申请实施例中的一种确定个人用户受企业用户影响的总分值的流程图。需要说的是，企业用户的数量为至少一个。如图4所示，基于上述实施例，图3中的步骤301的实现过程可以包括：FIG4 is a flow chart of determining the total score of an individual user affected by an enterprise user in an embodiment of the present application. It should be noted that the number of enterprise users is at least one. As shown in FIG4 , based on the above embodiment, the implementation process of step 301 in FIG3 may include:
步骤401，根据每个企业用户的用户信息，确定每个企业用户的影响力分值。Step 401: determine the influence score of each enterprise user based on the user information of each enterprise user.
在本申请的一些实施例中，企业用户的影响力分值可以为企业用户对于计算个人用户的可信度信息时的影响力参量值。比如，企业用户与个人用户间的交互越具有针对性，则说明企业用户对个人用户的可信度信息计算的影响力越高。In some embodiments of the present application, the influence score of the enterprise user can be the influence parameter value of the enterprise user in calculating the credibility information of the individual user. For example, the more targeted the interaction between the enterprise user and the individual user is, the higher the influence of the enterprise user on the credibility information calculation of the individual user is.
作为一种可能的实现方式，每个企业用户的用户信息包括每个企业用户发送的正常消息量、每个企业用户发送的总消息量、每个企业用户覆盖的个人用户量、每个企业用户与各个地域的用户的交互量。每个企业用户的影响力分值包括第一影响力分值、第二影响力分值和第三影响力分值。第一影响力分值、第二影响力分值和第三影响力分值均可以为0-1之间的值。根据每个企业用户的用户信息，确定每个企业用户的影响力分值的实现过程包括以下步骤：As a possible implementation method, the user information of each enterprise user includes the normal message volume sent by each enterprise user, the total message volume sent by each enterprise user, the number of personal users covered by each enterprise user, and the interaction volume between each enterprise user and users in each region. The influence score of each enterprise user includes a first influence score, a second influence score, and a third influence score. The first influence score, the second influence score, and the third influence score can all be values between 0 and 1. Based on the user information of each enterprise user, the implementation process of determining the influence score of each enterprise user includes the following steps:
步骤401-1，根据正常消息量和总消息量，确定每个企业用户的第一影响力分值。Step 401 - 1 , determining the first influence score of each enterprise user according to the normal message volume and the total message volume.
可以理解，比如发送推销信息、广告信息或者其他违规消息的企业用户，其发送的对象具备针对性，且发送的内容对于表明用户身份信息并无作用。所以可以根据企业用户发送违规消息的情况，来确定企业用户的第一影响力分值。It is understandable that, for example, corporate users who send promotional information, advertising information or other illegal messages have targeted recipients, and the content sent has no effect on indicating the user's identity information. Therefore, the first influence score of corporate users can be determined based on the illegal messages sent by corporate users.
在申请的一些实施例中，企业用户的第一影响力分值为基于企业用户发送违规消息的情况来确定的企业用户的影响力分值。每个企业用户发送的正常消息量是指每个企业用户发送的总消息量去掉违规消息之后剩余的消息量。In some embodiments of the application, the first influence score of the enterprise user is the influence score of the enterprise user determined based on the situation of the enterprise user sending illegal messages. The normal message volume sent by each enterprise user refers to the total message volume sent by each enterprise user after removing the illegal messages.
作为一种示例，可以将每个企业用户发送的正常消息量与总消息量的比值，确定为每个企业用户的第一影响力分值。若企业用户发送的违规消息越小，该企业用户的可信度越高，该企业用户的第一影响力分值越大。As an example, the ratio of the normal message volume to the total message volume sent by each enterprise user can be determined as the first influence score of each enterprise user. If the number of illegal messages sent by an enterprise user is smaller, the credibility of the enterprise user is higher, and the first influence score of the enterprise user is larger.
步骤401-2，将每个企业用户覆盖的个人用户量从大到小进行排序，并根据排序结果确定每个企业用户的第二影响力分值。Step 401 - 2 , sorting the number of individual users covered by each enterprise user from large to small, and determining the second influence score of each enterprise user according to the sorting result.
可以理解，某个企业用户覆盖的个人用户量越多，一般可认为该企业用户与个人用户间的交互针对性较低，比如，运营商、银行等具有一定公共属性的企业用户，其覆盖的个人用户量较多。而覆盖个人用户较少的企业用户，比如学校、企业等与个人用户之间的交互具有较强的针对性，有助于表明交互对象的身份。所以每个企业用户覆盖的个人用户量越大，其对个人用户的影响越大。It is understandable that the more individual users a certain enterprise user covers, the less targeted the interaction between the enterprise user and individual users. For example, enterprise users with certain public attributes such as operators and banks cover a large number of individual users. However, the interaction between enterprise users that cover fewer individual users, such as schools and enterprises, and individual users is more targeted and helps to indicate the identity of the interaction object. Therefore, the more individual users each enterprise user covers, the greater its influence on individual users.
在本申请的一些实施例中，可以将每个企业用户覆盖的个人用户量从大到小进行排序，并根据排序结果确定每个企业用户在该排序结果中的位置，将每个企业用户在排序结果中的位置的百分位数作为每个企业用户的第二影响力分值。企业用户的第二影响力分值越接近1，说明该企业用户覆盖个人用户量越少，对于评价个人用户的影响力越大。In some embodiments of the present application, the number of individual users covered by each enterprise user can be ranked from large to small, and the position of each enterprise user in the ranking result can be determined according to the ranking result, and the percentile of the position of each enterprise user in the ranking result can be used as the second influence score of each enterprise user. The closer the second influence score of an enterprise user is to 1, the fewer individual users the enterprise user covers, and the greater the influence on the evaluation of individual users.
需要说明的是，考虑到一个正常的个人用户通常会与运营商银行等第二影响力分值较低的企业用户存在交互，而违规用户一般与该类型的企业用户的交互较少，因此对于第二影响力分值接近0的企业用户，其对个人用户也是具备一定影响力，所以可以将百分位数小于0.1的企业用户的第二影响力分值均置为0.1。It should be noted that, considering that a normal individual user usually interacts with corporate users with lower second influence scores such as operators and banks, and illegal users generally have fewer interactions with this type of corporate users, corporate users with a second influence score close to 0 also have a certain influence on individual users. Therefore, the second influence scores of corporate users with percentiles less than 0.1 can be set to 0.1.
步骤401-3，根据每个企业用户与各个地域的用户的交互量，确定每个企业用户的第三影响力分值。Step 401 - 3 , determining a third influence score of each enterprise user according to the amount of interaction between each enterprise user and users in each region.
由于企事业单位、学校等针对性较强的企业用户，其交互的对象大多来源于同一地域，而一些针对性较弱的企业用户其交互的对象地域分别则较为分散，所以可以将企业用户与各个地域的用户的交互量也作为评估企业用户影响力的另一因素。Since the objects of interaction of enterprise users with strong targeting, such as enterprises, institutions, and schools, are mostly from the same region, while the objects of interaction of some enterprise users with weaker targeting are more dispersed in different regions, the amount of interaction between enterprise users and users in different regions can also be used as another factor in evaluating the influence of enterprise users.
在本申请的一些实施例中，根据每个企业用户与各个地域的用户的交互量，确定每个企业用户的第三影响力分值的实现过程可以包括：针对每个企业用户，将该企业用户与各个地域的用户的交互量从大到小进行排序，基于排序结果，确定排序前N个地域的交互量之和；根据该企业用户与各个地域的用户的交互量，确定该企业用户与所有地域的用户的总交互量；将排序前N个地域的交互量之和与总交互量的比值，确定为该企业用户的第三影响力分值。In some embodiments of the present application, the implementation process of determining the third influence score of each enterprise user based on the amount of interaction between each enterprise user and users in each region may include: for each enterprise user, sorting the amount of interaction between the enterprise user and users in each region from large to small, and based on the sorting result, determining the sum of the interaction amounts of the top N regions in the sort; determining the total interaction amount of the enterprise user with users in all regions based on the amount of interaction between the enterprise user and users in each region; and determining the ratio of the sum of the interaction amounts of the top N regions in the sort to the total interaction amount as the third influence score of the enterprise user.
作为一种示例，N可以取3，上述计算过程如公式(7)所示：As an example, N can be 3, and the above calculation process is shown in formula (7):
其中，Pc为企业用户的第三影响力分值；Ntop3表示排序前3个地域的交互量之和；Nall表示企业用户在设定的时间段内的各个地域的总交互量。Among them, Pc is the third influence score of the enterprise user; Ntop3 represents the sum of the interactions of the top three regions; Nall represents the total interactions of the enterprise users in each region within the set time period.
需要说明的是，本申请实施例中每个企业用户的用户信息包括每个企业用户发送的正常消息量、每个企业用户发送的总消息量、每个企业用户覆盖的个人用户量、每个企业用户与各个地域的用户的交互量，均可以为一段时间内的数据，此处的一段时间与上述实施例中的预设时间段可以相同也可以不同。It should be noted that the user information of each enterprise user in the embodiment of the present application includes the normal message volume sent by each enterprise user, the total message volume sent by each enterprise user, the number of personal users covered by each enterprise user, and the interaction volume between each enterprise user and users in various regions. All of these can be data within a period of time. The period of time here may be the same as or different from the preset time period in the above embodiment.
步骤402，根据每个企业用户的影响力分值和第二通信交互数据，确定个人用户受每个企业用户影响的分值。Step 402: Determine the score of the influence of each enterprise user on the individual user according to the influence score of each enterprise user and the second communication interaction data.
在本申请的一些实施例中，可以根据第二通信交互数据，确定个人用户与每个企业用户的交互量和交互类型，其中，交互类型包括消息类型和通话类型；根据个人用户与每个企业用户的交互类型，确定每个企业用户的三个影响力分值的权重值；根据影响力分值的权重值，对每个企业用户的第一影响力分值、第二影响力分值和第三影响力分值进行加权求和；根据个人用户与每个企业用户的交互量，确定个人用户与每个企业用户的紧密度；根据个人用户与每个企业用户的紧密度，以及上述加权求和结果，确定个人用户受企业用户的影响分值。In some embodiments of the present application, the amount and type of interaction between the personal user and each corporate user can be determined based on the second communication interaction data, wherein the interaction type includes a message type and a call type; the weight values of the three influence scores of each corporate user are determined based on the interaction type between the personal user and each corporate user; the first influence score, the second influence score, and the third influence score of each corporate user are weighted and summed based on the weight values of the influence scores; the closeness between the personal user and each corporate user is determined based on the amount of interaction between the personal user and each corporate user; the influence score of the personal user affected by the corporate user is determined based on the closeness between the personal user and each corporate user and the above-mentioned weighted summation result.
步骤403，根据个人用户受每个企业用户影响的分值，确定个人用户受企业用户影响的总分值。Step 403: Determine the total score of the influence of the enterprise users on the individual user according to the score of the influence of each enterprise user on the individual user.
可以理解，与个人用户存在交互的企业用户的数量越多，说明该个人用户的可信程度越高。在本申请的一些实施例中，可以针对每个个人用户，将该个人用户受每个企业用户影响的分值进行求和计算，得到每个个人用户受企业用户影响的总分值。It is understandable that the more corporate users that interact with an individual user, the more trustworthy the individual user is. In some embodiments of the present application, for each individual user, the score of the individual user influenced by each corporate user can be summed up to obtain the total score of each individual user influenced by the corporate user.
根据本申请实施例的基于交互关系的用户识别方法，根据每个企业用户的用户信息，分别从违规消息占比、覆盖用户量和地域分布三个维度进行企业用户的影响力计算，并根据企业用户的影响力分值和第二通信交互数据，确定个人用户受每个企业用户影响的分值，并根据个人用户受每个企业用户影响的分值，确定个人用户受企业用户影响的总分值，以确定个人用户的第二可信度信息。本方案从多个不同的维度来计算企业用户的影响力分值，可以综合考虑企业用户的影响力，从而可以提升个人用户的第二可信度信息的准确性，进而提升用户识别的准确性。According to the interactive relationship-based user identification method of the embodiment of the present application, based on the user information of each enterprise user, the influence of the enterprise user is calculated from three dimensions: the proportion of illegal messages, the number of covered users, and the geographical distribution. Based on the influence score of the enterprise user and the second communication interaction data, the score of the individual user affected by each enterprise user is determined, and based on the score of the individual user affected by each enterprise user, the total score of the individual user affected by the enterprise user is determined to determine the second credibility information of the individual user. This solution calculates the influence score of the enterprise user from multiple different dimensions, and can comprehensively consider the influence of the enterprise user, thereby improving the accuracy of the second credibility information of the individual user, and then improving the accuracy of user identification.
图5为本申请实施例中的一种确定个人用户受每个企业用户影响的分值的流程图。如图5所示，基于上述实施例，图4中的步骤402的实现方式可以包括以下步骤：FIG5 is a flow chart of determining the score of an individual user affected by each enterprise user in an embodiment of the present application. As shown in FIG5, based on the above embodiment, the implementation method of step 402 in FIG4 may include the following steps:
步骤501，根据第二通信交互数据，确定个人用户与每个企业用户之间的交互类型；其中，交互类型包括通话类型和消息类型。Step 501: Determine the interaction type between the individual user and each enterprise user according to the second communication interaction data; wherein the interaction type includes a call type and a message type.
在本申请实施例中，可以个人用户与企业用户之间的交互方式可以包括短信相交线、5G消息、电话、5G视频通话、文件调查、语音留意等，所以可以将个人用户与企业用户之间的交互方式分为通话类型和消息类型。其中，消息类型可以包括企业用户向个人用户发送短信、5G消息、问卷调查等。比如，余额提醒、验证码下发、用户满意度调查等。通话类型可以包括电话、视频通话等类型的交互方式。In the embodiment of the present application, the interaction mode between individual users and enterprise users may include SMS, 5G messages, phone calls, 5G video calls, file searches, voice calls, etc., so the interaction mode between individual users and enterprise users can be divided into call types and message types. Among them, the message type may include enterprise users sending SMS, 5G messages, questionnaires, etc. to individual users. For example, balance reminders, verification code issuance, user satisfaction surveys, etc. The call type may include phone calls, video calls and other types of interaction modes.
步骤502，根据交互类型，将至少一个企业用户划分为i个第一类企业用户和j个第二类企业用户；其中，i和j均为大于或者等于0的整数，第一类企业用户所对应的交互类型包括通话类型，第二类企业用户所对应的交互类型仅包括消息类型。Step 502: According to the interaction type, at least one enterprise user is divided into i first-category enterprise users and j second-category enterprise users; wherein i and j are both integers greater than or equal to 0, the interaction type corresponding to the first-category enterprise users includes the call type, and the interaction type corresponding to the second-category enterprise users includes only the message type.
作为一种示例，可以将个人用户与企业用户之间的交互类型包括通话类型时所对应的企业用户划分为第一类企业用户；将个人用户与企业用户之间的交互类型只包括消息类型时所对应的企业用户划分为第二类企业用户。As an example, the enterprise users corresponding to when the interaction type between personal users and enterprise users includes call type can be classified as first-category enterprise users; and the enterprise users corresponding to when the interaction type between personal users and enterprise users only includes message type can be classified as second-category enterprise users.
步骤503，根据每个第一类企业用户的第一影响力分值，确定个人用户受每个第一类企业用户影响的分值。Step 503: Determine the score of the individual user influenced by each first-category enterprise user according to the first influence score of each first-category enterprise user.
可以理解，若个人用户与企业用户之间的交互类型包括通话类型，比如个人用户与运营商、银行人工客服等存在通话行为，则可以认为该个人用户的可信度较高，此时对于个人用户的第二可信度信息的计算并不依赖于企业用户对交互对象是否具有针对性，所以可以基于用于表征企业用户违规消息发送情况的第一影响力分值，来确定个人用户受每个第一类企业用户影响的分值。It can be understood that if the interaction type between an individual user and a corporate user includes a call type, such as a call between an individual user and an operator, a bank's customer service representative, etc., then the individual user can be considered to have a higher degree of credibility. At this time, the calculation of the second credibility information for the individual user does not depend on whether the corporate user is targeted at the interaction object, so the score of the individual user's influence by each first-category corporate user can be determined based on the first influence score used to characterize the corporate user's sending of illegal messages.
步骤504，根据每个第二类企业用户的影响力分值和第二通信交互数据，确定个人用户受每个第二类企业用户影响的分值。Step 504 : determining the score of the individual user influenced by each second-category enterprise user according to the influence score of each second-category enterprise user and the second communication interaction data.
若个人用户与企业用户之间仅存在消息类型的交互，则说明对于该个人用户的第二可信度计算主要依赖于企业用户对交互对象的针对性上，所以企业用户对交互对象针对性越强其对个人用户的影响力越大。If there is only message-type interaction between the individual user and the corporate user, it means that the second credibility calculation for the individual user mainly depends on the corporate user's targeting of the interaction object. Therefore, the stronger the corporate user's targeting of the interaction object, the greater its influence on the individual user.
在本申请的一些实施例中，步骤504的实现过程可以包括：根据每个第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值，确定每个第二类企业用户的综合影响力分值；根据第二通信交互数据确定个人用户与每个第二类企业用户的紧密度；根据个人用户与每个第二类企业用户的紧密度，以及每个第二类企业用户的综合影响力分值，确定个人用户受每个第二类企业用户影响的分值。In some embodiments of the present application, the implementation process of step 504 may include: determining the comprehensive influence score of each second-category enterprise user based on the first influence score, the second influence score and the third influence score of each second-category enterprise user; determining the closeness between the individual user and each second-category enterprise user based on the second communication interaction data; determining the score of the individual user influenced by each second-category enterprise user based on the closeness between the individual user and each second-category enterprise user and the comprehensive influence score of each second-category enterprise user.
针对每个个人用户，将该个人用户受每个第一类企业用户的影响分值和个人用户受每个第二类企业用户的影响分值进行求和计算，得到该个人用户受企业用户影响的总分值。For each individual user, the influence score of each first-category enterprise user on the individual user and the influence score of each second-category enterprise user on the individual user are summed up to obtain the total influence score of the enterprise user on the individual user.
根据本申请实施例的基于交互关系的用户识别方法，基于个人用户与企业用户之间的交互类型，将交互类型为通话类型的企业用户划分为第一企业用户，将交互类型仅包括消息类型的企业用户划分为第二企业用户，并针对第一企业用户和第二企业用户，分别计算用户受每个企业用户影响的分值。本方案针对不同交互类型下的企业用户分别确定个人用户受企业用户影响的分值，可以有效地提高个人用户的可信度信息计算的准确性，从而可以进一步提升用户识别的准确性。According to the user identification method based on interaction relationship of the embodiment of the present application, based on the interaction type between the personal user and the corporate user, the corporate user whose interaction type is call type is classified as the first corporate user, and the corporate user whose interaction type only includes message type is classified as the second corporate user, and for the first corporate user and the second corporate user, the score of the user affected by each corporate user is calculated respectively. This solution determines the score of the personal user affected by the corporate user for corporate users under different interaction types, which can effectively improve the accuracy of the calculation of the personal user's credibility information, thereby further improving the accuracy of user identification.
接下来，将针对确定个人用户受每个第二类企业用户影响的分值的过程进行介绍。Next, the process of determining the score of an individual user's influence by each second-category enterprise user will be introduced.
图6为本申请实施例中的一种确定个人用户受每个第二类企业用户的影响分值的流程图。如图6所示，基于上述实施例，图5中的步骤504的实现过程可以包括以下步骤：FIG6 is a flow chart of determining the influence score of each second-category enterprise user on an individual user in an embodiment of the present application. As shown in FIG6 , based on the above embodiment, the implementation process of step 504 in FIG5 may include the following steps:
步骤601，根据每个第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值，确定每个第二类企业用户的综合影响力分值。Step 601: Determine the comprehensive influence score of each second-category enterprise user according to the first influence score, the second influence score, and the third influence score of each second-category enterprise user.
在本申请的一些实施例中，可以将每个第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值进行加权求和，其中各个影响力分值的权重值可以为预先设定的，并将加权求和结果作为每个第二类企业用户的综合影响力分值。In some embodiments of the present application, the first influence score, the second influence score and the third influence score of each second-category enterprise user may be weighted and summed, wherein the weight value of each influence score may be pre-set, and the weighted sum result may be used as the comprehensive influence score of each second-category enterprise user.
在本申请的另一些实施例中，可以将每个第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值的乘积作为每个第二类企业用户的综合影响力分值。In other embodiments of the present application, the product of the first influence score, the second influence score, and the third influence score of each second-category enterprise user may be used as the comprehensive influence score of each second-category enterprise user.
由于企业用户的第二影响力分值与第三影响力分值有关联性，企业用户的覆盖人数较少时，企业用户的地域离散度也较低，所以为了避免由于地域离散度也较低造成企业用户的综合影响力分值过低，步骤601还可以通过以下方式实现：针对每个第二类企业用户，将第二类企业用户的第二影响力分值与预设的影响力阈值进行比对；若第二类企业用户的第二影响力分值大于影响力阈值，根据第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值，确定第二类企业用户的综合影响力分值；若第二类企业用户的第二影响力分值小于或者等于影响力阈值，根据第二类企业用户的第一影响力分值、第二影响力分值，确定第二类企业用户的综合影响力分值。Since the second influence score of an enterprise user is correlated with the third influence score, when the number of people covered by an enterprise user is small, the geographical dispersion of the enterprise user is also low. Therefore, in order to avoid the comprehensive influence score of the enterprise user being too low due to the low geographical dispersion, step 601 can also be implemented in the following way: for each second-category enterprise user, the second influence score of the second-category enterprise user is compared with a preset influence threshold; if the second influence score of the second-category enterprise user is greater than the influence threshold, the comprehensive influence score of the second-category enterprise user is determined according to the first influence score, the second influence score and the third influence score of the second-category enterprise user; if the second influence score of the second-category enterprise user is less than or equal to the influence threshold, the comprehensive influence score of the second-category enterprise user is determined according to the first influence score and the second influence score of the second-category enterprise user.
举例而言，步骤601的实现过程如公式(8)所示，若第二类企业用户的第二影响力分值大于影响力阈值，则将第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值的乘积作为第二类企业用户的综合影响力分值；若第二类企业用户的第二影响力分值小于或者等于影响力阈值，则将第二类企业用户的第一影响力分值和第二影响力分值的乘积作为第二类企业用户的综合影响力分值。For example, the implementation process of step 601 is shown in formula (8). If the second influence score of the second category of enterprise users is greater than the influence threshold, the product of the first influence score, the second influence score and the third influence score of the second category of enterprise users is used as the comprehensive influence score of the second category of enterprise users; if the second influence score of the second category of enterprise users is less than or equal to the influence threshold, the product of the first influence score and the second influence score of the second category of enterprise users is used as the comprehensive influence score of the second category of enterprise users.
其中，Pa为企业用户的第一影响力分值；Pb为企业用户的第二影响力分值；Pc为企业用户的第三影响力分值；θ为影响力阈值。Among them, Pa is the first influence score of the enterprise user; Pb is the second influence score of the enterprise user; Pc is the third influence score of the enterprise user; θ is the influence threshold.
步骤602，根据第二通信交互数据和每个第二类企业用户的综合影响力分值，确定个人用户受每个第二类企业用户影响的分值。Step 602: Determine the score of the influence of each second-category enterprise user on the individual user based on the second communication interaction data and the comprehensive influence score of each second-category enterprise user.
作为一种示例，可以根据第二通信交互数据，确定个人用户与每个第二类企业用户的紧密度，再根据每个第二类企业用户的综合影响力分值和个人用户与每个第二类企业用户的紧密度，确定个人用户受每个第二类企业用户影响的分值。As an example, the closeness between an individual user and each second-category enterprise user can be determined based on the second communication interaction data, and then the score of the individual user's influence by each second-category enterprise user can be determined based on the comprehensive influence score of each second-category enterprise user and the closeness between the individual user and each second-category enterprise user.
可以理解，个人用户与第二类企业用户之间可以包括单向交互也可以包括双向交互。若个人用户与第二类企业用户之间只存在单向交互，则单向交互次数越多，说明二者之间的联系越紧密，传播得到的影响越大。若个人用户与第二类企业用户之间存在双向交互，也可以确定在之间的联系比较紧密。所以，为了表征个人用户与第二类企业用户之间联系的紧密程度，可以通过计算紧密度来表示。It can be understood that the interaction between individual users and the second type of enterprise users can include one-way interaction or two-way interaction. If there is only one-way interaction between individual users and the second type of enterprise users, the more one-way interactions there are, the closer the connection between the two is, and the greater the impact of the communication. If there is a two-way interaction between the individual user and the second type of enterprise users, it can also be determined that the connection between them is relatively close. Therefore, in order to characterize the closeness of the connection between the individual user and the second type of enterprise users, the closeness can be expressed by calculating.
在本申请的一些实施例中，图6中的步骤602的实现过程可以包括以下步骤：In some embodiments of the present application, the implementation process of step 602 in FIG. 6 may include the following steps:
步骤602-1，根据第二通信交互数据，确定个人用户与每个第二类企业用户的交互方向或者单向交互次数。Step 602-1: Determine the interaction direction or one-way interaction times between the individual user and each second-category enterprise user according to the second communication interaction data.
在本申请的一些实施例中，若个人用户与某个第二类企业用户的交互方向仅包括单向交互，可以根据第二类通信交互数据确定二者之间的单向交互次数。若个人用户与某个第二类企业用户的交互方向包括双向交互，可以不再需要获取二者之间的单向交互次数。In some embodiments of the present application, if the interaction direction between the individual user and a second-category enterprise user includes only one-way interaction, the number of one-way interactions between the two can be determined based on the second-category communication interaction data. If the interaction direction between the individual user and a second-category enterprise user includes two-way interaction, it is no longer necessary to obtain the number of one-way interactions between the two.
步骤602-2，根据个人用户与每个第二类企业用户的交互方向或者单向交互次数，确定个人用户与每个第二类企业用户的紧密度。Step 602-2: Determine the closeness between the individual user and each second-category enterprise user according to the interaction direction or the number of one-way interactions between the individual user and each second-category enterprise user.
在本申请的一些实施例中，紧密度为表征个人用户与第二类企业用户之间联系的紧密程度，紧密度可以为0-1之间的值。针对每个第二类企业用户，若个人用户与该第二类企业用户的交互方向为单向交互，可以根据个人用户与该第二类企业用户的单向交互次数，确定个人用户与每个第二类企业用户的紧密度。若个人用户与该第二类企业用户的交互方向为双向交互，可以认为个人用户与该第二类企业用户具有较紧密的联系，可以直接将个人用户与该第二类企业用户的紧密度确定为1。In some embodiments of the present application, the closeness is a measure of the closeness of the connection between the individual user and the second-category enterprise user, and the closeness can be a value between 0 and 1. For each second-category enterprise user, if the interaction direction between the individual user and the second-category enterprise user is a one-way interaction, the closeness between the individual user and each second-category enterprise user can be determined based on the number of one-way interactions between the individual user and the second-category enterprise user. If the interaction direction between the individual user and the second-category enterprise user is a two-way interaction, it can be considered that the individual user has a close connection with the second-category enterprise user, and the closeness between the individual user and the second-category enterprise user can be directly determined as 1.
作为一种示例，若个人用户与第二类企业用户的交互方向为单向交互，根据个人用户与该第二类企业用户的单向交互次数，确定个人用户与该第二类企业用户的紧密度的实现方式可以包括：基于预先设定单向交互次数与紧密度的映射关系，根据个人用户与该第二类企业用户的单向交互次数，确定个人用户与该第二类企业用户的紧密度。As an example, if the interaction direction between the personal user and the second category of enterprise users is one-way interaction, the implementation method of determining the closeness between the personal user and the second category of enterprise users based on the number of one-way interactions between the personal user and the second category of enterprise users may include: based on a pre-set mapping relationship between the number of one-way interactions and closeness, determining the closeness between the personal user and the second category of enterprise users based on the number of one-way interactions between the personal user and the second category of enterprise users.
作为另一种示例，可以预先设定单向交互次数参照值，每个第二类企业用户的单向交互次数参照值可以是相同的，也可以是不同的。比如，可以针对每个第二类企业用户，将该第二类企业用户与每个个人用户的单向交互次数进行排序，并将排序结果中的中位数确定为该第二类企业用户的单向交互次数参照值。如公式(9)所示，若个人用户与该第二类企业用户该单向交互次数大于该单向交互次数参照值，则可以将个人用户与该第二类企业用户的紧密度确定为1，否则可以将个人用户与该第二类企业用户该单向交互次数与单向次数参照值的比值，作为个人用户与该第二类企业用户的紧密度。As another example, a reference value of the number of one-way interactions may be preset, and the reference value of the number of one-way interactions for each second-category enterprise user may be the same or different. For example, for each second-category enterprise user, the number of one-way interactions between the second-category enterprise user and each individual user may be ranked, and the median of the ranking result may be determined as the reference value of the number of one-way interactions for the second-category enterprise user. As shown in formula (9), if the number of one-way interactions between the individual user and the second-category enterprise user is greater than the reference value of the number of one-way interactions, the closeness between the individual user and the second-category enterprise user may be determined as 1, otherwise the ratio of the number of one-way interactions between the individual user and the second-category enterprise user to the reference value of the number of one-way interactions may be used as the closeness between the individual user and the second-category enterprise user.
其中，Eui为个人用户与第二类企业用户i的紧密度；imed为第二类企业用户i的单向交互次数参照值，该值可以为第二类企业用户i与每个个人用户的单向交互次数排序中的中位数；Rui为个人用户与第二类企业用户i的单向交互次数。Among them, Eui is the closeness between the individual user and the second-category enterprise user i; imed is the reference value of the number of one-way interactions of the second-category enterprise user i, which can be the median of the number of one-way interactions between the second-category enterprise user i and each individual user; Rui is the number of one-way interactions between the individual user and the second-category enterprise user i.
步骤602-3，根据个人用户与每个第二类企业用户的紧密度和每个第二类企业用户的综合影响力分值，确定个人用户受每个第二类企业用户影响的分值。Step 602-3, determining the score of the influence of each second-category enterprise user on the individual user according to the closeness between the individual user and each second-category enterprise user and the comprehensive influence score of each second-category enterprise user.
作为一种可能的实施方式，可以将个人用户与每个第二类企业用户的紧密度和每个第二类企业用户的综合影响力分值的乘积，确定为个人用户受每个第二类企业用户影响的分值。As a possible implementation, the score of the influence of each second-category enterprise user on the individual user may be determined as the product of the closeness between the individual user and each second-category enterprise user and the comprehensive influence score of each second-category enterprise user.
根据本申请实施例的基于交互关系的用户识别方法，通过每个第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值，确定每个第二类企业用户的综合影响力分值，根据第二通信交互数据和每个第二类企业用户的综合影响力分值，确定个人用户受每个第二类企业用户影响的分值。同时在确定个人用户受第二类企业用户影响的分值时，引入个人用户与第二类企业用户的紧密度，以提升确定个人用户受第二类企业用户影响的分值的准确性，从而可以进一步提升个人用户的可信度信息的准确性，进而可以提升用户识别的准确性。According to the interactive relationship-based user identification method of the embodiment of the present application, the comprehensive influence score of each second-category enterprise user is determined by the first influence score, the second influence score, and the third influence score of each second-category enterprise user, and the score of the individual user affected by each second-category enterprise user is determined according to the second communication interaction data and the comprehensive influence score of each second-category enterprise user. At the same time, when determining the score of the individual user affected by the second-category enterprise user, the closeness between the individual user and the second-category enterprise user is introduced to improve the accuracy of determining the score of the individual user affected by the second-category enterprise user, thereby further improving the accuracy of the individual user's credibility information, and further improving the accuracy of user identification.
图7为本申请实施例中的一种确定个人用户的第三可信度信息的流程图。如图7所示，基于上述实施例，图1中的步骤104的实现过程可以包括：FIG7 is a flow chart of determining the third credibility information of an individual user in an embodiment of the present application. As shown in FIG7 , based on the above embodiment, the implementation process of step 104 in FIG1 may include:
步骤701，基于物联网设备的影响力分值，根据第三通信交互数据，确定个人用户受物联网设备影响的总分值。Step 701: Based on the influence score of the IoT device and according to the third communication interaction data, determine the total score of the individual user affected by the IoT device.
作为一种可能的实施方式，可以根据第三通信交互数据，确定个人用户与每个物联网设备之间的交互次数；根据个人用户与每个物联网设备之间的交互次数，个人用户与所有物联网设备之间的总交互次数；根据个人用户与每个物联网设备之间的交互次数，以及个人用户与所有物联网设备之间的总交互次数，确定个人用户与每个物联网设备之间的交互次数占比；根据个人用户与每个物联网设备之间的交互次数占比，对与个人用户存在交互的物联网设备的影响分值进行加权求和，得到个人用户受物联网设备影响的总分值。As a possible implementation method, the number of interactions between an individual user and each IoT device can be determined based on the third communication interaction data; the total number of interactions between the individual user and all IoT devices can be determined based on the number of interactions between the individual user and each IoT device; the proportion of interactions between the individual user and each IoT device can be determined based on the number of interactions between the individual user and the total number of interactions between the individual user and all IoT devices; and the influence scores of IoT devices that interact with the individual user can be weighted summed based on the proportion of interactions between the individual user and each IoT device to obtain the total score of the individual user affected by the IoT devices.
步骤702，将个人用户受物联网设备影响的总分值进行排序，并根据排序结果确定个人用户的第三可信度信息。Step 702: sort the total scores of the individual users affected by the IoT devices, and determine the third credibility information of the individual users according to the sorting results.
在本申请的一些实施例中，可以将每个个人用户受物联网设备影响的总分值组成集合N，集合N中的元素数量为n，其中，n为个人用户的数量。将N中的元素从小到大进行排序，根据排序后N中各个元素的位置，来确定个人用户的第三可信度信息。In some embodiments of the present application, the total score of each individual user affected by the IoT device can be formed into a set N, and the number of elements in the set N is n, where n is the number of individual users. The elements in N are sorted from small to large, and the third credibility information of the individual user is determined according to the position of each element in N after sorting.
作为一种示例，个人用户的第三可信度信息可以为百分位数，如公式(10)所示。若排序后，个人用户u受物联网设备影响的总分值在集合N中最大，则个人用户u的第三可信度信息为1；若排序后个人用户u受物联网设备影响的总分值为集合N中的75％分位数，则个人用户u的第三可信度信息为0.75。As an example, the third credibility information of an individual user may be a percentile, as shown in formula (10). If after sorting, the total score of the individual user u affected by the IoT device is the largest in the set N, then the third credibility information of the individual user u is 1; if after sorting, the total score of the individual user u affected by the IoT device is the 75% percentile in the set N, then the third credibility information of the individual user u is 0.75.
Du＝percentile(N，Nu) (10)Du=percentile(N,Nu) (10)
其中，Du为个人用户u的第三可信度信息；N为每个个人用户受物联网设备影响的总分值组成集合；Nu为个人用户u受物联网设备影响的总分值。Wherein, Du is the third credibility information of individual user u; N is a set of total scores of each individual user affected by IoT devices; Nu is the total score of individual user u affected by IoT devices.
根据本申请实施例的基于交互关系的用户识别方法，基于物联网设备的影响力分值，根据第三通信交互数据，确定个人用户受物联网设备影响的总分值，并将个人用户受物联网设备影响的总分值进行排序，根据排序结果来确定个人用户的第三可信度信息。本方案通过引入个人用户与物联网设备之间的交互，来确定个人用户的第三可信度信息，以提升用户识别的准确性。According to the interactive relationship-based user identification method of the embodiment of the present application, based on the influence score of the IoT device and according to the third communication interaction data, the total score of the individual user affected by the IoT device is determined, and the total score of the individual user affected by the IoT device is sorted, and the third credibility information of the individual user is determined according to the sorting result. This solution determines the third credibility information of the individual user by introducing the interaction between the individual user and the IoT device to improve the accuracy of user identification.
接下来，将针对确定个人用户受物联网设备影响的总分值的过程进行介绍。Next, the process of determining the total score of an individual user's impact by an IoT device will be described.
图8为本申请实施例中的一种确定个人用户受物联网设备影响的总分值的流程图。如图8所示，基于上述实施例，图7中的步骤702的实现过程可以包括：FIG8 is a flow chart of determining the total score of an individual user affected by an IoT device in an embodiment of the present application. As shown in FIG8 , based on the above embodiment, the implementation process of step 702 in FIG7 may include:
步骤801，根据第三通信交互数据，确定与个人用户进行单向交互的m个第一物联网设备和与个人用户进行双向交互的n个第二物联网设备；其中，m和n均为大于或者等于0的整数。Step 801: Determine, based on third communication interaction data, m first Internet of Things devices that perform unidirectional interaction with an individual user and n second Internet of Things devices that perform bidirectional interaction with the individual user; wherein m and n are both integers greater than or equal to 0.
可以理解，根据第三通信交互数据，可以确定与个人用户存在交互的物联网设备，同时也可以确定个人用户与每个物联网设备之间的交互方向，即只存在单向交互，或者存在双向交互。单向交互是指只有物联网设备向个人用户发送消息，双向交互是指物联网设备可以向个人用户发送消息，同时个人用户也可以向物联网设备下发指令，例如，远程设置空调、远程开门等。It can be understood that, based on the third communication interaction data, the IoT devices that interact with the individual user can be determined, and the direction of interaction between the individual user and each IoT device can also be determined, that is, there is only one-way interaction or two-way interaction. One-way interaction means that only the IoT device sends messages to the individual user, and two-way interaction means that the IoT device can send messages to the individual user, and the individual user can also issue instructions to the IoT device, for example, remotely set the air conditioner, remotely open the door, etc.
步骤802，根据每个第一物联网设备的影响力分值，确定个人用户受第一物联网设备影响的分值。Step 802: Determine the score of the individual user influenced by the first Internet of Things device according to the influence score of each first Internet of Things device.
在本申请的一些实施例中，可以根据每个第一物联网设备的影响力分值，确定第一物联网设备的总影响力分值；基于预设的单向交互影响系数，根据第一物联网设备的总影响力分值，确定个人用户受第一物联网设备影响的分值。In some embodiments of the present application, the total influence score of the first Internet of Things device can be determined based on the influence score of each first Internet of Things device; based on a preset one-way interaction influence coefficient, the score of the individual user affected by the first Internet of Things device can be determined based on the total influence score of the first Internet of Things device.
作为一种示例，可以针对每个个人用户，将每个第一物联网设备的影响力分值进行求和计算，并将求和结果作为第一物联网设备的总影响力分值；将单向交互影响系数与第一物联网设备的总影响力分值的乘积，确定为该个人用户受第一物联网设备影响的分值。As an example, for each individual user, the influence score of each first Internet of Things device can be summed up and calculated, and the sum result can be used as the total influence score of the first Internet of Things device; the product of the one-way interaction influence coefficient and the total influence score of the first Internet of Things device can be determined as the score of the individual user affected by the first Internet of Things device.
步骤803，根据每个第二物联网设备的影响力分值，确定个人用户受第二物联网设备影响的分值。Step 803: Determine the score of the influence of the second Internet of Things device on the individual user according to the influence score of each second Internet of Things device.
在本申请的一些实施例中，根据每个第二物联网设备的影响力分值，确定个人用户受第二物联网设备影响的分值的实现过程可以包括：根据每个第二物联网设备的影响力分值，确定第二物联网设备的总影响力分值；基于预设的双向交互影响系数，根据第二物联网设备的总影响力分值，确定个人用户受第二物联网设备影响的分值。In some embodiments of the present application, the implementation process of determining the score of an individual user influenced by a second Internet of Things device based on the influence score of each second Internet of Things device may include: determining the total influence score of the second Internet of Things devices based on the influence score of each second Internet of Things device; and determining the score of an individual user influenced by the second Internet of Things devices based on the total influence score of the second Internet of Things devices based on a preset two-way interaction influence coefficient.
需要说明的是，由于与物联网设备进行双向交互的个人用户的可信度更高，所以通常双向交互影响系数大于单向交互影响系数，比如，单向交互影响系数与双向交互影响系数的比值可以为1:2。It should be noted that since the credibility of individual users who interact with IoT devices in two-way directions is higher, the two-way interaction influence coefficient is usually greater than the one-way interaction influence coefficient. For example, the ratio of the one-way interaction influence coefficient to the two-way interaction influence coefficient can be 1:2.
作为一种示例，可以针对每个个人用户，将每个第二物联网设备的影响力分值进行求和计算，并将求和结果作为第二物联网设备的总影响力分值；将双向交互影响系数与第二物联网设备的总影响力分值的乘积，确定为该个人用户受第二物联网设备的影响分值。As an example, for each individual user, the influence score of each second Internet of Things device can be summed up and calculated, and the sum result can be used as the total influence score of the second Internet of Things device; the product of the two-way interaction influence coefficient and the total influence score of the second Internet of Things device can be determined as the influence score of the individual user affected by the second Internet of Things device.
步骤804，根据个人用户受第一物联网设备影响的分值和个人用户受第二物联网设备影响的分值，确定个人用户受物联网设备影响的总分值。Step 804: Determine a total score of the impact of the individual user on the Internet of Things devices according to the score of the individual user being impacted by the first Internet of Things device and the score of the individual user being impacted by the second Internet of Things device.
在本申请的一些实施例中，可以将个人用户受第一物联网设备影响的分值与个人用户受第二物联网设备影响的分值进行求和计算，得到个人用户受物联网设备影响的总分值，其计算过程如公式(11)所示：In some embodiments of the present application, the score of the individual user affected by the first IoT device and the score of the individual user affected by the second IoT device may be summed to obtain the total score of the individual user affected by the IoT devices. The calculation process is shown in formula (11):
其中，Nu为个人用户u受物联网设备影响的总分值；m为与个人用户u存在交互的第一物联网设备的数量；n为与个人用户u存在交互的第二物联网设备的数量；Eui为第i个与个人用户u存在交互的第一物联网设备的影响力分值；Euj为第j个与个人用户u存在交互的第二物联网设备的影响力分值；d为单向交互影响系数；e为双向交互影响系数。Among them, Nu is the total score of the influence of IoT devices on individual user u; m is the number of first IoT devices that interact with individual user u; n is the number of second IoT devices that interact with individual user u; Eui is the influence score of the i-th first IoT device that interacts with individual user u; Euj is the influence score of the j-th second IoT device that interacts with individual user u; d is the one-way interaction influence coefficient; e is the two-way interaction influence coefficient.
根据本申请实施例的基于交互关系的用户识别方法，基于第三通信交互数据，将与个人用户存在交互的物联网设备按照交互方向，分为与个人用户进行单向交互的第一物联网设备和与个人用户进行双向交互的第二物联网设备，再分别根据各自的影响力分值分别确定个人用户受第一物联网设备影响的分值和个人用户受第二物联网设备影响的分值，并根据个人用户受第一物联网设备影响的分值和个人用户受第二物联网设备影响的分值，确定个人用户受物联网设备影响的总分值。本方案通过考虑不同的交互方向，来确定个人用户受物联网设备影响的总分值，以提升第三可信度信息计算的准确性，从而可以提升用户识别的准确性。According to the user identification method based on interactive relationship of the embodiment of the present application, based on the third communication interaction data, the IoT devices that interact with the individual user are divided into the first IoT device that interacts with the individual user in a one-way manner and the second IoT device that interacts with the individual user in a two-way manner according to the interaction direction, and then the score of the individual user affected by the first IoT device and the score of the individual user affected by the second IoT device are determined respectively according to their respective influence scores, and the total score of the individual user affected by the IoT devices is determined according to the score of the individual user affected by the first IoT device and the score of the individual user affected by the second IoT device. This solution determines the total score of the individual user affected by the IoT devices by considering different interaction directions, so as to improve the accuracy of the calculation of the third credibility information, thereby improving the accuracy of user identification.
图9为本申请实施例所提供的另一种基于交互关系的用户识别方法的流程图。如图9所示，该方法包括以下步骤：FIG9 is a flow chart of another user identification method based on interactive relationship provided by an embodiment of the present application. As shown in FIG9 , the method includes the following steps:
步骤901，获取在预设时间段内的通信交互数据、个人用户的用户信息和与个人用户通信交互的企业用户的用户信息；其中，通信交互数据包括在预设时间段内个人用户之间第一通信交互数据，以及个人用户与企业用户之间的第二通信交互数据。Step 901, obtaining communication interaction data within a preset time period, user information of individual users, and user information of corporate users who communicate and interact with individual users; wherein the communication interaction data includes first communication interaction data between individual users within the preset time period, and second communication interaction data between individual users and corporate users.
步骤902，根据个人用户的用户信息和第一通信交互数据，确定个人用户的第一可信度信息。Step 902: Determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data.
步骤903，根据企业用户的用户信息和第二通信交互数据，确定个人用户的第二可信度信息。Step 903: Determine the second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data.
需要说明的是，步骤901-903的实现过程可以参见上述实施例的图1-图6中的实现方式，此处不再赘述。It should be noted that the implementation process of steps 901-903 can refer to the implementation methods in Figures 1 to 6 of the above embodiments, and will not be repeated here.
步骤904，根据第一可信度信息和第二可信度信息，识别个人用户在预设时间段内是否为违规用户。Step 904: Identify whether the individual user is an illegal user within a preset time period based on the first credibility information and the second credibility information.
在本申请的一些实施例中，根据第一可信度信息和第二可信度信息，识别个人用户在预设时间段内是否为违规用户的实现方式可以包括：根据第一可信度信息和第二可信度信息，确定个人用户的可信度信息；根据个人用户的可信度信息，识别个人用户在预设时间段内是否为违规用户。In some embodiments of the present application, an implementation method for identifying whether an individual user is an illegal user within a preset time period based on the first credibility information and the second credibility information may include: determining the credibility information of the individual user based on the first credibility information and the second credibility information; and identifying whether the individual user is an illegal user within a preset time period based on the credibility information of the individual user.
作为一种示例，可以针对每个个人用户，将该个人用户的第一可信度信息和第二可信度信息进行加权求和，并将加权求和结果确定为该个人用户的可信度信息；若可信度信息为用于表示个人用户可信度的可信度分值，则可以预先设定可信度分值阈值，将该个人用户的可信度分值与可信度分值阈值进行比对，若该个人用户的可信度分值小于可信度分值阈值，则识别该个人用户在预设时间段内为违规用户，否则识别该个人用户在预设时间段内非违规用户。As an example, for each individual user, the first credibility information and the second credibility information of the individual user may be weightedly summed, and the weighted sum result may be determined as the credibility information of the individual user; if the credibility information is a credibility score used to represent the credibility of the individual user, a credibility score threshold may be set in advance, and the credibility score of the individual user may be compared with the credibility score threshold; if the credibility score of the individual user is less than the credibility score threshold, the individual user is identified as a violating user within a preset time period; otherwise, the individual user is identified as a non-violating user within the preset time period.
根据本申请实施例的基于交互关系的用户识别方法，基于个人用户与个人用户之间的通信交互和个人用户与企业用户之间的通信交互，可以充分考虑与个人用户存在交互关系的所有交互对象对个人用户的可信度信息的影响，将企业用户应用到个人用户的识别过程中，不仅可以提升个人用户可信度信息的准确性，同时也可以提升用户识别的准确性，为移动通信领域违规行为的治理提供了可靠的依据。According to the user identification method based on interactive relationships in the embodiment of the present application, based on the communication interactions between individual users and the communication interactions between individual users and corporate users, the influence of all interactive objects that have interactive relationships with individual users on the credibility information of individual users can be fully considered. Applying corporate users to the identification process of individual users can not only improve the accuracy of individual user credibility information, but also improve the accuracy of user identification, providing a reliable basis for the governance of illegal behaviors in the field of mobile communications.
图10为本申请实施例所提供的又一种基于交互关系的用户识别方法的流程图。如图10所示，该方法可以包括：FIG10 is a flow chart of another method for identifying a user based on an interactive relationship provided by an embodiment of the present application. As shown in FIG10 , the method may include:
步骤1001，获取在预设时间段内的通信交互数据和个人用户的用户信息；其中，通信交互数据包括在预设时间段内个人用户之间第一通信交互数据，以及个人用户与物联网设备之间的第三通信交互数据。Step 1001, obtaining communication interaction data and user information of individual users within a preset time period; wherein the communication interaction data includes first communication interaction data between individual users within the preset time period, and third communication interaction data between the individual user and the Internet of Things device.
步骤1002，根据个人用户的用户信息和第一通信交互数据，确定个人用户的第一可信度信息。Step 1002: Determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data.
步骤1003，基于预设的物联网设备的影响力分值，根据第三通信交互数据，确定个人用户的第三可信度信息。Step 1003: Determine third credibility information of the individual user based on the preset influence score of the IoT device and the third communication interaction data.
需要说明的是，步骤1001-1003的实现过程可以参见上述实施例的图1、图2、图7及图8中的实现方式，此处不再赘述。It should be noted that the implementation process of steps 1001-1003 can refer to the implementation methods in Figures 1, 2, 7 and 8 of the above embodiments, and will not be repeated here.
步骤1004，根据第一可信度信息和第三可信度信息，识别个人用户在预设时间段内是否为违规用户。Step 1004: Identify whether the individual user is an illegal user within a preset time period based on the first credibility information and the third credibility information.
在本申请的一些实施例中，根据第一可信度信息和第三可信度信息，识别个人用户在预设时间段内是否为违规用户的实现方式可以包括：根据第一可信度信息和第三可信度信息，确定个人用户的可信度信息；根据个人用户的可信度信息，识别个人用户在预设时间段内是否为违规用户。In some embodiments of the present application, an implementation method for identifying whether an individual user is a violating user within a preset time period based on the first credibility information and the third credibility information may include: determining the credibility information of the individual user based on the first credibility information and the third credibility information; and identifying whether the individual user is a violating user within a preset time period based on the credibility information of the individual user.
作为一种示例，可以针对每个个人用户，将该个人用户的第一可信度信息和第三可信度信息进行加权求和，并将加权求和结果确定为该个人用户的可信度信息；若可信度信息为用于表示个人用户可信度的可信度分值，则可以预先设定可信度分值阈值，将该个人用户的可信度分值与可信度分值阈值进行比对，若该个人用户的可信度分值小于可信度分值阈值，则识别该个人用户在预设时间段内为违规用户，否则识别该个人用户在预设时间段内非违规用户。As an example, for each individual user, the first credibility information and the third credibility information of the individual user may be weightedly summed, and the weighted sum result may be determined as the credibility information of the individual user; if the credibility information is a credibility score used to represent the credibility of the individual user, a credibility score threshold may be set in advance, and the credibility score of the individual user may be compared with the credibility score threshold; if the credibility score of the individual user is less than the credibility score threshold, the individual user is identified as a violating user within a preset time period; otherwise, the individual user is identified as a non-violating user within the preset time period.
根据本申请实施例的基于交互关系的用户识别方法，基于个人用户与个人用户之间的通信交互和个人用户与物联网设备的通信交互，可以充分考虑与个人用户存在交互关系的所有交互对象对个人用户的可信度信息的影响，将物联网设备到个人用户的识别过程中，不仅可以提升个人用户可信度信息的准确性，同时也可以提升用户识别的准确性，为移动通信领域违规行为的治理提供了可靠的依据。According to the user identification method based on interactive relationships in the embodiment of the present application, based on the communication interactions between individual users and the communication interactions between individual users and Internet of Things devices, the influence of all interactive objects that have interactive relationships with individual users on the credibility information of individual users can be fully considered. In the process of identifying Internet of Things devices to individual users, not only the accuracy of individual user credibility information can be improved, but also the accuracy of user identification can be improved, providing a reliable basis for the governance of illegal behaviors in the field of mobile communications.
图11为本申请实施例所提供的又一种基于交互关系的用户识别方法的流程图。如图11所示，该方法可以包括：FIG11 is a flow chart of another method for identifying a user based on an interactive relationship provided by an embodiment of the present application. As shown in FIG11 , the method may include:
步骤1101，获取在预设时间段内个人用户之间第一通信交互数据和个人用户的用户信息。Step 1101: Acquire first communication interaction data between individual users and user information of individual users within a preset time period.
步骤1102，根据用户信息，确定个人用户的初始可信度信息。Step 1102: Determine initial credibility information of the individual user based on the user information.
步骤1103，根据第一通信交互数据，确定个人用户作为主叫用户时与每个被叫用户的交互次数。Step 1103: Determine the number of interactions between the individual user as a calling user and each called user according to the first communication interaction data.
步骤1104，根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代运算，获得个人用户的第一可信度信息。Step 1104: performing an iterative operation based on the number of interactions between the individual user as a calling user and each called user and the initial credibility information to obtain the first credibility information of the individual user.
需要说明的是，步骤1101-1104的实现方式可以参见上述实施例的图1和图2中的实现方式，此处不再赘述。It should be noted that the implementation of steps 1101-1104 can refer to the implementation in FIG. 1 and FIG. 2 of the above embodiment, and will not be repeated here.
步骤1105，根据第一可信度信息，识别个人用户在预设时间段内是否为违规用户。Step 1105: Identify whether the individual user is an illegal user within a preset time period based on the first credibility information.
作为一种示例，第一可信度信息可以为用于表示个人用户可信度的可信度分值，可以以将第一可信度信息与可信度分值阈值进行比对，若个人用户的第一可信度信息小于可信度分值阈值，则识别个人用户在预设时间段内为违规用户，否则识别个人用户在预设时间段内非违规用户。As an example, the first credibility information may be a credibility score used to represent the credibility of an individual user. The first credibility information may be compared with a credibility score threshold. If the first credibility information of the individual user is less than the credibility score threshold, the individual user is identified as a violating user within a preset time period; otherwise, the individual user is identified as a non-violating user within the preset time period.
根据本申请实施例的基于交互关系的用户识别方法，通过用户信息先确定个人用户的初始可信度信息，再根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代计算，以获取个人用户的第一可信度信息，并根据第一可信度信息识别个人用户在预设时间段内是否为违规用户。本方案基于移动通信领域中用户之间的交互特点，将交互次数引入迭代计算中，通过交互次数来表达个人用户之间联系紧密度的依据，使得到的第一可信度信息更加准确，从而可以提升用户识别的准确性。According to the interactive relationship-based user identification method of the embodiment of the present application, the initial credibility information of the individual user is first determined through user information, and then iterative calculation is performed based on the number of interactions between the individual user and each called user when the individual user is a calling user and the initial credibility information to obtain the first credibility information of the individual user, and identify whether the individual user is an illegal user within a preset time period based on the first credibility information. This solution is based on the interactive characteristics between users in the field of mobile communications, introduces the number of interactions into the iterative calculation, and uses the number of interactions to express the basis for the closeness of the connection between individual users, so that the first credibility information obtained is more accurate, thereby improving the accuracy of user identification.
为了实现上述实施例，本申请提供了一种基于交互关系的用户识别装置。In order to implement the above embodiments, the present application provides a user identification device based on interaction relationship.
图12为本申请实施例所提供的一种基于交互关系的用户识别装置的结构框图。如图12所示，该装置包括：FIG12 is a structural block diagram of a user identification device based on interactive relationship provided in an embodiment of the present application. As shown in FIG12 , the device includes:
获取模块1210，用于获取在预设时间段内的通信交互数据、个人用户的用户信息、与个人用户通信交互的企业用户的用户信息；其中，通信交互数据包括在预设时间段内个人用户之间第一通信交互数据、个人用户与企业用户之间的第二通信交互数据和个人用户与物联网设备之间的第三通信交互数据；The acquisition module 1210 is used to acquire communication interaction data, user information of individual users, and user information of enterprise users who communicate and interact with individual users within a preset time period; wherein the communication interaction data includes first communication interaction data between individual users, second communication interaction data between individual users and enterprise users, and third communication interaction data between individual users and IoT devices within the preset time period;
第一确定模块1220，用于根据个人用户的用户信息和第一通信交互数据，确定个人用户的第一可信度信息；A first determination module 1220, configured to determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data;
第二确定模块1230，用于根据企业用户的用户信息和第二通信交互数据，确定个人用户的第二可信度信息；The second determination module 1230 is used to determine the second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data;
第三确定模块1240，用于基于预设的物联网设备的影响力分值，根据第三通信交互数据，确定个人用户的第三可信度信息；A third determination module 1240 is used to determine third credibility information of the individual user based on the influence score of the preset IoT device and the third communication interaction data;
识别模块1250，用于根据第一可信度信息、第二可信度信息和第三可信度信息，识别个人用户在预设时间段内是否为违规用户。The identification module 1250 is used to identify whether the individual user is an illegal user within a preset time period according to the first credibility information, the second credibility information and the third credibility information.
在本申请的一些实施例中，第一确定模块1220具体用于：In some embodiments of the present application, the first determining module 1220 is specifically configured to:
根据个人用户的用户信息，确定个人用户的初始可信度信息；Determining initial credibility information of the individual user based on the user information of the individual user;
根据第一通信交互数据，确定个人用户作为主叫用户时与每个被叫用户的交互次数；Determining the number of interactions between the individual user as a calling user and each called user according to the first communication interaction data;
根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代运算，获得个人用户的第一可信度信息。An iterative calculation is performed based on the number of interactions between the individual user as a calling user and each called user and the initial credibility information to obtain the first credibility information of the individual user.
作为一种示例，第一确定模块1220具体用于：As an example, the first determining module 1220 is specifically configured to:
根据个人用户的用户信息，确定个人用户的用户特征信息；其中，所述用户特征信息包括用户属性特征信息、用户级别特征信息和用户地域特征信息。Determine user characteristic information of the individual user according to the user information of the individual user; wherein the user characteristic information includes user attribute characteristic information, user level characteristic information and user region characteristic information.
将用户特征信息输入至预设的初始评分机器学习模型，获得初始可信度信息；其中，初始评分机器学习模块已学习得到个人用户的用户特征信息与初始可信度信息的映射关系。The user characteristic information is input into a preset initial scoring machine learning model to obtain initial credibility information; wherein the initial scoring machine learning module has learned the mapping relationship between the user characteristic information of the individual user and the initial credibility information.
在本申请的一些实施例中，第一确定模块1220还用于：In some embodiments of the present application, the first determining module 1220 is further configured to:
根据个人用户作为主叫用户时与每个被叫用户的交互次数，确定个人用户作为主叫用户时与每个被叫用户之间的交互占比；Determine the interaction ratio between the individual user as the calling user and each called user according to the number of interactions between the individual user as the calling user and each called user;
基于网页排名Pagerank算法，根据个人用户作为主叫用户时与每个被叫用户之间的交互占比和初始可信度信息进行迭代运算，获取第一可信度信息。Based on the Pagerank algorithm, an iterative operation is performed according to the interaction ratio between the individual user as a calling user and each called user and the initial credibility information to obtain the first credibility information.
在本申请的一些实施例中，第二确定模块1230包括：In some embodiments of the present application, the second determination module 1230 includes:
第一确定单元1231，用于根据企业用户的用户信息和第二通信交互数据，确定个人用户受企业用户影响的总分值；The first determining unit 1231 is used to determine the total score of the individual user affected by the enterprise user according to the user information of the enterprise user and the second communication interaction data;
第二确定单元1232，用于将个人用户受企业用户影响的总分值进行排序，并根据排序结果确定个人用户的第二可信度信息。The second determining unit 1232 is used to sort the total scores of the personal users affected by the enterprise users, and determine the second credibility information of the personal users according to the sorting result.
作为一种可能的实施方式，企业用户的数量为至少一个；第一确定单元1231具体用于：As a possible implementation manner, the number of enterprise users is at least one; the first determining unit 1231 is specifically configured to:
根据每个企业用户的用户信息，确定每个企业用户的影响力分值；Determine the influence score of each enterprise user based on the user information of each enterprise user;
根据每个企业用户的影响力分值和第二通信交互数据，确定个人用户受每个企业用户影响的分值；Determine the score of the individual user influenced by each enterprise user according to the influence score of each enterprise user and the second communication interaction data;
根据个人用户受每个企业用户影响的分值，确定个人用户受企业用户影响的总分值。The total score of the influence of enterprise users on individual users is determined based on the score of the influence of each enterprise user on the individual user.
作为一种示例，每个企业用户的用户信息包括每个企业用户发送的正常消息量、每个企业用户发送的总消息量、每个企业用户覆盖的个人用户量、每个企业用户与各个地域的用户的交互量；每个企业用户的影响力分值包括第一影响力分值、第二影响力分值和第三影响力分值；第一确定单元1231还用于：As an example, the user information of each enterprise user includes the normal message volume sent by each enterprise user, the total message volume sent by each enterprise user, the number of individual users covered by each enterprise user, and the interaction volume between each enterprise user and users in each region; the influence score of each enterprise user includes a first influence score, a second influence score, and a third influence score; the first determination unit 1231 is further used to:
根据正常消息量和总消息量，确定每个企业用户的第一影响力分值；Determine the first influence score of each enterprise user based on the normal message volume and the total message volume;
将每个企业用户覆盖的个人用户量从大到小进行排序，并根据排序结果确定每个企业用户的第二影响力分值；Sort the number of individual users covered by each enterprise user from large to small, and determine the second influence score of each enterprise user based on the sorting result;
根据每个企业用户与各个地域的用户的交互量，确定每个企业用户的第三影响力分值。The third influence score of each enterprise user is determined based on the amount of interaction between each enterprise user and users in each region.
在本申请的一些实施例中，第一确定单元1231还用于：In some embodiments of the present application, the first determining unit 1231 is further configured to:
根据第二通信交互数据，确定个人用户与每个企业用户之间的交互类型；其中，交互类型包括通话类型和消息类型；Determining the interaction type between the individual user and each enterprise user according to the second communication interaction data; wherein the interaction type includes a call type and a message type;
根据交互类型，将至少一个企业用户划分为i个第一类企业用户和j个第二类企业用户；其中，i和j均为大于或者等于0的整数，第一类企业用户所对应的交互类型包括通话类型，第二类企业用户所对应的交互类型仅包括消息类型；According to the interaction type, at least one enterprise user is divided into i first-category enterprise users and j second-category enterprise users; wherein i and j are both integers greater than or equal to 0, the interaction type corresponding to the first-category enterprise users includes a call type, and the interaction type corresponding to the second-category enterprise users includes only a message type;
将每个第一类企业用户的第一影响力分值，确定为个人用户受每个第一类企业用户影响的分值。The first influence score of each first-category enterprise user is determined as the score of the individual user influenced by each first-category enterprise user.
根据每个第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值，确定每个第二类企业用户的综合影响力分值；Determine the comprehensive influence score of each second-category enterprise user according to the first influence score, the second influence score, and the third influence score of each second-category enterprise user;
根据第二通信交互数据和每个第二类企业用户的综合影响力分值，确定个人用户受每个第二类企业用户影响的分值。The score of the influence of each second-category enterprise user on the individual user is determined based on the second communication interaction data and the comprehensive influence score of each second-category enterprise user.
作为一种可能的实现方式，第一确定单元1231还用于：As a possible implementation manner, the first determining unit 1231 is further configured to:
针对每个第二类企业用户，将第二类企业用户的第二影响力分值与预设的影响力阈值进行比对；For each second-category enterprise user, comparing the second influence score of the second-category enterprise user with a preset influence threshold;
若第二类企业用户的第二影响力分值大于影响力阈值，根据第二类企业用户的第一影响力分值、第二影响力分值和第三影响力分值，确定第二类企业用户的综合影响力分值；If the second influence score of the second type of enterprise user is greater than the influence threshold, the comprehensive influence score of the second type of enterprise user is determined according to the first influence score, the second influence score and the third influence score of the second type of enterprise user;
若第二类企业用户的第二影响力分值小于或者等于影响力阈值，根据第二类企业用户的第一影响力分值、第二影响力分值，确定第二类企业用户的综合影响力分值。If the second influence score of the second category of enterprise users is less than or equal to the influence threshold, the comprehensive influence score of the second category of enterprise users is determined according to the first influence score and the second influence score of the second category of enterprise users.
作为一种可能的实现方式，第一确定单元1231还用于：As a possible implementation manner, the first determining unit 1231 is further configured to:
根据第二通信交互数据，确定个人用户与每个第二类企业用户的交互方向或者单向交互次数；Determining, based on the second communication interaction data, an interaction direction or a one-way interaction number between the individual user and each second-category enterprise user;
根据个人用户与每个第二类企业用户的交互方向或者单向交互次数，确定个人用户与每个第二类企业用户的紧密度；Determine the closeness between the individual user and each second-category enterprise user according to the interaction direction or one-way interaction number between the individual user and each second-category enterprise user;
根据个人用户与每个第二类企业用户的紧密度和每个第二类企业用户的综合影响力分值，确定个人用户受每个第二类企业用户影响的分值。The score of the influence of each second-category enterprise user on the individual user is determined based on the closeness between the individual user and each second-category enterprise user and the comprehensive influence score of each second-category enterprise user.
在本申请的一些实施例中，第三确定模块1240具体用于：In some embodiments of the present application, the third determination module 1240 is specifically used to:
基于物联网设备的影响力分值，根据第三通信交互数据，确定个人用户受物联网设备影响的总分值；Based on the influence score of the IoT device, and according to the third communication interaction data, determine the total score of the individual user affected by the IoT device;
将个人用户受物联网设备影响的总分值进行排序，并根据排序结果确定个人用户的第三可信度信息。The total scores of individual users affected by IoT devices are ranked, and the third credibility information of the individual users is determined based on the ranking results.
作为一种可能的实施方式，第三确定模块1240具体用于As a possible implementation, the third determination module 1240 is specifically configured to:
根据第三通信交互数据，确定与个人用户进行单向交互的m个第一物联网设备和与个人用户进行双向交互的n个第二物联网设备；其中，m和n均为大于或者等于0的整数；Determine, according to the third communication interaction data, m first Internet of Things devices that perform unidirectional interaction with the individual user and n second Internet of Things devices that perform bidirectional interaction with the individual user; wherein m and n are both integers greater than or equal to 0;
根据每个第一物联网设备的影响力分值，确定个人用户受第一物联网设备影响的分值；Determine, according to the influence score of each first IoT device, a score of the individual user affected by the first IoT device;
根据每个第二物联网设备的影响力分值，确定个人用户受第二物联网设备影响的分值；Determine, according to the influence score of each second IoT device, a score of the individual user affected by the second IoT device;
根据个人用户受第一物联网设备影响的分值和个人用户受第二物联网设备影响的分值，确定个人用户受物联网设备影响的总分值。A total score of the impact of the individual user on the Internet of Things devices is determined based on the score of the individual user being affected by the first Internet of Things device and the score of the individual user being affected by the second Internet of Things device.
作为一种示例，第三确定模块1240还用于：As an example, the third determining module 1240 is further configured to:
根据每个第一物联网设备的影响力分值，确定第一物联网设备的总影响力分值；Determine a total influence score of the first Internet of Things device according to the influence score of each first Internet of Things device;
基于预设的单向交互影响系数，根据第一物联网设备的总影响力分值，确定个人用户受第一物联网设备影响的分值。Based on the preset one-way interaction influence coefficient and according to the total influence score of the first Internet of Things device, the score of the individual user affected by the first Internet of Things device is determined.
作为一种示例，第三确定模块1240还用于：As an example, the third determining module 1240 is further configured to:
根据每个第二物联网设备的影响力分值，确定第二物联网设备的总影响力分值；Determine a total influence score of the second Internet of Things devices according to the influence score of each second Internet of Things device;
基于预设的双向交互影响系数，根据第二物联网设备的总影响力分值，确定个人用户受第二物联网设备影响的分值。Based on the preset two-way interactive influence coefficient and according to the total influence score of the second Internet of Things device, the score of the individual user affected by the second Internet of Things device is determined.
在本申请的一些实施例中，识别模块1250具体用于：In some embodiments of the present application, the identification module 1250 is specifically used to:
根据第一可信度信息、第二可信度信息和第三可信度信息，确定个人用户的可信度信息；Determining the credibility information of the individual user based on the first credibility information, the second credibility information, and the third credibility information;
根据个人用户的可信度信息，识别个人用户在预设时间段内是否为违规用户。Based on the credibility information of individual users, identify whether the individual users are illegal users within a preset time period.
作为一种示例，识别模块1250还用于：As an example, the identification module 1250 is further configured to:
根据第一可信度信息、第二可信度信息和第三可信度信息进行加权求和，并将加权求和结果确定为个人用户的可信度信息。A weighted sum is performed according to the first credibility information, the second credibility information and the third credibility information, and the weighted sum result is determined as the credibility information of the individual user.
需要说明的是，上述对基于交互关系的用户识别方法实施例中的解释说明也适用于本该实施例中的基于交互关系的用户识别装置，此处不再赘述。It should be noted that the above explanations and descriptions in the embodiment of the user identification method based on interactive relationship are also applicable to the user identification device based on interactive relationship in this embodiment, and will not be repeated here.
根据本申请实施例的基于交互关系的用户识别装置，基于个人用户与个人用户之间的通信交互、个人用户与企业用户之间的通信交互，以及个人用户与物联网设备之间的通信交互来确定个人用户的可信度信息，可以充分考虑与个人用户存在交互关系的所有交互对象对个人用户的可信度信息的影响，将企业用户和物联网设备均应用到个人用户的识别过程中，不仅可以提升个人用户可信度信息的准确性，同时也可以提升用户识别的准确性，为移动通信领域违规行为的治理提供了可靠的依据。According to the interactive relationship-based user identification device of the embodiment of the present application, the credibility information of individual users is determined based on the communication interactions between individual users and individual users, the communication interactions between individual users and corporate users, and the communication interactions between individual users and Internet of Things devices. The influence of all interactive objects that have an interactive relationship with the individual user on the credibility information of the individual user can be fully considered. Both corporate users and Internet of Things devices are applied to the identification process of individual users, which can not only improve the accuracy of the credibility information of individual users, but also improve the accuracy of user identification, providing a reliable basis for the governance of illegal behaviors in the field of mobile communications.
图13为本申请实施例所提供的另一种基于交互关系的用户识别装置的结构框图。如图13所示，该装置包括：FIG13 is a structural block diagram of another user identification device based on interactive relationship provided in an embodiment of the present application. As shown in FIG13 , the device includes:
获取模块1310，用于获取在预设时间段内的通信交互数据、个人用户的用户信息和与个人用户通信交互的企业用户的用户信息；其中，通信交互数据包括在预设时间段内个人用户之间第一通信交互数据，以及个人用户与企业用户之间的第二通信交互数据；The acquisition module 1310 is used to acquire communication interaction data within a preset time period, user information of individual users, and user information of enterprise users who communicate and interact with individual users; wherein the communication interaction data includes first communication interaction data between individual users within the preset time period, and second communication interaction data between individual users and enterprise users;
第一确定模块1320，用于根据个人用户的用户信息和第一通信交互数据，确定个人用户的第一可信度信息；A first determination module 1320, configured to determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data;
第二确定模块1330，用于根据企业用户的用户信息和第二通信交互数据，确定个人用户的第二可信度信息；The second determination module 1330 is used to determine the second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data;
识别模块1340，用于根据第一可信度信息和第二可信度信息，识别个人用户在预设时间段内是否为违规用户。The identification module 1340 is used to identify whether the individual user is an illegal user within a preset time period according to the first credibility information and the second credibility information.
需要说明的是，上述对基于交互关系的用户识别方法实施例中的解释说明也适用于本该实施例中的基于交互关系的用户识别装置，此处不再赘述。It should be noted that the above explanations and descriptions in the embodiment of the user identification method based on interactive relationship are also applicable to the user identification device based on interactive relationship in this embodiment, and will not be repeated here.
根据本申请实施例的基于交互关系的用户识别装置，基于个人用户与个人用户之间的通信交互和个人用户与企业用户之间的通信交互，可以充分考虑与个人用户存在交互关系的所有交互对象对个人用户的可信度信息的影响，将企业用户应用到个人用户的识别过程中，不仅可以提升个人用户可信度信息的准确性，同时也可以提升用户识别的准确性，为移动通信领域违规行为的治理提供了可靠的依据。According to the interactive relationship-based user identification device of the embodiment of the present application, based on the communication interaction between personal users and the communication interaction between personal users and corporate users, the influence of all interactive objects that have an interactive relationship with personal users on the credibility information of personal users can be fully considered. Applying corporate users to the identification process of personal users can not only improve the accuracy of personal user credibility information, but also improve the accuracy of user identification, providing a reliable basis for the governance of illegal behaviors in the field of mobile communications.
图14为本申请实施例所提供的又一种基于交互关系的用户识别装置的结构框图。如图14所示，该装置包括：FIG14 is a structural block diagram of another user identification device based on interactive relationship provided in an embodiment of the present application. As shown in FIG14 , the device includes:
获取模块1410，用于获取在预设时间段内的通信交互数据和个人用户的用户信息；其中，通信交互数据包括在预设时间段内个人用户之间第一通信交互数据，以及个人用户与物联网设备之间的第三通信交互数据；The acquisition module 1410 is used to acquire communication interaction data and user information of individual users within a preset time period; wherein the communication interaction data includes first communication interaction data between individual users within the preset time period, and third communication interaction data between the individual user and the IoT device;
第一确定模块1420，用于根据个人用户的用户信息和第一通信交互数据，确定个人用户的第一可信度信息；A first determination module 1420, configured to determine first credibility information of the individual user based on the user information of the individual user and the first communication interaction data;
第三确定模块1430，用于基于预设的物联网设备的影响力分值，根据第三通信交互数据，确定个人用户的第三可信度信息；A third determination module 1430 is used to determine third credibility information of the individual user based on the influence score of the preset IoT device and the third communication interaction data;
识别模块1440，用于根据第一可信度信息和第三可信度信息，识别个人用户在预设时间段内是否为违规用户。The identification module 1440 is used to identify whether the individual user is an illegal user within a preset time period according to the first credibility information and the third credibility information.
需要说明的是，上述对基于交互关系的用户识别方法实施例中的解释说明也适用于本该实施例中的基于交互关系的用户识别装置，此处不再赘述。It should be noted that the above explanations and descriptions in the embodiment of the user identification method based on interactive relationship are also applicable to the user identification device based on interactive relationship in this embodiment, and will not be repeated here.
根据本申请实施例的基于交互关系的用户识别装置，基于个人用户与个人用户之间的通信交互和个人用户与物联网设备的通信交互，可以充分考虑与个人用户存在交互关系的所有交互对象对个人用户的可信度信息的影响，将物联网设备到个人用户的识别过程中，不仅可以提升个人用户可信度信息的准确性，同时也可以提升用户识别的准确性，为移动通信领域违规行为的治理提供了可靠的依据。According to the user identification device based on interactive relationship in the embodiment of the present application, based on the communication interaction between individual users and the communication interaction between individual users and Internet of Things devices, the influence of all interactive objects that have an interactive relationship with the individual user on the credibility information of the individual user can be fully considered. In the process of identifying the Internet of Things device to the individual user, not only the accuracy of the individual user's credibility information can be improved, but also the accuracy of user identification can be improved, providing a reliable basis for the governance of illegal behaviors in the field of mobile communications.
图15为本申请实施例所提供的又一种基于交互关系的用户识别装置。如图14所示，该装置包括：FIG15 is another user identification device based on interactive relationship provided by an embodiment of the present application. As shown in FIG14 , the device includes:
第一获取模块1510，用于获取在预设时间段内个人用户之间第一通信交互数据和个人用户的用户信息；The first acquisition module 1510 is used to acquire first communication interaction data between individual users and user information of individual users within a preset time period;
第一确定模块1520，用于根据用户信息，确定个人用户的初始可信度信息；A first determination module 1520, configured to determine initial credibility information of an individual user based on the user information;
第二确定模块1530，用于根据第一通信交互数据，确定个人用户作为主叫用户时与每个被叫用户的交互次数；The second determination module 1530 is used to determine the number of interactions between the individual user as the calling user and each called user according to the first communication interaction data;
第二获取模块1540，用于根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代运算，获得个人用户的第一可信度信息；The second acquisition module 1540 is used to perform an iterative operation based on the number of interactions between the individual user as a calling user and each called user and the initial credibility information to obtain the first credibility information of the individual user;
识别模块1550，用于根据第一可信度信息，识别个人用户在预设时间段内是否为违规用户。The identification module 1550 is used to identify whether the individual user is an illegal user within a preset time period according to the first credibility information.
需要说明的是，上述对基于交互关系的用户识别方法实施例中的解释说明也适用于本该实施例中的基于交互关系的用户识别装置，此处不再赘述。It should be noted that the above explanations and descriptions in the embodiment of the user identification method based on interactive relationship are also applicable to the user identification device based on interactive relationship in this embodiment, and will not be repeated here.
根据本申请实施例的基于交互关系的用户识别装置，通过用户信息先确定个人用户的初始可信度信息，再根据个人用户作为主叫用户时与每个被叫用户的交互次数和初始可信度信息进行迭代计算，以获取个人用户的第一可信度信息，并根据第一可信度信息识别个人用户在预设时间段内是否为违规用户。本方案基于移动通信领域中用户之间的交互特点，将交互次数引入迭代计算中，通过交互次数来表达个人用户之间联系紧密度的依据，使得到的第一可信度信息更加准确，从而可以提升用户识别的准确性。According to the interactive relationship-based user identification device of the embodiment of the present application, the initial credibility information of the individual user is first determined through user information, and then iterative calculation is performed based on the number of interactions between the individual user and each called user when the individual user is a calling user and the initial credibility information to obtain the first credibility information of the individual user, and identify whether the individual user is an illegal user within a preset time period based on the first credibility information. This solution is based on the interactive characteristics between users in the field of mobile communications, introduces the number of interactions into the iterative calculation, and uses the number of interactions to express the basis for the closeness of the connection between individual users, so that the first credibility information obtained is more accurate, thereby improving the accuracy of user identification.
为了实现上述实施例，本申请提供了一种电子设备。In order to implement the above embodiments, the present application provides an electronic device.
图16为本申请实施例所提供的一种电子设备的结构框图。该电子设备可以为服务器、计算机等设备。如图16所示，该电子设备包括：FIG16 is a block diagram of an electronic device provided in an embodiment of the present application. The electronic device may be a server, a computer, or other device. As shown in FIG16 , the electronic device includes:
存储器1610及处理器1620，连接不同组件(包括存储器1610和处理器1620)的总线1630，存储器1610存储有处理器1620可执行指令；其中，处理器1620被配置为执行所述指令，以实现本公开实施例所述的基于交互关系的用户识别方法。The memory 1610 and the processor 1620, the bus 1630 connecting different components (including the memory 1610 and the processor 1620), the memory 1610 stores executable instructions for the processor 1620; wherein the processor 1620 is configured to execute the instructions to implement the user identification method based on interactive relationship described in the embodiment of the present disclosure.
总线1630表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(ISA)总线，微通道体系结构(MAC)总线，增强型ISA总线、视频电子标准协会(VESA)局域总线以及外围组件互连(PCI)总线。Bus 1630 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.
电子设备1600典型地包括多种电子设备可读介质。这些介质可以是任何能够被电子设备1600访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。存储器1610还可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(RAM)1640和/或高速缓存存储器1650。电子设备1600可以进一步包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统1660可以用于读写不可移动的、非易失性磁介质(图16未显示，通常称为“硬盘驱动器”)。尽管图16中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如CD-ROM,DVD-ROM或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线1630相连。存储器1610可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本公开各实施例的功能。The electronic device 1600 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by the electronic device 1600, including volatile and non-volatile media, removable and non-removable media. The memory 1610 can also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1640 and/or cache memory 1650. The electronic device 1600 can further include other removable/non-removable, volatile/non-volatile computer system storage media. Just as an example, the storage system 1660 can be used to read and write non-removable, non-volatile magnetic media (not shown in Figure 16, usually referred to as "hard drive"). Although not shown in Figure 16, a disk drive for reading and writing a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical media) can be provided. In these cases, each drive can be connected to the bus 1630 through one or more data medium interfaces. The memory 1610 may include at least one program product having a set (eg, at least one) of program modules, and these program modules are configured to perform the functions of various embodiments of the present disclosure.
具有一组(至少一个)程序模块1670的程序/实用工具1680，可以存储在例如存储器1610中，这样的程序模块1670包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块1670通常执行本公开所描述的实施例中的功能和/或方法。A program/utility 1680 having a set (at least one) of program modules 1670 may be stored, for example, in the memory 1610, such program modules 1670 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 1670 generally perform the functions and/or methods of the embodiments described in the present disclosure.
电子设备1600也可以与一个或多个外部设备1690(例如键盘、指向设备、显示器1691等)通信，还可与一个或者多个使得用户能与该电子设备1600交互的设备通信，和/或与使得该电子设备1600能与一个或多个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口1692进行。并且，电子设备1500还可以通过网络适配器1693与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器1693通过总线1630与电子设备1600的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备1600使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。The electronic device 1600 may also communicate with one or more external devices 1690 (e.g., keyboard, pointing device, display 1691, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1600, and/or communicate with any device that enables the electronic device 1600 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via an input/output (I/O) interface 1692. In addition, the electronic device 1500 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and/or public network, such as the Internet) via a network adapter 1693. As shown, the network adapter 1693 communicates with other modules of the electronic device 1600 via a bus 1630. It should be understood that, although not shown in the figure, other hardware and/or software modules may be used in conjunction with the electronic device 1600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
处理器1620通过运行存储在存储器1610中的程序，从而执行各种功能应用以及数据处理。The processor 1620 executes various functional applications and data processing by running the programs stored in the memory 1610 .
需要说明的是，本实施例的电子设备的实施过程和技术原理参见前述对本公开实施例的基于交互关系的用户识别方法的解释说明，此处不再赘述。It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the user identification method based on interactive relationship in the embodiment of the present disclosure, which will not be repeated here.
为了实现上述实施例，本公开还提出一种计算机存储介质。In order to implement the above embodiments, the present disclosure also proposes a computer storage medium.
其中，该存储介质中的指令由服务器的处理器执行时，使得服务器能够执行如前所述的基于互联网应用的多媒体资源投放方法。可选的，计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。When the instructions in the storage medium are executed by the processor of the server, the server can execute the multimedia resource delivery method based on Internet application as described above. Optionally, the computer readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk and optical data storage device, etc.
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本申请的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本申请的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本申请的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本申请的实施例所属技术领域的技术人员所理解。Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。The logic and/or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
应当理解，本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如，如果用硬件来实现和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
此外，在本申请各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
尽管上面已经示出和描述了本申请的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本申请的限制，本领域的普通技术人员在本申请的范围内可以对上述实施例进行变化、修改、替换和变型。Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953917.2ACN117056594B (en) | 2023-07-31 | 2023-07-31 | User identification method, device and electronic device based on interactive relationship |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953917.2ACN117056594B (en) | 2023-07-31 | 2023-07-31 | User identification method, device and electronic device based on interactive relationship |
| Publication Number | Publication Date |
|---|---|
| CN117056594A CN117056594A (en) | 2023-11-14 |
| CN117056594Btrue CN117056594B (en) | 2024-07-26 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310953917.2AActiveCN117056594B (en) | 2023-07-31 | 2023-07-31 | User identification method, device and electronic device based on interactive relationship |
| Country | Link |
|---|---|
| CN (1) | CN117056594B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110505196A (en)* | 2019-07-02 | 2019-11-26 | 中国联合网络通信集团有限公司 | Abnormality detection method and device for internet of things card |
| CN112153221A (en)* | 2020-09-16 | 2020-12-29 | 北京邮电大学 | Communication behavior identification method based on social network diagram calculation |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8681957B2 (en)* | 2012-05-10 | 2014-03-25 | International Business Machines Corporation | Extracting social relations from calling time data |
| CN115511606A (en)* | 2022-10-14 | 2022-12-23 | 深圳前海微众银行股份有限公司 | Object recognition method, device, equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110505196A (en)* | 2019-07-02 | 2019-11-26 | 中国联合网络通信集团有限公司 | Abnormality detection method and device for internet of things card |
| CN112153221A (en)* | 2020-09-16 | 2020-12-29 | 北京邮电大学 | Communication behavior identification method based on social network diagram calculation |
| Publication number | Publication date |
|---|---|
| CN117056594A (en) | 2023-11-14 |
| Publication | Publication Date | Title |
|---|---|---|
| CN110297912A (en) | Cheat recognition methods, device, equipment and computer readable storage medium | |
| CN110415032A (en) | Method, device, equipment and storage medium for estimating exposure conversion rate | |
| CN108322473A (en) | User behavior analysis method and apparatus | |
| CN106127505A (en) | The single recognition methods of a kind of brush and device | |
| CN106709318A (en) | Recognition method, device and calculation equipment for user equipment uniqueness | |
| CN107886361A (en) | A kind of method and server for assessing ad conversion rates prediction model | |
| CN108694626A (en) | Customer profile method for building up and device | |
| WO2020048056A1 (en) | Risk decision method and apparatus | |
| US20240152997A1 (en) | Using email history to estimate creditworthiness for applicants having insufficient credit history | |
| CN109472650A (en) | Method for tracing, device and the readable storage medium storing program for executing of amount of access after poster is shared | |
| CN112348659A (en) | User risk identification strategy allocation method and device and electronic equipment | |
| CN111966915A (en) | Information inspection method, computer equipment and storage medium | |
| CN109784352A (en) | A kind of method and apparatus for assessing disaggregated model | |
| CN113568739A (en) | User resource limit distribution method and device and electronic equipment | |
| CN117056594B (en) | User identification method, device and electronic device based on interactive relationship | |
| US10904185B1 (en) | Email address validation | |
| CN109636083A (en) | Blacklist analysis method, device, equipment and computer readable storage medium | |
| CN109214640A (en) | Determination method, equipment and the computer readable storage medium of index result | |
| CN115860907A (en) | Method, device, equipment and storage medium for determining loan recommendation method | |
| CN116208516A (en) | Enterprise internet private line perception evaluation method, device, equipment and medium | |
| CN115310102A (en) | Data allocation authority adjusting method and device based on video expression actions | |
| CN115390711A (en) | Display method, device, computer equipment and storage medium of unread message corner mark | |
| CN109919811B (en) | Insurance agent culture scheme generation method based on big data and related equipment | |
| CN113590310A (en) | Resource allocation method and device based on rule touch rate scoring and electronic equipment | |
| CN110033151A (en) | Relational risk evaluation method, device, electronic equipment and computer storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |