CN114331536A - Marketing control method and device - Google Patents
Marketing control method and deviceDownload PDFInfo
- Publication number
- CN114331536A CN114331536ACN202111637446.1ACN202111637446ACN114331536ACN 114331536 ACN114331536 ACN 114331536ACN 202111637446 ACN202111637446 ACN 202111637446ACN 114331536 ACN114331536 ACN 114331536A
- Authority
- CN
- China
- Prior art keywords
- user
- preset
- behavior
- marketing
- score
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本公开涉及营销技术领域，尤其涉及营销管控方法及装置。The present disclosure relates to the field of marketing technology, and in particular, to a marketing management and control method and device.
背景技术Background technique
目前，基于运营商大数据的精准挖掘目标用户，有两种方式，一个是基于机器学习训练的用户意向响应/成单分模型，另一个是基于专家经验的规则筛选。但是，前者对样本数量、特征数量及粒度、计算资源有一定的要求，并不适合业务冷启动阶段。后者依赖专家经验输出规则用以筛选目标用户，可以快速试验，短时间提升投资回报率，但是不能量化，无法满足精细化要求。At present, there are two ways to accurately mine target users based on operator big data. One is the user intent response/component model based on machine learning training, and the other is rule screening based on expert experience. However, the former has certain requirements on the number of samples, the number and granularity of features, and computing resources, and is not suitable for the cold start stage of the business. The latter relies on expert experience output rules to screen target users, which can quickly test and improve the return on investment in a short time, but cannot be quantified and cannot meet the refinement requirements.
发明内容SUMMARY OF THE INVENTION
为克服相关技术中存在的问题，本公开实施例提供营销管控方法及装置。所述技术方案如下：In order to overcome the problems existing in the related art, the embodiments of the present disclosure provide a marketing management and control method and apparatus. The technical solution is as follows:
根据本公开实施例的第一方面，提供一种营销管控方法，所述方法包括：According to a first aspect of the embodiments of the present disclosure, there is provided a marketing management and control method, the method comprising:
获取每一个用户在网络中操作时的用户网络行为得分；Obtain the user's network behavior score when each user operates in the network;
获取每一个用户与商家进行互通的互通行为得分；Obtain the interoperability score of each user and merchant for intercommunication;
获取每一个用户对商家产品的偏好度；Obtain each user's preference for the merchant's products;
根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；Obtain the marketing response score corresponding to each user according to the preset user network behavior weight value, user network behavior score, preset interworking behavior weight value, interworking behavior score, preset preference weight value and preference degree;
根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略。A marketing strategy for each of the users is determined according to the marketing response scores corresponding to each of the users.
在一个实施例中，所述获取用户在网络中操作时的用户网络行为得分，包括：In one embodiment, the obtaining the user's network behavior score when the user operates in the network includes:
根据当前时间和用户在网络中操作时的用户网络行为的产生时间获取第一时间衰减系数；Obtain the first time attenuation coefficient according to the current time and the generation time of the user's network behavior when the user operates in the network;
获取所述用户第t天访问目标网络中的目标页面的第一次数；t为大于或等于1的整数；Obtain the first number of times that the user visits the target page in the target network on day t; t is an integer greater than or equal to 1;
获取所述用户第t天访问所述目标页面的使用时长；Obtain the usage time of the user accessing the target page on the t day;
获取所述用户第t天访问所述目标页面的使用流量；Obtain the usage traffic of the user accessing the target page on the t day;
根据所述第一时间衰减系数、所述第一次数、所述第一次数对应的预设权重系数、所述使用时长、所述使用时长对应的预设权重系数、所述使用流量和所述使用流量对应的预设权重系数获取所述用户网络行为得分。According to the first time decay coefficient, the first number of times, the preset weight coefficient corresponding to the first number of times, the use duration, the preset weight coefficient corresponding to the use duration, the usage flow and The user network behavior score is obtained by using the preset weight coefficient corresponding to the traffic.
在一个实施例中，所述获取用户与商家进行互通的互通行为得分，包括：In one embodiment, the obtaining of the interworking behavior score of the user and the merchant for interworking includes:
根据当前时间和所述用户与商家进行互通的互通行为的产生时间获取第二时间衰减系数；Obtain the second time attenuation coefficient according to the current time and the generation time of the interworking behavior of the user and the merchant;
获取所述用户第t天与商家互通的第二次数；Obtain the second number of times that the user communicates with the merchant on the t day;
获取预设周期内初次联系的商家数量；Get the number of merchants contacted for the first time within a preset period;
根据所述第二时间衰减系数、所述第二次数、所述第二次数对应的预设权重、所述商家数量和所述商家数量的预设权重获取所述互通行为得分。The interworking behavior score is obtained according to the second time decay coefficient, the second number of times, a preset weight corresponding to the second number of times, the number of merchants, and the preset weight of the number of merchants.
在一个实施例中，所述获取用户对商家产品的偏好度，包括：In one embodiment, the acquiring the user's preference for the merchant's product includes:
获取用户浏览目标产品的次数；Get the number of times users browse the target product;
获取用户浏览与所述目标产品属于同类产品的数量；Obtain the number of products browsed by users that belong to the same category as the target product;
根据所述次数和所述数量获取所述偏好度。The preference is obtained according to the number of times and the number.
在一个实施例中，所述预设用户网络行为权重值大于所述预设互通行为权重值；所述预设互通行为权重值大于所述预设偏好权重值。In one embodiment, the preset user network behavior weight value is greater than the preset interworking behavior weight value; the preset interworking behavior weight value is greater than the preset preference weight value.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
当所述用户对应的营销响应分数小于第一预设阈值，则提示通过人工外呼所述用户；When the marketing response score corresponding to the user is less than the first preset threshold, prompting the user to call the user manually;
当所述用户对应的营销响应分数大于或等于所述第一预设阈值，则提示通过预设外呼方式开展用户触达，其中，所述预设外呼方式包括：短信或机器人。When the marketing response score corresponding to the user is greater than or equal to the first preset threshold, the user is prompted to reach the user through a preset outbound call method, wherein the preset outbound call method includes: SMS or robot.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
按照各个所述用户对应的营销响应分数从大到小的顺序对各个所述用户进行排序；Sort each of the users according to the marketing response score corresponding to each of the users in descending order;
输出所述排序结果。The sorting result is output.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
当所述用户对应的营销响应分数小于第二预设阈值，则删除所述用户；When the marketing response score corresponding to the user is less than the second preset threshold, delete the user;
当所述用户对应的营销响应分数大于或等于所述第二预设阈值，则提示开展用户触达。When the marketing response score corresponding to the user is greater than or equal to the second preset threshold, the user is prompted to reach out.
本公开的实施例提供的技术方案可以包括以下有益效果：本公开实施例提供的营销管控方法，包括：获取每一个用户在网络中操作时的用户网络行为得分；获取每一个用户与商家进行互通的互通行为得分；获取每一个用户对商家产品的偏好度；根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略。其中，从用户网络行为、用户与商家之间的互通行为、以及用户对商家产品的偏好度三个维度去计算营销响应分数，以挖掘目标用户，帮助企业实现精准获客，有效提高了外呼接通率和转化率。The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: the marketing management and control methods provided by the embodiments of the present disclosure include: obtaining the user network behavior score of each user when operating in the network; obtaining the intercommunication between each user and the merchant Obtaining each user’s preference for the merchant’s products; obtaining according to the preset user network behavior weight value, user network behavior score, preset interconnection behavior weight value, interconnection behavior score, preset preference weight value and preference degree The marketing response score corresponding to each user; the marketing strategy for each of the users is determined according to the marketing response score corresponding to each of the users. Among them, the marketing response score is calculated from the three dimensions of user network behavior, interaction behavior between users and merchants, and user preference for merchant products, so as to tap target users, help enterprises achieve accurate customer acquisition, and effectively improve outbound calls. Contact and conversion rates.
根据本公开实施例的第二方面，提供一种营销管控装置，包括：According to a second aspect of the embodiments of the present disclosure, there is provided a marketing management and control device, including:
第一获取模块，用于获取每一个用户在网络中操作时的用户网络行为得分；The first obtaining module is used to obtain the user's network behavior score when each user operates in the network;
第二获取模块，用于获取每一个用户与商家进行互通的互通行为得分；The second acquisition module is used to acquire the interworking behavior score of each user and the merchant for intercommunication;
第三获取模块，用于获取每一个用户对商家产品的偏好度；The third acquisition module is used to acquire each user's preference for the merchant's product;
第四获取模块，用于根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；a fourth obtaining module, configured to obtain the marketing response score corresponding to each user according to the preset user network behavior weight value, the user network behavior score, the preset interworking behavior weight value, the interworking behavior score, the preset preference weight value and the preference degree;
确定模块，用于根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略。A determination module, configured to determine a marketing strategy for each of the users according to the marketing response score corresponding to each of the users.
在一个实施例中，所述第一获取模块，包括：In one embodiment, the first obtaining module includes:
第一获取子模块，用于根据当前时间和用户在网络中操作时的用户网络行为的产生时间获取第一时间衰减系数；a first acquisition submodule, configured to acquire a first time decay coefficient according to the current time and the generation time of the user's network behavior when the user operates in the network;
第二获取子模块，用于获取所述用户第t天访问目标网络中的目标页面的第一次数；t为大于或等于1的整数；The second acquisition submodule is used to acquire the first number of times that the user visits the target page in the target network on the t day; t is an integer greater than or equal to 1;
第三获取子模块，用于获取所述用户第t天访问所述目标页面的使用时长；The third obtaining sub-module is used to obtain the usage duration of the user accessing the target page on the t day;
第四获取子模块，用于获取所述用户第t天访问所述目标页面的使用流量；The fourth acquisition sub-module is used to acquire the usage flow of the user accessing the target page on the t day;
网络行为得分获取子模块，用于根据所述第一时间衰减系数、所述第一次数、所述第一次数对应的预设权重系数、所述使用时长、所述使用时长对应的预设权重系数、所述使用流量和所述使用流量对应的预设权重系数获取所述用户网络行为得分。The network behavior score acquisition sub-module is configured to obtain a sub-module according to the first time decay coefficient, the first number of times, the preset weight coefficient corresponding to the first number of times, the use duration, and the pre-set corresponding to the use duration. The user network behavior score is obtained by setting a weight coefficient, the usage flow, and a preset weight coefficient corresponding to the usage flow.
在一个实施例中，所述第二获取模块，包括：In one embodiment, the second obtaining module includes:
第五获取子模块，用于根据当前时间和所述用户与商家进行互通的互通行为的产生时间获取第二时间衰减系数；a fifth acquisition submodule, configured to acquire a second time attenuation coefficient according to the current time and the generation time of the intercommunication behavior of the user and the merchant;
第六获取子模块，用于获取所述用户第t天与商家互通的第二次数；The sixth acquisition sub-module is used to acquire the second number of times that the user communicates with the merchant on the t day;
第七获取子模块，用于获取预设周期内初次联系的商家数量；The seventh obtaining sub-module is used to obtain the number of merchants contacted for the first time within the preset period;
第八获取子模块，用于根据所述第二时间衰减系数、所述第二次数、所述第二次数对应的预设权重、所述商家数量和所述商家数量的预设权重获取所述互通行为得分。The eighth acquisition sub-module is configured to acquire the said business according to the second time decay coefficient, the second number of times, the preset weight corresponding to the second number of times, the number of merchants and the preset weight of the number of merchants Interoperability score.
在一个实施例中，所述第三获取模块，包括：In one embodiment, the third obtaining module includes:
第九获取子模块，用于获取用户浏览目标产品的次数；The ninth acquisition sub-module is used to acquire the number of times the user browses the target product;
第十获取子模块，用于获取用户浏览与所述目标产品属于同类产品的数量；The tenth acquisition sub-module is used to acquire the number of products that the user browses and the target product belongs to the same category;
第十一获取子模块，用于根据所述次数和所述数量获取所述偏好度。The eleventh obtaining sub-module is configured to obtain the preference degree according to the number of times and the quantity.
在一个实施例中，所述预设用户网络行为权重值大于所述预设互通行为权重值；所述预设互通行为权重值大于所述预设偏好权重值。In one embodiment, the preset user network behavior weight value is greater than the preset interworking behavior weight value; the preset interworking behavior weight value is greater than the preset preference weight value.
在一个实施例中，所述确定模块，包括：In one embodiment, the determining module includes:
第一提示子模块，用于当所述用户对应的营销响应分数小于第一预设阈值，则提示通过人工外呼所述用户；a first prompting sub-module, configured to prompt the user to call the user manually when the marketing response score corresponding to the user is less than a first preset threshold;
第一外呼子模块，用于当所述用户对应的营销响应分数大于或等于所述第一预设阈值，则提示通过预设外呼方式开展用户触达，其中，所述预设外呼方式包括：短信或机器人。The first outbound call sub-module is configured to prompt the user to reach out through a preset outbound call mode when the marketing response score corresponding to the user is greater than or equal to the first preset threshold, wherein the preset outbound call mode Include: text messages or bots.
在一个实施例中，所述确定模块，包括：In one embodiment, the determining module includes:
排序子模块，用于按照各个所述用户对应的营销响应分数从大到小的顺序对各个所述用户进行排序；a sorting submodule, configured to sort each of the users in descending order of the marketing response scores corresponding to each of the users;
输出子模块，用于输出所述排序结果。An output sub-module for outputting the sorting result.
在一个实施例中，所述确定模块，包括：In one embodiment, the determining module includes:
删除子模块，用于当所述用户对应的营销响应分数小于第二预设阈值，则删除所述用户；a deletion submodule, configured to delete the user when the marketing response score corresponding to the user is less than a second preset threshold;
第二提示子模块，用于当所述用户对应的营销响应分数大于或等于所述第二预设阈值，则提示开展用户触达。The second prompting sub-module is configured to prompt the user to reach out when the marketing response score corresponding to the user is greater than or equal to the second preset threshold.
根据本公开实施例的第三方面，提供一种营销管控装置，其特征在于，包括：According to a third aspect of the embodiments of the present disclosure, there is provided a marketing management and control device, characterized by comprising:
处理器；processor;
用于存储处理器可执行指令的存储器；memory for storing processor-executable instructions;
其中，所述处理器被配置为：wherein the processor is configured to:
获取每一个用户在网络中操作时的用户网络行为得分；Obtain the user's network behavior score when each user operates in the network;
获取每一个用户与商家进行互通的互通行为得分；Obtain the interoperability score of each user and merchant for intercommunication;
获取每一个用户对商家产品的偏好度；Obtain each user's preference for the merchant's products;
根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；Obtain the marketing response score corresponding to each user according to the preset user network behavior weight value, user network behavior score, preset interworking behavior weight value, interworking behavior score, preset preference weight value and preference degree;
根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略。A marketing strategy for each of the users is determined according to the marketing response scores corresponding to each of the users.
根据本公开实施例的第四方面，提供一种计算机可读存储介质，其上存储有计算机指令，该指令被处理器执行时实现第一方面中任一项所述方法的步骤。According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium on which computer instructions are stored, and when the instructions are executed by a processor, implement the steps of any one of the methods in the first aspect.
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.
附图说明Description of drawings
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.
图1是根据一示例性实施例示出的营销管控方法的流程图。FIG. 1 is a flowchart of a marketing management and control method according to an exemplary embodiment.
图2是根据一示例性实施例示出的营销管控方法中步骤S101的流程图。FIG. 2 is a flowchart of step S101 in the marketing management and control method according to an exemplary embodiment.
图3是根据一示例性实施例一示出的营销管控方法中步骤S102的流程图。Fig. 3 is a flow chart of step S102 in the marketing management and control method according to an exemplary embodiment 1.
图4是根据一示例性实施例二示出的营销管控方法中步骤S103的流程图。FIG. 4 is a flowchart of step S103 in the marketing management and control method according to the second exemplary embodiment.
图5是根据一示例性实施例示出的营销管控装置的框图。Fig. 5 is a block diagram of a marketing management and control apparatus according to an exemplary embodiment.
图6是根据一示例性实施例示出的营销管控装置中第一获取模块11的框图。FIG. 6 is a block diagram of the
图7是根据一示例性实施例示出的营销管控装置中第二获取模块12的框图。FIG. 7 is a block diagram of the
图8是根据一示例性实施例示出的营销管控装置中第三获取模块13的框图。FIG. 8 is a block diagram of the
图9是根据一示例性实施例示出的营销管控装置中确定模块15的框图。FIG. 9 is a block diagram of the
图10是根据一示例性实施例示出的营销管控装置中确定模块15的框图。FIG. 10 is a block diagram of the
图11是根据一示例性实施例示出的营销管控装置中确定模块15的框图。FIG. 11 is a block diagram of the
图12是根据一示例性实施例示出的一种用于营销管控装置80的框图。FIG. 12 is a block diagram of a marketing management and
具体实施方式Detailed ways
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as recited in the appended claims.
图1是根据一示例性实施例示出的营销管控方法的流程图，如图1所示，该方法包括以下步骤S101-S105：Fig. 1 is a flowchart of a marketing management and control method according to an exemplary embodiment. As shown in Fig. 1 , the method includes the following steps S101-S105:
在步骤S101中，获取每一个用户在网络中操作时的用户网络行为得分。In step S101, the user network behavior score of each user when operating in the network is obtained.
在一个实施例中，如图2所示，该步骤S101包括以下子步骤S1011-S1015：In one embodiment, as shown in FIG. 2 , this step S101 includes the following sub-steps S1011-S1015:
在步骤S1011中，根据当前时间和用户在网络中操作时的用户网络行为的产生时间获取第一时间衰减系数；In step S1011, a first time attenuation coefficient is obtained according to the current time and the generation time of the user's network behavior when the user operates in the network;
其中，用户在网络中操作时的用户网络行为可以包括：用户在APP中操作时的用户网络行为，也可以为用户在Web中操作时的用户网络行为，本公开不对其加以限制。The user network behavior when the user operates on the network may include: the user network behavior when the user operates in the APP, or the user network behavior when the user operates on the Web, which is not limited in the present disclosure.
在步骤S1012中，获取用户第t天访问目标网络中的目标页面的第一次数；t为大于或等于1的整数；In step S1012, obtain the first number of times that the user visits the target page in the target network on the t-th day; t is an integer greater than or equal to 1;
在步骤S1013中，获取用户第t天访问目标页面的使用时长；In step S1013, obtain the usage time of the user accessing the target page on the t day;
在步骤S1014中，获取用户第t天访问目标页面的使用流量；In step S1014, the usage flow of the user accessing the target page on the t day is obtained;
在步骤S1015中，根据第一时间衰减系数、第一次数、第一次数对应的预设权重、使用时长、使用时长对应的预设权重、使用流量和使用流量对应的预设权重获取用户网络行为得分。In step S1015, users are acquired according to the first time decay coefficient, the first number of times, the preset weight corresponding to the first number of times, the duration of use, the preset weight corresponding to the duration of use, the usage flow, and the preset weight corresponding to the usage flow Internet Behavior Score.
用户网络行为得分是由上网数据计算得出的，包括应用程序(Application，简称为：App)数据和互联网(英文：web)数据。因为移动互联时代的到来，APP和web浏览最能体现用户近期的关注焦点。访问不同的APP或者统一资源定位符(Uniform Resource Locator，简称为：URL)代表了不同的用户需求。访问了同一个APP的不同页面代表了不同的需求阶段。The user's network behavior score is calculated from online data, including application (Application, referred to as: App) data and Internet (English: web) data. Because of the advent of the mobile Internet era, APP and web browsing can best reflect the recent focus of users. Accessing different APPs or Uniform Resource Locators (Uniform Resource Locator, URL for short) represents different user needs. Visiting different pages of the same app represents different stages of demand.
同时，考虑用户需求具有很强的时效性，使用用户产生行为的时间戳(行为的发生时间)，也即，定义一种方法用于衡量时效性，具体的，可以通过当前时间和用户在网络中操作时的用户网络行为的产生时间获取第一时间衰减系数，该第一时间衰减系数可以通过下式获取：At the same time, considering the strong timeliness of user needs, use the timestamp of the user's behavior (the time when the behavior occurs), that is, define a method to measure the timeliness. The first time attenuation coefficient is obtained from the generation time of the user's network behavior during the middle operation, and the first time attenuation coefficient can be obtained by the following formula:
p(t)＝1-α(T-t)β,T≥tp(t)=1-α(Tt)β , T≥t
其中，p(t)为第一时间衰减系数，α、β是需求衰减参数，T是当前时间，t是用户产生网络行为的时间戳(用户产生网络行为的时间)。当t＝T时，p(t)＝1，意味着需求时效性较强。具体参数的设置可以根据业务场景和需求而定。Among them, p(t) is the first time attenuation coefficient, α and β are the demand attenuation parameters, T is the current time, and t is the timestamp of the user's network behavior (the time when the user generated network behavior). When t=T, p(t)=1, which means that the demand is time-sensitive. The setting of specific parameters can be determined according to business scenarios and needs.
其中，p(t)越大，表示用户网络行为的发生时间距离当前时间越近，p(t)越小，表示用户网络行为的发生时间距离当前时间越远。Among them, the larger p(t) is, the closer the occurrence time of the user's network behavior is to the current time, and the smaller p(t) is, the farther the user's network behavior is from the current time.
例如：α为1/8，β为1/2，用户产生网络行为的时间距离当前时间为64天，那么，p(t)＝1-1/8×641/2＝0；用户产生网络行为的时间距离当前时间为4天，那么，p(t)＝1-1/8×41/2＝3/4。For example: α is 1/8, β is 1/2, and the time when the user generates network behavior is 64 days away from the current time, then, p(t)=1-1/8×641/2 =0; The time of the behavior is 4 days from the current time, then, p(t)=1-1/8×41/2 =3/4.
然后，可以通过下述公式得到用户网络行为得分：Then, the user network behavior score can be obtained by the following formula:
其中，w是用户网络行为得分，Webi是目标APP或者目标Web；VT(t,Webi)是第t天访问Web或APP目标页面的第一次数；VD(t,Webi)是第t天访问Web或APP目标页面的使用时长；VV(t,Webi)是第t天访问Web或APP目标页面的使用流量；θ为观察周期；a1是第一次数对应的预设权重系数，a2是使用时长对应的预设权重系数，a3是使用流量对应的预设权重系数。Among them, w is the user's network behavior score, Webi is the target APP or target Web; VT(t, Webi ) is the first number of visits to the Web or APP target page on the t day; VD(t, Webi ) is the th The usage time of accessing the Web or APP target page on day t; VV(t, Webi ) is the usage flow of accessing the Web or APP target page on day t; θ is the observation period; a1 is the preset weight corresponding to the first time coefficient, a2 is the preset weight coefficient corresponding to the usage duration, and a3 is the preset weight coefficient corresponding to the usage flow.
其中，θ为观察周期，根据不同业务场景周期不同。以购车场景为例，例如，从看车到购车共耗时1个月，那么，此时的θ即为从看车到购车的1个月。Among them, θ is the observation period, which varies according to different business scenarios. Taking a car buying scenario as an example, for example, it takes 1 month from viewing a car to buying a car. Then, θ at this time is 1 month from viewing a car to buying a car.
网络行为是在相关APP或web上浏览时的操作，并且不同行为反应用户的不同需求强度，可以根据业务经验定义不同行为的权重大小，也可以通过机器学习的方法确定不同行为的权重大小。Network behavior is the operation when browsing on the relevant APP or web, and different behaviors reflect the different needs of users. The weight of different behaviors can be defined according to business experience, or the weight of different behaviors can be determined by machine learning methods.
以某APP的某产品为例，提交信息的权重>查看产品详情的权重>浏览产品海报的权重。Taking a product of an APP as an example, the weight of submitting information > the weight of viewing product details > the weight of browsing product posters.
由于用户的网络行为还可能与其他的因素相关，在一个实施例中，还可以通过下述公式得到用户网络行为得分：Since the user's network behavior may also be related to other factors, in one embodiment, the user's network behavior score can also be obtained by the following formula:
在该式中，VX是预留特征，a4是预留特征对应的预设权重系数，其他参数含义与上述式子相同，此处不再赘述。In this formula, VX is a reserved feature, a4 is a preset weight coefficient corresponding to the reserved feature, and the meanings of other parameters are the same as those in the above formula, and will not be repeated here.
在步骤S102中，获取每一个用户与商家进行互通的互通行为得分。In step S102, the interworking behavior score of each user communicating with the merchant is obtained.
在一个实施例中，如图3所示，该步骤S102包括以下子步骤S1021-S1024：In one embodiment, as shown in FIG. 3 , this step S102 includes the following sub-steps S1021-S1024:
在步骤S1021中，根据当前时间和用户与商家进行互通的互通行为的产生时间获取第二时间衰减系数；In step S1021, the second time attenuation coefficient is obtained according to the current time and the generation time of the intercommunication behavior of the user and the merchant;
在步骤S1022中，获取用户第t天与商家互通的第二次数；In step S1022, obtain the second number of times that the user communicates with the merchant on the t-th day;
在步骤S1023中，获取预设周期内初次联系的商家数量；In step S1023, obtain the number of merchants contacted for the first time within a preset period;
在步骤S1024中，根据第二时间衰减系数、第二次数、第二次数对应的预设权重系数、商家数量和商家数量的预设权重系数获取互通行为得分。In step S1024, the interworking behavior score is obtained according to the second time decay coefficient, the second time, the preset weight coefficient corresponding to the second time, the number of merchants, and the preset weight coefficient of the number of merchants.
同时，考虑互通行为的时效性，可以通过当前时间和用户与商家进行互通的互通行为的产生时间获取第二时间衰减系数，该第二时间衰减系数可以通过下式获取：At the same time, considering the timeliness of the interworking behavior, the second time decay coefficient can be obtained through the current time and the generation time of the interworking behavior between the user and the merchant, and the second time decay coefficient can be obtained by the following formula:
其中，p’(t)为第二时间衰减系数，α’、β’是需求衰减参数，T是当前时间，t’是用户与商家进行互通的互通行为的产生时间。当t’＝T时，p’(t)＝1，意味着需求时效性较强。具体参数的设置可以根据业务场景和需求而定。Among them, p'(t) is the second time decay coefficient, α', β' are the demand decay parameters, T is the current time, and t' is the generation time of the interworking behavior between the user and the merchant. When t'=T, p'(t)=1, which means that the demand is time-sensitive. The setting of specific parameters can be determined according to business scenarios and needs.
其中，p’(t)越大，表示用户与商家进行互通的互通行为距离当前时间越近，p’(t)越小，表示用户与商家进行互通的互通行为距离当前时间越远。Among them, the larger p'(t) is, the closer the intercommunication behavior between the user and the merchant is to the current time, the smaller the p'(t) is, the farther the intercommunication behavior between the user and the merchant is from the current time.
经过长期积累，结合商户/企业数据和运营商数据，同样可以反应用户需求，具体的，可以通过以下公式获取互通行为得分：After long-term accumulation, combined with merchant/enterprise data and operator data, it can also reflect user needs. Specifically, the interoperability behavior score can be obtained through the following formula:
c表示互通行为得分，Bui是商家(商家可以包括：企业和商户)；CT(t,Bui)是第t天与商家互通的第二次数；b1是第二次数对应的预设权重系数；b3是商家数量的预设权重系数；p′(t)是第二时间衰减系数；CF(Bui)是周期θ内初次联系的商家的数量。c represents the score of interaction behavior, Bui is the merchant (merchant can include: enterprises and merchants); CT(t, Bui ) is the second number of times of intercommunication with the merchant on the t day; b1 is the preset weight corresponding to the second number of times coefficient; b3 is the preset weight coefficient of the number of merchants; p'(t) is the second time decay coefficient; CF(Bui ) is the number of merchants contacted for the first time in the period θ.
通过结合企业/商户黄页数据和运营商大数据，进一步从互通层面挖掘用户需求。By combining enterprise/merchant Yellow Pages data and operator big data, user needs can be further explored from the interoperability level.
由于用户的互通行为还可能与其他的因素相关，在一个实施例中，还可以通过下述公式得到用户互通行为得分：Since the user's interworking behavior may also be related to other factors, in one embodiment, the user's interworking behavior score can also be obtained by the following formula:
在该式中，CX是预留特征，b2是预留特征对应的预设权重系数；其他参数含义与上述式子相同，此处不再赘述。In this formula, CX is a reserved feature, and b2 is a preset weight coefficient corresponding to the reserved feature; the meanings of other parameters are the same as those in the above formula, and will not be repeated here.
在步骤S103中，获取每一个用户对商家产品的偏好度。In step S103, the preference of each user for the merchant's product is obtained.
在一个实施例中，如图4所示，该步骤S103包括以下子步骤S1031-S1033：In one embodiment, as shown in FIG. 4 , this step S103 includes the following sub-steps S1031-S1033:
在步骤S1031中，获取用户浏览目标产品的次数；In step S1031, the number of times the user browses the target product is obtained;
在步骤S1032中，获取用户浏览与目标产品属于同类产品的数量；In step S1032, obtain the number of products that the user browses and the target product belongs to the same product;
在步骤S1033中，根据次数和数量获取偏好度。In step S1033, the preference degree is obtained according to the number of times and the number.
用户对商家产品的偏好度可以进一步精细化用户的需求。The user's preference for the merchant's products can further refine the user's needs.
具体的，产品匹配度反应用户浏览产品的集中程度，背后实际上体现的是产品的偏好度，比如价格、品牌、风险等。匹配度越高，说明用户对某类产品越感兴趣。设用户对商家产品的偏好度为p，用户浏览产品A的次数为pnum，用户浏览同类产品数量为ptotal，则p定义为：Specifically, product matching reflects the concentration of users browsing products, which actually reflects product preferences, such as price, brand, and risk. The higher the matching degree, the more interested the user is in a certain type of product. Suppose the user's preference for the merchant's product is p, the number of times the user browses product A is pnum , and the number of users browsing similar products is ptotal , then p is defined as:
以金融产品为例，市面上金融贷款类产品的利率有18/24/36不等，如果产品匹配度较高的产品利率是18％，那么，可以说明该用户对低利率产品有兴趣，反映了用户风险偏好。Taking financial products as an example, the interest rates of financial loan products on the market range from 18/24/36. If the interest rate of a product with a higher product matching degree is 18%, it can indicate that the user is interested in low-interest rate products, reflecting user risk appetite.
在步骤S104中，根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数。In step S104, the marketing response score corresponding to each user is obtained according to the preset user network behavior weight value, user network behavior score, preset interworking behavior weight value, interworking behavior score, preset preference weight value and preference degree.
设s表示用户对应的营销响应分数，也可以称之为用户意向分，其反映了一种“概率”。c表示互通行为得分，w表示用户网络行为得分，p表示用户对商家产品的偏好度。通过w和c判断用户需求，圈定大致用户范围。通过p细分用户需求，圈定适合特定产品的用户。s定义为：Let s represent the marketing response score corresponding to the user, which can also be called the user intent score, which reflects a "probability". c represents the intercommunication behavior score, w represents the user's network behavior score, and p represents the user's preference for the merchant's products. Determine the user needs by w and c, and delineate the approximate user range. Segment user needs through p to delineate users who are suitable for specific products. s is defined as:
s＝β1w+β2c+β3ps=β1 w+β2 c+β3 p
上式中，s表示用户对应的营销响应分数；β1表示预设用户网络行为权重值；β2表示预设用户网络行为权重值；β3表示预设用户网络行为权重值。In the above formula, s represents the marketing response score corresponding to the user; β1 represents the preset user network behavior weight value; β2 represents the preset user network behavior weight value; β3 represents the preset user network behavior weight value.
各因子的选取是基于对各行业获客方法总结得出的，对用户的影响大小是不同的。网络广告和电话作为获客的主要触达方式，从网络和互通行为，非常直接的定位目标用户，所以权重较大。The selection of each factor is based on the summary of customer acquisition methods in various industries, and the impact on users is different. Online advertisements and phone calls are the main ways of reaching customers. From the Internet and interoperability behaviors, they can directly locate target users, so they have a large weight.
在一种可实现方式中，预设用户网络行为权重值大于预设互通行为权重值；预设互通行为权重值大于预设偏好权重值。也即，w>c>p。In an implementation manner, the preset user network behavior weight value is greater than the preset interworking behavior weight value; the preset interworking behavior weight value is greater than the preset preference weight value. That is, w>c>p.
以消费品手机为例，通过w和c可以圈定有手机需求的用户，但是手机品牌众多，价格不一，可以通过p细分用户感兴趣的手机品牌和价格，反映了用户品牌偏好和价格偏好。Taking consumer mobile phones as an example, w and c can be used to delineate users who have mobile phone needs, but there are many mobile phone brands with different prices, and p can be used to subdivide the mobile phone brands and prices that users are interested in, reflecting the user's brand preference and price preference.
在确定用户意向分时引入p，体现了精准意向挖掘中千人千面的思想，进一步定位目标用户，降低目标用户数量的同时，提升了投资回报率。The introduction of p in the time-sharing of user intentions reflects the idea of precise intention mining, which further locates target users, reduces the number of target users, and improves the return on investment.
在步骤S105中，根据各个用户对应的营销响应分数确定对各个用户的营销策略。In step S105, a marketing strategy for each user is determined according to the marketing response score corresponding to each user.
其中，用户对应的营销响应分数越大表示用户的意向越高。Among them, the higher the marketing response score corresponding to the user is, the higher the user's intention is.
在一个实施例中，该步骤S105包括以下子步骤A1-A2：In one embodiment, this step S105 includes the following sub-steps A1-A2:
在A1中，当用户对应的营销响应分数小于第一预设阈值，则提示通过人工外呼用户。In A1, when the user's corresponding marketing response score is less than the first preset threshold, the user is prompted to call the user manually.
在A2中，当用户对应的营销响应分数大于或等于第一预设阈值，则提示通过预设外呼方式开展用户触达，其中，预设外呼方式包括：短信或机器人。In A2, when the user's corresponding marketing response score is greater than or equal to the first preset threshold, the user is prompted to reach the user through a preset outbound call method, wherein the preset outbound call method includes: SMS or robot.
对营销响应分数较大的用户，可以提示客户通过人工外呼的方式进行呼叫，而对比营销响应分数较低的用户，可以通过成本较低的短信、机器人外呼等形式开展用户触达。Users with higher marketing response scores can be prompted to make calls through manual outbound calls, while users with lower marketing response scores can be reached through lower-cost SMS messages and robot outbound calls.
在一个实施例中，该步骤S105包括以下子步骤B1-B2：In one embodiment, this step S105 includes the following sub-steps B1-B2:
在B1中，按照各个用户对应的营销响应分数从大到小的顺序对各个用户进行排序；In B1, sort each user according to the corresponding marketing response score of each user in descending order;
在B2中，输出排序结果。In B2, output the sorted result.
对营销响应分数由高到底顺序进行排序，以让客户基于该顺序开展分期人工外呼。Sort the marketing response scores in descending order, so that customers can make outbound manual calls based on this order.
在一个实施例中，该步骤S105包括以下子步骤C1-C2：In one embodiment, this step S105 includes the following sub-steps C1-C2:
在C1中，当用户对应的营销响应分数小于第二预设阈值，则删除用户；In C1, when the user's corresponding marketing response score is less than the second preset threshold, delete the user;
在C2中，当用户对应的营销响应分数大于或等于第二预设阈值，则提示开展用户触达。In C2, when the marketing response score corresponding to the user is greater than or equal to the second preset threshold, a prompt is given to carry out user engagement.
只向客户展示营销响应分数较大的用户，从而可以有效减少客户查看的数据量。Only show customers users with high marketing response scores, which can effectively reduce the amount of data customers see.
在确定w、c、p的权重系数时，可以通过积累的样本，确定w、c、p合适的权重系数和第一预设阈值以及第二预设阈值，使用户对应的营销响应分数和成功率正相关。并通过实际触达用户来验证。不断调整，最终达到一个稳定的状态。When determining the weight coefficients of w, c, and p, the accumulated samples can be used to determine the appropriate weight coefficients of w, c, and p, the first preset threshold and the second preset threshold, so that the user's corresponding marketing response score and success rate is positively correlated. And verify it by actually reaching the user. Constantly adjust, and eventually reach a stable state.
进一步的，对上网初筛日志进行加工，以获取用户的网络操作类型、用户的各个网络操作类型的总操作次数、与用户有互通行为的商家类型、用户与各个商家类型的互通次数、用户浏览目标产品的次数以及用户浏览与目标产品属于同类产品的数量。Further, the initial screening log of the Internet is processed to obtain the user's network operation type, the total number of operations of each network operation type of the user, the type of merchants that communicate with the user, the number of interactions between the user and each merchant type, and the user browsing. The number of times the target product is viewed and the number of user views that belong to the same category as the target product.
具体的，根据业务需要，加工并积累以下业务字段：Specifically, according to business needs, the following business fields are processed and accumulated:
1.Type，该条记录所对应的行业领域，如房产、家装、贷款；1. Type, the industry field corresponding to this record, such as real estate, home improvement, loan;
2.Behavior,该条记录所对应的行为，如”贷款用户挖掘”，则可以是“登录贷款APP”“浏览贷款产品海报””提交申请”等。这个可以根据专家经验，分行业，自行定义获客关键节点；2. Behavior, the behavior corresponding to this record, such as "loan user mining", can be "login to the loan APP", "browse the loan product poster", "submit an application" and so on. This can be based on expert experience, sub-industry, self-defining key points of customer acquisition;
3.Time，该条记录所产生的时间，即行为发生的时间；3. Time, the time when the record was generated, that is, the time when the behavior occurred;
4.Object，导致用户记录产生的产品，比如某某金条；4. Object, products that lead to user records, such as certain gold bars;
5.From，该条记录产生的app或者web名称；5.From, the name of the app or web generated by the record;
6.Expansion，扩展属性，比如流量。6.Expansion, extended attributes, such as traffic.
从上数该些业务字段中便可以提取出上述的信息，具体提取方式与相关技术中类似，此处不再赘述。The above-mentioned information can be extracted from the above-mentioned business fields, and the specific extraction method is similar to that in the related art, and will not be repeated here.
本公开实施例提供的营销管控方法，包括：获取每一个用户在网络中操作时的用户网络行为得分；获取每一个用户与商家进行互通的互通行为得分；获取每一个用户对商家产品的偏好度；根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；根据各个用户对应的营销响应分数确定对各个用户的营销策略。其中，通过黄页数据配合运营商数据，从用户网络行为、用户与商家之间的互通行为、以及用户对商家产品的偏好度三个维度去计算营销响应分数，以挖掘目标用户，帮助企业实现精准获客，有效提高了外呼接通率和转化率。The marketing management and control method provided by the embodiment of the present disclosure includes: acquiring a user's network behavior score when each user operates in the network; acquiring each user's intercommunication behavior score with a merchant; acquiring each user's preference for the merchant's products ; Obtain the marketing response score corresponding to each user according to the preset user network behavior weight value, user network behavior score, preset interoperability behavior weight value, interoperability behavior score, preset preference weight value and preference degree; according to the marketing response score corresponding to each user Response scores determine marketing strategies for individual users. Among them, through the yellow pages data and operator data, the marketing response score is calculated from the three dimensions of user network behavior, interaction behavior between users and merchants, and user preference for merchant products, so as to mine target users and help enterprises achieve accurate Acquiring customers, effectively improving the connection rate and conversion rate of outbound calls.
再者，本公开中的方法，无需像相关技术中，基于机器学习训练的用户意向响应/成单分模型的方法，对样本数量、特征数量及粒度、计算资源有一定的要求，该方法适用于业务冷启动阶段。并且，本公开中的方法由于无需依赖专家经验输出规则，从而可以量化，以满足精细化与要求。Furthermore, the method in the present disclosure does not need to have certain requirements on the number of samples, the number and granularity of features, and computing resources as in the related art, the method based on the user intention response/component model trained by machine learning, and the method is applicable. in the cold start stage of the business. Moreover, since the method in the present disclosure does not need to rely on expert experience to output rules, it can be quantified to meet refinement and requirements.
具体的，本公开中通过公开的黄页数据配合运营商数据，从网络和互通行为两个维度挖掘目标用户，通过产品匹配度细分目标用户需求；并且基于数据时效性，计算用户的营销响应分数；从而可以有效提高了外呼接通率和转化率。Specifically, in this disclosure, target users are mined from the two dimensions of network and interworking behavior by using the disclosed yellow pages data and operator data, and the needs of target users are subdivided by product matching degree; and based on the timeliness of the data, the user's marketing response score is calculated. ; which can effectively improve the outbound call completion rate and conversion rate.
下述为本公开装置实施例，可以用于执行本公开方法实施例。The following are the apparatus embodiments of the present disclosure, which can be used to execute the method embodiments of the present disclosure.
图5是根据一示例性实施例示出的一种营销管控装置的框图，该装置可以通过软件、硬件或者两者的结合实现成为电子设备的部分或者全部。如图5所示，该营销管控装置包括：Fig. 5 is a block diagram of an apparatus for marketing management and control according to an exemplary embodiment. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of the two. As shown in Figure 5, the marketing control device includes:
第一获取模块11，用于获取每一个用户在网络中操作时的用户网络行为得分；The
第二获取模块12，用于获取每一个用户与商家进行互通的互通行为得分；The
第三获取模块13，用于获取每一个用户对商家产品的偏好度；The third obtaining
第四获取模块14，用于根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；The fourth obtaining
确定模块15，用于根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略。The determining
在一个实施例中，如图6所示，所述第一获取模块11，包括：In one embodiment, as shown in FIG. 6 , the first obtaining
第一获取子模块111，用于根据当前时间和用户在网络中操作时的用户网络行为的产生时间获取第一时间衰减系数；The
第二获取子模块112，用于获取所述用户第t天访问目标网络中的目标页面的第一次数；t为大于或等于1的整数；The second obtaining
第三获取子模块113，用于获取所述用户第t天访问所述目标页面的使用时长；The third obtaining sub-module 113 is used to obtain the usage duration of the user accessing the target page on the t day;
第四获取子模块114，用于获取所述用户第t天访问所述目标页面的使用流量；The fourth obtaining sub-module 114 is used to obtain the usage flow of the user accessing the target page on the t day;
网络行为得分获取子模块115，用于根据所述第一时间衰减系数、所述第一次数、所述第一次数对应的预设权重系数、所述使用时长、所述使用时长对应的预设权重系数、所述使用流量和所述使用流量对应的预设权重系数获取所述用户网络行为得分。The network behavior
在一个实施例中，如图7所示，所述第二获取模块12，包括：In one embodiment, as shown in FIG. 7 , the second obtaining
第五获取子模块121，用于根据当前时间和所述用户与商家进行互通的互通行为的产生时间获取第二时间衰减系数；The
第六获取子模块122，用于获取所述用户第t天与商家互通的第二次数；The sixth obtaining sub-module 122 is used to obtain the second number of times that the user communicates with the merchant on the t day;
第七获取子模块123，用于获取预设周期内初次联系的商家数量；The seventh obtaining sub-module 123 is used to obtain the number of merchants contacted for the first time within the preset period;
第八获取子模块124，用于根据所述第二时间衰减系数、所述第二次数、所述第二次数对应的预设权重、所述商家数量和所述商家数量的预设权重获取所述互通行为得分。The eighth obtaining sub-module 124 is configured to obtain the data according to the second time decay coefficient, the second number of times, the preset weight corresponding to the second number of times, the number of merchants, and the preset weight of the number of merchants. score for the interaction behavior described above.
在一个实施例中，如图8所示，所述第三获取模块13，包括：In one embodiment, as shown in FIG. 8 , the third obtaining
第九获取子模块131，用于获取用户浏览目标产品的次数；The
第十获取子模块132，用于获取用户浏览与所述目标产品属于同类产品的数量；The
第十一获取子模块133，用于根据所述次数和所述数量获取所述偏好度。The eleventh obtaining sub-module 133 is configured to obtain the preference degree according to the number of times and the quantity.
在一个实施例中，所述预设用户网络行为权重值大于所述预设互通行为权重值；所述预设互通行为权重值大于所述预设偏好权重值。In one embodiment, the preset user network behavior weight value is greater than the preset interworking behavior weight value; the preset interworking behavior weight value is greater than the preset preference weight value.
在一个实施例中，如图9所示，所述确定模块15，包括：In one embodiment, as shown in FIG. 9 , the determining
第一提示子模块151，用于当所述用户对应的营销响应分数小于第一预设阈值，则提示通过人工外呼所述用户；The
第一外呼子模块152，用于当所述用户对应的营销响应分数大于或等于所述第一预设阈值，则提示通过预设外呼方式开展用户触达，其中，所述预设外呼方式包括：短信或机器人。The first
在一个实施例中，如图10所示，所述确定模块15，包括：In one embodiment, as shown in FIG. 10 , the determining
排序子模块153，用于按照各个所述用户对应的营销响应分数从大到小的顺序对各个所述用户进行排序；a sorting
输出子模块154，用于输出所述排序结果。The
在一个实施例中，如图11所示，所述确定模块15，包括：In one embodiment, as shown in FIG. 11 , the determining
删除子模块155，用于当所述用户对应的营销响应分数小于第二预设阈值，则删除所述用户；A
第二提示子模块156，用于当所述用户对应的营销响应分数大于或等于所述第二预设阈值，则提示开展用户触达。The
根据本公开实施例的第三方面，提供一种营销管控装置，包括：According to a third aspect of the embodiments of the present disclosure, there is provided a marketing management and control device, including:
处理器；processor;
用于存储处理器可执行指令的存储器；memory for storing processor-executable instructions;
其中，处理器被配置为：where the processor is configured as:
获取每一个用户在网络中操作时的用户网络行为得分；Obtain the user's network behavior score when each user operates in the network;
获取每一个用户与商家进行互通的互通行为得分；Obtain the interoperability score of each user and merchant for intercommunication;
获取每一个用户对商家产品的偏好度；Obtain each user's preference for the merchant's products;
根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；Obtain the marketing response score corresponding to each user according to the preset user network behavior weight value, user network behavior score, preset interworking behavior weight value, interworking behavior score, preset preference weight value and preference degree;
根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略。A marketing strategy for each of the users is determined according to the marketing response scores corresponding to each of the users.
上述处理器还可被配置为：The above processor can also be configured to:
在一个实施例中，所述获取用户在网络中操作时的用户网络行为得分，包括：In one embodiment, the obtaining the user's network behavior score when the user operates in the network includes:
根据当前时间和用户在网络中操作时的用户网络行为的产生时间获取第一时间衰减系数；Obtain the first time attenuation coefficient according to the current time and the generation time of the user's network behavior when the user operates in the network;
获取所述用户第t天访问目标网络中的目标页面的第一次数；t为大于或等于1的整数；Obtain the first number of times that the user visits the target page in the target network on day t; t is an integer greater than or equal to 1;
获取所述用户第t天访问所述目标页面的使用时长；Obtain the usage time of the user accessing the target page on the t day;
获取所述用户第t天访问所述目标页面的使用流量；Obtain the usage traffic of the user accessing the target page on the t day;
根据所述第一时间衰减系数、所述第一次数、所述第一次数对应的预设权重系数、所述使用时长、所述使用时长对应的预设权重系数、所述使用流量和所述使用流量对应的预设权重系数获取所述用户网络行为得分。According to the first time decay coefficient, the first number of times, the preset weight coefficient corresponding to the first number of times, the use duration, the preset weight coefficient corresponding to the use duration, the usage flow and The user network behavior score is obtained by using the preset weight coefficient corresponding to the traffic.
在一个实施例中，所述获取用户与商家进行互通的互通行为得分，包括：In one embodiment, the obtaining of the interworking behavior score of the user and the merchant for interworking includes:
根据当前时间和所述用户与商家进行互通的互通行为的产生时间获取第二时间衰减系数；Obtain the second time attenuation coefficient according to the current time and the generation time of the interworking behavior of the user and the merchant;
获取所述用户第t天与商家互通的第二次数；Obtain the second number of times that the user communicates with the merchant on the t day;
获取预设周期内初次联系的商家数量；Get the number of merchants contacted for the first time within a preset period;
根据所述第二时间衰减系数、所述第二次数、所述第二次数对应的预设权重、所述商家数量和所述商家数量的预设权重获取所述互通行为得分。The interworking behavior score is obtained according to the second time decay coefficient, the second number of times, a preset weight corresponding to the second number of times, the number of merchants, and the preset weight of the number of merchants.
在一个实施例中，所述获取用户对商家产品的偏好度，包括：In one embodiment, the acquiring the user's preference for the merchant's product includes:
获取用户浏览目标产品的次数；Get the number of times users browse the target product;
获取用户浏览与所述目标产品属于同类产品的数量；Obtain the number of products browsed by users that belong to the same category as the target product;
根据所述次数和所述数量获取所述偏好度。The preference is obtained according to the number of times and the number.
在一个实施例中，所述预设用户网络行为权重值大于所述预设互通行为权重值；所述预设互通行为权重值大于所述预设偏好权重值。In one embodiment, the preset user network behavior weight value is greater than the preset interworking behavior weight value; the preset interworking behavior weight value is greater than the preset preference weight value.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
当所述用户对应的营销响应分数小于第一预设阈值，则提示通过人工外呼所述用户；When the marketing response score corresponding to the user is less than the first preset threshold, prompting the user to call the user manually;
当所述用户对应的营销响应分数大于或等于所述第一预设阈值，则提示通过预设外呼方式开展用户触达，其中，所述预设外呼方式包括：短信或机器人。When the marketing response score corresponding to the user is greater than or equal to the first preset threshold, the user is prompted to reach the user through a preset outbound call method, wherein the preset outbound call method includes: SMS or robot.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
按照各个所述用户对应的营销响应分数从大到小的顺序对各个所述用户进行排序；Sort each of the users according to the marketing response score corresponding to each of the users in descending order;
输出所述排序结果。The sorting result is output.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
当所述用户对应的营销响应分数小于第二预设阈值，则删除所述用户；When the marketing response score corresponding to the user is less than the second preset threshold, delete the user;
当所述用户对应的营销响应分数大于或等于所述第二预设阈值，则提示开展用户触达。When the marketing response score corresponding to the user is greater than or equal to the second preset threshold, the user is prompted to reach out.
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.
图12是根据一示例性实施例示出的一种用于营销管控装置80的框图，该装置适用于终端设备。例如，装置80可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。FIG. 12 is a block diagram of an
装置80可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制装置80的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。The
存储器804被配置为存储各种类型的数据以支持在装置80的操作。这些数据的示例包括用于在装置80上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为装置80的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为装置80生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述装置80和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当装置80处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当装置80处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。The I/
传感器组件814包括一个或多个传感器，用于为装置80提供各个方面的状态评估。例如，传感器组件814可以检测到装置80的打开/关闭状态，组件的相对定位，例如所述组件为装置80的显示器和小键盘，传感器组件814还可以检测装置80或装置80一个组件的位置改变，用户与装置80接触的存在或不存在，装置80方位或加速/减速和装置80的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于装置80和其他设备之间有线或无线方式的通信。装置80可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，装置80可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子组件实现，用于执行上述方法。In an exemplary embodiment,
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器804，上述指令可由装置80的处理器820执行以完成上述方法。例如，所述非临时性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。In an exemplary embodiment, there is also provided a non-transitory computer-readable storage medium including instructions, such as
一种非临时性计算机可读存储介质，当所述存储介质中的指令由装置80的处理器执行时，使得装置80能够执行上述的营销管控方法，所述方法包括：A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the
获取每一个用户在网络中操作时的用户网络行为得分；Obtain the user's network behavior score when each user operates in the network;
获取每一个用户与商家进行互通的互通行为得分；Obtain the interoperability score of each user and merchant for intercommunication;
获取每一个用户对商家产品的偏好度；Obtain each user's preference for the merchant's products;
根据预设用户网络行为权重值、用户网络行为得分、预设互通行为权重值、互通行为得分、预设偏好权重值和偏好度获取每一个用户对应的营销响应分数；Obtain the marketing response score corresponding to each user according to the preset user network behavior weight value, user network behavior score, preset interworking behavior weight value, interworking behavior score, preset preference weight value and preference degree;
根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略。A marketing strategy for each of the users is determined according to the marketing response scores corresponding to each of the users.
在一个实施例中，所述获取用户在网络中操作时的用户网络行为得分，包括：In one embodiment, the obtaining the user's network behavior score when the user operates in the network includes:
根据当前时间和用户在网络中操作时的用户网络行为的产生时间获取第一时间衰减系数；Obtain the first time attenuation coefficient according to the current time and the generation time of the user's network behavior when the user operates in the network;
获取所述用户第t天访问目标网络中的目标页面的第一次数；t为大于或等于1的整数；Obtain the first number of times that the user visits the target page in the target network on day t; t is an integer greater than or equal to 1;
获取所述用户第t天访问所述目标页面的使用时长；Obtain the usage time of the user accessing the target page on the t day;
获取所述用户第t天访问所述目标页面的使用流量；Obtain the usage traffic of the user accessing the target page on the t day;
根据所述第一时间衰减系数、所述第一次数、所述第一次数对应的预设权重系数、所述使用时长、所述使用时长对应的预设权重系数、所述使用流量和所述使用流量对应的预设权重系数获取所述用户网络行为得分。According to the first time attenuation coefficient, the first number of times, the preset weight coefficient corresponding to the first number of times, the use duration, the preset weight coefficient corresponding to the use duration, the usage flow and The user network behavior score is obtained by using the preset weight coefficient corresponding to the traffic.
在一个实施例中，所述获取用户与商家进行互通的互通行为得分，包括：In one embodiment, the obtaining of the interworking behavior score of the user and the merchant for interworking includes:
根据当前时间和所述用户与商家进行互通的互通行为的产生时间获取第二时间衰减系数；Obtain the second time attenuation coefficient according to the current time and the generation time of the interworking behavior of the user and the merchant;
获取所述用户第t天与商家互通的第二次数；Obtain the second number of times that the user communicates with the merchant on the t day;
获取预设周期内初次联系的商家数量；Get the number of merchants contacted for the first time within a preset period;
根据所述第二时间衰减系数、所述第二次数、所述第二次数对应的预设权重、所述商家数量和所述商家数量的预设权重获取所述互通行为得分。The interworking behavior score is obtained according to the second time decay coefficient, the second number of times, a preset weight corresponding to the second number of times, the number of merchants, and the preset weight of the number of merchants.
在一个实施例中，所述获取用户对商家产品的偏好度，包括：In one embodiment, the acquiring the user's preference for the merchant's product includes:
获取用户浏览目标产品的次数；Get the number of times users browse the target product;
获取用户浏览与所述目标产品属于同类产品的数量；Obtain the number of products browsed by users that belong to the same category as the target product;
根据所述次数和所述数量获取所述偏好度。The preference is obtained according to the number of times and the number.
在一个实施例中，所述预设用户网络行为权重值大于所述预设互通行为权重值；所述预设互通行为权重值大于所述预设偏好权重值。In one embodiment, the preset user network behavior weight value is greater than the preset interworking behavior weight value; the preset interworking behavior weight value is greater than the preset preference weight value.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
当所述用户对应的营销响应分数小于第一预设阈值，则提示通过人工外呼所述用户；When the marketing response score corresponding to the user is less than the first preset threshold, prompting the user to call the user manually;
当所述用户对应的营销响应分数大于或等于所述第一预设阈值，则提示通过预设外呼方式开展用户触达，其中，所述预设外呼方式包括：短信或机器人。When the marketing response score corresponding to the user is greater than or equal to the first preset threshold, the user is prompted to reach the user through a preset outbound call method, wherein the preset outbound call method includes: SMS or robot.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
按照各个所述用户对应的营销响应分数从大到小的顺序对各个所述用户进行排序；Sort each of the users according to the marketing response score corresponding to each of the users in descending order;
输出所述排序结果。The sorting result is output.
在一个实施例中，所述根据各个所述用户对应的营销响应分数确定对各个所述用户的营销策略，包括：In one embodiment, the determining a marketing strategy for each of the users according to the marketing response score corresponding to each of the users includes:
当所述用户对应的营销响应分数小于第二预设阈值，则删除所述用户；When the marketing response score corresponding to the user is less than the second preset threshold, delete the user;
当所述用户对应的营销响应分数大于或等于所述第二预设阈值，则提示开展用户触达。When the marketing response score corresponding to the user is greater than or equal to the second preset threshold, the user is prompted to reach out.
本领域技术人员在考虑说明书及实践这里公开的公开后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。Other embodiments of the present disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or techniques in the technical field not disclosed by the present disclosure . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637446.1ACN114331536A (en) | 2021-12-29 | 2021-12-29 | Marketing control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637446.1ACN114331536A (en) | 2021-12-29 | 2021-12-29 | Marketing control method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114331536Atrue CN114331536A (en) | 2022-04-12 |
Family
ID=81017608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111637446.1APendingCN114331536A (en) | 2021-12-29 | 2021-12-29 | Marketing control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114331536A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164804A (en)* | 2011-12-16 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Personalized method and personalized device of information push |
| CN109598564A (en)* | 2019-02-21 | 2019-04-09 | 上海宝尊电子商务有限公司 | The calculation method and device of a kind of user with timeliness to commodity interest level |
| US20200294089A1 (en)* | 2014-11-18 | 2020-09-17 | Square, Inc. | Calculating Customer Interest In Merchant Communications |
| CN112667899A (en)* | 2020-12-30 | 2021-04-16 | 杭州智聪网络科技有限公司 | Cold start recommendation method and device based on user interest migration and storage equipment |
| CN112927017A (en)* | 2021-02-26 | 2021-06-08 | 第四范式（北京）技术有限公司 | Control method, device and system for outbound marketing process |
- 2021
- 2021-12-29CNCN202111637446.1Apatent/CN114331536A/enactivePending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164804A (en)* | 2011-12-16 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Personalized method and personalized device of information push |
| US20200294089A1 (en)* | 2014-11-18 | 2020-09-17 | Square, Inc. | Calculating Customer Interest In Merchant Communications |
| CN109598564A (en)* | 2019-02-21 | 2019-04-09 | 上海宝尊电子商务有限公司 | The calculation method and device of a kind of user with timeliness to commodity interest level |
| CN112667899A (en)* | 2020-12-30 | 2021-04-16 | 杭州智聪网络科技有限公司 | Cold start recommendation method and device based on user interest migration and storage equipment |
| CN112927017A (en)* | 2021-02-26 | 2021-06-08 | 第四范式（北京）技术有限公司 | Control method, device and system for outbound marketing process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463643B (en) | Display method, device and storage medium of bullet screen data | |
| CN111127053B (en) | Page content recommendation method and device and electronic equipment | |
| CN107256509B (en) | Price comparison method and device, terminal, server and storage medium | |
| CN106547904B (en) | Cross-account information sharing method and device | |
| CN106502527A (en) | Method, device and terminal that a kind of content is shared | |
| CN107203398B (en) | Application distribution method and device | |
| CN105337847A (en) | Instant messaging information processing method, device and equipment | |
| CN107193606B (en) | Application distribution method and device | |
| CN113065008A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN117009691A (en) | Information display method and device, electronic equipment and storage medium | |
| CN106097040A (en) | Information-pushing method, device and terminal unit | |
| CN104517222A (en) | Method and device for setting intelligent hardware commodities on tops and displaying intelligent hardware commodities | |
| CN107239351B (en) | Paste method and device | |
| CN105373580A (en) | Method and device for displaying subjects | |
| CN109213942A (en) | A kind of search result methods of exhibiting and device | |
| JP2017529640A (en) | Short message processing method, apparatus, program, and recording medium | |
| CN105976201B (en) | Purchase behavior monitoring method and device for e-commerce system | |
| CN104850592B (en) | The method and apparatus for generating model file | |
| CN114371781A (en) | User portrait generation method and system in real estate marketing | |
| CN110968492B (en) | Information processing method and device and storage medium | |
| CN113765953A (en) | Information pushing method, device and equipment | |
| CN114666643B (en) | Information display method and device, electronic equipment and storage medium | |
| CN114022248B (en) | Product recommendation calculation method, device and equipment | |
| CN113190725B (en) | Object recommendation and model training method and device, equipment, medium and product | |
| CN114331536A (en) | Marketing control method and device |
Legal Events
| 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20220412 |