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

Abstract

The embodiment of the invention provides an information interaction method and device, computing equipment, a storage medium and a program product. Wherein the server determines a target interaction condition matched with user feature data from a plurality of preset interaction conditions by utilizing an artificial intelligence model and combining the user feature data corresponding to the user identifier, and generates first interaction prompt information by combining an operation object associated with the target interaction condition, determining at least one piece of first operation prompt information corresponding to the first interaction prompt information; sending the first interaction prompt message and the at least one first operation prompt message as session messages to the client, so that the client displays the first session message in any interface in an overlapping manner; and receiving a first operation instruction sent by the client for the triggering operation of any first operation prompt information, determining an operation type corresponding to the first operation instruction, and processing the operation object according to the operation type. According to the technical scheme provided by the embodiment of the invention, the initiative of the interaction mode is improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technologies, and in particular, to an information interaction method, apparatus, computing device, storage medium, and program product. Background Art

[0002] With the development of artificial intelligence technologies, the application of artificial intelligence technologies in e-commerce systems is increasing. For example, an e-commerce system introduces an artificial intelligence model (such as an intelligent customer service) to interact with users to improve the interaction quality.

[0003] Currently, the artificial intelligence model in an e-commerce system usually replaces a human customer service in an Instant Messaging (IM) interface to automatically reply to questions raised by users, so as to reduce the message reply cost and improve the message reply efficiency. However, there is a problem of passive interaction method, which urgently needs to be improved. Summary of the Invention

[0004] Embodiments of the present application provide an information interaction method, apparatus, computing device, storage medium, and program product, which are used to solve the problem of passive interaction method when an artificial intelligence model interacts with a user in the prior art.

[0005] An information interaction method provided in an embodiment of the present application is applied to a server, and includes: using an artificial intelligence model, combining user feature data corresponding to a user identifier, determining a target interaction condition matching the user feature data from a plurality of preset interaction conditions, and generating a first interaction prompt message in combination with an operation object associated with the target interaction condition, and determining at least one first operation prompt message corresponding to the first interaction prompt message; sending the first interaction prompt message and the at least one first operation prompt message as a first session message to a client, so that the client superimposes and displays the first session message in any interface; receiving 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 messages; determining an operation type corresponding to the first operation instruction, and processing the operation object according to the operation type.

[0006] An information interaction method is provided in an embodiment of the present application and is applied to a client, including: receiving a first session message sent by a server; the first session message includes 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 using an artificial intelligence model in combination with an operation object associated with a target interaction condition; the target interaction condition is determined from multiple preset interaction conditions by using an artificial intelligence model in combination with user feature data corresponding to a user identifier; superimposing and displaying the first session message on any interface; generating a first operation instruction in response to a trigger operation for any one of the first operation prompt information in the first session message; and sending the first operation instruction to the server so that the server determines an operation type corresponding to the first operation instruction and processes the operation object according to the operation type.

[0007] An information interaction device is provided in an embodiment of the present application and is configured in a server, including: a model operation module, configured to use an artificial intelligence model to determine, from multiple preset interaction conditions, a target interaction condition that matches the user feature data in combination with the user feature data corresponding to the user identifier, and generate first interaction prompt information in combination with an operation object associated with the target interaction condition, and determine at least one first operation prompt information corresponding to the first interaction prompt information; a first sending module, configured to send the first interaction prompt information and the at least one first operation prompt information as a first session message to the client so that the client superimposes and displays the first session message on any interface; a first receiving module, configured to receive the 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, configured to determine an operation type corresponding to the first operation instruction and process the operation object according to the operation type.

[0008] In an embodiment of the present application, an information interaction device is provided, configured in a client, including: a second receiving module, configured to receive a first session message sent by a server; the first session message includes 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 using an artificial intelligence model in combination with an operation object associated with a target interaction condition; the target interaction condition is determined from a plurality of preset interaction conditions by using an artificial intelligence model in combination with user feature data corresponding to a user identifier; a display module, configured to superimpose and display the first session message on any interface; an instruction generation module, configured to generate a first operation instruction in response to a trigger operation for any one of the first operation prompt information in the first session message; a second sending module, configured to send the first operation instruction to the server, so that the server determines an operation type corresponding to the first operation instruction and processes the operation object according to the operation type.

[0009] An embodiment of the present application further provides a computing device, including a processing component and a storage component; the storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the above information interaction method.

[0010] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processing component, the above information interaction method is implemented.

[0011] An embodiment of the present application further provides a computer program product, including a computer program or instruction, and when the computer program or instruction is executed by a processing component, the above information interaction method is implemented.

[0012] In the embodiment of the present application, the server utilizes an artificial intelligence model, combines the user feature data corresponding to the user identifier, determines a target interaction condition that meets the user feature data from multiple preset conditions, and combines the operation object associated with the target interaction condition to generate a first interaction prompt message and at least one corresponding first operation prompt message as a first session message. The first session message is sent to the client so that the client can superimpose and display the first session message on any interface. After the client generates a first operation instruction in response to the trigger operation of any first operation prompt message and sends it to the server, after the server determines the operation type corresponding to the first operation instruction, it processes the operation object according to the operation type. This embodiment provides a way to actively reach out and interact with users, improving the initiative of the interaction method when using an artificial intelligence model to interact with users. In addition, the first session message generated by the server in this embodiment can be superimposed and displayed on any interface currently displayed by the client, realizing the ability to interact with users even in non-instant messaging interfaces, improving the flexibility and real-time nature of the interaction. Furthermore, the session message in this embodiment not only includes interaction prompt messages but also operation prompt messages. Users only need to trigger the corresponding operation prompt message on the client to trigger the server to execute the relevant processing operation on the operation object. The entire interaction process does not require the user to input interaction content and can be completed with at least one trigger operation, improving the convenience of the operation and helping to enhance the acceptance and satisfaction of users with the actively reached interaction operation.

[0013] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0015] Figure 1 A system architecture diagram for information interaction provided by an exemplary embodiment of the present application is shown.

[0016] Figure 2 A flowchart of an information interaction method provided by an exemplary embodiment of the present application is shown.

[0017] Figure 3 A schematic diagram of superimposing and displaying a session message on any interface provided by an exemplary embodiment of the present application is shown.

[0018] Figure 4 A set of schematic diagrams of superimposing and displaying a session message on any interface provided by an exemplary embodiment of the present application is shown.

[0019] Figure 5The flowchart of an information interaction method provided by an exemplary embodiment of the present application is shown.

[0020] Figure 6 The signaling diagram of an information interaction method in an application scenario provided by an exemplary embodiment of the present application is shown.

[0021] Figure 7 The schematic structural diagram of an information interaction device provided by an exemplary embodiment of the present application is shown.

[0022] Figure 8 The schematic structural diagram of an information interaction device provided by an exemplary embodiment of the present application is shown.

[0023] Figure 9 The schematic structural diagram of a computing device for information interaction provided by the present application is shown. Detailed implementation manners

[0024] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Apparently, the described embodiments are only a part rather than all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0025] It should be noted that the technical solutions of the embodiments of the present application are applicable to a network virtual environment. The described users generally refer to "virtual users". Real users can register user accounts on the server through registration to obtain user identities in the network environment. The same user account can be logged in to the server through different types of clients, enabling the server to identify the same user.

[0026] The interaction operations between the server and the user can be implemented based on the user account. The corresponding data received or sent by the server to the user is also implemented based on the user account. Actually, it is the client corresponding to the user account that receives or sends the corresponding data to the server. In addition, communication between users can also be achieved through the user account. Among them, the user can refer to an individual or an organization, such as an enterprise, etc. The present application does not make specific limitations on this.

[0027] It should be noted that in the case where the embodiments of the present application involve user information, the user information (including but not limited to user characteristic data, user identifiers, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject. Additionally, various artificial intelligence models (including but not limited to language models or large models) involved in the present application comply with relevant laws and standards.

[0028] In addition, it should be noted that in the case where the embodiments of the present application involve user interaction operations or trigger operations, the user interaction operations or trigger operations involved in the embodiments of the present application include but are not limited to: interaction operations in various ways such as touch operations, gesture operations, voice operations, head movement operations, eye movement operations, etc.; among them, touch operations include but are not limited to: click operations, double-click operations, long-press operations, swipe operations, pinch operations, or mouse hover operations, etc. Swipe operations include but are not limited to: straight-line swipes, curved swipes, etc.

[0029] Furthermore, it should be noted that in the case where the embodiments of the present application involve the jump between a first interface and a second interface, the jump methods involved in the embodiments of the present application include but are not limited to: directly jumping from the first interface to the second interface, first jumping from the first interface to a task interface and then jumping to the second interface when corresponding task operations are completed on the task interface; completing corresponding task operations on the task interface includes but is not limited to: completing identity authentication on the identity authentication interface when the task interface is implemented as an identity authentication interface; completing a recharge operation on the recharge interface when the task interface is implemented as a recharge interface; and so on.

[0030] With the development of artificial intelligence technology, the application of artificial intelligence technology in e-commerce systems is increasing. For example, e-commerce systems introduce artificial intelligence models to interact with users to improve the quality of interaction. Currently, the scenario where the artificial intelligence model in an e-commerce system interacts with users is usually as follows: when a user has an interaction need, the user enters the instant messaging interface through the client, and then enters a question in this interface. At this time, the artificial intelligence model will replace the human customer service to automatically reply to the questions raised by the user, so as to reduce the message reply cost and improve the message reply efficiency. However, the existing artificial intelligence models can only passively reach the interaction in response to the user's questions. To address this problem, the embodiments of the present application provide a solution. The basic idea is that the server uses the artificial intelligence model, combines the user feature data corresponding to the user identifier, determines the target interaction condition that meets the user feature data from multiple preset conditions, and combines the operation object associated with the target interaction condition to generate the first interaction prompt message and at least one corresponding first operation prompt message as the first session message. The first session message is sent to the client so that the client can superimpose and display the first session message on any interface. After the client generates a first operation instruction in response to the trigger operation of any first operation prompt message and sends it to the server, the server determines the operation type corresponding to the first operation instruction and processes the operation object according to the operation type. This embodiment provides a way to actively reach the interaction with the user, improving the initiative of the interaction method when using the artificial intelligence model to interact with the user. In addition, the session message generated by the server in this embodiment can be superimposed and displayed on any interface currently displayed by the client, realizing the ability to interact with the user even in a non-instant messaging interface, improving the flexibility and real-time nature of the interaction. Furthermore, the session message in this embodiment not only includes the interaction prompt message but also the operation prompt message. The user only needs to trigger the corresponding operation prompt message on the client to trigger the server to execute the relevant processing operation on the operation object. The entire interaction process does not require the user to input interaction content and can be completed with at least one trigger operation, improving the convenience of the operation and helping to enhance the user's acceptance and satisfaction of the actively reached interaction operation.

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0032] Figure 1The figure shows a system architecture diagram of an e-commerce system that can apply the technical solution of an embodiment of the present application to information interaction. The system architecture may include a client 101 and a server 102. (Or: It may include a server and multiple clients; or it may include a server, a first client, and a second client, etc.)

[0033] Among them, a connection can be established between the client 101 and the server 102 through a network. The network provides a medium for the communication link between the client 101 and the server 102. The network can include various connection types, such as wired, wireless, or fiber optic cables, etc. The client 101 can interact with the server 102 through the network to receive or send messages, etc.

[0034] Among them, the client 101 can be a browser, an APP (Application), a web application such as an H5 (HyperText Markup Language 5) application, a light application (also known as a small program, a lightweight application program), or a cloud application, etc. The client 101 can be deployed in an electronic device and needs to rely on the device or certain apps in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, etc., such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc. For the sake of understanding, Figure 1 the client is mainly represented by the image of the device. Various other types of applications can usually be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. The electronic device can refer to a device used by a user and having functions such as computing, Internet access, and communication required by the user, such as a mobile phone, a tablet computer, a personal computer, a wearable device, etc. The electronic device usually includes at least one processing component and at least one storage component. The electronic device may also include basic configurations such as a network card chip, an IO (input / output) bus, and audio-video components. The present application does not limit this. Optionally, according to the implementation form of the electronic device, some peripheral devices may also be included, such as a keyboard, a mouse, a stylus, a printer, etc. The present application does not limit this.

[0035] The server 102 can include servers that provide various services, such as a server for background training that provides support for the models used on the client 101, and a server that processes the interaction information sent by the client, etc.

[0036] It should be noted that the server 102 can be implemented as a distributed server cluster composed of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), as well as big data and artificial intelligence platforms, or an intelligent cloud computing server or an intelligent cloud host with artificial intelligence technology.

[0037] It should be noted that the information interaction method provided by the embodiments of the present application can also be jointly executed by the client 101 and the server 102. It should be understood that Figure 1 the numbers of the client and the server in

[0038] are merely illustrative. According to the implementation requirements, there can be any number of clients and servers.

[0039] The implementation details of the technical solutions of the embodiments of the present application are elaborated in detail below.

[0040] Figure 2 is a flowchart of an embodiment of an information interaction method provided by the present application. The technical solution of this embodiment can be executed by the server. As Figure 2 shown, the method can include the following steps:

[0041] S201, using an artificial intelligence model, combining user feature data corresponding to a user identifier, determining a target interaction condition that matches the user feature data from multiple preset interaction conditions, and generating a first interaction prompt message in combination with an operation object associated with the target interaction condition, and determining at least one first operation prompt message corresponding to the first interaction prompt message.

[0042] Among them, the user identifier can be the unique identifier of the user. For example, it can be the username, phone number, etc. registered by the user in the e-commerce system.

[0043] The user characteristic data can be the user attribute information and user historical behavior information maintained in the e-commerce system, etc. Specifically, if the user is a service provider, the user characteristic data at this time can be the client login time of the service provider, the purchase and consultation situation of the service objects published, the historical published information in the e-commerce system (such as the post information of the service objects published), the relevant information of the purchased function objects (for example, if the function object is a system member, the relevant information can be the handling time, expiration time, introduction information, etc. of the system member). If the user is a consumer, the user characteristic data at this time can be the gender, age, region, preferences of the consumer, the relevant information of the purchased service objects and function objects, the client login time, etc.

[0044] The preset interaction condition can be a pre-set judgment condition for determining whether to actively trigger an interaction. For example, the preset interaction condition can include but is not limited to the following: First, the user has performed an operation to purchase a function object or a service object; Second, the user's current login is the first login within a preset time period (such as one day, one week, or one month); Third, the function object purchased by the user on the e-commerce platform is about to expire; Fourth, the user is an intended user of the function object to be promoted on the e-commerce platform, etc. Optionally, if the user is a service provider, the preset interaction condition can also include having marketing problems, outstanding marketing performance, etc.

[0045] The operation object can be the object to be operated in this interaction. It can be an object that can actually perform operations, such as a certain function object to be promoted provided by the e-commerce system, or an object that cannot actually perform operations, such as a caring message.

[0046] The first interaction prompt information can be the interaction content when actively triggering an interaction. The first operation prompt information can be the operations that the user can choose to perform in response to the first interaction prompt information. For example, it can include operation prompt information indicating the willingness to continue the interaction, such as "Okay", "Agree", etc.; it can also include operation prompt information indicating the unwillingness to continue the interaction, such as "Don't need", "Don't want", etc. It can also include operation prompt information indicating that the situation has been understood, such as "Thank you".

[0047] Optionally, in this embodiment, the server can obtain the user feature data corresponding to any user identifier maintained in the e-commerce system, and then generate a prompt instruction based on the user feature data, preset interaction conditions, task descriptions, task examples, output format requirements, etc., and input it into the artificial intelligence model to guide the artificial intelligence model to infer whether there is a target interaction condition that meets the user feature data among multiple preset interaction conditions, and further determine the operation object corresponding to the target interaction condition. Exemplarily, if the target interaction condition of this embodiment is determined from the four preset interaction conditions listed above, the determination of the operation object corresponding to the target interaction condition may include the following situations: if the target interaction condition is the first or second of the above preset interaction conditions, the operation object may be a caring message; if the target interaction condition is the third of the above preset interaction conditions, the operation object may be a function object that is about to expire; if the target interaction condition is the fourth of the above preset interaction conditions, the operation object may be a function object to be promoted.

[0048] Optionally, when the number of preset interaction conditions that match the user feature data is multiple, this embodiment may select the one with the highest priority from the multiple matching preset interaction conditions according to the priority of each preset interaction condition as the target interaction condition. It may also be to use the artificial intelligence model to output the matching degree between the user feature data and each matching preset interaction condition, and then select the one with the highest matching degree from the multiple matching preset interaction conditions as the target interaction condition. It may also be to regard all the multiple matching preset interaction conditions as target interaction conditions, and for each target interaction condition, determine the first interaction prompt information and the first operation prompt information and subsequent operations at different time intervals, so as to achieve active interaction at different time intervals for each target interaction condition. There is no limitation on this.

[0049] It should be noted that for any user feature data, there may or may not be a matching target interaction condition. If there is, the first interaction prompt information, the first operation prompt information and subsequent operations are executed. If not, it is considered that the user identifier does not require active interaction, and subsequent operations are not executed. Just re-select the user feature data corresponding to other user identifiers for judgment.

[0050] After determining the target interaction object and its associated operation object using an artificial intelligence model, the artificial intelligence model will further generate a first interaction prompt message for the associated operation object. Specifically, it can be that the artificial intelligence model can learn the examples given in the prompt instructions and generate a first interaction prompt message for the operation object associated with the target interaction condition; or it can be that preset interaction information (such as standard interaction scripts) is set in advance for the operation object associated with the target interaction condition. In this case, the artificial intelligence model can polish the preset interaction information of the operation object in an oral style, making the generated first interaction prompt message more similar to the effect of a real person speaking. Exemplarily, for the four preset interaction conditions listed above, the corresponding first interaction prompt messages can be: "Welcome to become a system member!", "Have a great week in the new week!", "Your membership is about to expire. Do you need to renew it?", and "This is the newly launched XX product. Do you want to know more?" etc.

[0051] After generating the first interaction prompt message, at least one operation prompt message can be determined according to the content of the first interaction prompt message. Specifically, one implementable way can be: using the artificial intelligence model to combine the user's historical operation habits, the operation content that can be provided in the e-commerce system for the target interaction condition, and the preset operation prompt scripts, etc., to generate at least one operation prompt message for the first interaction prompt message. This method can improve the flexibility and diversity of determining the operation prompt message, and the determined operation prompt message is more in line with the user's operation habits.

[0052] Another implementable way can be: determining at least one optional operation item corresponding to the first interaction prompt message; respectively filling the relevant information of at least one optional operation item into the control component template to obtain at least one first operation prompt message corresponding to the first interaction prompt message. Among them, the optional operation item is an option for the user to operate on the first interaction prompt message. The control component template can be a general template set in advance for generating control components in the display interface.

[0053] The relevant information of the optional operation item includes but is not limited to: the name corresponding to the optional operation item, animated emoji, website link, etc. For example, if the optional operation item is "Okay", the corresponding relevant information at this time can include: the name "Okay" and the animated emoji representing okay. If the optional operation item is "Go to recharge", the corresponding relevant information at this time can include: the name "Go to recharge" and the website link of the recharge page. Optionally, for each optional operation item, its corresponding relevant information can be determined in advance and stored in the server.

[0054] Since the operation object corresponding to the interactive prompt information in this embodiment is usually fixed, such as a care message or a promotion function object, and for a certain type of operation object, the corresponding optional operation items are often relatively fixed. For example, when the operation object is a promotion function object, the first interactive prompt information may be to promote the handling of the function object to the user. For example, it can be "Your membership is about to expire. Do you want to renew it?" At this time, the corresponding optional operation items include operation items with the willingness to continue the interaction (such as "Okay", "Go to renew", etc.) and operation items without the willingness to continue the interaction (such as "No need", "Don't want", etc.). When the operation object is a care message, such as weekly welcome, monthly incentive, new member welcome, etc., the corresponding optional operation items at this time are operation items that have understood the situation (such as "Okay", "Thank you", etc.). Therefore, this embodiment can pre-store the optional operation items corresponding to the care message and the promotion function object, the relevant information corresponding to each optional operation item, and a general control component template.

[0055] When determining the first operation prompt information in this step, analyze the operation object corresponding to the first interactive prompt information, find at least one optional operation item pre-set for this operation object, and then for each optional operation item corresponding to this operation object, obtain the relevant information pre-stored for this optional operation item, and fill the relevant information into the general control component template to obtain the control component corresponding to this optional operation item, and use it as a first operation prompt information corresponding to the first interactive prompt information. This method can quickly and conveniently determine at least one first operation prompt information based on the pre-configured relationship between the operation object and the optional operation item, and the control component template corresponding to the optional operation item, without generating operation prompt information by combining an artificial intelligence model every time, reducing the interaction cost during active reach interaction and improving the interaction efficiency.

[0056] It should be noted that there are many triggering conditions for the server to execute S201, which are not limited here. One implementable method is to set different triggering time periods according to different operation objects for multiple preset interaction conditions, and execute the operation of S201 when the triggering time period is reached. For example, it can be set from 8:00 to 10:00 in the morning to determine whether the user characteristic data matches the preset interaction conditions corresponding to the care message category; set from 2:00 to 5:00 in the afternoon to determine whether the user characteristic data matches the preset interaction conditions corresponding to the function object category. Another implementable method is that the client detects a target triggering operation on any interface, generates a triggering request containing the user identifier and sends it to the server, and the server executes the operation of S201 after receiving the triggering request. The target triggering operation can be a specific operation, such as an operation to browse a function object. It can also be the first triggering operation detected after the client starts running for the first time every day.

[0057] It should be noted that the artificial intelligence model involved in this article can be a language model (LM) or a multimodal model (MM) based on artificial intelligence, etc. The embodiments of this application do not limit the number of model parameters supported by the model, aiming to meet actual needs. If the model parameters are relatively large, the scale of the language model will be relatively large and the model performance will be relatively better. Of course, more time and resources will be consumed during the inference or training process; if the model parameters are relatively small, the scale of the model will be relatively small. When the performance meets the requirements, the model is more lightweight and consumes relatively less time and resources during the inference or training process. The artificial intelligence model involved in the embodiments of this application can be a deep learning model used to process and generate natural language text or multimodal data, which can be implemented based on a neural network architecture and can be pre-trained on a large amount of data. In an alternative implementation, the artificial intelligence model involved in this article can include an encoder, a decoder, a self-attention layer, and a feed-forward neural network, etc. The encoder is mainly used to convert the input data (usually in the form of a sequence) into a vector representation, and this process can capture the 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 that enables the model to pay attention to other positions in the sequence to better encode the information of the current position; the feed-forward neural network is used to perform non-linear transformations on the output of the self-attention layer, etc., to enhance the model's expression ability. Each part works together to make the model constructed based on them perform well in various complex processing tasks, such as natural language processing, computer vision, speech recognition, machine translation, text summarization, and intelligent question answering, etc.

[0058] S202, send the first interaction prompt message and at least one first operation prompt message as the first session message to the client, so that the client can superimpose and display the first session message on any interface.

[0059] Among them, the so-called any interface can refer to any interface currently displayed by the client, which can be the system home page, the service list interface, the detail display interface, etc.

[0060] In this embodiment, the server can generate a first session message containing a first interaction prompt message and at least one operation prompt message in the format of a session message, and then send the first session message to the client. After receiving the first session message, the client will superimpose and display the first session message on any interface currently being displayed (i.e., the current display interface of the client). For example, a conversation card or a prompt pop-up window can be superimposed and displayed on the any interface, and then the first interaction prompt message is added to the conversation card or the prompt pop-up window in the form of text content, and at least one operation prompt message is added to the conversation card or the prompt pop-up window in the form of a touch control component. Exemplarily, as shown in FIG. 3, there is an effect diagram of superimposing and displaying the first session message on any interface. Among them, the square 301 is the dialog box displayed on the any interface, and the text "Do you want to upgrade your membership?" displayed in the square 301 is the first interaction prompt message; the touch control components "Not available" and "Go to upgrade" correspond to two operation prompt messages.

[0061] It should be noted that the server can render the first session message in a superimposed display manner into any interface currently displayed on the client, and then directly send the rendered any interface to the client. At this time, the client can directly display the received rendered any interface. It can also be that the server sends the first session message to the client, and the client performs the operations of rendering the first session message in a superimposed display manner on the any interface and displaying the rendered any interface.

[0062] S203. Receive a first operation instruction sent by the client. The first operation instruction is generated by the client in response to a trigger operation for any one of the first operation prompt messages.

[0063] Optionally, after the client superimposes and displays the first session message on any interface, the user can click on the touch control component corresponding to one of the first operation prompt messages according to the need, that is, perform a trigger operation for the first operation prompt message. After detecting the trigger operation, the client will generate a first operation instruction based on the first operation prompt message corresponding to the trigger operation and send it to the server. Correspondingly, the server will receive the first operation instruction.

[0064] S204. Determine the operation type corresponding to the first operation instruction, and process the operation object according to the operation type.

[0065] Among them, the operation types in this embodiment can include a continue operation type indicating that the user is willing to continue the interaction, and a stop operation indicating that the user does not want to continue the interaction.

[0066] Since the first operation instruction is generated based on the first operation prompt message, the server can, through the first operation instruction, deduce the first operation prompt message selected by the user for the first interaction prompt message. At this time, the server can determine the operation type corresponding to the first operation instruction according to whether the first interaction prompt message corresponding to the first operation instruction indicates that the user is willing to continue the interaction. For example, if the first interaction prompt message corresponding to the first operation instruction is "Okay", "Go to callback", "Go to recharge", etc., the operation type corresponding to the first operation instruction is a continue operation; if the first interaction prompt message corresponding to the first operation instruction is "Busy", "Don't need", "No thanks", etc., the operation type corresponding to the first operation instruction is a stop operation. It should be noted that for the first operation prompt message indicating that the situation has been understood, since the user does not need to perform a processing operation on the operation object after understanding the situation, the operation type corresponding to this type of first operation prompt message can be considered a stop operation. For example, when the operation object is a caring message, the operation type corresponding to the generated first operation instruction is a stop operation.

[0067] Optionally, if the operation type corresponding to the first operation instruction is a continue operation, at this time the server analyzes the first interaction prompt message to determine the operation content for the operation object, and then performs relevant processing operations on the operation object according to the operation content. Exemplarily, for Figure 3 the first interaction prompt message in; if the first interaction prompt message corresponding to the first operation instruction is "Go to upgrade", and at this time the operation object is a system member, the server can perform a member upgrade processing operation for the user.

[0068] If the operation type corresponding to the first operation instruction is a stop operation, send a first session message closing instruction to the client to instruct the client to close the first session message superimposed and displayed on any interface. Exemplarily, for Figure 3 the first interaction prompt message in, if the first interaction prompt message corresponding to the first operation instruction is "Busy", it means that the user does not want to upgrade the membership at present. At this time, the server can send a first session message closing instruction to the client, and the client will respond to this instruction to close the first session message superimposed and displayed on any interface and restore the original arbitrary interface. This is to avoid the long-term display of the session message, which affects the user's normal browsing of the interface and causes the user's resistance to active interaction.

[0069] Optionally, in this embodiment, the client can also directly close the first session message superimposed and displayed on any interface without interacting with the server after detecting that the user has not performed a trigger operation on the first operation prompt message for a long time (such as 10s), or after detecting a trigger operation for the first prompt message without the willingness to continue the interaction.

[0070] In this embodiment, the server uses an artificial intelligence model, combines the user feature data corresponding to the user identifier, determines a target interaction condition that meets the user feature data from multiple preset conditions, and generates a first interaction prompt message and at least one corresponding first operation prompt message as the first session message in combination with the operation object associated with the target interaction condition. The first session message is sent to the client so that the client can superimpose and display the first session message on any interface. After the client generates a first operation instruction in response to the trigger operation of any first operation prompt message and sends it to the server, after the server determines the operation type corresponding to the first operation instruction, it processes the operation object according to the operation type. This embodiment provides a way to actively reach out and interact with users, improving the initiative of the interaction method when using an artificial intelligence model to interact with users. In addition, the session message generated by the server in this embodiment can be superimposed and displayed on any interface currently displayed by the client, realizing the ability to interact with users even in non-instant messaging interfaces, improving the flexibility and real-time nature of the interaction. Furthermore, the session message in this embodiment not only includes interaction prompt messages but also operation prompt messages. The user only needs to trigger the corresponding operation prompt message on the client to trigger the server to execute the relevant processing operation on the operation object. The entire interaction process does not require the user to input interaction content and can be completed with at least one trigger operation, improving the convenience of the operation and helping to enhance the user's acceptance and satisfaction of the actively reached interaction operation.

[0071] In some embodiments, for an operation object, there may be multiple optional operation contents. For example, for a system member, there may be multiple operations to upgrade to different member levels. The higher the member level, the more benefits can be enjoyed, and the corresponding fee is also higher. To make the operation content for the operation object more acceptable to the user, in this embodiment, if the operation type corresponding to the first operation instruction is a continue operation, an artificial intelligence model can be used to generate the operation content for the operation object in combination with the user feature data; the operation object is processed according to the operation content. Specifically, the artificial intelligence model can be used to analyze the user feature data in combination with the operation object to find the operation content that the user is most likely to accept and use it as the operation content for the operation object to perform the processing of the operation object. When determining the operation content for the operation object in this embodiment, it does not perform a unified operation content without discrimination or the operation content with the most profit, but selects the operation content that is most suitable for the user in combination with the user feature data, which can improve the user's acceptance and recognition of the actively reached interaction operation.

[0072] In some embodiments, when the operation object associated with the target interaction condition is the target function object and the target function object includes at least two selectable levels, an operation content for the operation object is generated by using an artificial intelligence model in combination with user feature data, including: using the artificial intelligence model in combination with user feature data to determine the current user level of the target function object, determining the target level from at least two selectable levels according to the current user level, and taking the operation content for upgrading to the target level as the operation content for the operation object. Specifically, if the user has previously purchased the target function object, the user feature data may include the fees paid by the user when purchasing the target function object, and the levels corresponding to different fees are different. Therefore, the artificial intelligence model can be used to parse the current user level of the user for the target function object from the user feature data, and then, based on the current user level, the level is upgraded, such as upgrading by one level, as the target level, and the operation of upgrading from the current user level to the target level is taken as the operation content for the operation object. This embodiment selects the target level for the user based on the user feature data, which can gradually guide the user to upgrade and improve the user's acceptance of upgrading.

[0073] In some embodiments, to facilitate the user to more intuitively understand the operation content of the server for the operation object and prevent the situation where the server processes the operation object due to the user's accidental touch, this embodiment may also be to use an artificial intelligence model to generate a second interaction prompt message and at least one second operation prompt message corresponding to the second interaction prompt message in combination with the operation content; the second interaction prompt message is used to indicate the confirmation of the execution of the operation content; the second interaction prompt message and at least one second operation prompt message are sent to the client as a second session message so that the client can superimpose and display the second session message on any interface; a second operation instruction sent by the client is received, and the second operation instruction is generated by the client in response to a trigger operation for any one of the second operation prompt messages; if the operation type corresponding to the second operation instruction is a continue operation, the operation object is processed according to the operation content.

[0074] Specifically, the server can use an artificial intelligence model to generate a second interaction prompt message for describing the operation content to the user and confirming with the user whether to execute the operation content in combination with the operation content. Then, in a manner similar to the above S201 - S204, at least one second operation prompt message is generated, and the second interaction prompt message and at least one second operation prompt message are sent to the client as a second session message, so that the client can superimpose and display the second session message on any interface. Receive the second operation instruction sent by the client. The second operation instruction is generated by the client in response to a trigger operation for any one of the second operation prompt messages. If the operation type corresponding to the second operation instruction is a continue operation, process the operation object according to the operation content. If the operation type corresponding to the second operation instruction is a stop operation, send a second session message close instruction to the client to instruct the client to close the second session message superimposed and displayed on any interface.

[0075] Optionally, in order to better enable the user to understand the processing result of the operation object, in this embodiment, after processing the operation object according to the operation content, an artificial intelligence model can be used to generate a third interaction prompt message for describing the operation result and a third operation prompt message for indicating that the user understands the operation result (such as "Okay", "Thank you", etc.) in combination with the operation result; the third interaction prompt message and the third operation prompt message are sent to the client as a third session message, so that the client can superimpose and display the third session message on any interface; since the third operation prompt message at this time indicates that the user understands the operation result, after the client generates a third operation instruction in response to a trigger operation for the third operation prompt message and sends it to the server, the server can send a third session message close instruction to the client to instruct the client to close the session message superimposed and displayed on any interface. Or after the client detects a trigger operation for the third operation prompt message, directly close the third session message superimposed and displayed on any interface.

[0076] Exemplarily, Figure 4 The first conversation card superimposed on the first arbitrary interface shows the first interaction prompt message, that is, "Do you need to increase the post display duration?" The touch components corresponding to the two first operation prompt messages are "Okay" and "No, thanks" respectively. If the client detects that the user clicks the touch component "Okay", it means that the user wants to consider increasing the post display duration. At this time, the client will send a first operation instruction indicating a willingness to continue the interaction to the server, and the server will generate a second interaction prompt message "Okay, adjust the display duration to all day?" and two second operation prompt messages "Okay" and "No, thanks" as session information and send it to the client for superimposed display on any interface. The display effect is as Figure 4As shown in the second arbitrary interface diagram in [reference], if the client detects that the user triggers the touch component "OK" again, it indicates that the user agrees to the operation content. The client will send a second operation instruction representing the agreement to continue the operation to the server, and the server will respond to this second operation and perform the adjustment operation of the post display duration. After the execution is completed, the server will also generate a third interaction prompt message "OK, the adjustment operation has been completed." representing the execution result, and a third operation prompt message "Thank you", and send them to the client as session information for the server to superimpose and display on any interface. The display effect is as shown in Figure 4 As shown in the third arbitrary interface diagram in [reference], if the client detects that the user triggers the touch component "Thank you" again, it can directly close the session information superimposed on this arbitrary interface, or interact with the server and close it after receiving the close instruction sent by the server.

[0077] In some embodiments, when the operation content corresponding to the operation object is clear, or the operation process requires the participation of the user (such as the user needs to enter a payment password during the recharge operation process), in order to improve the user's autonomy in processing the operation object and reduce the number of interactions, this embodiment can also be to send the operation interface information corresponding to the operation content to the client, so that the client can jump from this arbitrary interface to the operation interface of the operation object and display the operation interface information on the operation interface; in response to the object operation request sent by the client, process the operation object; this object operation request is generated for the trigger operation of the operation interface information. Specifically, in this embodiment, after determining the operation content for the operation object, the operation interface information corresponding to the operation content is obtained and sent to the client, and the client jumps from the currently displayed arbitrary interface to the operation interface of the operation object to display the operation interface information. The user can, according to their own needs, independently trigger relevant operations on this operation interface, and the client will generate an object operation request for the operation triggered by the user and send it to the server, so that the server can process the operation object according to the relevant operations independently triggered by the user. Exemplarily, if the operation content is to upgrade the membership, at this time, the web page link of the membership upgrade interface, the QR code, or the detailed information of the membership upgrade interface can be used as the operation interface information and sent to the client.

[0078] In some embodiments, to improve the user's acceptance of the first interaction prompt information and avoid directly recommending the functional object with fixed words, this embodiment can also use an artificial intelligence model to generate the first interaction prompt information by combining user feature data and preset interaction information. Specifically, it can be to use an artificial intelligence model to combine the operation object associated with the target interaction condition and user feature data to generate interaction guidance information, and then combine the interaction guidance information and the preset interaction information of the operation object to generate the first interaction prompt information. Among them, the interaction guidance information can be an introductory statement that explains the reason why the user needs to order the functional object when the operation object is a functional object, and can be generated based on user feature data. Specifically, an artificial intelligence model can be used to analyze user feature data to persuade the user of the reason for ordering the functional object, and then convert the style of the reason into a colloquial style to generate the interaction guidance information. Then, the interaction guidance information is combined with the preset interaction information of the functional object (such as the preset standard recommendation words) to generate the first interaction prompt information with higher user acceptance.

[0079] In some embodiments, when the operation object associated with the target interaction condition is the target functional object, to make it easier for the user to receive the order of the target functional object, this embodiment uses an artificial intelligence model to combine the operation object associated with the target interaction condition and user feature data to generate interaction guidance information, including: using an artificial intelligence model to generate interaction guidance information based on the user transaction data and / or phone consultation data in the user feature data, and the function introduction information of the target functional object; the interaction guidance information is used to describe the logical relationship between the user transaction data and / or phone consultation data and the order of the target functional object. Specifically, an artificial intelligence model can be used to analyze the user transaction data and / or phone consultation data in the user feature data, and the recent business situation of the user (i.e., the service provider) can be obtained, such as whether the recent business operation has improved or decreased compared with before. Then, a statement is established to transition from the analysis of the recent business situation to guiding the user to purchase the functional object as the interaction guidance information. Exemplarily, for Figure 4 the first interaction prompt information shown, the corresponding interaction guidance information can be "The business of the merchant has improved, which is related to the post display duration of the target functional object, so the user can be prompted to increase the post display duration again."

[0080] In some embodiments, the server of this embodiment actively reaches the interaction by interacting with the user in the way of superimposing session messages on the current interface. After the session message is closed, to facilitate the user to view the content of this interaction later. This embodiment can also generate an instant messaging message based on the first interaction prompt information, at least one first operation prompt information, and a first operation instruction; add the instant messaging message to the instant messaging interface of the client so that when the client enters the instant messaging interface, the instant messaging message is displayed.

[0081] Specifically, every time the server completes an interaction with the user, that is, the server completes generating and sending the first interaction prompt message and at least one first operation prompt message to the client, and the user performs a trigger operation on a certain first operation prompt message on the client, the server will generate an instant messaging message based on the information of this interaction, that is, the first interaction prompt message and at least one first operation prompt message generated by the server, and the first operation prompt message triggered by the user. For example, the first interaction prompt message and at least one first operation prompt message generated by the server can be used as messages sent by a non-user party (such as an intelligent customer service party), and the first operation prompt message triggered by the user can be used as a message sent by the user party. And synchronize the instant messaging message to the instant messaging interface of the client, so that when the client needs to display the instant messaging interface in response to the user's reach operation next time, the instant messaging message corresponding to the active reach interaction can be displayed in the instant messaging interface.

[0082] It should be noted that the first interaction prompt message, at least one first operation prompt message, and the first operation instruction only represent one interaction operation. In this embodiment, for one active reach interaction, there may be multiple interaction operations. For example, there may be a second interaction prompt message, a second operation prompt message, a second operation instruction, a third interaction prompt message, a third operation prompt message, and a third operation instruction, etc. In this embodiment, instant messaging messages can be generated for the relevant information of each interaction operation and synchronized to the instant messaging interface for the user to view in the instant messaging interface of the client.

[0083] In some embodiments, in order to improve the flexibility and diversity of the interaction method, in addition to actively reaching the interaction with the user using the artificial intelligence model, this embodiment can also passively reach the interaction with the user when the user has an inquiry need. That is, receive the target inquiry information sent by the client; the target inquiry information is generated by the client in response to an input operation on the instant messaging interface; use the artificial intelligence model to generate inquiry interaction information for the target inquiry information; send the inquiry interaction information to the client so that the client can display the inquiry interaction information in the instant messaging interface.

[0084] Specifically, in this embodiment, when the user has an inquiry need, the user can enter the instant messaging interface with the service provider or the system administrator through the client to interact with the service provider or the system administrator. The user can input the target inquiry information through the client in the instant messaging interface, or click on the selectable inquiry information prompted in the instant messaging interface. The client will send the inquiry information input or clicked by the user as the target inquiry information to the server. In this embodiment, an artificial intelligence model can be used to combine the knowledge base of the service provider or the system administrator, as well as user characteristic data, etc. to determine the inquiry interaction information corresponding to the target inquiry information. And the determined inquiry interaction information is sent to the client so that the client can display the inquiry interaction information in the instant messaging interface. Since the inquiry interaction information in this embodiment is generated by adjusting the standard conversation words in the knowledge base according to the user characteristic data using an artificial intelligence model, compared with directly searching for the inquiry interaction information in the knowledge base, the inquiry interaction information determined in this embodiment is closer to the reply context of the artificial customer and better meets the actual needs of the user.

[0085] Figure 5 The figure is a flowchart of an information interaction method provided by an exemplary embodiment of the present application. The technical solution of this embodiment can be executed by a client, which is a client used by a consumer in an e-commerce system or a client used by a service provider in an e-commerce system. The method may include the following steps:

[0086] S501, Receive a first session message sent by the server.

[0087] Among them, the first session message includes 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 using an artificial intelligence model in combination with an operation object associated with a target interaction condition; the target interaction condition is determined from a plurality of preset interaction conditions by using an artificial intelligence model in combination with user characteristic data corresponding to a user identifier.

[0088] S502, Overlay and display the first session message on any interface.

[0089] S503, In response to a trigger operation on any one of the first operation prompt information in the first session message, generate a first operation instruction.

[0090] S504, Send 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 object according to the operation type.

[0091] In some embodiments, to facilitate the user's more intuitive understanding of the operation content of the server on the operation object and prevent the situation where the server processes the operation object due to the user's accidental touch, this embodiment may also receive a second session message sent by the server. The second session message includes second interaction prompt information and at least one second operation prompt information corresponding to the second interaction prompt information. The second interaction prompt information and the at least one second operation prompt information are generated by the server using the artificial intelligence model in combination with the operation content. The second session message is superimposed and displayed in any interface. In response to a trigger operation on any one of the second operation prompt information in the second session message, a second operation instruction is generated. The second operation instruction is sent to the server so that when the operation type corresponding to the second operation instruction is a continue operation, the server processes the operation object according to the operation content.

[0092] In some embodiments, to improve the user's autonomy in processing the operation object and reduce the number of interactions, this embodiment may also receive operation interface information corresponding to the operation content sent by the server, jump from any interface to the operation interface of the operation object, and display the operation interface information in the operation interface. In response to a trigger operation on the operation interface information, an object operation request is generated. The object operation request is sent to the server so that the server processes the operation object in response to the object operation request.

[0093] In some embodiments, the method further includes: receiving a first session message closing instruction sent by the server and closing the first session message superimposed and displayed in any interface. The first session closing instruction is generated by the server when the operation type corresponding to the first operation instruction is a stop operation.

[0094] In some embodiments, the method further includes: in response to an input operation on the instant messaging interface, generating target inquiry information. The target inquiry information is sent to the server so that the server uses the artificial intelligence model to generate inquiry interaction information for the target inquiry information. The inquiry interaction information sent by the server is received and displayed in the instant messaging interface.

[0095] In a practical application, Figure 6 FIG. shows a signaling diagram of an information interaction method for an application scenario provided by an exemplary embodiment of the present application. This method is jointly implemented by a client and a server. Specifically, it includes the following steps:

[0096] S601. The server uses an artificial intelligence model, combines the user feature data corresponding to the user identifier, determines a target interaction condition that matches the user feature data from multiple preset interaction conditions, and combines the operation object associated with the target interaction condition to generate a first interaction prompt message, and determines at least one first operation prompt message corresponding to the first interaction prompt message.

[0097] Optionally, when generating the first interaction prompt message, the server may use the artificial intelligence model, combine the operation object associated with the target interaction condition and the user feature data to generate interaction guidance information, and combine the interaction guidance information and the preset interaction information of the operation object to generate the first interaction prompt message.

[0098] S602. The server sends the first interaction prompt message and at least one first operation prompt message as a first session message to the client.

[0099] S603. The client superimposes and displays the first session message on any interface.

[0100] S604. The client generates a first operation instruction in response to a trigger operation for any one of the first operation prompt messages.

[0101] S605. The client sends the first operation instruction to the server.

[0102] S606. The server determines the operation type corresponding to the first operation instruction and processes the operation object according to the operation type.

[0103] Specifically, if the operation type corresponding to the first operation instruction is a stop operation, the server may send a first session message close instruction to the client to instruct the client to close the first session message superimposed and displayed on the any interface. If the operation type corresponding to the first operation instruction is a continue operation, the server uses the artificial intelligence model to combine the user feature data to generate operation content for the operation object; processes the operation object according to the operation content.

[0104] Furthermore, when the server processes the operation object according to the operation content, it can further consider whether the user is clear about the operation content. If it is clear, it can send the operation interface information corresponding to the operation content to the client. The client will jump from the any interface to the operation interface of the operation object and display the operation interface information on the operation interface; the client generates an object operation request for the trigger operation of the operation interface information and sends the object operation request to the server. The server will respond to the object operation request and process the operation object.

[0105] If the user is not clear about the operation content, the server can use the artificial intelligence model to generate a second interaction prompt message and at least one second operation prompt message corresponding to the second interaction prompt message in combination with the operation content; the second interaction prompt message is used to indicate the confirmation of the execution of the operation content; the second interaction prompt message and the at least one second operation prompt message are sent to the client as a second session message, and the client will superimpose and display the second session message on any interface; the client will also generate a second operation instruction in response to a trigger operation for any one of the second operation prompt messages and send the second operation instruction to the server, and the server will process the operation object according to the operation content when the operation type corresponding to the second operation instruction is a continue operation.

[0106] Further, the server will also generate an instant messaging message based on the first interaction prompt message, the at least one first operation prompt message, and the first operation instruction; add the instant messaging message to the instant messaging interface of the client so that when the client enters the instant messaging interface, the instant messaging message is displayed.

[0107] S607, the client generates a target inquiry message in response to an input operation on the instant messaging interface.

[0108] S608, the client sends the target inquiry message to the server.

[0109] S609, the server uses the artificial intelligence model to generate an inquiry interaction message for the target inquiry message.

[0110] S610, the server sends the inquiry interaction message to the client.

[0111] S611, the client displays the inquiry interaction message on the instant messaging interface.

[0112] The detailed implementation manners and beneficial effects of the steps in the method of this embodiment have been described in detail in the foregoing embodiments, and will not be elaborated here.

[0113] It should be noted that in some of the processes described in the above embodiments and the accompanying drawings, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as the process of actively reaching the interaction 601-606 and the process of passively reaching the interaction 607-611, are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0114] Figure 7 FIG. is a schematic structural diagram of an information interaction device provided by an exemplary embodiment of the present application. The device is configured on the server side and includes: a model operation module 701, configured to use an artificial intelligence model, combine user feature data corresponding to a user identifier, determine a target interaction condition that matches the user feature data from a plurality of preset interaction conditions, and combine an operation object associated with the target interaction condition to generate a first interaction prompt message, and determine at least one first operation prompt message corresponding to the first interaction prompt message; a first sending module 702, configured to send the first interaction prompt message and the at least one first operation prompt message as a first session message to the client, so that the client superimposes and displays the first session message on 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 messages; 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.

[0115] In an optional embodiment, the operation processing module 704 is specifically configured to, if the operation type corresponding to the first operation instruction is a continue operation, use the artificial intelligence model to combine the user feature data to generate operation content for the operation object; process the operation object according to the operation content.

[0116] In an optional 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 optional levels, the operation processing module 704 is specifically configured to: use the artificial intelligence model to combine the user feature data to determine the current user level of the target function object, determine a target level from the at least two optional levels according to the current user level, and use the operation content of upgrading to the target level as the operation content for the operation object.

[0117] In an alternative embodiment, the operation processing module 704 is further specifically configured to use the artificial intelligence model to generate, in combination with the operation content, a second interaction prompt message and at least one second operation prompt message corresponding to the second interaction prompt message; the second interaction prompt message is used to indicate confirmation of the 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 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 messages; if the operation type corresponding to the second operation instruction is a continue operation, process the operation object according to the operation content.

[0118] In an alternative embodiment, the operation processing module 704 is further specifically configured to send the operation interface information corresponding to the operation content to the client, so that the client jumps from any interface to the operation interface of the operation object and displays the operation interface information in the operation interface; respond to an object operation request sent by the client, where the object operation request is generated in response to a trigger operation for the operation interface information, and process the operation object.

[0119] In an alternative embodiment, if the operation type corresponding to the first operation instruction is a stop operation, 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 superimposed and displayed in any interface.

[0120] In an alternative embodiment, the model operation module 701 is specifically configured to use the artificial intelligence model to generate interaction guidance information in combination with the operation object associated with the target interaction condition and the user feature data, and generate a first interaction prompt message in combination with the interaction guidance information and the preset interaction information of the operation object.

[0121] In an alternative embodiment, if the operation object associated with the target interaction condition is a target function object, the model operation module 701 is specifically configured to use the artificial intelligence model to generate interaction guidance information according to the user transaction data and / or telephone consultation data in the user feature data and the function introduction information of the target function object; the interaction guidance information is used to describe the logical relationship between the user transaction data and / or telephone consultation data and subscribing to the target function object.

[0122] In an alternative embodiment, the device further includes an information synchronization module, configured to generate an instant messaging message based on the first interaction prompt message, the at least one first operation prompt message, and the first operation instruction; and add the instant messaging message to the instant messaging interface of the client, so that when the client enters the instant messaging interface, the instant messaging message is displayed.

[0123] In an alternative embodiment, the first receiving module 703 is further configured to receive target inquiry information sent by the client; the target inquiry information is generated by the client in response to an input operation on the instant messaging interface; the model operation module 701 is further configured to use the artificial intelligence model to generate inquiry interaction information for the target inquiry information; and the first sending module 702 is further configured to send the inquiry interaction information to the client, so that the client displays the inquiry interaction information in the instant messaging interface.

[0124] Figure 7 The information interaction device described above can execute Figure 2 the information interaction method described in the embodiments shown. The implementation principles and technical effects will not be elaborated further. For each module and unit in the device 7 in the above embodiments, the specific manners of performing operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0125] Figure 8 The figure is a schematic structural diagram of an information interaction device provided by an exemplary embodiment of the present application. The device is configured in a client and includes:

[0126] A second receiving module 801, configured to receive a first session message sent by a server; the first session message includes a first interaction prompt message and at least one first operation prompt message corresponding to the first interaction prompt message; the first interaction prompt message and the at least one first operation prompt message are generated by using an artificial intelligence model in combination with an operation object associated with a target interaction condition; the target interaction condition is determined from a plurality of preset interaction conditions by using an artificial intelligence model in combination with user feature data corresponding to a user identifier; a display module 802, configured to superimpose and display the first session message in any interface; an instruction generation module 803, configured to generate a first operation instruction in response to a trigger operation on any one of the first operation prompt messages in the first session message; and a second sending module 804, configured to send the first operation instruction to the server, so that the server determines an operation type corresponding to the first operation instruction and processes the operation object according to the operation type.

[0127] 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 second interaction prompt information and at least one second operation prompt information corresponding to the second interaction prompt information; the second interaction prompt information and the at least one second operation prompt information are generated by the server using the artificial intelligence model in combination with the operation content; the display module 802 is further configured to superimpose and display the second session message on any interface; the instruction generation module 803 is further configured to generate a second operation instruction in response to a trigger operation on any one of the second operation prompt information in the second session message; the second sending module 804 is further configured to send the second operation instruction to the server, so that when the operation type corresponding to the second operation instruction is a continue operation, the server processes the operation object according to the operation content.

[0128] In an alternative embodiment, the second receiving module 801 is further configured to receive operation interface information corresponding to the operation content sent by the server; the display module 802 is further configured to jump from any interface to the operation interface of the operation object and display the operation interface information on the operation interface; the request generation module is configured to generate an object operation request in response to a trigger operation on the operation interface information; the second sending module 804 sends the object operation request to the server, so that the server processes the operation object in response to the object operation request.

[0129] 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 superimposed and displayed on any interface; the first session closing instruction is generated by the server when the operation type corresponding to the first operation instruction is a stop operation.

[0130] In an alternative embodiment, the device further includes an inquiry generation module configured to generate target inquiry information in response to an input operation on the instant messaging interface; the second sending module 804 is further configured to send the target inquiry information to the server, so that the server uses the artificial intelligence model to generate inquiry interaction information for the target inquiry information; the second receiving module 801 is further configured to receive the inquiry interaction information sent by the server; the display module 802 is further configured to display the inquiry interaction information on the instant messaging interface.

[0131] Figure 8 The information interaction device described above can execute Figure 5 the information interaction method described in the embodiments shown, and its implementation principle and technical effects will not be elaborated further. For the specific manners in which each module and unit in the device in the above embodiments perform operations, they have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0132] Figure 9 Schematic diagram of the structure of an embodiment of a computing device provided for this application. As Figure 9 shown, in practice, the computing device may include: a storage component 901 and a processing component 902.

[0133] The storage component 901 is used to store computer programs and can be configured to store various other data to support operations on the computing device. Examples of such data include instructions for any application program or method for operating on the computing device, data structures, contact data, phone book data, messages, pictures, videos, etc.

[0134] The processing component 902 is coupled to the storage component 901 and is used to execute the computer programs in the storage component 901 to be used to implement a server device such as a server array, etc., then the components within the dashed box may not be included Figure 9 in.

[0135] The above-mentioned processing component includes one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by 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 components for executing the above method.

[0136] The above storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disks or optical discs.

[0137] The above communication component is configured to facilitate communication, either wired or wireless, between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as a mobile communication network, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.

[0138] The above display component may include a screen, and the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen can 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 sensors can sense not only the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operations.

[0139] The above power component supplies power to various components of the device where the power component is located. The power component may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device where the power component is located.

[0140] The above audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signals can be further stored in the memory or transmitted via the communication component. In some embodiments, the audio component further includes a speaker for outputting audio signals.

[0141] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to implement the steps in the above method embodiments. Among them, the computer-readable storage medium can be implemented by volatile or non-volatile or a combination thereof, and can be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium

[0142] Accordingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instruction that, when executed by a processor, enables the processor to implement the steps in the above method embodiments. It should be understood that each process or a combination of multiple processes in the above method flow can be implemented by the computer program or instruction. In addition, these computer programs or instructions can be applied to the processors of general-purpose computers, special-purpose computers, embedded processors or other programmable data processing devices, so that the processors of general-purpose computers, special-purpose computers, embedded processors or other programmable data processing devices can be used as devices to implement the corresponding functions in the above method embodiments

[0143] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again

[0144] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0145] Finally, it should be noted that the above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An information interaction method, characterized in that, Applied to the server side, including: Using an artificial intelligence model, combining user feature data corresponding to a user identifier, determining a target interaction condition that matches the user feature data from multiple preset interaction conditions, and combining an operation object associated with the target interaction condition to generate a first interaction prompt message, and determining at least one first operation prompt message corresponding to the first interaction prompt message; Sending the first interaction prompt message and the at least one first operation prompt message as a first session message to the client, so that the client superimposes and displays the first session message on any interface; Receiving 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 messages; Determining an operation type corresponding to the first operation instruction, and processing the operation object according to the operation type.

2. The method according to claim 1, wherein The determining at least one first operation prompt message corresponding to the first interaction prompt message includes: Determining at least one optional operation item corresponding to the first interaction prompt message; Filling relevant information of the at least one optional operation item into a control component template respectively to obtain at least one first operation prompt message corresponding to the first interaction prompt message.

3. The method according to claim 1, characterized in that, The processing the operation object according to the operation type includes: If the operation type corresponding to the first operation instruction is a continue operation, using the artificial intelligence model, combining the user feature data to generate operation content for the operation object; Processing the operation object according to the operation content.

4. The method according to claim 3, wherein If the operation object associated with the target interaction condition is a target function object, and the target function object includes at least two optional levels; Using the artificial intelligence model, combining the user feature data to generate operation content for the operation object, including: Using the artificial intelligence model, combining the user feature data, determining the current user level of the target function object, determining a target level from the at least two optional levels according to the current user level, and taking the operation content of upgrading to the target level as the operation content for the operation object.

5. The method according to claim 3, characterized in that, The processing the operation object according to the operation content includes: Using the artificial intelligence model, combining the operation content, generating a second interaction prompt message and at least one second operation prompt message corresponding to the second interaction prompt message; the second interaction prompt message is used to indicate confirmation of executing the operation content; Sending 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 any interface; Receiving 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; If the operation type corresponding to the second operation instruction is a continue operation, processing the operation object according to the operation content.

6. The method according to claim 3 or 5, characterized in that The processing the operation object according to the operation content includes: Send the operation interface information corresponding to the operation content to the client, so that the client can jump from any interface to the operation interface of the operation object, and display the operation interface information on the operation interface; In response to the object operation request sent by the client, process the operation object; the object operation request is generated for the trigger operation of the operation interface information.

7. The method according to claim 1, characterized in that The processing of the operation object according to the operation type includes: If the operation type corresponding to the first operation instruction is a stop operation, send a first session message closing instruction to the client to instruct the client to close the first session message superimposed and displayed in any interface.

8. The method according to claim 1, wherein Using an artificial intelligence model, combine the operation object associated with the target interaction condition to generate first interaction prompt information, including: Using an artificial intelligence model, combine the operation object associated with the target interaction condition and the user feature data to generate interaction guidance information, and combine the interaction guidance information and the preset interaction information of the operation object to generate first interaction prompt information.

9. The method according to claim 8, wherein If the operation object associated with the target interaction condition is a target function object; The generating of the interaction guidance information by using the artificial intelligence model and combining the operation object associated with the target interaction condition and the user feature data includes: Using an artificial intelligence model, generate interaction guidance information according to the user transaction data and / or telephone consultation data in the user feature data, and the function introduction information of the target function object; the interaction guidance information is used to describe the logical relationship between the user transaction data and / or telephone consultation data and subscribing to the target function object.

10. The method according to claim 1, wherein It also includes: Generate an instant messaging message based on the first interaction prompt information, the at least one first operation prompt information, and the first operation instruction; Add the instant messaging message to the instant messaging interface of the client, so that when the client enters the instant messaging interface, the instant messaging message is displayed.

11. The method according to claim 1, wherein It also includes: Receive the target inquiry information sent by the client; The target inquiry information is generated by the client in response to an input operation on the instant messaging interface; Using the artificial intelligence model, generate inquiry interaction information for the target inquiry information; Send the inquiry interaction information to the client, so that the client can display the inquiry interaction information on the instant messaging interface.

12. An information interaction method, characterized in that, Applied to the client, it includes: Receive the first session message sent by the server; the first session message contains the 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 using an artificial intelligence model and combining the operation object associated with the target interaction condition; the target interaction condition is determined from multiple preset interaction conditions by using an artificial intelligence model and combining the user feature data corresponding to the user identifier; Superimpose and display the first session message in any interface; In response to a trigger operation on any one of the first operation prompt information in the first session message, generate a first operation instruction; Send the first operation instruction to the server so that the server determines the operation type corresponding to the first operation instruction and processes the operation object according to the operation type.

13. An information interaction device, characterized in that, Configured in the server, including: A model operation module, which is used to use an artificial intelligence model, combine user feature data corresponding to a user identifier, determine a target interaction condition that matches the user feature data from multiple preset interaction conditions, and combine the operation object associated with the target interaction condition to generate a first interaction prompt message, and determine at least one first operation prompt message corresponding to the first interaction prompt message; A first sending module, which is used to send the first interaction prompt message and the at least one first operation prompt message as a first session message to the client so that the client superimposes and displays the first session message on any interface; A first receiving module, which is used to receive the first operation instruction sent by the client, and the first operation instruction is generated by the client in response to a trigger operation on any one of the first operation prompt messages; An operation processing module, which is used to determine the operation type corresponding to the first operation instruction and process the operation object according to the operation type.

14. An information interaction device, characterized in that, Configured in the client, including: A second receiving module, which is used to receive the first session message sent by the server; the first session message includes a first interaction prompt message and at least one first operation prompt message corresponding to the first interaction prompt message; the first interaction prompt message and the at least one first operation prompt message are generated by using an artificial intelligence model and combining the operation object associated with the target interaction condition; the target interaction condition is determined from multiple preset interaction conditions by using an artificial intelligence model and combining the user feature data corresponding to the user identifier; A display module, which is used to superimpose and display the first session message on any interface; An instruction generation module, which is used to generate a first operation instruction in response to a trigger operation on any one of the first operation prompt messages in the first session message; A second sending module, which is used to send the first operation instruction to the server so that the server determines the operation type corresponding to the first operation instruction and processes the operation object according to the operation type.

15. A computing device, characterized in that, Includes a processing component and a storage component; The storage component stores a computer program; the computer program is used to be called and executed by the processing component to implement the information interaction method according to any one of claims 1-12.

16. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and when the computer program is executed by the processing component, the information interaction method according to any one of claims 1-12 is implemented.

17. A computer program product, characterized in that, Includes a computer program or instruction, and when the computer program or instruction is executed by the processing component, the information interaction method according to any one of claims 1-12 is implemented.

Images