Information interaction method and device, computing equipment, storage medium and program product
Through the collaborative work of the server and the client, the artificial intelligence model is used to generate accurate response content, which solves the problem of low service conversion rate of service providers in the e-commerce system, and realizes efficient interaction and service conversion between consumers and service providers.
Patent Information
- Application Number
- CN202510526999.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-24
- Publication Date
- 2025-07-11
AI Technical Summary
The service conversion rate of service providers in the e-commerce system is low, making it difficult for service providers to attract more entry, and the existing technology is difficult to effectively improve the interaction rate between consumers and service providers.
The server receives the client's information viewing request, obtains the relevant information of the target object and sends inquiry prompts, uses the artificial intelligence model to generate the response content, and the client displays the response content in the form of a card, and performs processing operations in response to consumer operation requests, realizing accurate recommendations and interactions.
It improves the service conversion rate of service providers, and through accurate recommendations and interactions, it helps consumers find service objects that meet their needs to place orders, enhancing cooperation between consumers and service providers.
Smart Images

Figure CN120297986A_ABST
Abstract
Description
Technical Field
[0001] The 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 computer technologies, e-commerce systems that provide various services have gradually emerged. Consumers can view relevant information of service providers or the services they publish in the e-commerce system, such as published service posts, and then communicate with the service providers to place orders.
[0003] Currently, the number of consumers who view service providers and their services in the e-commerce system every day is much larger than the number of consumers who place orders, and the service conversion rate is a factor that service providers focus on when choosing a cooperative e-commerce system. Therefore, in order to attract more service providers to settle in, the e-commerce system urgently needs to help service providers improve their service conversion rates. Summary of the Invention
[0004] The embodiments of the present application provide an information interaction method, apparatus, computing device, storage medium, and program product to solve the problem of low service conversion rate of service providers in the prior art.
[0005] An information interaction method provided in the embodiments of the present application is applied to a server and includes: receiving an information viewing request sent by a client for a target object; the information viewing request includes an object identifier of the target object; based on the object identifier, obtaining first object-related information corresponding to the target object; sending the first object-related information and an inquiry prompt information to the client so that the client displays the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt an inquiry operation; receiving an inquiry request sent by the client; the inquiry request includes target inquiry information; the target inquiry information is determined by the client in response to the inquiry operation; when using an artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information, combining second object-related information of the at least one associated object and the target inquiry information to generate a first target response content; sending the first target response content to the client so that the client displays the first target response content in the form of a card; receiving an operation request sent by the client; the operation request is generated by the client in response to a trigger operation on second object-related information corresponding to a target associated object; performing a processing operation on the target associated object according to the operation type corresponding to the operation request.
[0006] The embodiment of the present application further provides an information interaction method, which is applied to a client and includes: in response to a trigger operation on a target object, generating an information viewing request according to the object identifier of the target object; sending the information viewing request to a server so that the server obtains first object-related information corresponding to the target object; receiving the first object-related information and an inquiry prompt information sent by the server; displaying the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt an inquiry operation; in response to the inquiry operation, determining target inquiry information; based on the target inquiry information, sending an inquiry request to the server so that the server uses an artificial intelligence model to determine at least one associated object related to the target object, and in combination with the second object-related information of the at least one associated object and the target inquiry information, generating a first target response content; receiving the first target response content sent by the server; displaying the first target response content in the form of a card; in response to a trigger operation on the second object-related information corresponding to the target associated object in the first target response content, sending an operation request to the server so that the server performs a processing operation on the target associated object according to the operation type corresponding to the operation request.
[0007] The embodiment of the present application further provides an information interaction device, which is configured in a server and includes: a first receiving module, configured to receive an information viewing request sent by a client for a target object; the information viewing request includes an object identifier of the target object; an information obtaining module, configured to obtain first object-related information corresponding to the target object based on the object identifier; a first sending module, configured to send the first object-related information and an inquiry prompt information to the client, so that the client displays the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt an inquiry operation to be performed; the first receiving module is further configured to receive an inquiry request sent by the client; the inquiry request includes target inquiry information; the target inquiry information is determined by the client in response to the inquiry operation; a model running module, configured to use an artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information, and combine second object-related information of the at least one associated object and the target inquiry information to generate a first target response content; the first sending module is further configured to send the first target response content to the client, so that the client displays the first target response content in a card form; the first receiving module is further configured to receive an operation request sent by the client; the operation request is generated by the client in response to a trigger operation on second object-related information corresponding to a target associated object; an operation execution module, configured to perform a processing operation on the target associated object according to the operation type corresponding to the operation request.
[0008] An embodiment of the present application further provides an information interaction device, configured in a client, including: a request generation module, configured to generate an information viewing request according to the object identifier of the target object in response to a triggering operation on the target object; a second sending module, configured to send the information viewing request to a server, so that the server obtains first object-related information corresponding to the target object; a second receiving module, configured to receive the first object-related information and an inquiry prompt information sent by the server; a display module, configured to display the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt an inquiry operation; an information determination module, configured to determine target inquiry information in response to the inquiry operation; the second sending module is further configured to send an inquiry request to the server based on the target inquiry information, so that when the server uses an artificial intelligence model to determine at least one associated object related to the target object, in combination with the second object-related information of the at least one associated object and the target inquiry information, generate a first target response content; the second receiving module is further configured to receive the first target response content sent by the server; the display module is further configured to display the first target response content in a card form; the second sending module is further configured to send an operation request to the server in response to a triggering operation on the second object-related information corresponding to the target associated object in the first target response content, so that the server performs a processing operation on the target associated object according to the operation type corresponding to the operation request.
[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] After the server end of the embodiment of the present application receives an information viewing request sent by the client for a target object, it will obtain the first object-related information of the target object and send it to the client for display together with the inquiry prompt information. After receiving the inquiry request triggered by the client for the inquiry prompt information, when using an artificial intelligence model to determine an associated object related to the target object based on the target inquiry information, the first target response content is generated by combining the second object-related information of the associated object and the target inquiry information, and is sent to the client so that the client can display it in the form of a card. The client responds to the trigger operation for the second object-related information and initiates an operation request to the server end. The server end will perform a processing operation on the target associated object based on the operation type corresponding to the operation request. The embodiment of the present application can display the object-related information of the target object and the target inquiry information to the consumer through the client when the consumer requests to view the target object, guiding the user to ask questions. When the user's question involves an associated object of the target object, the object-related information of the associated object is displayed in the form of a card, which not only helps the consumer solve the problem, but also realizes accurate recommendation of the associated object, facilitating the consumer to find a service object that meets the requirements and place an order. It realizes active interaction with the consumer on behalf of the service provider, promotes cooperation between the consumer and the service provider, and thus helps the service provider improve its service conversion rate. In addition, this solution generates the target response content based on an artificial intelligence model instead of using fixed words to reply, making the target response content more accurate and closer to the manual reply of the service provider, facilitating the consumer's reception and use.
[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 constitute 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 The system architecture diagram for information interaction provided by the exemplary embodiment of the present application is shown.
[0016] Figure 2 The flowchart of an information interaction method provided by the exemplary embodiment of the present application is shown.
[0017] Figure 3 The schematic diagram of an interaction interface provided by the exemplary embodiment of the present application is shown.
[0018] Figure 4a The schematic diagram of another interaction interface provided by the exemplary embodiment of the present application is shown.
[0019] Figure 4b The figure shows a schematic diagram of another interactive interface provided by an exemplary embodiment of the present application.
[0020] Figure 5 The figure shows a flowchart of an information interaction method provided by an exemplary embodiment of the present application.
[0021] Figure 6 The figure shows a signaling diagram of an information interaction method in an application scenario provided by an exemplary embodiment of the present application.
[0022] Figure 7 The figure shows a schematic structural diagram of an information interaction device provided by an exemplary embodiment of the present application.
[0023] Figure 8 The figure shows a schematic structural diagram of an information interaction device provided by an exemplary embodiment of the present application.
[0024] Figure 9 The figure shows a schematic structural diagram of a computing device for information interaction provided by the present application. Detailed implementation manners
[0025] 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 of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
[0026] It should be noted that the technical solutions of the embodiments of the present application are applicable to a network virtual environment. The users described 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.
[0027] 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, the corresponding data is received or sent by the client corresponding to the user account to the server. In addition, users can also communicate with each other 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 specifically limit this. However, it should be noted that the user corresponding to the client in the embodiments of the present application is a consumer in an e-commerce service.
[0028] 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 device information, user personal information, 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 regulations and standards.
[0029] 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: linear swipes, curved swipes, etc.
[0030] At present, consumers can view the relevant information of the service provider or its published services in the e-commerce system, such as the published service posts, and then communicate with the service provider to place an order. However, the number of consumers who view the service provider and its services every day in the e-commerce system is much greater than the number of consumers who place orders, and the service conversion rate is a factor that the service provider focuses on when cooperating with the e-commerce system. Because how the e-commerce system can help the service provider improve its service conversion rate is still a problem that needs to be solved urgently. In response to this problem, the embodiment of the present application provides a solution, and the basic idea is that after the server receives the information viewing request sent by the client for the target object, it will obtain the first object related information of the target object, and send it and the inquiry prompt information to the client for display. After receiving the inquiry request triggered by the client for the inquiry prompt information, the artificial intelligence model is used to determine the case of the associated object involving the target object based on the target inquiry information, and the first target response content is generated in combination with the second object related information of the associated object and the target inquiry information, and sent to the client so that the client can display it in the form of a card. The client responds to the trigger operation for the relevant information of the second object and initiates an operation request to the server. The server will perform the processing operation on the target associated object based on the operation type corresponding to the operation request. The embodiment of the present application can display the target object-related information and target inquiry information to the consumer through the client when the consumer requests to view the target object, and guide the user to ask questions. When the user's question involves the associated object of the target object, the object-related information of the associated object is displayed in the form of a card, which not only helps the consumer solve the problem, but also achieves accurate recommendation of associated objects, making it easier for consumers to find service objects that meet their needs and place orders. It realizes active interaction with consumers on behalf of service providers, promotes cooperation between consumers and service providers, and then helps service providers improve their service conversion rates. In addition, this solution generates target response content based on an artificial intelligence model instead of using fixed replies, so that the target response content is more accurate and closer to the manual reply of the service provider, which is convenient for consumers to receive and use.
[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0032] Figure 1The figure shows a system architecture diagram of an e-commerce system that can be applied to information interaction and implement the technical solution of an embodiment of the present application. 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 cable, 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 mini-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, or 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 intelligent cloud host with artificial intelligence technology.
[0037] It should be noted that the information interaction method provided in the embodiments of the present application is generally executed jointly 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 only illustrative. According to the implementation requirements, there can be any number of clients and servers.
[0039] 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 may include the following steps:
[0040] S201, receiving an information viewing request sent by the client for a target object.
[0041] Among them, the target object can be an object provided in the e-commerce system for consumers to view. The target object can be a service provider that has entered the e-commerce system; it can also be a service provided by the service provider. For example, it can be a certain merchant store in the e-commerce system, or a certain service product provided in the store.
[0042] The information viewing request can be a request to view the relevant information of the target object, which at least includes the object identifier of the target object; the object identifier of the target object can be a unique identifier used to locate the target object. For example, an identity document (ID).
[0043] Optionally, in this embodiment, the client will display brief introduction information (such as post cover information) of service products or service providers through interfaces such as the home page, list display interface, or service recommendation interface. When the consumer is browsing the interface and is interested in a certain service product or service provider and wants to know more, the consumer can trigger the brief introduction information of the service product or service provider on the client. At this time, the client will use the service product or service provider corresponding to the user's trigger operation as the target object, and based on the object identifier of the target object, send an information viewing request to the server. The request is used to obtain the object-related information of the target object from the server and display it to the consumer. Correspondingly, the server will receive the information viewing request.
[0044] S202. Based on the object identifier, obtain the first object-related information corresponding to the target object.
[0045] Among them, the first object-related information can be the information used to introduce the target object extracted from the detailed introduction information of the target object. For example, if the target object is a service provider, the first object-related information may include, but is not limited to: the store name of the service provider, the consultation phone number, the store introduction, the service area, the service guarantee, the service image, etc. If the target object is a service product, the first object-related information may include, but is not limited to: the name of the service product, the consultation phone number, the service image, the service introduction, etc.
[0046] Optionally, in this embodiment, the server can maintain a service provider knowledge base for each service provider in the system. The service provider knowledge base stores the detailed information of the service provider and all the services provided by the service provider. For example, it can store the store information of the service provider (such as store name, store city, store industry, store introduction, service area, and service time, etc.), service information (such as service name, service price, and service introduction, etc.), and preferential information (such as coupon information and group purchase information, etc.). For the convenience of data search, each service provider has a unique identifier, which is used to associate and store the store information, service information, and preferential information of the service provider. For each service provider, each service it can provide also has a corresponding service identifier, which is used to associate and store the service information corresponding to each service. In this embodiment, the server responds to the information viewing request, obtains the object identifier included therein, then searches the service knowledge base for all the detailed information corresponding to the object identifier, and then summarizes and extracts the obtained all the detailed information according to the relevant information extraction rules to obtain the first object-related information.
[0047] S203. Send the first object-related information and the inquiry prompt information to the client so that the client can display the first object-related information and the inquiry prompt information.
[0048] Among them, the inquiry prompt information can be information that prompts the user to make an inquiry. For example, it can be information related to a question input box; it can also be associated inquiry information of a target object preset for the user to select; it can also be information that simultaneously includes the information of the question input box and the associated inquiry information of the target object. There is no limitation on this. The inquiry prompt information is used to prompt the execution of an inquiry operation, which can be an operation of entering a question in the question input box or an operation of clicking on any associated inquiry information.
[0049] In this embodiment, the information of the question input box and the associated inquiry information of the target object in the inquiry prompt information can be preset and stored on the server. At this time, the server can directly obtain the inquiry prompt information and then send it to the client together with the relevant information of the first object. Specifically, the server of this embodiment can render the inquiry prompt information and the relevant information of the first object and then send it to the client. At this time, the client can directly display the rendered relevant information of the first object and the inquiry prompt information; the server can also directly send the obtained relevant information of the first object and the inquiry prompt information to the client, and the client renders and displays the inquiry prompt information and the relevant information of the first object.
[0050] Optionally, in this embodiment, the method of rendering the inquiry prompt information and the relevant information of the first object can be to render the relevant information of the first object into an object card and display it in the interaction interface. The object card can include text-based introduction content, image introduction content, and component-based operation components. The inquiry prompt information is rendered below the object card in the interaction interface to facilitate prompting the user to perform an inquiry operation after the consumer has browsed the content in the object card.
[0051] Exemplarily, Figure 3 shows the effect diagram of the interaction interface displaying the inquiry prompt information and the relevant information of the first object. Figure 3 In 301 area, the object card of the relevant information of the first object is displayed. The object card includes both the store name introduced in text form and the service information introduced in image form, and also includes operation components such as telephone consultation. The inquiry prompt information is displayed below the 301 area.
[0052] In some embodiments, in order to better introduce interactive operations with users and improve the user experience. This embodiment can also add opening interaction information to the interactive page, and lead to subsequent first object related information and inquiry prompt information through the opening interaction information. Optionally, the server can use an artificial intelligence model to generate opening interaction information before sending first object related information and inquiry prompt information to the client; accordingly, when executing S203 operation, the opening interaction information, first object related information and inquiry prompt information can be sent to the client, so that the client displays the opening interaction information, first object related information and inquiry prompt information.
[0053] In this embodiment, an artificial intelligence model may be used to generate opening interaction prompt information based on the first object related information of the target object. The opening interaction prompt information may be one sentence or multiple sentences. If it is multiple sentences, there may be one sentence of opening interaction information before the first object related information and one sentence of opening interaction information before the inquiry prompt information. For example, Figure 3 Two opening interaction messages are shown, namely, "I can help you solve the generation service problem. Here are the post details shown to you" and "What other questions do you want to know?".
[0054] S204: Receive a query request sent by the client.
[0055] The query request includes target query information; the target query information is determined by the client in response to the query operation (i.e., the query operation for the query prompt information). Specifically, if the consumer performs a query operation on the client for the question input box in the query prompt information, the target query information at this time may be the content input by the consumer in the question input box, i.e., the client obtains the input content corresponding to the query operation as the target query information; if the consumer performs a related query information on the client for the target object in the query prompt information, the target query information at this time may be the related query information triggered by the consumer, i.e., the client obtains the related query information corresponding to the triggering operation as the target query information.
[0056] After obtaining the target query information, the client will initiate a query request to the server based on the target query information for the query operation triggered by the query prompt information. The corresponding server will receive the query request.
[0057] S205, using an artificial intelligence model to determine at least one associated object involving the target object based on the target query information, and generating a first target response content by combining second object related information of the at least one associated object and the target query information.
[0058] Among them, the associated object can be an object stored in the service provider's knowledge base, which can answer the target inquiry information, has an association relationship with the target object, can be displayed in the form of a card, and is available for user interaction. For example, it can include but is not limited to: service products, coupon products, and group-buying products, etc. The second object-related information can be the related information of the associated object stored in the service provider's knowledge base, which can be obtained by refining and summarizing the detailed information of the associated object based on the card display requirements of the associated object. It should be noted that although the first object-related information and the second object-related information are both obtained by refining and summarizing the detailed information of the object, the corresponding content types can be the same or different, and this is not limited. The first target response content can be the response content for the target inquiry information.
[0059] In this embodiment, the server extracts the target inquiry information in response to the received inquiry request, and then generates a prompt instruction based on the target inquiry information, the service provider's knowledge base, the target object identifier, the role description, the task description, the output format requirements, etc., and inputs it into the artificial intelligence model to guide the artificial intelligence model to determine whether there is at least one associated object related to the target object in the service knowledge base in combination with the target inquiry question. For example, if the target object is the service provider and the target inquiry information is "What are the discounts?", if there are cards corresponding to coupon products or group-buying products stored in the service knowledge base at this time, it means that there is at least one associated object related to the target object, that is, the associated object at this time is the coupon product or the group-buying product. At this time, the artificial intelligence model will further obtain the second object-related information of at least one associated object from the service provider's knowledge base, and then generate the first target response content by organizing the language based on the target inquiry information and the second object information.
[0060] 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 the 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. It 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, enabling the model built based on them to 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.
[0061] S206, send the first target response content to the client so that the client can display the first target response content in the form of a card.
[0062] Optionally, after generating the first target response content, the server can render the first target response content into the form of a card locally and then send it to the client for display, or directly send the first target response content to the client, and the client renders it into the form of a card for display.
[0063] Optionally, after obtaining the inquiry prompt information, the client can first display the target inquiry information in the interaction interface, and after obtaining the first target response content, display the card corresponding to the first target response content after the target inquiry information. Exemplarily, Figure 4aAmong them, the area 401 shows the first target response content displayed in the form of a card. Among them, 4011-4013 are the second object-related information of three associated objects displayed in the form of a card.
[0064] In some embodiments, considering that the card corresponding to the first target response content displayed on the client may not meet the needs of consumers, in order to further retain consumers, in this example, before performing the operation of S206, an operation of generating a response prompt message by using an artificial intelligence model may further be performed; the response prompt message is used to prompt the user to continue to perform an inquiry operation; correspondingly, when performing the operation of S206, the first target response content and the response prompt message are sent to the client, so that the client displays the first target response content in the form of a card, and displays the response prompt message in the form of text below the card. Among them, the response prompt message may also remind the consumer whether there are other questions to ask. For example, it may be Figure 4a The "Do you have any other questions you want to know?" displayed in the area 401 in
[0065] It should be noted that if the consumer triggers an inquiry operation for the response prompt message through the client, the client will obtain the target inquiry information corresponding to the inquiry operation and initiate an inquiry request to the server, and the server will return to continue performing S204 and its subsequent operations.
[0066] S207, receive the operation request sent by the client.
[0067] Among them, the operation request is generated by the client in response to a trigger operation for the second object-related information corresponding to the target associated object. Since the first target response content includes the second object-related information corresponding to at least one associated object respectively, and the second object-related information contains various types of operation components. For example, Figure 4a contains operation components such as "Snap up immediately" and "Claim within limited time". Therefore, in the embodiment, the trigger operation for the second object-related information corresponding to the target associated object may refer to the trigger operation for the operation components in the second object-related information.
[0068] Optionally, when the consumer performs a trigger operation on any second object-related information on the client, the client will initiate an operation request to the server based on the control component corresponding to the trigger operation. For example, if the trigger operation is for Figure 4a the immediate snap-up operation triggered by the 500 yuan voucher for 156 generations in
[0069] S208, perform a processing operation on the target associated object according to the operation type corresponding to the operation request.
[0070] After receiving the operation request sent by the client, the server will perform corresponding operation processing on the target associated object based on the operation type corresponding to the operation request. For example, if the operation request initiated by the client to the server is to snap up a 500-yuan voucher for 156 generations, at this time, the server will obtain the snap-up interface of the 500-yuan voucher for 156 generations and send it to the client so that the client can display the snap-up interface for consumers to place an order for the 500-yuan voucher for 156 generations on the snap-up interface.
[0071] In this embodiment, after the server receives the information viewing request sent by the client for the target object, it will obtain the first object-related information of the target object and send it to the client for display together with the inquiry prompt information. After receiving the inquiry request triggered by the client for the inquiry prompt information, when the artificial intelligence model determines the associated object related to the target object based on the target inquiry information, the first target response content is generated by combining the second object-related information of the associated object and the target inquiry information, and sent to the client so that the client can display it in the form of a card. The client responds to the trigger operation for the second object-related information and initiates an operation request to the server, and the server will perform the processing operation on the target associated object based on the operation type corresponding to the operation request. The embodiment of the present application can display the object-related information of the target object and the target inquiry information to the consumer through the client when the consumer requests to view the target object, guiding the user to ask questions. When the user's question involves the associated object of the target object, the object-related information of the associated object is displayed in the form of a card, which not only helps the consumer solve the problem, but also realizes the accurate recommendation of the associated object, facilitating the consumer to find the service object that meets the requirements and place an order. It realizes the active interaction with the consumer on behalf of the service provider, promotes the cooperation between the consumer and the service provider, and thus helps the service provider improve its service conversion rate. In addition, this solution generates the target response content based on the artificial intelligence model instead of using fixed words to reply, making the target response content more accurate and closer to the manual reply of the service provider, facilitating the reception and use by the consumer.
[0072] In some embodiments, in order to help consumers better inquire about the target object and improve the user experience, this embodiment may further include: obtaining at least one associated inquiry information corresponding to the target object and using the at least one associated inquiry information as the inquiry prompt information; the target inquiry information is specifically determined by the client in response to the selection operation for the at least one associated inquiry information. Specifically, one implementable way to obtain at least one associated inquiry information corresponding to the target object in this embodiment may be to pre-collect some high-frequency inquiry information, and at this time, the pre-collected high-frequency inquiry information can be obtained as the at least one associated inquiry information corresponding to the target object.
[0073] In order to improve the relevance of the associated query information and the target object and provide more accurate query prompts to consumers, another achievable method of this embodiment is to pre-collect high-frequency query information corresponding to each industry category to which each service provider in the e-commerce system belongs, and store it in the query knowledge base as the preset query information corresponding to the industry. For example, the industry category identifier and the preset query information corresponding to the industry category are stored in the query knowledge base as the key and value in the key-value pair. At this time, the industry category corresponding to the target object can be determined; the artificial intelligence model is used to search for at least one preset query information corresponding to the target industry category from the query knowledge base, and at least one associated query information corresponding to the target object is generated for at least one preset query information.
[0074] Specifically, it can be to determine the industry category corresponding to the target object, such as determining the industry category identifier to which the industry category belongs, and then generate prompt instructions based on the industry category identifier, inquiry knowledge base, output format, preset information language style and consultation direction requirements, and then input the prompt instructions into the artificial intelligence model. The artificial intelligence model, based on the prompt instructions, screens out common consultation directions such as service content, contact information, price discounts, etc. from the inquiry knowledge base according to the consultation direction requirements, and at least one preset inquiry information associated with the industry category. Then, according to the language style requirements, polish the screened preset inquiry information, for example, keep it colloquial, include basic information inquiries and promotional questions, have reasonable expressions, etc., to obtain at least one related inquiry information corresponding to the target object. For example, Figure 3 The questions displayed in the form of "What's your phone number?", "Are there any discounts?" and "What services do you have?" are all related inquiry information. This method polishes the preset inquiry information based on the artificial intelligence model and then outputs it, making the output related inquiry information more similar to consumers' spoken inquiries, adding elements such as expressions, and improving the richness and diversity of related inquiry information.
[0075] Optionally, when there are multiple related inquiry information in this embodiment, the client can display the related inquiry information in the form of bubbles by sliding horizontally for consumers to click. Every time the consumer clicks on a question bubble, the bubble can show dynamic effects such as breaking to increase fun.
[0076] In some embodiments, a situation may occur where at least one associated object that does not involve the target object is determined based on the target query information. In this case, the second target response content may be generated by combining the object detail information corresponding to the target object and the target query information; the second target response content is sent to the client so that the client displays the second target response content in text form.
[0077] Specifically, when an artificial intelligence model is used to determine at least one associated object that does not involve the target object based on the target inquiry information, the object details information of the target object associated with the storage of the object identifier can be extracted from the service provider's knowledge base based on the object identifier of the target object, and then the relevant content that can answer the target inquiry information is extracted from the object details information for integration processing to obtain the second target response content. For example, if the target inquiry information is what time is the business hours, at this time, the content related to the business hours can be extracted from the object details information, polished and integrated, and used as the second target response content. This method can also use the artificial intelligence model to analyze the answer corresponding to the target based on the object details information in the case of not involving the associated object of the target object. This process can well replace the service provider to answer questions for consumers, thereby promoting the conversion of services.
[0078] It should be noted that for the case of at least one associated object that does not involve the target object and the object details information cannot answer the target inquiry information, this embodiment can also use the artificial intelligence model to output a fallback statement based on the target inquiry information. For example, Figure 4b shows the second target response content for this case.
[0079] In some embodiments, the method of analyzing whether there is at least one associated object of the target object can be to use an artificial intelligence model to analyze the inquiry category corresponding to the target inquiry information, and based on the inquiry category, determine whether there is at least one associated object of the target object in the service provider's knowledge base corresponding to the target object.
[0080] Among them, the inquiry category can include but is not limited to: service item category, coupon category, group purchase category, and other categories, etc. Specifically, the artificial intelligence model can be used to first identify the inquiry category of the target inquiry information. If the inquiry category corresponding to the target inquiry information is any one of the service item category, coupon category, or group purchase category, at this time, it is further identified whether the inquiry is about services, coupons, group purchases, etc., or details. If it is an item, it is determined that there is at least one associated object of the target object in the service provider's knowledge base corresponding to the target object; if it is details, or the inquiry category is other categories, it is determined that there is no at least one associated object of the target object in the service provider's knowledge base corresponding to the target object. This method can quickly and accurately identify whether there is at least one associated object of the target object.
[0081] In some embodiments, in order to better help the service provider to divert traffic, this embodiment can also use the artificial intelligence model to analyze the target diversion information corresponding to the first target response content or the second target response content, and add the target diversion information to the first target response content or the second target response content.
[0082] Optionally, in this embodiment, for the target response content, the corresponding target drainage information can be parsed based on the artificial intelligence model and added to the target response content. It can also be for the target response content of the fuzzy type or with a clear order intention, parse the corresponding target drainage information and add it to the target response content. The target drainage information parsed based on the artificial intelligence model in this embodiment can be to guide consumers to leave their phone numbers, or to guide consumers to click the dial button to consult, or to ask consumers if they are convenient to answer the phone, etc. After the server sends the first target response content or the second target response content with the target drainage information to the client, when the client displays the first target response content or the second target response content in the form of a card or text, the target drainage information can be displayed behind the card or text and shown in the form of a bubble component for consumers to select. After the consumer selects, the corresponding bubble can also display different animation effects, such as the effect of the bubble bursting.
[0083] Exemplarily, Figure 4b shows the display of the target drainage information after the second target response content in text form. There are two target drainage information in the figure, namely "Contact later" and "Okay, I'm available now".
[0084] In some embodiments, during the process of consumers viewing the first target response content or the second target response content with the target drainage information through the client, the target drainage information for agreeing to the service provider to call back may be triggered. At this time, the method of this embodiment further includes: determining the communication time in response to the communication appointment request sent by the client; the communication appointment request is generated for the triggering operation of the target drainage information; establishing a communication connection based on the communication time so that the client can communicate with the service provider corresponding to the object identifier based on the communication connection.
[0085] Specifically, when the client detects the triggering operation for the target drainage information for agreeing to the service provider to call back, it will generate a communication appointment request and send it to the server. The server will respond to the appointment request and determine the communication time. If the target drainage information corresponding to the triggering operation contains time information, such as "Contact later" or "Contact now", etc., the communication time can be determined based on the target drainage information corresponding to the triggering operation at this time. If not, the server can also interact with the client one more time to determine the communication time and establish a call reminder.
[0086] Exemplarily, if the target drainage information contains definite time information, at this time, it can be to perform dual-call dialing based on the consumer's phone number and the service provider's phone number corresponding to the object identifier when reaching that moment, and establish a communication link between the consumer and the service provider so that both parties can make a call based on the communication link; if the target drainage information contains words such as "call immediately" or "contact now", it can be to wait for a short duration (such as 30 seconds) and then perform dual-call dialing based on the consumer's phone number and the service provider's phone number corresponding to the object identifier to establish a communication link between the consumer and the service provider so that both parties can make a call based on the communication link. If the target drainage information contains vague time such as "contact later", at this time, the sending time of the reservation request can be further checked. If it belongs to a convenient communication period, such as from 8 am to 9 pm, at this time, it can wait for a period of time (such as half an hour) and then perform dual-call dialing based on the consumer's phone number and the service provider's phone number corresponding to the object identifier to establish a communication link between the consumer and the service provider. If the sending time of the reservation request belongs to an inconvenient communication period, such as from 9 pm to 8 am the next day, at this time, it can establish a communication link the next day, or inform the service provider of the consumer information, that is, only create a business opportunity for the service provider and not establish a communication connection, etc. There is no limitation on this. The advantage of such a setting in this embodiment is that it can flexibly guide and help the service provider and the consumer to establish a communication opportunity, thereby improving the service conversion rate.
[0087] In some embodiments, in order to prevent there being a risk control danger in the interaction process, in this embodiment, when using an artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information and generating the first target response content by combining the second object-related information of at least one associated object and the target inquiry information, the following steps can be specifically executed: Use the artificial intelligence model to perform risk control detection on the target inquiry information based on the risk control knowledge base, and when the detection passes and at least one associated object related to the target object is determined based on the target inquiry information, generate the first target response content by combining the second object-related information of at least one associated object and the target inquiry information.
[0088] Specifically, a risk control knowledge base for storing various risk control words and high-risk words can be pre-configured. After determining the target inquiry information, an artificial intelligence model can be used to detect whether the target inquiry information hits the risk control words and high-risk words in the risk control knowledge base. If it does not hit, it means that the target inquiry information has no risk control danger, and the subsequent operation of determining the first target response content can be executed. If it hits a risk control word or a high-risk word, the subsequent operation of generating the first target response content will no longer be executed, and a risk prompt message will be directly sent to the client. Compared with judging whether the target inquiry information hits the risk control knowledge base based on the word matching algorithm, in this embodiment, the risk control judgment is based on the artificial intelligence model and the risk control knowledge base, which can more accurately identify the situation where the risk control knowledge base is marginally hit through transcription, rewriting, etc., thereby improving the accuracy of risk control detection.
[0089] In some embodiments, since there are many service providers in the e-commerce service system and the computing power of the artificial intelligence model is limited, in order to better replace the service providers to interact with consumers and improve the service conversion rate. In this embodiment, the service providers can be classified by level. For example, the level can be divided according to whether the service provider has purchased the product with the interaction function, or the level can be divided according to the length of time the user has entered the system. Correspondingly, when the service end obtains the first object-related information corresponding to the target object based on the object identifier, it can be to obtain the level information of the service provider corresponding to the object identifier; when the level information meets the level requirements, the first object-related information corresponding to the target object is obtained based on the object identifier.
[0090] Specifically, the service end can first obtain the service provider identifier corresponding to the target object at this time, and then determine the level information of the service provider identifier according to the pre-set level division rule, and then further determine whether the level information of the service provider identifier meets the level requirements for enjoying the interaction function. For example, whether the service provider corresponding to the service provider identifier is a member, or whether the registration duration of the service provider identifier is greater than or less than the preset duration. If it is judged that the level requirements are met, the operation of obtaining the first object-related information corresponding to the target object based on the object identifier is further executed. Thus, the function of replacing the service provider to interact with the consumer is provided to the service provider with rights and interests.
[0091] Based on the above embodiments, in order to better meet the personalized needs of service providers, in this embodiment, an interaction function switch can also be set for the interaction function between alternative service providers and consumers. When the level information meets the level requirements, it is determined whether the service provider corresponding to the object identifier has enabled the interaction function; if it is enabled, based on the object identifier, the first object-related information corresponding to the target object is obtained. That is, in this embodiment, the first object-related information corresponding to the target object is obtained only when the service provider meets both the level requirements and enables the interaction function, and subsequent services are provided for it. It should be noted that the service provider can set the switch status of the interaction function on its client.
[0092] If the level information does not meet the level requirements, or the service provider has not enabled the interaction function, based on the object identifier, the detailed information of the target object is obtained; the detailed information of the target object is sent to the client so that the client can display the detailed information of the target object on the detailed display interface; the first object-related information of the target object is extracted from the detailed information of the target object. Specifically, for service providers who do not meet the level requirements or have not enabled the interaction function, in this embodiment, the detailed information of the target object can be extracted from the service provider knowledge base and then sent to the client so that the client can jump to the detailed display interface to display the detailed information of the target object. This method can flexibly provide personalized services for service providers with different levels and different needs. It should be noted that the server can either render the detailed information of the target object to the detailed display interface and then send the rendered detailed display interface to the client, or directly send the detailed information of the target object to the client, and the client renders it to the detailed display interface and then displays it. There is no limitation on this.
[0093] Figure 5 The 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 the client, and this client is the client used by consumers in the e-commerce system. This method may include the following steps:
[0094] S501, in response to a trigger operation for a target object, generate an information viewing request according to the object identifier of the target object.
[0095] S502, send the information viewing request to the server so that the server can obtain the first object-related information corresponding to the target object.
[0096] S503, receive the first object-related information and inquiry prompt information sent by the server.
[0097] S504, display the first object-related information and inquiry prompt information.
[0098] Among them, the inquiry prompt information is used to prompt the execution of an inquiry operation.
[0099] S505. In response to the inquiry operation triggered by the inquiry prompt information, determine the target inquiry information.
[0100] Optionally, if the server obtains at least one associated inquiry information corresponding to the target object and uses it as the inquiry prompt information. At this time, it may be in response to the selection operation for the at least one associated inquiry information, and the associated inquiry information corresponding to the selection operation is used as the target inquiry information.
[0101] S506. Based on the target inquiry information, send an inquiry request to the server, so that when the server uses the artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information, combine the second object-related information of the at least one associated object and the target inquiry information to generate the first target response content.
[0102] S507. Receive the first target response content sent by the server.
[0103] S508. Display the first target response content in the form of a card.
[0104] S509. In response to the trigger operation for the second object-related information corresponding to the target associated object in the first target response content, send an operation request to the server, so that the server executes the processing operation on the target associated object according to the operation type corresponding to the operation request.
[0105] In some embodiments, if the first target response content or the second target response content sent by the server contains the target drainage information parsed by using the artificial intelligence model, after the client displays the first target response content or the second target response content containing the target drainage information, consumers may trigger the target drainage information. At this time, it further includes: generating a communication appointment request in response to the trigger operation for the target drainage information; sending the communication appointment request to the server, so that the server determines the communication time in response to the communication appointment request sent by the client, and establishes a communication connection based on the communication time, so that the client corresponding user and the service provider corresponding to the object identifier have a conversation based on the communication connection.
[0106] In some embodiments, the steps of S503 and S504 may further specifically include: receiving the opening interaction information, the first object-related information and the inquiry prompt information sent by the server, and displaying the opening interaction information, the first object-related information and the inquiry prompt information.
[0107] In some embodiments, it further includes: receiving the detailed information of the target object sent by the server and displaying the detailed information of the target object on the detailed display interface. The detailed information of the target object is obtained by the server based on the object identifier when the level information does not meet the level requirements or the service provider does not enable the interaction function, and in this embodiment, the first object-related information of the target object is extracted from the detailed information of the target object.
[0108] In some embodiments, the specific implementation manners of S507 and S508 may be: receiving the first target response content and the response prompt information sent by the server; displaying the first target response content in the form of a card, and displaying the response prompt information in text form below the card.
[0109] It should be noted that the process and beneficial effects of the client in this embodiment implementing the above information display method have been introduced in the above embodiments and will not be elaborated here.
[0110] In a practical application, Figure 6 The signaling diagram of an information interaction method for an application scenario provided by an exemplary embodiment of the present application is shown. This method is jointly implemented by the client and the server. Specifically, it includes the following steps:
[0111] S601, in response to a trigger operation for the target object, the client generates an information viewing request according to the object identifier of the target object.
[0112] S602, the client sends the information viewing request to the server.
[0113] S603, the server obtains the level information of the service provider corresponding to the object identifier, and when the level information meets the level requirements and the service provider corresponding to the object identifier enables the interaction function, based on the object identifier, obtains the first object-related information corresponding to the target object.
[0114] S604, the server determines the industry category corresponding to the target object, uses an artificial intelligence model to search for at least one preset inquiry information corresponding to the target industry category from the inquiry knowledge base, and respectively generates at least one associated inquiry information corresponding to the target object for the at least one preset inquiry information as the inquiry prompt information.
[0115] S605, the server uses an artificial intelligence model to generate the opening interaction information
[0116] S606, the server sends the opening interaction information, the first object-related information, and the inquiry prompt information to the client.
[0117] S607, the client displays the opening interaction information, the first object-related information, and the inquiry prompt information.
[0118] S608. The client determines the target inquiry information in response to the inquiry operation;
[0119] S609. The client sends an inquiry request to the server based on the target inquiry information.
[0120] S610. The server uses an artificial intelligence model to perform risk control detection on the target inquiry information based on the risk control knowledge base. In the case of passing the detection, the server analyzes the inquiry category corresponding to the target inquiry information. When determining at least one associated object related to the target object in the service provider knowledge base corresponding to the target object based on the inquiry category, the server uses the artificial intelligence model to combine the second object-related information of each associated object and the target inquiry information to generate the first target response content.
[0121] S611. The server uses the artificial intelligence model to analyze the target drainage information of the first target response content and add it to the first target response content, and generates a response prompt information.
[0122] S612. The server sends the first target response content and the response prompt information to the client
[0123] S613. The client displays the first target response content in the form of a card, and displays the response prompt information in text form below the card.
[0124] S614. In response to a trigger operation on the second object-related information corresponding to the target associated object in the first target response content, the client sends an operation request to the server.
[0125] S615. The server executes a processing operation on the target associated object according to the operation type corresponding to the operation request.
[0126] Optionally, in this scenario, the method of this embodiment further includes: if not involved, the server uses the artificial intelligence model to combine the object details information corresponding to the target object and the target inquiry information to generate a second target response content, and analyzes the target drainage information of the second target response content and adds it to the second target response content; the server sends the second target response content to the client,
[0127] The client displays the second target response content in text form. In response to a trigger operation on the target drainage information in the second target response content, the client generates a communication appointment request; the client sends the communication appointment request to the server; the server determines the communication time and establishes a communication connection based on the communication time, so that the client corresponding user can have a conversation with the service provider corresponding to the object identifier based on the communication connection.
[0128] The detailed implementation manners and beneficial effects of each step in the method of this embodiment have been described in detail in the foregoing embodiments, and will not be elaborated herein.
[0129] It should be noted that in some of the processes described in the above embodiments and the accompanying drawings, there are multiple operations that 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 in this document or may be executed in parallel. The operation numbers such as 603, 604, and 605 are only used to distinguish different operations, and the numbers themselves do not represent any execution order. Additionally, 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 document 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.
[0130] Figure 7 The following 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 first receiving module 701, configured to receive an information viewing request sent by a client for a target object; the information viewing request includes an object identifier of the target object; an information obtaining module 702, configured to obtain first object-related information corresponding to the target object based on the object identifier; a first sending module 703, configured to send the first object-related information and an inquiry prompt information to the client, so that the client displays the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt an inquiry operation; the first receiving module 701 is further configured to receive an inquiry request sent by the client; the inquiry request includes target inquiry information; the target inquiry information is determined by the client in response to the inquiry operation; a model operation module 704, configured to use an artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information, and in combination with second object-related information of the at least one associated object and the target inquiry information, generate a first target response content; the first sending module 703 is further configured to send the first target response content to the client, so that the client displays the first target response content in the form of a card; the first receiving module 701 is further configured to receive an operation request sent by the client; the operation request is generated by the client in response to a trigger operation on second object-related information corresponding to a target associated object; an operation execution module 705, configured to execute a processing operation on the target associated object according to the operation type corresponding to the operation request.
[0131] In an alternative embodiment, the information acquisition module 702 is further configured to acquire at least one associated inquiry information corresponding to the target object, and use the at least one associated inquiry information as the inquiry prompt information; the target inquiry information is specifically determined by the client in response to a selection operation for the at least one associated inquiry information.
[0132] In an alternative embodiment, the information acquisition module 702 is further configured to determine the industry category corresponding to the target object; use the artificial intelligence model to find at least one preset inquiry information corresponding to the target industry category from the inquiry knowledge base, and respectively generate at least one associated inquiry information corresponding to the target object for the at least one preset inquiry information.
[0133] In an alternative embodiment, the model operation module 704 is further configured to, when using the artificial intelligence model to determine that there is at least one associated object not related to the target object based on the target inquiry information, generate a second target response content in combination with the object detail information corresponding to the target object and the target inquiry information; the first sending module 703 is further configured to send the second target response content to the client, so that the client displays the second target response content in text form.
[0134] In an alternative embodiment, the model operation module 704 is further configured to use the artificial intelligence model to analyze the inquiry category corresponding to the target inquiry information, and based on the inquiry category, determine whether there is at least one associated object related to the target object in the service provider knowledge base corresponding to the target object.
[0135] In an alternative embodiment, the model operation module 704 is further configured to use the artificial intelligence model to analyze the target drainage information corresponding to the first target response content or the second target response content, and add the target drainage information to the first target response content or the second target response content.
[0136] In an alternative embodiment, the device further includes a communication connection module, configured to determine a communication time in response to a communication appointment request sent by the client; the communication appointment request is generated in response to a trigger operation for the target drainage information; establish a communication connection based on the communication time, so that the user corresponding to the client and the service provider corresponding to the object identifier have a conversation based on the communication connection.
[0137] In an optional embodiment, the model operation module 704 is specifically configured to: use the artificial intelligence model to perform risk control detection on the target inquiry information based on the risk control knowledge base, and when the detection passes and at least one associated object related to the target object is determined based on the target inquiry information, combine the second object-related information of the at least one associated object and the target inquiry information to generate a first target response content.
[0138] In an optional embodiment, the model operation module 704 is further configured to use the artificial intelligence model to generate an opening interaction message; the first sending module 703 is specifically configured to send the opening interaction message, the first object-related information, and the inquiry prompt message to the client, so that the client can display the opening interaction message, the first object-related information, and the inquiry prompt message.
[0139] In an optional embodiment, the information acquisition module 702 is specifically configured to acquire the level information of the service provider corresponding to the object identifier; when the level information meets the level requirement, acquire the first object-related information corresponding to the target object based on the object identifier.
[0140] In an optional embodiment, the information acquisition module 702 is further specifically configured to determine whether the service provider corresponding to the object identifier has enabled the interaction function when the level information meets the level requirement; if it is enabled, acquire the first object-related information corresponding to the target object based on the object identifier.
[0141] In an optional embodiment, the information acquisition module 702 is further configured to acquire the detailed information of the target object based on the object identifier when the level information does not meet the level requirement or the service provider has not enabled the interaction function; the first sending module 703 is further configured to send the detailed information of the target object to the client, so that the client can display the detailed information of the target object on the detailed information display interface; the first object-related information of the target object is extracted from the detailed information of the target object.
[0142] In an optional embodiment, the model operation module 704 is further configured to generate a response prompt message using the artificial intelligence model; the response prompt message is used to prompt the user to continue to perform the inquiry operation; the first sending module 703 is further configured to send the first target response content and the response prompt message to the client, so that the client can display the first target response content in the form of a card, and display the response prompt message in text form below the card.
[0143] Figure 7 The described information interaction device can execute Figure 2The information interaction method described in the illustrated embodiment will not be elaborated on in terms of its implementation principle and technical effects. For the various modules and units in the device in the above embodiment, the specific manners of their operations have been described in detail in the embodiment of the method, and will not be elaborated here.
[0144] Figure 8 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 a client and includes: a request generation module 801, configured to generate an information viewing request according to the object identifier of the target object in response to a trigger operation for the target object; a second sending module 802, configured to send the information viewing request to a server so that the server obtains first object-related information corresponding to the target object; a second receiving module 803, configured to receive the first object-related information and an inquiry prompt information sent by the server; a display module 804, configured to display the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt an inquiry operation; an information determination module 805, configured to determine target inquiry information in response to the inquiry operation; the second sending module 802 is further configured to send an inquiry request to the server based on the target inquiry information so that when the server uses an artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information, in combination with second object-related information of the at least one associated object and the target inquiry information, generate a first target response content; the second receiving module 803 is further configured to receive the first target response content sent by the server; the display module 804 is further configured to display the first target response content in the form of a card; the second sending module 802 is further configured to send an operation request to the server in response to a trigger operation for the second object-related information corresponding to the target associated object in the first target response content so that the server performs a processing operation on the target associated object according to the operation type corresponding to the operation request.
[0145] In an optional embodiment, if the first target response content or the second target response content sent by the server contains target drainage information parsed by using an artificial intelligence model, after the display module 804 of the client displays the first target response content or the second target response content containing the target drainage information, a consumer may trigger the target drainage information. At this time, the request generation module 801 is further configured to generate a communication reservation request in response to a trigger operation for the target drainage information; the second sending module 802 is further configured to send the communication reservation request to the server so that the server determines a communication time in response to the communication reservation request sent by the client, and establishes a communication connection based on the communication time, so that the user corresponding to the client and the service provider corresponding to the object identifier have a conversation based on the communication connection.
[0146] In an optional embodiment, the second receiving module 803 is specifically configured to receive the opening interaction information, the first object-related information, and the inquiry prompt information sent by the server; the display module 804 is specifically configured to display the opening interaction information, the first object-related information, and the inquiry prompt information.
[0147] In an optional embodiment, the second receiving module 803 is further configured to receive the detailed information of the target object sent by the server, and the display module 804 is specifically configured to display the detailed information of the target object on the detailed display interface. The detailed information of the target object is obtained by the server based on the object identifier when the level information does not meet the level requirement or the service provider does not enable the interaction function, and in this embodiment, the first object-related information of the target object is extracted from the detailed information of the target object.
[0148] In an optional embodiment, the second receiving module 803 is specifically configured to receive the first target response content and the response prompt information sent by the server; the display module 804 is specifically configured to display the first target response content in the form of a card, and display the response prompt information in text form below the card.
[0149] Figure 8 The information interaction device described above can execute Figure 5 the information interaction method described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated. For each module and unit in the device 8 in the above embodiments, the specific manner of performing operations has been described in detail in the embodiments related to the method, and will not be elaborated here.
[0150] Figure 9 FIG. is a schematic structural diagram of an embodiment of a computing device provided by the present application. As Figure 9 shown, in practice, the computing device may include: a storage component 901 and a processing component 902.
[0151] 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 these data include instructions for any application program or method operating on the computing device, data structures, contact data, phone book data, messages, pictures, videos, etc.
[0152] The processing component 902 is coupled to the storage component 901 and is configured to execute the computer programs in the storage component 901 to implement the information interaction method as Figure 2 or Figure 5 shown.
[0153] Further, as Figure 9As shown, the computing device may further include: a communication component 903, a display component 904, a power supply component 905, an audio component 906, and other components. Figure 9 Only some components are schematically shown, which does not mean that the computing device only includes Figure 9 the components shown. Additionally, Figure 9 the components within the dashed box are optional components, rather than mandatory components, and are specifically determined according to the product form of the computing device. The computing device in this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT (Internet of Things) device, or can also be a server device such as a conventional server, a cloud server, or a server array. If the computing device in this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, or a smart phone, it may include Figure 9 the components within the dashed box; if the computing device in this embodiment is implemented as a server device such as a conventional server, a cloud server, or a server array, it may not include Figure 9 the components within the dashed box.
[0154] The above 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.
[0155] 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, a magnetic disk, or an optical disc.
[0156] The above communication component is configured to facilitate communication, in a wired or wireless manner, 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.
[0157] 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.
[0158] The above power supply component provides power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device where the power supply component is located.
[0159] 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 sent via the communication component. In some embodiments, the audio component further includes a speaker for outputting audio signals.
[0160] 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 embodiment. 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
[0161] Accordingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instruction, and when the computer program or instruction is executed by a processor, enables the processor to implement the steps in the above method embodiment. 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 embodiment.
[0162] 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 elaborated herein.
[0163] It should also be noted that the terms "comprises", "comprising" or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or 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.
[0164] 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: Receiving an information viewing request sent by the client for a target object; the information viewing request includes the object identifier of the target object; Based on the object identifier, obtaining first object-related information corresponding to the target object; Sending the first object-related information and an inquiry prompt message to the client, so that the client can display the first object-related information and the inquiry prompt message; the inquiry prompt message is used to prompt the execution of an inquiry operation; Receiving an inquiry request sent by the client; the inquiry request includes target inquiry information; the target inquiry information is determined by the client in response to the inquiry operation; When using an artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information, combining the second object-related information of the at least one associated object and the target inquiry information to generate a first target response content; Sending the first target response content to the client, so that the client can display the first target response content in the form of a card; Receiving an operation request sent by the client; the operation request is generated by the client in response to a trigger operation on the second object-related information corresponding to the target associated object; Performing a processing operation on the target associated object according to the operation type corresponding to the operation request.
2. The method according to claim 1, wherein It also includes: Obtaining at least one associated inquiry information corresponding to the target object and using the at least one associated inquiry information as the inquiry prompt message; The target inquiry information is specifically determined by the client in response to a selection operation on the at least one associated inquiry information.
3. The method according to claim 2, wherein It also includes: Determining the industry category corresponding to the target object; Using the artificial intelligence model to search the inquiry knowledge base for at least one preset inquiry information corresponding to the target industry category, and respectively generating at least one associated inquiry information corresponding to the target object for the at least one preset inquiry information.
4. The method according to claim 1, characterized in that It also includes: When using the artificial intelligence model to determine that there are no at least one associated objects related to the target object based on the target inquiry information, combining the object details information corresponding to the target object and the target inquiry information to generate a second target response content; Sending the second target response content to the client, so that the client can display the second target response content in text form.
5. The method according to claim 1 or 4, characterized in that, It also includes: Using the artificial intelligence model to parse the inquiry category corresponding to the target inquiry information, and based on the inquiry category, determining whether there are at least one associated objects related to the target object in the service provider knowledge base corresponding to the target object.
6. The method according to claim 1 or 4, characterized in that, It also includes: Using the artificial intelligence model to parse the target drainage information corresponding to the first target response content or the second target response content, and adding the target drainage information to the first target response content or the second target response content.
7. The method according to claim 6, characterized in that It also includes: Responding to a communication appointment request sent by the client to determine the communication time; The communication appointment request is generated in response to a trigger operation on the target drainage information; Establish a communication connection based on the communication time so that the client user can have a conversation with the service provider corresponding to the object identifier based on the communication connection.
8. The method according to claim 1, wherein When using the artificial intelligence model to determine at least one associated object related to the target object based on the target inquiry information, the first target response content is generated by combining the second object-related information of the at least one associated object and the target inquiry information, including: Using the artificial intelligence model, based on the risk control knowledge base, perform risk control detection on the target inquiry information. When the detection passes and at least one associated object related to the target object is determined based on the target inquiry information, combine the second object-related information of the at least one associated object and the target inquiry information to generate the first target response content.
9. The method according to claim 1, characterized in that, It also includes: Using the artificial intelligence model to generate opening interaction information; Sending the first object-related information and inquiry prompt information to the client so that the client can display the first object-related information and the inquiry prompt information, including: Sending the opening interaction information, the first object-related information, and the inquiry prompt information to the client so that the client can display the opening interaction information, the first object-related information, and the inquiry prompt information.
10. The method according to claim 1, characterized in that, The obtaining of the first object-related information corresponding to the target object based on the object identifier includes: Obtaining the level information of the service provider corresponding to the object identifier; When the level information meets the level requirements, obtain the first object-related information corresponding to the target object based on the object identifier.
11. The method according to claim 10, characterized in that, The obtaining of the first object-related information corresponding to the target object based on the object identifier when the level information meets the level requirements includes: When the level information meets the level requirements, determine whether the service provider corresponding to the object identifier has enabled the interaction function; If it is enabled, obtain the first object-related information corresponding to the target object based on the object identifier.
12. The method according to claim 10 or 11, characterized in that, After receiving the information viewing request sent by the client for the target object, it also includes: When the level information does not meet the level requirements or the service provider has not enabled the interaction function, obtain the detailed information of the target object based on the object identifier; Send the detailed information of the target object to the client so that the client can display the detailed information of the target object on the detailed display interface; the first object-related information of the target object is extracted from the detailed information of the target object.
13. The method according to claim 1, characterized in that It also includes: Using the artificial intelligence model to generate response prompt information; The response prompt information is used to prompt the user to continue performing the inquiry operation; The sending of the first target response content to the client so that the client can display the first target response content in the form of a card includes: Sending the first target response content and the response prompt information to the client so that the client can display the first target response content in the form of a card and display the response prompt information in text form below the card.
14. An information interaction method, characterized in that, Applied to the client, including: In response to a trigger operation for a target object, generate an information viewing request according to the object identifier of the target object; Send the information viewing request to the server so that the server can obtain the first object-related information corresponding to the target object; Receive the first object-related information and inquiry prompt information sent by the server; Display the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt the execution of an inquiry operation; In response to the inquiry operation, determine the target inquiry information; Based on the target inquiry information, send an inquiry request to the server so that the server can use an artificial intelligence model to determine at least one associated object related to the target object, and combine the second object-related information of the at least one associated object and the target inquiry information to generate a first target response content; Receive the first target response content sent by the server; Display the first target response content in the form of a card; In response to a trigger operation for the second object-related information corresponding to the target associated object in the first target response content, send an operation request to the server so that the server can perform a processing operation on the target associated object according to the operation type corresponding to the operation request.
15. An information interaction device, characterized in that, Configured in the server, including: A first receiving module, configured to receive an information viewing request sent by the client for a target object; the information viewing request includes the object identifier of the target object; An information acquisition module, configured to obtain the first object-related information corresponding to the target object based on the object identifier; A first sending module, configured to send the first object-related information and the inquiry prompt information to the client so that the client can display the first object-related information and the inquiry prompt information; the inquiry prompt information is used to prompt the execution of an inquiry operation; The first receiving module is further configured to receive the inquiry request sent by the client; the inquiry request includes the target inquiry information; the target inquiry information is determined by the client in response to the inquiry operation; A model operation module, configured to use an artificial intelligence model to determine at least one associated object related to the target object, and combine the second object-related information of the at least one associated object and the target inquiry information to generate a first target response content; The first sending module is further configured to send the first target response content to the client so that the client can display the first target response content in the form of a card; The first receiving module is further configured to receive the operation request sent by the client; the operation request is generated by the client in response to a trigger operation for the second object-related information corresponding to the target associated object; An operation execution module, configured to perform a processing operation on the target associated object according to the operation type corresponding to the operation request.
16. An information interaction device, characterized in that, Configured in the client, including: A request generation module, configured to generate an information viewing request according to the object identifier of the target object in response to a trigger operation for the target object; A second sending module, configured to send the information viewing request to a server, so that the server obtains first object-related information corresponding to the target object; A second receiving module, configured to receive the first object-related information and an inquiry prompt message sent by the server; A display module, configured to display the first object-related information and the inquiry prompt message; the inquiry prompt message is used to prompt an inquiry operation; An information determination module, configured to determine target inquiry information in response to the inquiry operation; The second sending module is further configured to send an inquiry request to the server based on the target inquiry information, so that when the server uses an artificial intelligence model to determine at least one associated object related to the target object, in combination with second object-related information of the at least one associated object and the target inquiry information, generate a first target response content; The second receiving module is further configured to receive the first target response content sent by the server; The display module is further configured to display the first target response content in a card form; The second sending module is further configured to, in response to a trigger operation on the second object-related information corresponding to a target associated object in the first target response content, send an operation request to the server, so that the server performs a processing operation on the target associated object according to the operation type corresponding to the operation request.
17. A computing device, characterized in that, Comprising 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 1-14.
18. 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 1-14 is implemented.
19. A computer program product, characterized in that, Comprising 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 1-14 is implemented.
Citation Information
Cited By
Interaction method and device, equipment and medium
CN121658133A