Movatterモバイル変換


[0]ホーム

URL:


CN120342987A - Information interaction method, device, computing device, storage medium and program product - Google Patents

Information interaction method, device, computing device, storage medium and program product

Info

Publication number
CN120342987A
CN120342987ACN202510551472.4ACN202510551472ACN120342987ACN 120342987 ACN120342987 ACN 120342987ACN 202510551472 ACN202510551472 ACN 202510551472ACN 120342987 ACN120342987 ACN 120342987A
Authority
CN
China
Prior art keywords
interaction
information
client
user
prompt information
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
Application number
CN202510551472.4A
Other languages
Chinese (zh)
Inventor
张博
王柏淋
高文静
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Chengshi Wanglin Information Technology Co Ltd
Original Assignee
Beijing Chengshi Wanglin Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Chengshi Wanglin Information Technology Co LtdfiledCriticalBeijing Chengshi Wanglin Information Technology Co Ltd
Priority to CN202510551472.4ApriorityCriticalpatent/CN120342987A/en
Publication of CN120342987ApublicationCriticalpatent/CN120342987A/en
Pendinglegal-statusCriticalCurrent

Links

Landscapes

Abstract

Translated fromChinese

本申请实施例提供一种信息交互方法、装置、计算设备、存储介质及程序产品。其中,服务端利用人工智能模型,结合用户标识对应的用户特征数据,从多个预设交互条件中确定与用户特征数据匹配的目标交互条件,以及结合目标交互条件关联的操作对象,生成第一交互提示信息,并确定第一交互提示信息对应的至少一个第一操作提示信息;将第一交互提示信息,以及至少一个第一操作提示信息作为会话消息发送至客户端,以便客户端在任意界面中叠加显示第一会话消息;接收客户端针对任意第一操作提示信息的触发操作发送的第一操作指令,确定第一操作指令对应的操作类型,并按照该操作类型处理操作对象。本申请实施例提供的技术方案提高了交互方式的主动性。

The embodiments of the present application provide an information interaction method, apparatus, computing device, storage medium and program product. Among them, the server uses an artificial intelligence model, combined with user feature data corresponding to a user identifier, to determine a target interaction condition matching the user feature data from multiple preset interaction conditions, and an operation object associated with the target interaction condition, to generate a first interaction prompt message, and to determine at least one first operation prompt message corresponding to the first interaction prompt message; the first interaction prompt message and at least one first operation prompt message are sent to the client as a session message, so that the client can overlay and display the first session message in any interface; the first operation instruction sent by the client for the trigger operation of any first operation prompt message is received, the operation type corresponding to the first operation instruction is determined, and the operation object is processed according to the operation type. The technical solution provided by the embodiments of the present application improves the initiative of the interaction method.

Description

Information interaction method, apparatus, computing device, storage medium and program product
Technical Field
Embodiments of the present application relate to the field of computer technologies, and in particular, to an information interaction method, an information interaction device, a computing device, a storage medium, and a program product.
Background
With the development of artificial intelligence technology, the application of artificial intelligence technology in electronic commerce systems is increasing, for example, the electronic commerce system introduces an artificial intelligence model (for example, intelligent customer service) to interact with users, so as to improve the interaction quality.
Currently, artificial intelligence models in electronic commerce systems. In an instant messaging (INSTANT MESSAGING, IM) interface, a user can automatically reply to a problem instead of a manual customer service, so that the message reply cost is reduced and the message reply efficiency is improved. However, there is a passive interaction mode, and improvement is needed.
Disclosure of Invention
The embodiment of the application provides an information interaction method, an information interaction device, a computing device, a storage medium and a program product, which are used for solving the problem that an interaction mode is passive when an artificial intelligent model is interacted with a user in the prior art.
The embodiment of the application provides an information interaction method which is applied to a server and comprises the steps of utilizing an artificial intelligent model, combining user characteristic data corresponding to user identification, determining target interaction conditions matched with the user characteristic data from a plurality of preset interaction conditions, combining operation objects associated with the target interaction conditions, generating first interaction prompt information, determining at least one first operation prompt information corresponding to the first interaction prompt information, sending the first interaction prompt information and the at least one first operation prompt information to a client as first session information, so that the client displays the first session information in an overlapping mode in any interface, receiving a first operation instruction sent by the client, wherein the first operation instruction is generated by the client in response to triggering operation aiming at any one of the first operation prompt information, determining an operation type corresponding to the first operation instruction, and processing the operation objects according to the operation type.
The embodiment of the application provides an information interaction method which is applied to a client and comprises the steps of receiving a first session message sent by a server, wherein the first session message comprises first interaction prompt information and at least one first operation prompt message corresponding to the first interaction prompt information, the first interaction prompt information and the at least one first operation prompt message are generated by utilizing an artificial intelligent model and combining operation objects associated with target interaction conditions, the target interaction conditions are determined from a plurality of preset interaction conditions by utilizing the artificial intelligent model and combining user characteristic data corresponding to user identification, the first session message is displayed in any interface in a superposition mode, a first operation instruction is generated in response to triggering operation aiming at any one of the first operation prompt messages, and the first operation instruction is sent to the server so that the server can determine an operation type corresponding to the first operation instruction and process the operation objects according to the operation type.
The embodiment of the application provides an information interaction device which is configured at a server and comprises a model running module, a first sending module, a first receiving module and an operation processing module, wherein the model running module is used for utilizing an artificial intelligent model, combining user characteristic data corresponding to user identification, determining target interaction conditions matched with the user characteristic data from a plurality of preset interaction conditions, combining operation objects associated with the target interaction conditions, generating first interaction prompt information, determining at least one first operation prompt information corresponding to the first interaction prompt information, the first sending module is used for sending the first interaction prompt information and the at least one first operation prompt information to a client as a first session message so that the client can display the first session message in an overlapped mode in any interface, the first receiving module is used for receiving a first operation instruction sent by the client, the first operation instruction is generated by the client in response to trigger operation aiming at any one first operation prompt information, and the operation processing module is used for determining the operation type corresponding to the first operation instruction and processing the operation objects according to the operation type.
The embodiment of the application provides an information interaction device which is configured at a client and comprises a second receiving module, an instruction generating module and a second sending module, wherein the second receiving module is used for receiving a first session message sent by a server, the first session message comprises first interaction prompt information and at least one first operation prompt message corresponding to the first interaction prompt information, the first interaction prompt information and the at least one first operation prompt message are generated by utilizing an artificial intelligent model and combining operation objects associated with target interaction conditions, the target interaction conditions are determined by utilizing the artificial intelligent model and combining user characteristic data corresponding to user identifications from a plurality of preset interaction conditions, the display module is used for displaying the first session message in an overlapped mode in any interface, the instruction generating module is used for responding to triggering operation aiming at any one of the first operation prompt messages, and the second sending module is used for sending the first operation instruction to the server so that the server can determine the operation type corresponding to the first operation instruction and process the operation objects according to the operation type.
The embodiment of the application also provides a computing device which comprises a processing component and a storage component, wherein the storage component stores a computer program, and the computer program is used for being called and executed by the processing component so as to realize the information interaction method.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processing component, realizes the information interaction method.
The embodiment of the application also provides a computer program product, which comprises a computer program or instructions, wherein the computer program or instructions realize the information interaction method when being executed by a processing component.
The server side of the embodiment of the application utilizes an artificial intelligent model, combines user characteristic data corresponding to the user identifier, determines target interaction conditions meeting the user characteristic data from a plurality of preset conditions, and combines operation objects associated with the target interaction conditions to generate first interaction prompt information and at least one first operation prompt information corresponding to the first interaction prompt information as a first session message. The first session message is sent to the client so that the client superimposes and displays the first session message in any interface. The client generates a first operation instruction in response to the triggering operation of any first operation prompt information, and then sends the first operation instruction to the server, and the server processes the operation object according to the operation type after determining the operation type corresponding to the first operation instruction. The embodiment provides a mode of actively touching and interacting with a user, and improves the initiative of the interaction mode when the artificial intelligent model is used for interacting with the user. In addition, the first session message generated by the server side can be displayed in a superimposed manner in any interface currently displayed by the client side, so that interaction with the user in a non-instant communication interface is realized, and the flexibility and instantaneity of interaction are improved. In addition, the session message in this embodiment includes not only the interaction prompt information but also the operation prompt information, and the user only needs to trigger the corresponding operation prompt information on the client side to trigger the server side to execute the related processing operation on the operation object. The whole interaction process can be completed by only triggering operation at least once without inputting interaction content by a user, so that the convenience of operation is improved, and the acceptance and satisfaction of the user on the actively touched interaction operation are improved.
These and other aspects of the application will be more readily apparent from the following description of the embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
Fig. 1 shows a system architecture diagram for information interaction according to an exemplary embodiment of the present application.
Fig. 2 shows a flowchart of an information interaction method according to an exemplary embodiment of the present application.
Fig. 3 is a schematic diagram of overlaying and displaying session messages in any interface according to an exemplary embodiment of the present application.
Fig. 4 is a schematic diagram of a set of overlaid display session messages in any interface provided by an exemplary embodiment of the present application.
Fig. 5 shows a flowchart of an information interaction method according to an exemplary embodiment of the present application.
Fig. 6 shows a signaling diagram of an information interaction method of an application scenario according to an exemplary embodiment of the present application.
Fig. 7 is a schematic structural diagram of an information interaction device according to an exemplary embodiment of the present application.
Fig. 8 is a schematic structural diagram of an information interaction device according to an exemplary embodiment of the present application.
FIG. 9 illustrates a schematic diagram of a computing device for information interaction provided by the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that, the technical solution of the embodiment of the present application is applicable to a network virtual environment, where the described user is generally referred to as a "virtual user", and a real user may register a user account in a server through a registration manner to obtain a user identity in the network environment. The same user account can log in to the server through different types of clients, so that the server can identify the same user.
The interaction operation between the server and the user can be realized based on the user account, and the corresponding data received or sent by the server to the user is realized based on the user account, so that the corresponding data is actually received or sent by the client corresponding to the user account to the server. In addition, communication and the like can be realized among users through user accounts. The user may refer to an individual, or may refer to an organization, such as an enterprise, and the present application is not particularly limited thereto.
It should be noted that, in the case where the embodiment of the present application relates to user information, the user information (including, but not limited to, user feature data, user identifier, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) related to the embodiment of the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and are provided with corresponding operation entries for the user to select authorization or rejection. In addition, the various artificial intelligence models (including but not limited to language models or large models) to which the present application relates are compliant with relevant legal and standard regulations.
In addition, it should be noted that, in the case where the embodiment of the present application relates to a user interaction operation or trigger operation, the user interaction operation or trigger operation related to the embodiment of the present application includes, but is not limited to, an interaction operation in various manners, such as a touch operation, a gesture operation, a voice operation, a head movement operation, an eye movement operation, and the like, where the touch operation includes, but is not limited to, a click operation, a double click operation, a long press operation, a sliding operation, a pinch operation, or a mouse hovering operation. The sliding operation includes, but is not limited to, linear sliding, curved sliding, and the like.
Furthermore, it should be noted that, in the case where the embodiment of the present application relates to a jump between a first interface and a second interface, the jump mode according to the embodiment of the present application includes, but is not limited to, directly jumping from the first interface to the second interface, jumping from the first interface to the task interface first, and jumping to the second interface if the task interface is completed with the task operation, where the task interface is completed with the task operation including, but not limited to, completing identity authentication on the identity authentication interface if the task interface is implemented as the identity authentication interface, completing recharging operation on the recharging interface if the task interface is implemented as the recharging interface, and so on
With the development of artificial intelligence technology, the application of artificial intelligence technology in electronic commerce systems is increasing, for example, the electronic commerce system introduces an artificial intelligence model to interact with users to improve the interaction quality. At present, a scene of interaction between an artificial intelligent model in an electronic commerce system and a user is generally that when the user has an interaction requirement, the user enters an instant messaging interface through a client, then a problem is input in the interface, and at the moment, the artificial intelligent model can replace manual customer service to automatically reply the problem raised by the user, so that the message reply cost is reduced, and the message reply efficiency is improved. However, existing artificial intelligence models can only passively reach interactions for users' questions. Aiming at the problem, the embodiment of the application provides a solution, and the basic idea is that a server side utilizes an artificial intelligent model, combines user characteristic data corresponding to user identification, determines target interaction conditions meeting the user characteristic data from a plurality of preset conditions, and combines operation objects associated with the target interaction conditions to generate first interaction prompt information and at least one first operation prompt information corresponding to the first interaction prompt information as a first session message. The first session message is sent to the client so that the client superimposes and displays the first session message in any interface. The client generates a first operation instruction in response to the triggering operation of any first operation prompt information, and then sends the first operation instruction to the server, and the server processes the operation object according to the operation type after determining the operation type corresponding to the first operation instruction. The embodiment provides a mode of actively touching and interacting with a user, and improves the initiative of the interaction mode when the artificial intelligent model is used for interacting with the user. In addition, the session message generated by the server side can be displayed in a superimposed manner in any interface currently displayed by the client side, so that interaction with the user can be realized in a non-instant communication interface, and the flexibility and instantaneity of interaction are improved. In addition, the session message in this embodiment includes not only the interaction prompt information but also the operation prompt information, and the user only needs to trigger the corresponding operation prompt information on the client side to trigger the server side to execute the related processing operation on the operation object. The whole interaction process can be completed by only triggering operation at least once without inputting interaction content by a user, so that the convenience of operation is improved, and the acceptance and satisfaction of the user on the actively touched interaction operation are improved.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Fig. 1 shows a system architecture diagram of an electronic commerce system applicable to information interaction according to an embodiment of the present application, where the system architecture may include a client 101 and a server 102. (or may include a server, a plurality of clients, or may include a server, a first client, a second client, etc.)
Wherein, the connection between the client 101 and the server 102 can be established through a network. The network provides a medium for a communication link between client 101 and server 102. The network may include various connection types, such as wired, wireless, or fiber optic cables, etc. The client 101 may interact with the server 102 over a network to receive or send messages, etc.
The client 101 may be a browser, an APP (Application program), or a web Application such as an H5 (HyperText Markup Language, 5 th edition of hypertext markup language) Application, or a light Application (also called applet, a lightweight Application program), or a cloud Application, etc., and the client 101 may be deployed in an electronic device, and needs to run depending on the device or some APPs in the device, etc. The electronic device may for example have a display screen and support information browsing etc. as may be a personal mobile terminal such as a mobile phone, tablet computer, personal computer, desktop computer, smart phone, smart watch etc. for ease of understanding, the client is mainly represented in fig. 1 by a device image. Various other types of applications are also commonly deployed in electronic devices, such as human-machine conversation type applications, model training type applications, text processing type applications, web browser applications, shopping type applications, search type applications, instant messaging tools, mailbox clients, social platform software, and the like. The electronic device may be a device used by a user and having functions of calculation, internet surfing, communication and the like required by the user, for example, may be a mobile phone, a tablet computer, a personal computer, a wearable device and the like. An electronic device may generally include at least one processing component and at least one storage component. The electronic device may also include basic configurations of a network card chip, an IO (input/output) bus, an audio/video component, and the like, which is not limited in this regard. Optionally, depending on the electronic device implementation, some peripheral devices may be included, such as a keyboard, mouse, stylus, printer, etc., as the application is not limited in this regard.
The server 102 may include a server that provides various services, such as a server for background training that provides support for a model used on the client 101, a server that processes interaction information sent by the client, and so on.
It should be noted that, the server 102 may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. The server may also be a server of a distributed system or a server that incorporates a blockchain. The server may also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.
It should be noted that, the information interaction method provided by the embodiment of the present application may also be performed by the client 101 and the server 102 together, and it should be understood that the numbers of clients and servers in fig. 1 are only illustrative. There may be any number of clients and servers, as desired for implementation.
In addition, it should be noted that, since the e-commerce system in the present embodiment can provide a transaction platform for a service provider (such as a merchant), a consumer can know and purchase a service object (such as a service commodity) provided by the service provider through the transaction platform, and meanwhile, a management party (such as a system operation and maintenance party) of the e-commerce system can provide some functional objects (such as a commodity provided by the e-commerce system, such as a system member, an intelligent customer service, etc.) for the consumer or the service provider. Therefore, the user in this embodiment may be a service provider (e.g., a merchant), the client may be a service provider version client (e.g., a seller version client) in the e-commerce system, and the user may also be a consumer, and the client may be a consumer version client (e.g., a buyer version client) in the e-commerce system.
Implementation details of the technical solution of the embodiment of the present application are set forth in detail below.
Fig. 2 is a flowchart of an embodiment of an information interaction method provided by the present application, where the technical solution of the present embodiment may be executed by a server. As shown in fig. 2, the method may include the following steps:
S201, determining target interaction conditions matched with user feature data from a plurality of preset interaction conditions by utilizing an artificial intelligent model and combining user feature data corresponding to user identification, generating first interaction prompt information by combining operation objects associated with the target interaction conditions, and determining at least one first operation prompt information corresponding to the first interaction prompt information.
The user identifier may be a unique identifier of the user, for example, a user name, a telephone, etc. registered in the electronic commerce system by the user.
The user characteristic data may be user attribute information, user history behavior information, and the like maintained in the electronic commerce system. Specifically, if the user is a service provider, the user characteristic data at this time may be a client login time of the service provider, a purchase and consultation condition of the issued service object, historical issue information in the e-commerce system (such as post information of the issued service object), related information of the purchased function object (for example, if the function object is a system member, the related information may be a handling time, an expiration time, introduction information, etc. of the system member). If the user is a consumer, the user characteristic data may be gender, age, region, preference, information about purchased service objects and function objects, client login time, etc.
The preset interaction condition may be a preset judgment condition for judging whether to actively touch the interaction. For example, the preset interaction conditions may include, but are not limited to, first, that the user has performed an operation of purchasing the function object or the service object, second, that the user logs in for the first time within a preset period (such as a day, a week, or a month), third, that the user is about to expire when purchasing the function object on the e-commerce platform, fourth, that the user is an intended user of the function object to be promoted on the e-commerce platform, and so on. Optionally, if the user is a service provider, the preset interaction condition may further include that there is a marketing problem, a marketing performance is outstanding, and the like.
The operation object may be an object that needs to be operated in the interaction, may be an object that can actually perform the operation, such as a certain functional object to be promoted provided by an e-commerce system, or may be an object that cannot actually perform the operation, such as a care operation.
The first interaction prompt information may be interaction content when actively touching the interaction. The first operation prompt information may be for the first interaction prompt information, and prompt the user to select an operation to be executed. For example, operational cues may be included that characterize willing to continue with interactions, such as "good," "agreeing," etc., and operational cues may be included that characterize unintended to continue with interactions, such as "no need," "unused," etc. An operational prompt may also be included to characterize the known condition, such as "thank you".
Optionally, in this embodiment, the server may acquire, for any user identifier maintained in the electronic commerce system, user feature data corresponding to the user identifier, and then generate, based on the user feature data, a preset interaction condition, task description, task examples, output format requirements, and the like, a prompt instruction to be input into the artificial intelligence model, to guide the artificial intelligence model to infer whether a target interaction condition satisfying the user feature data exists in the multiple preset interaction conditions, and further determine an operation object corresponding to the target interaction condition. For example, if the target interaction condition in this embodiment is determined from the four preset interaction conditions listed above, determining the operation object corresponding to the target interaction condition may include a case where the operation object may be a care if the target interaction condition is the first or second one of the preset interaction conditions, a case where the operation object may be a function object to be expired if the target interaction condition is the third one of the preset interaction conditions, and a case where the operation object may be a function object to be promoted if the target interaction condition is the fourth one of the preset interaction conditions.
Optionally, if the number of preset interaction conditions matching the user feature data is multiple, the embodiment may select, according to the priority of each preset interaction condition, the highest priority from the multiple matched preset interaction conditions as the target interaction condition. The matching degree between the user characteristic data and each matched preset interaction condition can be output by utilizing the artificial intelligent model, and the highest matching degree is selected from a plurality of matched preset interaction conditions to serve as a target interaction condition. Or the method comprises the steps of taking a plurality of matched preset interaction conditions as target interaction conditions, and executing and determining the first interaction prompt information, the first operation prompt information and subsequent operations according to each target interaction condition in a time-sharing mode, so that the active interaction is achieved according to each target interaction condition in a time-sharing mode. This is not limited.
It should be noted that, for any user feature data, there may be a matched target interaction condition, or there may not be a matched target interaction condition, if so, the first interaction prompt information, the first operation prompt information and the subsequent operation are determined, if not, the user identifier is considered to need no active interaction, and the subsequent operation is not performed. And reselecting the user characteristic data corresponding to other user identifications to judge.
After the artificial intelligence model is utilized to determine the target interaction object and the associated operation object, the artificial intelligence model can further generate first interaction prompt information aiming at the associated operation object. Specifically, the method can be an example that an artificial intelligent model can learn a prompt instruction and generate first interaction prompt information aiming at an operation object associated with a target interaction condition, or can set preset interaction information (such as standard interaction speech) for the operation object associated with the target interaction condition in advance, and at the moment, the artificial intelligent model can moisten the preset interaction information of the operation object according to a spoken language style, so that the first interaction prompt information is generated to be closer to the speaking effect of a real person. For example, for the four preset interaction conditions listed above, the corresponding first interaction prompt messages may be "welcome you to become a system member |", "new week, wish you to get a big luck |", "you member will expire soon, need renewal.
After the first interactive prompt message is generated, at least one operation prompt message may be determined for the first interactive prompt message according to the content of the first interactive prompt message. Specifically, one implementation manner may be to generate at least one operation prompt message for the first interaction prompt message by using an artificial intelligence model in combination with a user historical operation habit, an operation content available for a target interaction condition in an electronic commerce system, a preset operation prompt ticket operation and the like. The method can improve the flexibility and the diversity of the determination of the operation prompt information, and the determined operation prompt information is more in line with the operation habit of the user.
Another implementation manner may be that at least one selectable operation item corresponding to the first interaction prompt information is determined, and relevant information of the at least one selectable operation item is filled into a control component template to obtain at least one first operation prompt information corresponding to the first interaction prompt information. The selectable operation items are options for the first interaction prompt information to be operated by a user. The control component template may be a preset generic template for generating control components in the display interface.
The related information of the selectable operation items includes, but is not limited to, names, animation expressions, website links and the like corresponding to the selectable operation items. For example, if the selectable operation item is "good", the corresponding relevant information may include the name "good" and the animated expression characterizing the good. If the optional operation item is "recharge", the corresponding related information may include a name "recharge" and a website link of the recharge page. Alternatively, for each selectable operation item, the corresponding related information thereof may be predetermined and stored in the server.
Since the operation object corresponding to the interaction prompt information in this embodiment is usually fixed, such as care words or promotion function objects, and the corresponding selectable operation items are often fixed for a certain class of operation objects, for example, when the operation object is a promotion function object, the first interaction prompt information may be to promote and transact the function object to the user, for example, "you member will expire, and is about to renew. When the operation object is a care utterance, such as weekly welcome, monthly incentives, new member welcome, etc., the corresponding selectable operation item is an operation item (such as "good", "thank you", etc.) that has been known about the situation. The embodiment can prestore the selectable operation items corresponding to the care words and the promotion function objects, the related information corresponding to each selectable operation item and the general control component template.
When the step is executed to determine the first operation prompt information, an operation object corresponding to the first interaction prompt information is analyzed, at least one optional operation item preset for the operation object is searched, then for each optional operation item corresponding to the operation object, the prestored relevant information corresponding to the optional operation item is obtained, the relevant information is filled into a general control component template, a control component corresponding to the optional operation item is obtained, and the control component is used as one first operation prompt information corresponding to the first interaction prompt information. According to the method, based on the relation between the preconfigured operation object and the selectable operation item and the control component template corresponding to the selectable operation item, at least one first operation prompt message is quickly and conveniently determined, the operation prompt message is not required to be generated by combining with an artificial intelligent model each time, the interaction cost in active touch interaction is reduced, and the interaction efficiency is improved.
The trigger condition for the server to execute S201 is numerous, and this is not limited. One implementation manner is to set different trigger periods according to different operation objects for a plurality of preset interaction conditions, and execute the operation of S201 after reaching the trigger period. For example, eight to ten points in the morning can be set to judge whether the user characteristic data matches the preset interaction condition corresponding to the care session class, and two to five points in the afternoon can be set to judge whether the user characteristic data matches the preset interaction condition corresponding to the function object class. Another implementation manner is that the client detects the target trigger operation in any interface, generates a trigger request containing the user identifier, sends the trigger request to the server, and the server executes the operation of S201 after receiving the trigger request. The target trigger operation may be a specific operation, such as an operation of browsing a functional object. The first triggering operation detected after the client starts operation for the first time every day can also be used.
It should be noted that, the artificial intelligence model referred to herein may be a Language Model (LM) based on artificial intelligence or a multi-modal model (Multimodal Model, MM), and the embodiment of the present application does not limit how many model parameters are supported by the model, so as to meet the actual needs. If the model parameters are relatively more, the scale of the language model is relatively larger, the model performance is relatively better, more time and resources are consumed in the reasoning or training process, if the model parameters are relatively less, the scale of the model is relatively smaller, the model is lighter under the condition that the performance meets the requirements, and the time and resources consumed in the reasoning or training process are relatively less. The artificial intelligence model according to the embodiments of the present application may be a deep learning model for processing and generating natural language text or multimodal data, and may be implemented based on a neural network architecture, which may be pre-trained on a large amount of data. In an alternative implementation, the artificial intelligence model referred to herein may include an encoder (Encoder), a Decoder (Decoder), a Self-Attention Layer (Self-Attention Layer), a Feed-forward neural network (Feed-Forward NeuralNetwork), and the like. The encoder is primarily used to convert input data (typically in sequential form) into a vector representation, a process that captures semantic features of the input data. The decoder is responsible for converting the intermediate representation generated by the encoder into output data (usually in the form of a sequence), the self-attention layer is a mechanism for enabling the model to focus on other positions in the sequence to better encode current position information, and the feedforward neural network is used for performing nonlinear transformation and the like on the output of the self-attention layer to enhance the expression capability of the model, and the various parts work together so that the model constructed based on the feedforward neural network can be excellent in various complex processing tasks, such as natural language processing, computer vision, voice recognition, machine translation, text summarization, intelligent question-answering and the like.
S202, the first interaction prompt information and at least one first operation prompt information are sent to the client side as first session information, so that the client side displays the first session information in an overlapping mode in any interface.
The arbitrary interface may be any interface currently displayed by the client, and may be a system homepage, a service list interface, a detail display interface, and the like.
In this embodiment, the server may generate a first session message including the first interaction prompt information and at least one operation prompt information according to the format of the session message, and then send the first session message to the client, where after receiving the first session message, the client superimposes and displays the first session message on any interface currently displayed (i.e. the currently displayed interface of the client). For example, a dialog card or a prompt box may be displayed in an overlapping manner in the arbitrary interface, and then the first interactive prompt message-text content form is added to the dialog card or the prompt box, and at least one operation prompt message is added to the dialog card or the prompt box in the form of a touch component. An exemplary embodiment, as shown in fig. 3, is an effect diagram of displaying a first session message in an overlapping manner in any interface, where a box 301 is a dialog box displayed in any interface, the text "please ask your member if it needs to be upgraded" displayed in box 301 is a first interactive prompt message, and the touch component "none" and the touch component "to be upgraded" correspond to two operation prompts.
It should be noted that, the server may render the first session message to any interface currently displayed by the client in a manner of superposition display, and then directly send the rendered any interface to the client, where the client directly displays the received rendered any interface. The server may send the first session message to the client, and the client may perform the operations of rendering the first session message to the arbitrary interface in a manner of displaying the first session message in a superimposed manner, and displaying the rendered arbitrary interface.
S203, receiving a first operation instruction sent by the client, wherein the first operation instruction is generated by the client in response to the triggering operation aiming at any one of the first operation prompt messages.
Optionally, after the client displays the first session message in a superimposed manner in any interface, the user may click on a touch component corresponding to one of the first operation prompt messages according to the requirement, that is, perform a triggering operation on the first operation prompt message, and after the client detects the triggering operation, generate a first operation instruction based on the first operation prompt message corresponding to the triggering operation, and send the first operation instruction to the server. Correspondingly, the server side receives the first operation instruction.
S204, determining an operation type corresponding to the first operation instruction, and processing an operation object according to the operation type.
The operation types of the embodiment may include a continuation operation type indicating that the user wants to continue interaction and a stop operation indicating that the user does not want to continue interaction.
Because the first operation instruction is generated based on the first operation prompt information, the server can reversely push the first operation prompt information selected by the user aiming at the first interaction prompt information through the first operation instruction. At this time, the server may determine the operation type corresponding to the first operation instruction according to whether the first interaction prompt information corresponding to the first operation instruction indicates that the user has a wish to continue interaction. For example, if the first interaction prompt information corresponding to the first operation instruction is "good", "callback removing", "recharging" and the like, the operation type corresponding to the first operation instruction is continuous operation, and if the first interaction prompt information corresponding to the first operation instruction is "blank", "unnecessary", "unused" and the like, the operation type corresponding to the first operation instruction is stop operation. It should be noted that, for the first operation prompt information representing the known situation, since the user does not need to perform the processing operation on the operation object after knowing the situation, the corresponding operation type of the first operation prompt information can be considered as the stop operation. For example, when the operation object is a care operation, the operation types corresponding to the generated first operation instruction are all stop operations.
Optionally, if the operation type corresponding to the first operation instruction is continuous operation, at this time, the server analyzes the first interaction prompt information to determine the operation content of the operation object, and then executes the related processing operation on the operation object according to the operation content. For example, for the first interaction prompt message in fig. 3, if the first interaction prompt message corresponding to the first operation instruction is "upgrade-removing", the operation object is a system member, and the server may execute the member upgrade processing operation for the user.
And if the operation type corresponding to the first operation instruction is stop operation, sending a first session message closing instruction to the client so as to instruct the client to close the first session message which is overlapped and displayed in any interface. For example, for the first interaction prompt information in fig. 3, if the first interaction prompt information corresponding to the first operation instruction is "blank", it is indicated that the user does not want to upgrade the member currently, at this time, the server may send a first session message closing instruction to the client, and the client may respond to the instruction to close the first session message displayed in an overlapping manner in any interface, and restore the original any interface. So as to avoid the long-time display of session information, and influence the normal browsing interface of the user, and cause the conflict of the user on active interaction.
Optionally, in this embodiment, the client may directly close the first session message displayed in any interface in a superimposed manner after detecting that the triggering operation is not performed on the first operation prompt message for a long time (e.g. 10 s) by the user, or after detecting that the triggering operation is performed on the first prompt message which is not intended to continue to interact, so that the client does not interact with the server.
The server side of the embodiment utilizes an artificial intelligent model, combines user characteristic data corresponding to the user identifier, determines target interaction conditions meeting the user characteristic data from a plurality of preset conditions, and combines operation objects associated with the target interaction conditions to generate first interaction prompt information and at least one first operation prompt information corresponding to the first interaction prompt information as a first session message. The first session message is sent to the client so that the client superimposes and displays the first session message in any interface. The client generates a first operation instruction in response to the triggering operation of any first operation prompt information, and then sends the first operation instruction to the server, and the server processes the operation object according to the operation type after determining the operation type corresponding to the first operation instruction. The embodiment provides a mode of actively touching and interacting with a user, and improves the initiative of the interaction mode when the artificial intelligent model is used for interacting with the user. In addition, the session message generated by the server side can be displayed in a superimposed manner in any interface currently displayed by the client side, so that interaction with the user can be realized in a non-instant communication interface, and the flexibility and instantaneity of interaction are improved. In addition, the session message in this embodiment includes not only the interaction prompt information but also the operation prompt information, and the user only needs to trigger the corresponding operation prompt information on the client side to trigger the server side to execute the related processing operation on the operation object. The whole interaction process can be completed by only triggering operation at least once without inputting interaction content by a user, so that the convenience of operation is improved, and the acceptance and satisfaction of the user on the actively touched interaction operation are improved.
In some embodiments, for an operation object, it may correspond to a plurality of selectable operation contents, for example, for a system member, it may include a plurality of operations for upgrading to different member levels, and the higher the member level, the more interests they enjoy and the higher the corresponding charges. In order to make the operation content of the operation object more consistent with the acceptance of the user, the embodiment may use an artificial intelligence model to generate the operation content of the operation object in combination with the user feature data if the operation type corresponding to the first operation instruction is continuous operation, and process the operation object according to the operation content. Specifically, the processing of the operation object may be performed by analyzing the operation content most likely to be accepted by the user for the operation object by using the artificial intelligence model in combination with the user feature data, and using the operation content as the operation content for the operation object. In the embodiment, when determining the operation content aiming at the operation object, the unified operation content is not executed indifferently, or the operation content with the most profit is executed, but the operation content which is most suitable for the user is selected by combining the user characteristic data, so that the acceptance and acceptance of the interactive operation of the user on the active touch can be improved.
In some embodiments, when the operation object associated with the target interaction condition is a target function object and the target function object comprises at least two selectable levels, generating operation content for the operation object by utilizing an artificial intelligence model and combining user characteristic data, wherein the operation content for the operation object is generated by utilizing the artificial intelligence model and combining user characteristic data, determining the current user level of the target function object, determining the target level from the at least two selectable levels according to the current user level, and upgrading the operation content to the target level. Specifically, if the user purchases the targeting function object before, the user characteristic data may include fees paid when the user purchases the targeting function object, and the grades corresponding to the different fees are different, so that the current user grade of the user for the targeting function object can be analyzed from the user characteristic data by using the artificial intelligence model, and then the grade is improved on the basis of the current user grade, for example, one grade is improved to be used as the target grade, and the operation of upgrading from the current user grade to the target grade is used as the operation content for the operation object. According to the embodiment, the target grade is selected for the user based on the user characteristic data, so that the user can be guided to upgrade the grade gradually, and the acceptance of the user to upgrade the grade is improved.
In some embodiments, in order to facilitate the user to more intuitively understand the operation content of the server on the operation object, to prevent the situation that the server processes the operation object due to the user's false touch, the embodiment may further use an artificial intelligence model to generate second interaction prompt information and at least one second operation prompt information corresponding to the second interaction prompt information in combination with the operation content, where the second interaction prompt information is used to instruct to confirm execution of the operation content, send the second interaction prompt information and the at least one second operation prompt information to the client as a second session message, so that the client superimposes and displays the second session message in any interface, receive a second operation instruction sent by the client, where the second operation instruction is generated by the client in response to a trigger operation for any one of the second operation prompt information, and process the operation object according to the operation content if the operation type corresponding to the second operation instruction is continuous operation.
Specifically, the server may use the artificial intelligence model to generate a section of second interactive prompt information for describing the operation content to the user in combination with the operation content, and confirm whether to execute the operation content to the user. And then, generating at least one second operation prompt message according to the similar manner of the S201-S204, and sending the second interaction prompt message and the at least one second operation prompt message to the client as a second session message, so that the client displays the second session message in a superposition manner in any interface. Receiving a second operation instruction sent by the client, wherein the second operation instruction is generated by the client in response to the triggering operation aiming at any second operation prompt information; and if the operation type corresponding to the second operation instruction is continuous operation, processing the operation object according to the operation content. And if the operation type corresponding to the second operation instruction is stop operation, sending a second session message closing instruction to the client so as to instruct the client to close the second session message which is overlapped and displayed in any interface.
Optionally, in order to better enable the user to know the processing result of the operation object, the embodiment may further utilize an artificial intelligence model to generate, in combination with the operation result, third interaction prompt information for describing the operation result and third operation prompt information (such as "good", "thank you", etc.) for characterizing the user to know the operation result, send the third interaction prompt information and the third operation prompt information as a third session message to the client so that the client displays the third session message in an overlapping manner in any interface, and because the third operation prompt information characterizes the user to know the operation result, the client performs a triggering operation on the third operation prompt information, after generating the third operation instruction and sending the third operation instruction to the server, the server may send a third session message closing instruction to the client to instruct the client to close the session message displayed in an overlapping manner in any interface. Or after the client detects the triggering operation aiming at the third operation prompt information, the third session message which is overlapped and displayed in any interface is directly closed.
By way of example, the superimposed dialog card in the first arbitrary interface shown in fig. 4 shows a first interactive prompt, i.e. "please ask you if you need to increase the post presentation time duration? the touch control components corresponding to the two first operation prompt messages are good and unused respectively. If the client detects that the user clicks the touch component "good", which indicates that the user wants to consider increasing the post display duration, the client sends a first operation instruction representing that there is a desire to continue interaction to the server, the server responds to the first operation instruction to generate second interaction prompt information "good" for describing the operation content, the display duration is adjusted to be "good" and "unused" for the two second operation prompt information, and sending the session information to the client so that the server can display the session information in a superimposed manner on any interface, wherein the display effect is shown in a second arbitrary interface diagram in fig. 4, and if the client detects that the user triggers the touch component to be good again, which indicates that the user agrees to the operation content, the client sends a second operation instruction representing that the operation is agreed to continue to the server, and the server responds to the second operation to execute the operation for adjusting the post display duration. After the execution is completed, the server side also generates a third interaction prompt message which characterizes the execution result, and the adjustment operation is completed. And the third operation prompt information of 'thank you' is sent to the client as session information so that the server can display the session information in a superimposed manner on any interface, the display effect is shown in a third arbitrary interface diagram in fig. 4, if the client detects that the user triggers the touch component again, the client can directly close the session information superimposed on any interface, and can also interact with the server, and after receiving a closing instruction sent by the server, the client closes the session information.
In some embodiments, in order to improve autonomy of a user in processing an operation object and reduce interaction times when operation content corresponding to the operation object is clear or the operation process requires user participation (such as a payment password is required to be input by the user in a recharging operation process), the embodiment may further send operation interface information corresponding to the operation content to a client so that the client jumps from any interface to an operation interface of the operation object and displays the operation interface information on the operation interface, and process the operation object in response to an object operation request sent by the client, where the object operation request is generated for triggering operation of the operation interface information. Specifically, in this embodiment, after determining the operation content for the operation object, the operation interface information sending client corresponding to the operation content is obtained, and the operation interface information is displayed by skipping from any interface currently displayed to the operation interface of the operation object by the client, where the user may autonomously trigger related operations according to own needs, and the client may generate an object operation request for the user-triggered operations and send the object operation request to the server, so that the server processes the operation object according to the user-autonomously triggered related operations. For example, if the operation content is member upgrade, the webpage link, the two-dimensional code or the detailed information of the member upgrade interface may be sent to the client as the operation interface information.
In some embodiments, in order to improve the acceptance of the first interaction prompt information by the user and avoid directly recommending the functional object by using the fixed phone, the embodiment may further combine the user feature data and the preset interaction information to generate the first interaction prompt information while using the artificial intelligence model. Specifically, the artificial intelligent model is utilized, the operation object and the user characteristic data associated with the target interaction condition are combined to generate interaction guiding information, and the interaction guiding information and the preset interaction information of the operation object are combined to generate first interaction prompt information. The interactive guidance information may be a section of introduction language explaining a reason why the user needs to order the function object when the operation object is the function object, and may be generated according to the user characteristic data. Specifically, the artificial intelligent model can be utilized to combine with user characteristic data analysis to persuade a user to order a reason of a functional object, then the reason is subjected to spoken style conversion to generate interaction guiding information, and then the interaction guiding information is combined with preset interaction information (such as preset standard recommended speaking) of the functional object to generate first interaction prompting information with higher user receiving degree.
In some embodiments, in order to enable a user to receive a target function object more easily when an operation object associated with a target interaction condition is a target function object, the method includes generating interaction guide information by combining the operation object associated with the target interaction condition and user feature data by using an artificial intelligence model, wherein the interaction guide information is used for describing a logical relationship between the user transaction data and/or the telephone consultation data and the target function object. Specifically, the artificial intelligence model may be used to analyze the user transaction data and/or the telephone consultation data in the user feature data, so as to obtain the recent business condition of the user (i.e. the service provider), such as whether the recent business condition is improved or reduced compared with the previous business condition, and then establish the words from analyzing the recent business condition to guiding the user to purchase the functional object as the interactive guiding information. For example, for the first interaction prompt information shown in fig. 4, the corresponding interaction guidance information may be "the business of the merchant is promoted, which is related to the post showing duration of the target function object, so the user may be prompted to increase the post showing duration again.
In some embodiments, the active touch interaction of the server side in this embodiment interacts with the user by superimposing the session message on the current interface, and after the session message is closed, the user is convenient to view the content of the interaction subsequently. The embodiment can also generate the instant communication message based on the first interaction prompt message, at least one first operation prompt message and the first operation instruction, and add the instant communication message into the instant communication interface of the client so as to display the instant communication message when the client enters the instant communication interface.
Specifically, each time the server completes interaction with the user, that is, the server completes generation and sends first interaction prompt information and at least one first operation prompt information to the client, and the user performs triggering operation on the client for a certain first operation prompt information, the server generates an instant messaging message based on the information of the interaction, that is, the first interaction prompt information and at least one first operation prompt information generated by the server, and the first operation prompt information triggered by the user, for example, the first interaction prompt information and the at least one first operation prompt information generated by the server can be used as a message sent by a non-user side (for example, can be an intelligent customer service side), and the first operation prompt information triggered by the user is used as a message sent by the user side. And synchronizing the instant messaging messages to an instant messaging interface of the client so that the client can display the instant messaging messages corresponding to the active touch interaction in the instant messaging interface when the instant messaging interface needs to be displayed next time in response to the touch operation of the user.
It should be noted that, the first interaction prompt information, at least one first operation prompt information, and the first operation instruction represent only one interaction operation, in this embodiment, for one active touch interaction, there may be multiple interactions, for example, there may be a second interaction prompt information, a second operation instruction, a third interaction prompt information, a third operation prompt information, and a third operation instruction, etc., and this embodiment may generate an instant communication message for relevant information of each interaction operation, and synchronize the instant communication message to an instant communication interface, so as to facilitate viewing of an instant communication interface of a user client.
In some embodiments, in order to improve flexibility and diversity of interaction modes, the embodiment can utilize the artificial intelligent model to actively reach the interaction with the user, and can also utilize the passive reach to interact with the user when the user has a query requirement. The method comprises the steps of receiving target query information sent by a client, generating the target query information by the client in response to input operation for an instant messaging interface, generating query interaction information for the target query information by using an artificial intelligent model, and sending the query interaction information to the client so that the client can display the query interaction information on the instant messaging interface.
Specifically, in this embodiment, when a user has a query requirement, the user may interact with the service provider or the system manager by entering an instant messaging interface with the service provider or the system manager through the client. The user can input target query information through the instant communication interface of the client, or can be alternative query information prompted in the communication interface when clicking, the client can send the query information input or clicked by the user as target query information to the server, and the embodiment can determine query interaction information corresponding to the target query information by combining an artificial intelligence model with a knowledge base of a service provider or a system manager, user characteristic data and the like. And sending the determined query interaction information to the client so that the client displays the query interaction information in the instant messaging interface. Because the query interaction information in this embodiment is generated by using an artificial intelligence model and adjusting the standard speech technology in the knowledge base according to the user feature data, the query interaction information determined in this embodiment is closer to the reply context of the artificial client and meets the actual requirements of the user compared with the query interaction information directly searched from the knowledge base.
Fig. 5 is a flowchart of an information interaction method according to an exemplary embodiment of the present application, where the technical solution of the present embodiment may be executed by a client, and the client is a client used by a consumer in an electronic commerce system. Or may be a client used by a service provider in an e-commerce system. The method may comprise the steps of:
S501, receiving a first session message sent by a server.
The first session message comprises first interaction prompt information and at least one first operation prompt information corresponding to the first interaction prompt information, wherein the first interaction prompt information and the at least one first operation prompt information are generated by utilizing an artificial intelligent model and combining operation objects associated with target interaction conditions, and the target interaction conditions are determined from a plurality of preset interaction conditions by utilizing the artificial intelligent model and combining user characteristic data corresponding to user identifiers.
S502, the first session message is displayed in a superposition mode in any interface.
S503, responding to the triggering operation of any one of the first operation prompt information in the first session message, and generating a first operation instruction.
S504, a first operation instruction is sent to the server side, so that the server side determines an operation type corresponding to the first operation instruction, and the operation object is processed according to the operation type.
In some embodiments, in order to facilitate a user to intuitively understand the operation content of the server on the operation object, to prevent the situation that the server processes the operation object due to the user's mistouching, the embodiment may further receive a second session message sent by the server, where the second session message includes a second interaction prompt message and at least one second operation prompt message corresponding to the second interaction prompt message, where the second interaction prompt message and the at least one second operation prompt message are generated by the server by using the artificial intelligence model in combination with the operation content, superimpose and display the second session message in the arbitrary interface, generate a second operation instruction in response to a triggering operation for any one of the second operation prompt messages, and send the second operation instruction to the server, so that the server processes the operation object according to the operation content when the operation type corresponding to the second operation instruction is continuous operation.
In some embodiments, in order to improve the autonomy of a user for processing an operation object and reduce the interaction times, the embodiment may further be to receive operation interface information corresponding to operation content sent by a server, skip from the arbitrary interface to an operation interface of the operation object, display the operation interface information on the operation interface, trigger operation for the operation interface information, generate an object operation request, and send the object operation request to the server, so that the server responds to the object operation request and processes the operation object.
In some embodiments, the method further comprises the step of receiving a first session message closing instruction sent by the server, closing the first session message which is overlapped and displayed in the optional interface, wherein the first session closing instruction is generated by the server under the condition that an operation type corresponding to the first operation instruction is stop operation.
In some embodiments, the method further comprises the steps of responding to input operation for an instant messaging interface, generating target query information, sending the target query information to a server side, enabling the server side to utilize the artificial intelligent model to generate query interaction information for the target query information, receiving the query interaction information sent by the server side, and displaying the query interaction information on the instant messaging interface.
In a practical application, fig. 6 shows a signaling diagram of an information interaction method of an application scenario provided by an exemplary embodiment of the present application, where the method is implemented by a client and a server together. The method specifically comprises the following steps:
S601, a server side utilizes an artificial intelligent model, combines user characteristic data corresponding to user identification, determines target interaction conditions matched with the user characteristic data from a plurality of preset interaction conditions, combines operation objects associated with the target interaction conditions, generates first interaction prompt information, and determines at least one first operation prompt information corresponding to the first interaction prompt information.
Optionally, when the server generates the first interaction prompt information, an artificial intelligent model may be used to combine the operation object associated with the target interaction condition with the user feature data to generate interaction guide information, and combine the interaction guide information with preset interaction information of the operation object to generate the first interaction prompt information.
S602, the server sends the first interaction prompt information and at least one first operation prompt information to the client as a first session message.
S603, the client displays the first session message in an overlapped mode in any interface.
S604, the client responds to the triggering operation aiming at any one of the first operation prompt messages to generate a first operation instruction.
S605, the client sends a first operation instruction to the server.
S606, the server determines the operation type corresponding to the first operation instruction, and processes the operation object according to the operation type.
Specifically, if the operation type corresponding to the first operation instruction is stop operation, the server may send a first session message closing instruction to the client to instruct the client to close the first session message that is displayed in a superimposed manner in the arbitrary interface. And if the operation type corresponding to the first operation instruction is continuous operation, the server side generates operation content aiming at the operation object by combining the user characteristic data by utilizing the artificial intelligent model, and processes the operation object according to the operation content.
Further, when the server side processes the operation object according to the operation content, whether the operation content is clear or not by the user can be further considered, if yes, operation interface information corresponding to the operation content can be sent to the client side, the client side jumps to an operation interface of the operation object from any interface and displays the operation interface information on the operation interface, the client side triggers operation on the operation interface information, generates an object operation request, sends the object operation request to the server side, and the server side responds to the object operation request to process the operation object.
If the user does not clearly operate the content, the server side can use the artificial intelligent model to combine the operation content to generate second interaction prompt information and at least one second operation prompt information corresponding to the second interaction prompt information, wherein the second interaction prompt information is used for indicating to confirm the execution of the operation content, the second interaction prompt information and the at least one second operation prompt information are sent to the client side as second session information, the client side can display the second session information in an overlapping mode in any interface, the client side can also respond to triggering operation for any one of the second operation prompt information to generate a second operation instruction, the second operation instruction is sent to the server side, and the server side can process the operation object according to the operation content when the operation type corresponding to the second operation instruction is continuous operation.
Further, the server side also generates an instant communication message based on the first interaction prompt message, the at least one first operation prompt message and the first operation instruction, and adds the instant communication message into an instant communication interface of the client side so that the instant communication message is displayed when the client side enters the instant communication interface.
S607, the client responds to the input operation for the instant communication interface to generate the target query information.
And S608, the client sends the target query information to the server.
S609, the server generates query interaction information aiming at target query information by utilizing the artificial intelligence model.
S610, the server sends the query interaction information to the client.
S611, the client displays the query interaction information on the instant communication interface.
The detailed implementation and the beneficial effects of each step in the method of this embodiment have been described in the foregoing embodiments, and will not be described in detail herein.
It should be noted that, in some of the above embodiments and the flows described in the drawings, a plurality of operations appearing in a specific order are included, but it should be clearly understood that the operations may be performed in an order other than the order in which they appear herein or performed in parallel, the sequence numbers of the operations are such as the process of 601-606 active touch interaction, the process of 607-611 passive touch interaction, and are merely used to distinguish between the various operations, and the sequence numbers themselves do not represent any execution order. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
Fig. 7 is a schematic structural diagram of an information interaction device provided in an exemplary embodiment of the present application, where the device is configured on a server, and includes a model running module 701 configured to determine, by using an artificial intelligence model and in combination with user feature data corresponding to a user identifier, a target interaction condition matching with the user feature data from a plurality of preset interaction conditions, and in combination with an operation object associated with the target interaction condition, generate first interaction prompt information, and determine at least one first operation prompt information corresponding to the first interaction prompt information, a first sending module 702 configured to send the first interaction prompt information, and the at least one first operation prompt information as a first session message to a client, so that the client superimposes and displays the first session message in any interface, a first receiving module 703 configured to receive a first operation instruction sent by the client, where the first operation instruction is generated by the client in response to a trigger operation for any one of the first operation prompt information, and an operation processing module 704 configured to determine an operation type corresponding to the first operation instruction, and process the operation object according to the operation type.
In an alternative embodiment, the operation processing module 704 is specifically configured to generate, by using the artificial intelligence model and in combination with the user feature data, an operation content for the operation object if the operation type corresponding to the first operation instruction is a continuous operation, and process the operation object according to the operation content.
In an alternative embodiment, if the operation object associated with the target interaction condition is a target function object and the target function object includes at least two alternative levels, the operation processing module 704 is specifically configured to determine, by using the artificial intelligence model and in combination with the user feature data, a current user level of the target function object, determine, according to the current user level, a target level from the at least two alternative levels, and upgrade operation content to the target level as operation content for the operation object.
In an optional embodiment, the operation processing module 704 is further specifically configured to use the artificial intelligence model to combine the operation content to generate a second interaction prompt message and at least one second operation prompt message corresponding to the second interaction prompt message, where the second interaction prompt message is used to instruct to confirm execution of the operation content, send the second interaction prompt message and the at least one second operation prompt message as a second session message to the client so that the client superimposes and displays the second session message on the arbitrary interface, receive a second operation instruction sent by the client, where the second operation instruction is generated by the client in response to a trigger operation for any one of the second operation prompt messages, and if an operation type corresponding to the second operation instruction is a continuous operation, process the operation object according to the operation content.
In an optional embodiment, the operation processing module 704 is further specifically configured to send operation interface information corresponding to the operation content to the client, so that the client jumps from the arbitrary interface to an operation interface of the operation object, and displays the operation interface information on the operation interface, and process the operation object in response to an object operation request sent by the client, where the object operation request is generated for a triggering operation of the operation interface information.
In an optional embodiment, the operation processing module 704 is further specifically configured to send a first session message closing instruction to the client to instruct the client to close the first session message that is displayed in the optional interface in a superimposed manner if the operation type corresponding to the first operation instruction is a stop operation.
In an alternative embodiment, the model running module 701 is specifically configured to generate, by using an artificial intelligence model, interaction guiding information by combining the operation object associated with the target interaction condition and the user feature data, and generate first interaction prompt information by combining the interaction guiding information and preset interaction information of the operation object.
In an alternative embodiment, if the operation object associated with the target interaction condition is a target function object, the model running module 701 is specifically configured to generate interaction guidance information according to user transaction data and/or telephone consultation data in the user feature data and function introduction information of the target function object by using an artificial intelligence model, where the interaction guidance information is used to describe a logical relationship between the user transaction data and/or telephone consultation data and ordering the target function object.
In an optional embodiment, the device further includes an information synchronization module, configured to generate an instant communication message based on the first interaction prompt information, the at least one first operation prompt information, and the first operation instruction, and add the instant communication message to an instant communication interface of the client, so that the client displays the instant communication message when entering the instant communication interface.
In an alternative embodiment, the first receiving module 703 is further configured to receive target query information sent by the client, where the target query information is generated by the client in response to an input operation for an instant messaging interface, the model running module 701 is further configured to generate query interaction information for the target query information using the artificial intelligence model, and the first sending module 702 is further configured to send the query interaction information to the client, so that the client displays the query interaction information on the instant messaging interface.
The information interaction device shown in fig. 7 may perform the information interaction method shown in the embodiment shown in fig. 2, and its implementation principle and technical effects are not repeated. The specific manner in which the individual modules, units, and operations of the apparatus of the above embodiment are performed has been described in detail in connection with the embodiment of the method, and will not be described in detail here.
Fig. 8 is a schematic structural diagram of an information interaction device according to an exemplary embodiment of the present application, where the device is configured at a client, and includes:
The system comprises a server, a second receiving module 801, a display module 802, an instruction generating module 803 and a second sending module 804, wherein the first receiving module 801 is used for receiving a first session message sent by the server, the first session message comprises first interaction prompt information and at least one first operation prompt information corresponding to the first interaction prompt information, the first interaction prompt information and the at least one first operation prompt information are generated by utilizing an artificial intelligent model and combining operation objects related to target interaction conditions, the target interaction conditions are determined from a plurality of preset interaction conditions by utilizing the artificial intelligent model and combining user characteristic data corresponding to user identification, the display module 802 is used for displaying the first session message in an overlapped mode in any interface, the instruction generating module 803 is used for responding to triggering operation of any one of the first operation prompt information in the first session message, and the second sending module 804 is used for sending the first operation instruction to the server so that the server can determine an operation type corresponding to the first operation instruction and process the operation objects according to the operation type.
In an alternative embodiment, the second receiving module 801 is further configured to receive a second session message sent by the server, where the second session message includes a second interaction prompt message and at least one second operation prompt message corresponding to the second interaction prompt message, where the second interaction prompt message and the at least one second operation prompt message are generated by the server by using the artificial intelligence model and in combination with the operation content, the display module 802 is further configured to superimpose and display the second session message on the arbitrary interface, the instruction generating module 803 is further configured to generate a second operation instruction in response to a trigger operation for any one of the second operation prompt messages, and the second sending module 804 is further configured to send the second operation instruction to the server, so that the server processes the operation object according to the operation content when an operation type corresponding to the second operation instruction is a continuous operation.
In an alternative embodiment, the second receiving module 801 is further configured to receive operation interface information corresponding to an operation content sent by a server, the display module 802 is further configured to skip from the arbitrary interface to an operation interface of the operation object and display the operation interface information on the operation interface, the request generating module is configured to generate an object operation request for a triggering operation of the operation interface information, and the second sending module 804 sends the object operation request to the server, so that the server responds to the object operation request and processes the operation object.
In an alternative embodiment, the second receiving module 801 is further configured to receive a first session message closing instruction sent by the server, the display module 802 is further configured to close the first session message displayed in an overlapping manner in the arbitrary interface, and the first session closing instruction is generated by the server when an operation type corresponding to the first operation instruction is a stop operation.
In an alternative embodiment, the device further includes a query generation module, configured to generate target query information in response to an input operation for an instant messaging interface, the second sending module 804 is further configured to send the target query information to a server, so that the server uses the artificial intelligence model to generate query interaction information for the target query information, the second receiving module 801 is further configured to receive the query interaction information sent by the server, and the display module 802 is further configured to display the query interaction information on the instant messaging interface.
The information interaction device shown in fig. 8 may perform the information interaction method shown in the embodiment shown in fig. 5, and its implementation principle and technical effects are not repeated. The specific manner in which the individual modules, units, and operations of the apparatus 8 in the above embodiments are described in detail in connection with the embodiments of the method will not be described in detail here.
FIG. 9 is a schematic diagram illustrating one embodiment of a computing device provided by the present application. As shown in FIG. 9, in practice, the computing device may include a storage component 901 and a processing component 902.
Storage component 901 is used to store computer programs and may be configured to store various other data to support operations on a computing device. Examples of such data include instructions, data structures, contact data, phonebook data, messages, pictures, videos, etc. for any application or method operating on the computing device.
The processing component 902, coupled to the storage component 901, is configured to execute a computer program in the storage component 901 for implementing a server device such as a server array, and may not include the components within the dashed box in fig. 9.
The processing assembly includes one or more processors executing computer instructions to perform all or part of the steps of the methods described above. Of course, the processing component may also be implemented as one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements for executing the methods described above.
The Memory components described above may be implemented by any type or combination of volatile or non-volatile Memory devices, such as Static Random-Access Memory (SRAM), electrically erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY, EEPROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
The communication component is configured to facilitate wired or wireless communication between the device in which the communication component is located and other devices. The device in which the communication component is located may access a wireless network based on a communication standard, such as a mobile communication network, or a combination thereof. In one exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.
The display assembly may include a screen, which may include a Liquid crystal display (Liquid CRYSTAL DISPLAY, LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or sliding action, but also the duration and pressure associated with the touch or sliding operation.
The power supply component provides power for various components of equipment where the power supply component is located. The power components may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the devices in which the power components are located.
The audio component described above may be configured to output and/or input an audio signal. For example, the audio component includes a Microphone (MIC) configured to receive external audio signals when the device in which the audio component is located is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may be further stored in a memory or transmitted via a communication component. In some embodiments, the audio assembly further comprises a speaker for outputting audio signals.
Accordingly, embodiments of the present application also provide a computer-readable storage medium storing a computer program, which when executed by a processor, causes the processor to implement the steps of the method embodiments described above. Wherein the computer-readable storage medium includes volatile or nonvolatile or a combination thereof implementations, which may be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change Memory (Phase-change Random Access Memory, PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (Dynamic Random Access Memory, DRAM), other types of Random Access Memory (RAM), read-only Memory (ROM), electrically erasable programmable read-only Memory (EEPROM), erasable programmable read-only Memory (EPROM), programmable read-only Memory (PROM), flash Memory or other Memory technology, compact disc read-only Memory (CD-ROM), digital versatile disc (Digital Video Disc, DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices, or any other non-transmission media
Accordingly, embodiments of the present application also provide a computer program product comprising a computer program or instructions which, when executed by a processor, cause the processor to carry out the steps of the above-described method embodiments. It should be understood that each of the above-described method flows or a combination of flows may be implemented by a computer program or instructions. In addition, these computer programs or instructions may be applied to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus, such that the processor of the general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus is implemented as a device that performs the corresponding functions in the above described method embodiments.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
Finally, it should be noted that the above is only an example of the application and is not intended to limit the application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims (17)

The system comprises a server, a second receiving module, a target interaction condition generation module and a user identification module, wherein the server is used for receiving a first session message sent by the server, the first session message comprises first interaction prompt information and at least one first operation prompt information corresponding to the first interaction prompt information, the first interaction prompt information and the at least one first operation prompt information are generated by utilizing an artificial intelligent model and combining operation objects associated with the target interaction condition, and the target interaction condition is determined from a plurality of preset interaction conditions by utilizing the artificial intelligent model and combining user characteristic data corresponding to the user identification;
CN202510551472.4A2025-04-282025-04-28 Information interaction method, device, computing device, storage medium and program productPendingCN120342987A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202510551472.4ACN120342987A (en)2025-04-282025-04-28 Information interaction method, device, computing device, storage medium and program product

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202510551472.4ACN120342987A (en)2025-04-282025-04-28 Information interaction method, device, computing device, storage medium and program product

Publications (1)

Publication NumberPublication Date
CN120342987Atrue CN120342987A (en)2025-07-18

Family

ID=96357630

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202510551472.4APendingCN120342987A (en)2025-04-282025-04-28 Information interaction method, device, computing device, storage medium and program product

Country Status (1)

CountryLink
CN (1)CN120342987A (en)

Similar Documents

PublicationPublication DateTitle
US11997055B2 (en)Chat management system
US11790376B2 (en)Predicting customer support requests
US11196863B2 (en)Method and system for virtual assistant conversations
US11102152B2 (en)System and method of using conversational agent to collect information and trigger actions
CN109661675B (en)Using semantic processing for customer support
US20210201359A1 (en)Systems and methods relating to automation for personalizing the customer experience
US8849791B1 (en)Assisted shopping
AU2018223060A1 (en)Method and apparatus for providing customized interaction experience to customers
CN109313665A (en)The creation of computer message robot
US9697057B2 (en)Automated transfer of user data between applications utilizing different interaction modes
AU2021265099A1 (en)System and method for personalization as a service
BoonstraDefinitive guide to conversational AI with dialogflow and Google cloud
US12418499B2 (en)Intelligent assistant content generation
Graham et al.Chatbots in customer service within banking and finance: Do chatbots herald the start of an AI revolution in the corporate world?
US20240428275A1 (en)Foundation model integrations for personalized engagement with software applications
CN119477304A (en) Recharge QR code generation method, device, storage medium and program product based on artificial intelligence
CN119202414A (en) Page display method, device, storage medium and program product
CN120342987A (en) Information interaction method, device, computing device, storage medium and program product
CN120297986A (en) Information interaction method, device, computing device, storage medium and program product
CN120499319A (en) Online customer service method, system, device, storage medium and program product
CN120301930A (en) Information prompt method, device, computing equipment, storage medium and program product
CN120386908A (en) Information search and display method, device, computing device, storage medium and product
CN120358366A (en)Information issuing method, apparatus, computing device, storage medium, and program product
CN120499468A (en) Information processing method, device, computing device, storage medium and program product
CN119537523A (en) Knowledge question answering and knowledge content processing method, device, storage medium and program product

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination

[8]ページ先頭

©2009-2025 Movatter.jp