Method and device for providing commodity evaluation information and electronic equipment
By using AI generative models to generate user evaluation cards during customer service, it solves the problem that consumers find it difficult to efficiently obtain product evaluation information, and realizes efficient information transmission and decision support in pre-purchase decisions.
Patent Information
- Application Number
- CN202510361561.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-25
- Publication Date
- 2025-08-01
AI Technical Summary
In the prior art, it is difficult for consumers to efficiently obtain user evaluation information of products when making decisions before purchase. Especially in certain product categories such as pharmaceutical categories, users have a low willingness to actively view product evaluation content through the product details page, which makes it difficult for users to effectively help decision-making.
During the customer service process, user evaluation cards are generated through artificial intelligence AI generative model, including feature tags and representative evaluation details, and sent to consultant users through messages to provide product evaluation information.
It improves the efficiency of users to obtain product evaluation information, enhances the effectiveness of pre-purchase decisions, and reaches user evaluation content through multiple channels, improving the convenience and comprehensiveness of information acquisition.
Smart Images
Figure CN120410663A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of information processing, and particularly to a method, an apparatus, and an electronic device for providing product evaluation information. Background Art
[0002] In a product information service system (also known as an e-commerce platform, etc., which can provide information services in all or part of the links such as product release, display, and transaction), before purchasing a product, a consumer user may need to obtain product information from multiple aspects, including product details, price, specifications, etc. In addition, there are also multiple channels for consumer users to obtain information, including browsing the information in the product details page, or communicating with customer service staff, including asking about details of preferential activities, size recommendation information, etc.
[0003] Although the prior art has provided multiple channels for consumer users to obtain product information, how to further assist users in making pre-purchase decisions has always been the focus of attention of those skilled in the art. Summary of the Invention
[0004] The present application provides a method, an apparatus, and an electronic device for providing product evaluation information, which can improve the efficiency of users in obtaining information and assist users in making pre-purchase decisions.
[0005] The present application provides the following solutions:
[0006] A method for providing product evaluation information, comprising:
[0007] In an interface for providing consultation services, providing an operation option for generating a user evaluation card for an associated product of the consultation service;
[0008] In response to an operation request submitted by a customer service provider through the operation option, generating a first prompt message according to the product identifier of the associated product, and invoking an artificial intelligence AI generative model according to the first prompt message, so that the AI generative model generates target information according to multiple pieces of user evaluation detail content of the associated product, the target information including: at least one feature tag, and at least one piece of representative user evaluation detail content corresponding to the feature tag; the feature tag is a general text content obtained by classifying multiple pieces of user evaluation detail content of the associated product and summarizing the user evaluation detail content of the same class;
[0009] Generating a user evaluation card according to the target information and a preset format template, so as to send the user evaluation card of the associated product to the current consulting user side for display by sending a conversation message during the process of providing the consultation service.
[0010] Among them, it further includes:
[0011] Provide the target information generated by the AI generative model to the customer service provider for confirmation, and provide operation options for editing the target information, so that the customer service provider can adjust the text, order of the feature tags, and / or the order of the corresponding representative user evaluation detail content.
[0012] Among them, the target information generated by the AI generative model further includes: the representative user evaluation detail content ranked first determined by the AI generative model for the feature tag;
[0013] The operation options for editing the target information include: operation options for designating other representative user evaluation detail content as the first.
[0014] Among them, when displaying the user evaluation card to the current inquirer user side, the user evaluation card includes at least one label option and a shared user evaluation detail content display area. The at least one label option corresponds to the at least one feature tag and is used to display the text of the feature tag; the shared user evaluation detail content display area is used to display the representative user evaluation detail content ranked first corresponding to the feature tag of the currently selected label option, and provide operation options for displaying more representative user evaluation detail content.
[0015] Among them, the label option is further used to display the number of users who mentioned the corresponding feature tag in the user evaluation detail content.
[0016] Among them, before providing the operation options for generating the user evaluation card, it further includes:
[0017] Generate second prompt information according to the product identifier of the associated product and a preset second prompt information template, and call the AI generative model according to the second prompt information, so that the AI generative model obtains the user evaluation detail content of the associated product, and judges whether the associated product meets the conditions for generating the user evaluation card according to the user evaluation detail content. If it meets the conditions, trigger the step of providing the operation options for generating the user evaluation card.
[0018] A device for providing product evaluation information, including:
[0019] An operation option providing unit, configured to provide operation options for generating a user evaluation card for an associated product of the consultation service in an interface for providing consultation services;
[0020] A target information generation unit, configured to, in response to an operation request submitted by a customer service provider through the operation option, generate a first prompt message according to the product identifier of the associated product, and call an artificial intelligence AI generative model according to the first prompt message, so that the AI generative model generates target information according to multiple pieces of user evaluation details of the associated product. The target information includes: at least one feature tag, and at least one representative piece of user evaluation details corresponding to the feature tag; the feature tag is a general text content obtained by classifying multiple pieces of user evaluation details of the associated product and summarizing the user evaluation details of the same class.
[0021] A user evaluation card generation unit, configured to generate a user evaluation card according to the target information and a preset format template, so as to send the user evaluation card of the associated product to the current inquiring user side for display by sending a conversation message during the process of providing the consultation service.
[0022] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in any one of the foregoing are implemented.
[0023] An electronic device, comprising:
[0024] One or more processors; and
[0025] A memory associated with the one or more processors, the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, the steps of the method described in any one of the foregoing are executed.
[0026] A computer program product, comprising computer programs / computer-executable instructions, and when the computer programs / computer-executable instructions are executed by a processor in an electronic device, the steps of the method described in any one of the foregoing are implemented.
[0027] According to the specific embodiments provided in the present application, the following technical effects are disclosed in the present application:
[0028] Through the embodiments of the present application, during the process of providing consulting services to inquirers, an operation option for generating a user evaluation card for associated products of the consulting service can be provided; after the customer service provider submits an operation request through the operation option, a first prompt message can be generated according to the product identifier of the associated product, and an artificial intelligence AI generative model can be called according to the first prompt message, so that the AI generative model generates target information according to multiple pieces of user evaluation details of the associated product. Among them, the specific target information may include: at least one feature label, and at least one representative piece of user evaluation details corresponding to the feature label; the feature label is a general text content obtained by classifying multiple pieces of user evaluation details of the associated product and summarizing the user evaluation details of the same category. Then, a user evaluation card can be generated according to the target information and a preset format template, so as to send the user evaluation card of the associated product to the current inquirer user side for display by sending a conversation message during the process of providing the consulting service. In this way, during the process of providing consulting services, relevant user evaluation information of products can be provided to inquirer users by sending messages, so that the relevant user evaluation information can reach users through more channels and play a more effective role in helping users make pre-purchase decisions and other aspects. In addition, since multiple pieces of user evaluation details of a product can be classified to summarize feature labels, and such feature labels and representative pieces of user evaluation details are provided in the user evaluation card, the efficiency of users obtaining information can be further improved.
[0029] Of course, it is not necessary for any product implementing the present application to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.
[0031] Figure 1 It is a schematic diagram of the system architecture provided by the embodiments of the present application;
[0032] Figure 2 It is a flowchart of the method provided by the embodiments of the present application;
[0033] Figures 3 to 5 It is a schematic diagram of the interface provided by the embodiments of the present application;
[0034] Figure 6It is a schematic diagram of the device provided by the embodiment of the present application;
[0035] Figure 7 It is a schematic diagram of the electronic device provided by the embodiment of the present application. Detailed implementation manners
[0036] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.
[0037] First of all, it should be noted that the inventors of the present application found in the process of implementing the present application that the user evaluation content of a commodity is an important reference information during the process of consumers purchasing commodities. The so-called user evaluation content is the evaluation content made by other users who have already purchased a certain commodity for that commodity, including the comprehensive evaluation level (good review, medium review, bad review, etc.) under the standardized evaluation system given by the system, the evaluation stars of multiple evaluation items (items such as logistics, description, service, etc., and five stars, four stars, etc. can be selected, and the more stars, the better the evaluation), and in addition, specific usage feelings, experiences and other text contents can be input, and photos, videos, etc. can be uploaded. These user evaluation contents reflect the relatively real evaluations made by users after receiving the physical commodity. Therefore, it can help users make pre-purchase decisions, and commodities with more good reviews are more likely to be selected.
[0038] Regarding the detailed content of the user evaluation of a commodity, in the prior art, a corresponding viewing entry can usually be provided on the commodity detail page, and users can click through this entry to view the detailed content of the user evaluation. Some systems may consider that the number of user evaluation entries of a commodity may be very large, affecting the viewing efficiency of users and other situations, and can use an AI (Artificial Intelligence) generative model to summarize the detailed content of the user evaluation of the commodity, and display it at the forefront of the detailed content of the user evaluation, etc. Users can get an overall impression of the user evaluation situation of the commodity by viewing the content summarized by AI, saving the time of users.
[0039] By leveraging the capabilities of AI generative models, it is possible to help users improve the efficiency of obtaining product review content. However, users still need to enter the product details page and click on the review option before they can view it, and the display path is relatively single. However, for some special categories of products (such as pharmaceuticals, etc.), users may have a relatively low willingness to actively view product review content through the product details page, and thus have few opportunities to view the summary results of the AI generative model. As a result, the user review content of the product is difficult to play its due role in helping users make pre-purchase decisions.
[0040] In response to the above situation, the embodiments of the present application provide corresponding solutions. In this solution, during the process of providing customer consultation services to consumer users, a user review card of the product can be generated based on the user review content of the product and sent to the consumer user in the form of a message. In this way, the user review content of the product can reach the consumer user through the message, and thus the product review content can play a more effective role in helping users make pre-purchase decisions and other aspects.
[0041] Specifically, in implementation, during the process of providing consultation services to users by the customer service provider (such as the platform party or the customer service staff of the seller, etc.), an operation option for generating a user review card for the associated product can be provided in the user interface of the customer service provider. When the customer service provider deems it necessary, a specific generation request can be submitted through this operation option. After that, the target information for generating the user review card can be obtained to generate the user review card according to a certain format template. Regarding the above target information, it can specifically include at least one feature label and at least one representative user review detail content corresponding to the feature label. Regarding the feature label, it can specifically be a general text content obtained by classifying multiple user review detail contents of the associated product and summarizing the user review detail contents of the same category, such as high cost performance, fast delivery speed, etc. In addition, there can be at least one user review detail content corresponding to each feature label. For example, under the label of "high cost performance", the details of how the user specifically evaluates can be displayed, etc.
[0042] Regarding the target information specifically used to generate user evaluation cards, it can be obtained in various ways. For example, in one way, it can be manually input by customer service providers. Or, it can also be generated through an AI generative model. Or, it can also be a combination of the generation by the AI generative model and the manual input of customer service providers. For example, in the third case, the AI generative model can first reason about the details of multiple user evaluations of the product, generate multiple feature tags, and assign at least one representative user evaluation detail content to each feature tag. It can also designate one of the user evaluation detail contents as the first to be displayed, and so on. After that, the generation results of the AI generative model can be provided to the customer service provider, and the customer service provider can adjust the sorting of the feature tags, the text, the sorting of the user evaluation detail contents under each feature tag, etc. When adjusting the sorting of the user evaluation detail contents, etc., it can include re-designating other user evaluation detail contents as the first to be displayed, and so on.
[0043] After determining the target information, a specific evaluation card can be generated according to a pre-set format template. Then, under the trigger of the customer service provider clicking the "send" button or the like, the user evaluation card can be provided to the inquiring user by sending a message to the inquiring user. In this way, during the process of providing consulting services to the inquiring user, information about the user evaluation card can be additionally provided to the inquiring user, so that the consulting service also becomes a channel for revealing content related to user evaluations. Users can obtain information related to the user evaluation content of the product without having to enter the product detail page.
[0044] From the perspective of the system architecture, the embodiments of the present application can provide corresponding services in the customer service system related to the product information service system. See Figure 1, the customer service system can provide a workbench for customer service providers. After a consumer user initiates a consultation service request for a certain product through their client, the server can assign the consultation service task to a specific customer service provider. The customer service provider can then receive the consultation service task initiated by the inquirer through their workbench and communicate with the inquirer through a dialog box provided in the workbench interface to answer questions raised by the inquirer user, etc. During this process, an operation option for generating a user evaluation card for the associated product of the consultation service can be provided in the above workbench interface. It should be noted here that in specific implementation, the specific product evaluation card can mainly display the positive user evaluation content obtained by the product. If the user evaluation content associated with a certain product is relatively small or mainly negative, it belongs to the situation where it is not suitable to generate a user evaluation card. Therefore, before providing the above operation option for generating a user evaluation card, the AI generative model can also be used to judge the user evaluation details content of the product to determine whether it is suitable to generate a user evaluation card. If it is suitable, then provide the above operation option for generating a user evaluation card.
[0045] If the customer service provider clicks on this operation option, the workbench server can obtain the target information for generating the user evaluation card, including generating the target information by the AI generative model, or manually inputting the target information by the customer service provider, or a combination of both. That is, after the AI generative model generates the target information, it is sent to the customer service provider for confirmation, and the target information can also be edited during this period. After the customer service provider confirms the sending of the user evaluation card, the workbench server can generate the user evaluation card for providing the user evaluation card to the inquirer user's client in the form of sending a message.
[0046] The following provides a detailed introduction to the specific implementation solutions provided by the embodiments of the present application.
[0047] First, from the perspective of the above workbench for customer service providers, the embodiments of the present application provide a method for providing product evaluation information. See Figure 2 , this method may include:
[0048] S201: In the interface for providing consultation services, provide an operation option for generating a user evaluation card for the associated product of the consultation service.
[0049] Among them, the interface for providing consulting services can be the working interface of the workbench for customer service providers. The customer service provider can have a conversation with the inquirer through this interface. Specifically, the inquirer usually initiates a consultation for a specific product. That is to say, there is an associated product for a specific consultation request. The specific content of the consultation can include the price of the product, information about promotional activities participated in, logistics information, and so on. Of course, other auxiliary information can also be provided in this interface. In the embodiment of the present application, an operation option for generating a user evaluation card for the associated product of the consulting service can be provided in the above workbench interface. For example, as Figure 3 shown, it is a schematic diagram of the workbench interface in an example. The "good review card" shown at 31 is the above operation option provided in the embodiment of the present application. The customer service provider can initiate the process of generating a user evaluation card by clicking on this operation option.
[0050] It should be noted here that in specific implementation, as described above, some products may not be suitable for generating a user evaluation card and sending it to the inquiring user in the manner provided by the embodiment of the present application due to reasons such as being new products, resulting in too little user evaluation details or mostly negative evaluations. Therefore, in specific implementation, a judgment can also be made before specifically providing the above operation option to determine whether the product associated with the current consultation request is suitable for generating a user evaluation card.
[0051] Among them, the specific judgment process can be completed through an AI generative model. For example, in specific implementation, first, prompt information can be generated according to the product identifier of the product associated with the current consultation request and a preset prompt information template (to distinguish it from the prompt information template used in the subsequent specific card generation process, this is called the "second prompt information template" here, and correspondingly, the generated prompt information can be called "second prompt information"). Among them, the prompt information is also called Prompt, and its main function is to provide the context of the input information, generation tasks, etc. for the AI generative model. After that, the AI generative model can be called according to the above second prompt information, so that the AI generative model obtains the user evaluation details of the associated product and judges whether the associated product meets the conditions for generating a user evaluation card according to the user evaluation details. If the judgment result of the AI generative model is yes, the step of providing an operation option for generating a user evaluation card can be triggered.
[0052] Among them, the so-called AI generative model refers to a deep learning model containing a large number of parameters. Because of its huge parameter scale, this AI generative model can store and process a large amount of information, thus achieving higher performance in various tasks. The embodiment of the present application can utilize the capabilities of this AI generative model to complete the judgment and subsequent user evaluation card generation tasks.
[0053] S202: In response to an operation request submitted by the customer service provider through the operation option, generate first prompt information based on the product identifier of the associated product, and call an AI generative model according to the first prompt information, so that the AI generative model generates target information based on multiple pieces of user evaluation details of the associated product. The target information includes: at least one feature tag, and at least one representative piece of user evaluation details corresponding to the feature tag; the feature tag is general text content obtained by classifying multiple pieces of user evaluation details of the associated product and summarizing the user evaluation details of the same class.
[0054] In the case where the above operation option is provided, the customer service provider can initiate a request to generate a user evaluation card by clicking on the operation option or other means. After that, the workbench server can obtain the target information for generating the user evaluation card. Among them, in the embodiments of the present application, the above target information may specifically include at least one feature tag, and at least one representative piece of user evaluation details corresponding to the feature tag. Among them, the specific feature tag may be general text content obtained by classifying multiple pieces of user evaluation details of the associated product and summarizing the user evaluation details of the same class.
[0055] In one specific implementation manner, the customer service provider can browse the user evaluation details of the specific associated product by himself / herself, classify and summarize them to obtain multiple feature tags. The workbench can then provide an operation interface for the customer service provider to input the feature tags and specify the representative user evaluation details. After that, the server can obtain the specific target information for generating the user evaluation card according to the input result of the customer service provider for generating the user evaluation card.
[0056] In another way, the multimodal information understanding and content generation capabilities of the AI generative model can also be used to assist in the generation of target information. In specific implementation, the first prompt information can be generated based on the product identifier of the related product of the current consultation request and the preset first prompt information template, and the artificial intelligence AI generative model can be called according to the first prompt information, so that the AI generative model obtains multiple user evaluation details of the related products, and generates the target information based on the multiple user evaluation details. In other words, the task of the AI generative model in the first prompt information can be to understand and reason about the multiple user evaluation details of the product, classify the user evaluation details, and generate the aforementioned feature labels. It can also determine representative user evaluation details for specific feature labels, and so on. Specifically, after determining the representative user evaluation details, it can also designate one of the representative user evaluation details as the first display, and so on.
[0057] In specific implementations, after the target information is generated by the AI generative model, it can be confirmed by the customer service provider. If the customer service provider deems it inappropriate, it can also be adjusted. In other words, the target information generated by the AI generative model can be provided to the customer service provider for confirmation, and an operation option for editing the target information can be provided, so that the customer service provider can adjust the text and order of the feature tags and / or the order of the corresponding representative user review details.
[0058] If the target information generated by the AI generative model includes the representative user review details ranked first as determined by the AI generative model for the feature tag, the specific operation options for editing the target information include: an operation option for designating other representative user review details as the first.
[0059] For example, after the AI generative model generates target information, the workbench interface can be displayed as follows: Figure 4As shown, the target information generated by the AI generative model for the current associated product is shown at 41. It can be seen that the feature tags include "repair skin", "high satisfaction", "high cost performance", "delivery speed", "arrival speed", and so on. Among them, each feature tag can include multiple representative user evaluation details, and one of them is set as the first by the AI generative model. After these information are provided to the customer service provider, the customer service provider can adjust the text, order, etc. of the feature tags, and can also adjust the order of each representative user evaluation detail under the specific feature tag, and so on. Among them, when adjusting the order of the representative user evaluation details, it can be to set another representative user evaluation detail as the first, and so on.
[0060] S203: Generate a user evaluation card according to the target information and a preset format template, so as to send the user evaluation card of the associated product to the current inquiring user side for display by sending a conversation message during the provision of the consultation service.
[0061] After obtaining the target information for generating the user evaluation card, the user evaluation card can be generated according to the target information and a preset format template. Specifically, there can be various specific display styles for the user evaluation card. For example, in one specific way, a specific user evaluation card can include at least one label option and a shared display area for user evaluation details. Among them, the above at least one label option corresponds to at least one feature tag, that is, the number of generated feature tags determines the number of label options provided in the card, and each label option is used to display the text of a feature tag; the shared display area for user evaluation details can be used to display the first representative user evaluation detail corresponding to the feature tag of the currently selected label option, and an operation option for displaying more representative user evaluation details can also be provided.
[0062] For example, as Figure 5As shown, it shows a specific display style of a user evaluation card. Among them, the area shown at 51 is the label option display area, where 4 label options are shown, corresponding to 4 feature labels, and the text of each feature label is shown respectively. Of course, more label options can also be viewed through the left and right arrows. The area shown at 52 is the display area for the details of user evaluations. Since the currently selected label option is "Repair skin", the content shown in this area is the representative user evaluation details content that is set as the first under the feature label of "Repair skin". Among them, when showing this representative user evaluation details content, not only the text content in the evaluation details can be shown, but also the picture content in the evaluation details can be shown, and so on. In addition, users can click on options such as "More real evaluations" below to view more representative user evaluation details content under the corresponding category of this feature label.
[0063] In an optional way, the specific label options can also be used to show the number of users who mention the corresponding feature label in the user evaluation details content. For example, in the example shown as Figure 5 shown, information such as "**User mentions" corresponding to each feature label can also be shown on the specific label options.
[0064] In summary, through the embodiments of the present application, during the process of providing consulting services to inquirers, an operation option for generating a user evaluation card for the associated products of the consulting services can be provided; after the customer service provider submits an operation request through the operation option, a first prompt message can be generated according to the product identifier of the associated product, and an artificial intelligence AI generative model can be called according to the first prompt message, so that the AI generative model generates target information according to multiple pieces of user evaluation details of the associated product. Among them, the specific target information may include: at least one feature tag, and at least one representative piece of user evaluation details corresponding to the feature tag; the feature tag is a general text content obtained by classifying multiple pieces of user evaluation details of the associated product and summarizing the user evaluation details of the same class. Then, a user evaluation card can be generated according to the target information and a preset format template, so that during the process of providing the consulting service, the user evaluation card of the associated product can be sent to the current inquirer user side for display by sending a conversation message. In this way, during the process of providing consulting services, relevant information about user evaluations of products can be provided to inquirer users by sending messages, so that the relevant information about user evaluations can reach more users and play a more effective role in helping users make pre-purchase decisions and other aspects. In addition, since multiple pieces of user evaluation details of a product can be classified to summarize feature tags, and such feature tags and representative pieces of user evaluation details are provided in the user evaluation card, the efficiency of users obtaining information can be further improved.
[0065] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the solutions described in this article within the scope permitted by applicable laws and regulations, provided that the requirements of applicable laws and regulations in the country of residence are met (for example, users clearly consent, and users are effectively notified, etc.).
[0066] Corresponding to the foregoing method embodiments, the embodiments of the present application further provide a device for providing product evaluation information. See Figure 6 , the device may include:
[0067] An operation option providing unit 601, configured to provide an operation option for generating a user evaluation card for an associated product of the consulting service in an interface for providing consulting services;
[0068] A target information generation unit 602, configured to, in response to an operation request submitted by a customer service provider through the operation option, generate a first prompt message according to the product identifier of the associated product, and call an artificial intelligence (AI) generative model according to the first prompt message, so that the AI generative model generates target information according to multiple pieces of user evaluation detail content of the associated product. The target information includes: at least one feature label, and at least one piece of representative user evaluation detail content corresponding to the feature label; the feature label is a general text content obtained by classifying multiple pieces of user evaluation detail content of the associated product and summarizing the user evaluation detail content of the same class.
[0069] A user evaluation card generation unit 603, configured to generate a user evaluation card according to the target information and a preset format template, so as to send the user evaluation card of the associated product to the current inquiring user side for display by sending a conversation message during the provision of the consultation service.
[0070] Specifically, the device may further include:
[0071] An information confirmation unit, configured to provide the target information generated by the AI generative model to the customer service provider for confirmation, and provide an operation option for editing the target information, so that the customer service provider can adjust the text, order, and / or the order of the corresponding representative user evaluation detail content of the feature label.
[0072] Wherein, the target information generated by the AI generative model further includes: the representative user evaluation detail content ranked first determined by the AI generative model for the feature label.
[0073] The operation option for editing the target information includes: an operation option for designating other representative user evaluation detail content as the first.
[0074] Specifically, when displaying the user evaluation card to the current inquiring user side, the user evaluation card may include at least one label option and a shared user evaluation detail content display area. The at least one label option corresponds to the at least one feature label and is used to display the text of the feature label; the shared user evaluation detail content display area is used to display the representative user evaluation detail content ranked first corresponding to the feature label of the currently selected label option, and provide an operation option for expanding and displaying more representative user evaluation detail content.
[0075] In specific implementation, the tag option is also used to display the number of users who mention the corresponding feature tag in the user evaluation details content.
[0076] In addition, the device may further include:
[0077] A judgment unit, configured to generate second prompt information according to the product identifier of the associated product and a preset second prompt information template before providing an operation option for generating a user evaluation card, and call an AI generative model according to the second prompt information, so that the AI generative model obtains the user evaluation details content of the associated product, and determines whether the associated product meets the condition for generating the user evaluation card according to the user evaluation details content. If it meets the condition, the step of providing the operation option for generating the user evaluation card is triggered.
[0078] In addition, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in any one of the foregoing method embodiments are implemented.
[0079] And an electronic device, including:
[0080]
[0081] One or more processors; and
[0082] A memory associated with the one or more processors, the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, the steps of the method described in any one of the foregoing method embodiments are executed.
[0083] Wherein, Figure 7 An exemplary architecture of the electronic device is shown, which may specifically include a processor 710, a video display adapter 711, a disk drive 712, an input / output interface 713, a network interface 714, and a memory 720. The above-mentioned processor 710, video display adapter 711, disk drive 712, input / output interface 713, network interface 714, and memory 720 can be communicatively connected through a communication bus 730.
[0084] Among them, the processor 710 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in this application.
[0085] The memory 720 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 720 can store an operating system 721 for controlling the operation of the electronic device 700, and a basic input / output system (BIOS) for controlling the low-level operations of the electronic device 700. In addition, a web browser 723, a data storage management system 724, a product evaluation information processing system 725, etc. can also be stored. The above-mentioned product evaluation information processing system 725 can be the application program that specifically implements the operations of the foregoing steps in the embodiments of this application. In short, when implementing the technical solutions provided in this application through software or firmware, the relevant program codes are stored in the memory 720 and called and executed by the processor 710.
[0086] The input / output interface 713 is used to connect to an input / output module to implement information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.
[0087] The network interface 714 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module can implement communication in a wired manner (such as USB, network cable, etc.) or in a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).
[0088] The bus 730 includes a path for transmitting information between various components of the device (such as the processor 710, the video display adapter 711, the disk drive 712, the input / output interface 713, the network interface 714, and the memory 720).
[0089] It should be noted that although the above device only shows a processor 710, a video display adapter 711, a disk drive 712, an input / output interface 713, a network interface 714, a memory 720, a bus 730, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary for implementing the solution of the present application, and does not necessarily include all the components shown in the figure.
[0090] From the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present application.
[0091] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for a system or a system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The systems and system embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.
[0092] The above provides a detailed introduction to the method, device, and electronic device for providing commodity evaluation information of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.
Claims
1. A method for providing product evaluation information, characterized in that, Including: In an interface for providing consulting services, providing an operation option for generating a user evaluation card for associated products of the consulting service; In response to an operation request submitted by a customer service provider through the operation option, generating a first prompt message according to the product identifier of the associated product, and invoking an AI generative model according to the first prompt message, so that the AI generative model generates target information according to multiple pieces of user evaluation detail content of the associated product. The target information includes: at least one feature tag, and at least one piece of representative user evaluation detail content corresponding to the feature tag; the feature tag is a general text content obtained by classifying multiple pieces of user evaluation detail content of the associated product and summarizing the user evaluation detail content of the same class; Generating a user evaluation card according to the target information and a preset format template, so as to send the user evaluation card of the associated product to the current consulting user side for display by sending a conversation message during the process of providing the consulting service.
2. The method according to claim 1, wherein Further including: Providing the target information generated by the AI generative model to the customer service provider for confirmation, and providing an operation option for editing the target information, so that the customer service provider can adjust the text, order and / or the order of the corresponding representative user evaluation detail content of the feature tag.
3. The method according to claim 2, wherein The target information generated by the AI generative model further includes: the representative user evaluation detail content ranked first determined by the AI generative model for the feature tag; The operation option for editing the target information includes: an operation option for designating other representative user evaluation detail content as the first one.
4. The method according to claim 3, wherein When displaying the user evaluation card to the current consulting user side, the user evaluation card includes at least one tag option and a shared user evaluation detail content display area. The at least one tag option corresponds to the at least one feature tag and is used to display the text of the feature tag; the shared user evaluation detail content display area is used to display the representative user evaluation detail content ranked first corresponding to the feature tag of the currently selected tag option, and provides an operation option for displaying more representative user evaluation detail content.
5. The method according to claim 4, wherein The tag option is further used to display the number of users who mention the corresponding feature tag in the user evaluation detail content.
6. The method according to claim 1, wherein Before providing the operation option for generating the user evaluation card, further including: Generate a second prompt message based on the product identifier of the associated product and a preset second prompt message template, and call an AI generative model according to the second prompt message, so that the AI generative model obtains the user evaluation detail content of the associated product, and determines whether the associated product meets the condition for generating the user evaluation card according to the user evaluation detail content. If it meets the condition, trigger the step of providing the operation option for generating the user evaluation card.
7. An apparatus for providing product evaluation information, characterized in that, It includes: An operation option providing unit, configured to provide an operation option for generating a user evaluation card for the associated product of the consultation service in an interface for providing consultation services; A target information generating unit, configured to, in response to an operation request submitted by a customer service provider through the operation option, generate a first prompt message according to the product identifier of the associated product, and call an artificial intelligence (AI) generative model according to the first prompt message, so that the AI generative model generates target information according to the multiple user evaluation detail contents of the associated product. The target information includes: at least one feature tag, and at least one representative user evaluation detail content corresponding to the feature tag; the feature tag is a general text content obtained by classifying the multiple user evaluation detail contents of the associated product and summarizing the user evaluation detail contents of the same class; A user evaluation card generating unit, configured to generate a user evaluation card according to the target information and a preset format template, so as to send the user evaluation card of the associated product to the current inquiring user side for display by sending a conversation message during the process of providing the consultation service.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
9. An electronic device, characterized in that, It includes: One or more processors; And A memory associated with the one or more processors, where the memory is used to store program instructions. When the program instructions are read and executed by the one or more processors, they execute the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program / computer-executable instructions, characterized in that, When the computer program / computer executable instructions are executed by a processor in an electronic device, they implement the steps of the method according to any one of claims 1 to 6.