Product review content generating method and electronic device

Abstract

Disclosed in embodiments of the present disclosure are a product review content generating method and an electronic device. The method comprises: determining a target product for which review content needs to be supplemented, wherein the target product includes a newly released product and / or a product having the number of user reviews less than a threshold; obtaining material content, wherein the material content comprises related information of the target product, and / or user review content corresponding to at least one associated product of the target product; and calling a pre-trained artificial intelligence (AI) content generating model on the basis of the material content, so as to generate product review content for the target product by means of the AI content generating model for display in a target page related to the target product. According to the embodiments of the present disclosure, product review content can be enriched, and conversion rates and other metrics for pages such as product detail pages can be improved.

Description

Product evaluation content generation method and electronic device

[0001] This disclosure claims priority to Chinese patent application number 202410114831.5, filed with the Patent Office of China on January 26, 2024, entitled “Method and Electronic Device for Generating Product Evaluation Content,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the technical field of content generation, and in particular to a method and electronic device for generating product evaluation content. Background Art

[0003] In the product information service system, the number and quality of user reviews of a product are highly correlated with the product's DO conversion (the user conversion rate from the details page to placing an order). Generally, if a product has a large number of user reviews of high quality, it can lead to a higher DO conversion rate. However, this type of user review data relies on the user's active participation. Although the platform or merchants can encourage users to fill in reviews by providing additional rewards, there are still frequent cases where users give up filling in reviews, or the review content is too simple and has limited reference value, resulting in a relatively low effective review rate for the product. In addition, for some new products, this low user review rate phenomenon is even more serious. Summary of the Invention

[0004] The present disclosure provides a method and electronic device for generating product evaluation content, which can enrich product evaluation content and improve indicators such as the conversion rate of pages such as product details pages.

[0005] The present disclosure provides the following solutions:

[0006] A method for generating product evaluation content, comprising:

[0007] Determining target products for which review content is to be supplemented, wherein the target products include newly released products and / or products for which the number of user reviews is less than a threshold;

[0008] Acquiring material content, the material content including relevant information of the target product itself and / or user evaluation content corresponding to at least one related product of the target product;

[0009] A pre-trained artificial intelligence (AI) content generation model is called based on the material content, so as to generate product evaluation content for the target product through the AI ​​content generation model, so as to be displayed in a target page related to the target product.

[0010] The relevant information of the target product itself includes: detailed description information of the target product, and / or conversation record information related to the target product in the customer service system.

[0011] The associated products include the same / similar products of the target product, and / or products under the leaf category to which the target product belongs.

[0012] There are multiple items of product evaluation content, each used to evaluate the target product from different dimensions.

[0013] The AI ​​content generation model is specifically used to generate core decision attributes of the target product granularity based on the material content, so that the generated product evaluation content includes the core decision attributes and their attribute values.

[0014] The attribute value corresponding to the core decision attribute is a fine-grained attribute value expressed quantitatively.

[0015] The related products include products under the leaf category to which the target product belongs;

[0016] The AI ​​content generation model is also used to generate core decision attributes of the leaf category granularity and corresponding optional candidate attribute values ​​based on the information of the products under the leaf category to which the target product belongs, so as to provide structured evaluation guidance information after receiving a request submitted by the user to evaluate the target product.

[0017] The AI ​​content generation model is further used to generate question-and-answer feedback content for the target product based on the relevant information of the target product itself.

[0018] A method for displaying a product details page, comprising:

[0019] In response to a request to display a target product's details page, obtaining product review content generated for the target product by an AI content generation model based on source content, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user reviews, and the source content includes relevant information about the target product itself and / or user review content corresponding to at least one associated product of the target product;

[0020] The product review content generated by the AI ​​content generation model is displayed based on the details page.

[0021] The AI ​​content generation model is specifically configured to summarize the product review content from the source content, and / or extract representative user review content from user review content corresponding to at least one associated product of the target product to serve as the product review content of the target product;

[0022] The displaying of the product review content generated by the AI ​​content generation model based on the details page includes:

[0023] Based on the details page of the target product, the product evaluation content summarized by the AI ​​content generation model is displayed, and / or the representative user evaluation content corresponding to the related products extracted by the AI ​​content generation model is quoted.

[0024] The display of the product review content generated by the AI ​​content generation model based on the details page includes:

[0025] In the user evaluation content display area of ​​the details page, the product evaluation content generated by the AI ​​content generation model is displayed.

[0026] The display of the product review content generated by the AI ​​content generation model based on the details page includes:

[0027] A separate AI-generated content display sub-area is added to the user evaluation content display area of ​​the details page, and the product evaluation content generated by the AI ​​content generation model is displayed in the AI-generated content display sub-area.

[0028] A method for displaying a product details page, comprising:

[0029] In response to a request to display a target product's details page, obtaining question-and-answer feedback content generated by an AI content generation model for the target product based on source content, wherein the target product includes a newly released product and / or a product with less than a threshold amount of question-and-answer feedback content, and the source content includes detailed description information of the target product and / or conversation records related to the target product in a customer service system;

[0030] In the question-and-answer feedback content display area of ​​the details page, the question-and-answer feedback content generated by the AI ​​content generation model is displayed.

[0031] A method for displaying a product review editing interface, comprising:

[0032] In response to a request to fill in user evaluation content for a target product, obtaining structured evaluation guidance information generated by an AI content generation model based on source content for a leaf category to which the target product belongs, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user evaluations, the structured evaluation guidance information includes core decision attributes at the leaf category granularity and corresponding optional candidate attribute values, and the source content includes user evaluation content for products in the leaf category to which the target product belongs;

[0033] The structured evaluation guidance information is displayed so that the user can complete filling in the evaluation content based on the structured evaluation guidance information.

[0034] A device for generating product evaluation content, comprising:

[0035] a target product determining unit, configured to determine target products for which review content is to be supplemented, wherein the target products include newly released products and / or products for which the number of user reviews is less than a threshold;

[0036] a material content acquisition unit, configured to acquire material content, wherein the material content includes relevant information of the target product itself and / or user evaluation content corresponding to at least one associated product of the target product;

[0037] An evaluation content generation unit is used to call a pre-trained artificial intelligence (AI) content generation model based on the material content, so as to generate product evaluation content for the target product through the AI ​​content generation model, so as to be displayed in a target page related to the target product.

[0038] A device for displaying a product details page, comprising:

[0039] a product review content acquisition unit, configured to, in response to a request to display a target product details page, acquire product review content generated for the target product by the AI ​​content generation model based on source content, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user reviews, and the source content includes relevant information about the target product itself and / or user review content corresponding to at least one associated product of the target product;

[0040] A product review content display unit is used to display the product review content generated by the AI ​​content generation model based on the details page.

[0041] A device for displaying a product details page, comprising:

[0042] A question-and-answer feedback content acquisition unit is configured to, in response to a request to display a target product's details page, acquire question-and-answer feedback content generated for the target product by the AI ​​content generation model based on source content, wherein the target product includes a newly released product and / or a product for which the amount of question-and-answer feedback content is less than a threshold, and the source content includes detailed description information of the target product and / or conversation records related to the target product in a customer service system;

[0043] The question-and-answer feedback content display unit is used to display the question-and-answer feedback content generated by the AI ​​content generation model in the question-and-answer feedback content display area of ​​the details page.

[0044] A device for displaying a product review editing interface, comprising:

[0045] a structured evaluation guidance information acquisition unit, configured to, in response to a request to fill in user evaluation content for a target product, acquire structured evaluation guidance information generated by an AI content generation model based on source content for a leaf category to which the target product belongs, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user evaluations, the structured evaluation guidance information includes core decision attributes at the leaf category granularity and corresponding optional candidate attribute values, and the source content includes user evaluation content for products under the leaf category to which the target product belongs;

[0046] The structured evaluation guidance information display unit is used to display the structured evaluation guidance information so as to complete the filling of the user evaluation content based on the structured evaluation guidance information.

[0047] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the aforementioned methods.

[0048] An electronic device, comprising:

[0049] one or more processors; and

[0050] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any of the aforementioned methods.

[0051] A computer program product comprises a computer program / computer executable instructions, wherein the computer program / computer executable instructions are capable of implementing the steps of any of the aforementioned methods when executed by a processor in an electronic device.

[0052] According to the specific embodiments provided by the present disclosure, the present disclosure discloses the following technical effects:

[0053] Through the embodiments of the present disclosure, for new products or target products with relatively low user review rates, relevant information of the target product itself and / or user review content corresponding to at least one associated product of the target product can be obtained as material content. Based on the material content, a pre-trained artificial intelligence (AI) content generation model is called to generate product review content for the target product through the AI ​​content generation model. This AI-generated product review content can be used for display on the target page related to the target product. In this way, the AI-generated product review content can be used as a supplement to the user review content, thereby helping users make shopping decisions and helping to improve indicators such as the conversion rate of pages such as product details pages.

[0054] Of course, any product implementing the present disclosure does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] FIG1 is a schematic diagram of a system architecture provided by an embodiment of the present disclosure;

[0057] FIG2 is a flow chart of a first method provided by an embodiment of the present disclosure;

[0058] FIG3 is a schematic diagram of a first interface provided by an embodiment of the present disclosure;

[0059] FIG4 is a schematic diagram of a second interface provided by an embodiment of the present disclosure;

[0060] FIG5 is a flow chart of a second method provided by an embodiment of the present disclosure;

[0061] FIG6 is a flowchart of a third method provided by an embodiment of the present disclosure;

[0062] FIG7 is a flowchart of a fourth method provided by an embodiment of the present disclosure;

[0063] FIG8 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0064] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present disclosure.

[0065] In the embodiments of the present disclosure, for new products released in the system or products with a relatively low user review rate, the evaluation content for such products can be supplemented in a manner based on AIGC (Artificial Intelligence General Computationalism, artificial intelligence production content). Among them, AIGC describes a theoretical framework that believes that artificial intelligence systems can achieve intelligence by imitating human intelligent behavior and thinking processes. The core idea of ​​AIGC is that artificial intelligence systems can achieve intelligent behavior by using computational models to simulate the human brain and cognitive processes. In other words, computational models can provide explanations and simulations of human intelligence, and can also be used to build higher-level artificial intelligence systems. The goal of AIGC is to establish a theoretical framework for better understanding and realizing artificial intelligence.

[0066] Based on the above framework, a variety of content generation models have emerged in the industry, including the "text-to-text" model (generating text from text), the "text-to-image" model (generating images from text), and the "image-to-text" model (generating text from images). In the embodiments of the present disclosure, the capabilities of the above-mentioned AI content generation models can be leveraged to generate reviews for specific products to supplement user reviews.

[0067] It should be noted here that in some implementation schemes, the user evaluation content of the product can be summarized by the AI ​​content generation model to help users understand the overall evaluation of the user on the product more quickly. However, this solution is usually suitable for products with a relatively high user review rate. However, since the target product in the embodiment of the present disclosure can usually be a new product or a product with a relatively low user review rate, the above solution will no longer be applicable to the scenario in the embodiment of the present disclosure. To this end, in the embodiment of the present disclosure, the detailed description information of the specific product itself, the conversation record information in the customer service system, and the user evaluation information of some related products (for example, the same / similar products, products under the same leaf category, etc.) can be used as the input content of the AI ​​big model. Then, the AI ​​big model can understand and summarize the above material content to generate evaluation content with a specified format. In this way, the user evaluation area of ​​the product details information page of this AI-generated evaluation content can be used as a supplement to the user evaluation content to help users browsing the product make decisions and improve the DO conversion rate.

[0068] From the perspective of system architecture, referring to FIG1 , the embodiment of the present disclosure can provide a product evaluation content generation service, and a specific evaluation content generation process can be initiated by inputting the identifier of the target product (for example, product ID) into the service. Afterwards, information about the target product itself (including detailed description information, conversation record information in the customer service system), user evaluation content of related products of the target product, etc. can be obtained from the product information library, etc. as material content, which can be input into the AI ​​content generation model to generate product evaluation content for the target product. The generated evaluation content can be saved in the product information library. When a user needs to view the details information page of the target product, the product evaluation content generated by this AI can be displayed through the details information page to reduce the probability of users abandoning orders due to the lack of evaluation content or too little evaluation content.

[0069] The specific implementation scheme provided by the embodiment of the present disclosure is introduced in detail below.

[0070] First, from the perspective of the above-mentioned evaluation content generation service, the embodiment of the present disclosure provides a method for generating product evaluation content. Referring to FIG2 , the method may include:

[0071] S201: Determine target products for which review content is to be supplemented. The target products include newly released products and / or products for which the number of user reviews is less than a threshold.

[0072] The target product may specifically be a newly released product in the product information service system (referred to as a "new product"), or a product with a relatively low user review rate, that is, a product with a relatively small number of user reviews, etc. In specific implementation, the review content generation service provided by the embodiments of the present disclosure may be provided to system staff or merchant users. Users may initiate a specific generation process by inputting the ID of a specific product, or the service may automatically select qualified products from the product library as target products, etc.

[0073] S202: Acquire material content, where the material content includes relevant information of the target product itself and / or user evaluation content corresponding to at least one associated product of the target product.

[0074] After the target product is determined, the relevant material content can be obtained. Specifically, since the target product in the embodiment of the present disclosure is a product that has not yet obtained user evaluation, or the number of user evaluations is very small, it is impossible for the AI ​​generation model to directly generate evaluation content by summarizing the existing user evaluation content of the specific target product itself. Therefore, the material content obtained in the embodiment of the present disclosure may include relevant information of the target product, and / or user evaluation content corresponding to at least one associated product of the target product. In other words, the specific material content either comes from some relevant information of the current target product itself, or from the user evaluation content obtained for the associated products of the current target product.

[0075] Among them, the relevant information of the target product itself may specifically include detailed description information of the product (including pictures, text, videos, etc.), and may also include conversation content related to the target product in the customer service system (that is, conversation records generated during the conversation between the user and the store's customer service staff or customer service robot), etc.

[0076] There are many types of related products for a target product. For example, these can be identical or similar products to the target product, or products within the same sub-category as the target product, and so on. These identical or similar products typically have the same or similar key attributes as the target product. For example, if a clothing item A is identical or similar to another clothing item B in terms of brand, style, color, etc., then item B is considered identical or similar to item A.

[0077] That is, even though the target product itself may not have any user reviews, or there may be very little user reviews, the user reviews of the same or similar products can be used as reference material to generate reviews for the target product. Furthermore, if there are no same or similar products for a specific product, or if there are no or very few user reviews for the same or similar products, the user reviews of products in the leaf category to which the current target product belongs can also be used as reference to generate reviews for the target product.

[0078] Among them, the so-called leaf category is the most specific category in the product classification. It describes the most detailed attribute information of the product and can accurately locate the type of product. Different leaf categories are independent of each other and there is no hierarchical relationship. For example, the "apparel" category can include "women's clothing", "men's clothing", "children's clothing", etc., the "women's clothing" category can include "women's pants", "jackets", "women's skirts", "suits", etc., and the "women's pants" category also includes "casual pants", "jeans", "leggings", etc. Among them, the "casual pants", "jeans", and "leggings" level belongs to the leaf category because there are no further subcategories. In other words, assuming that the current target product is product A and its leaf category is "casual pants", the user evaluation content of other products under the "casual pants" category can be used as a reference to generate evaluation content for product A.

[0079] S203: Calling a pre-trained artificial intelligence (AI) content generation model based on the material content, so as to generate product evaluation content for the target product through the AI ​​content generation model, so as to be displayed in a target page related to the target product.

[0080] After obtaining the material content, a pre-trained AI content generation model can be called based on this material content to generate product evaluation content for the target product through the AI ​​content generation model. Among them, the AI ​​content generation model can be a "wenshengwen" type content generation model, that is, it can generate text content based on text-based materials. Of course, in the specific implementation, since the specific material content may also include image materials and audio materials, this part of the material content can also be pre-processed through image understanding models, audio understanding models, etc., and after generating relevant text content, the evaluation content can be generated.

[0081] In specific implementation, the specifically generated product evaluation content can be multiple, each used to evaluate the target product from different dimensions. That is to say, when a user evaluates a product, he or she may evaluate it from multiple dimensions. If the evaluation contents on these dimensions are all put into the same evaluation, the key points may not be highlighted enough due to the length of the content, etc. Therefore, in the embodiment of the present disclosure, when the evaluation content is generated by AI, the evaluation contents on different dimensions can be put into multiple different evaluations to make the key points of each evaluation content more prominent. In addition, it can also play a role in increasing the number of evaluation contents. For example, assuming that the current target product is a pendant, different evaluation contents can be generated from dimensions such as applicable occasions and craftsmanship, etc.

[0082] Regarding AI-generated product review content, the disclosed embodiments may also implement special processing. Specifically, the AI ​​content generation model can first generate core decision attributes at the target product granularity based on the source content. Specifically, it can determine which attributes the user should focus on when making a decision regarding the target product. These attributes become the core decision attributes of the target product. Furthermore, the generated product review content can include these core decision attributes and their corresponding attribute values. In preferred embodiments, these attribute values ​​can be quantitatively expressed at a fine-grained level, rather than simply providing a qualitative, fuzzy evaluation. For example, regarding some product parameters and performance, rather than simply providing qualitative evaluations such as "fast," "slow," "large," or "small," specific numerical values ​​can be used. Of course, for some products, both quantitative and qualitative attribute values ​​can be included to provide users with a more intuitive understanding of the specific numerical values. In short, decision factors (i.e., the aforementioned core decision attributes) can be incorporated into the generated product review content, and the generated product review content can be tailored to the user's mindset at the finest level, ensuring that the generated product review content truly assists users in making decisions.

[0083] After the above-mentioned product evaluation content is generated, this AI-generated product evaluation content can be displayed on the page related to the target product. For example, this product evaluation content can be displayed directly in the user evaluation area of ​​the product details page of the target product. Of course, during the display process, an "AI generated" mark can be added to distinguish it from the user evaluation content posted by the user. Alternatively, in another way, a separate AI-generated content display sub-area can be added to the user evaluation area of ​​the product details page, and then the product evaluation content generated by the AI ​​content generation model can be displayed in the AI-generated content display sub-area. For example, as shown in (A) in Figure 3, assuming that the target product is a pendant, the "Product Impression" area shown in 31 in the details page of the product is the newly added AI-generated content display sub-area in the embodiment of the present disclosure, and information related to the AI-generated product evaluation content can be displayed in this sub-area. Of course, in order to avoid such AI-generated content from having too much impact on the display of user evaluation content of the product, in specific implementation, this independent AI-generated content display sub-area can only display part of the information about the AI-generated product evaluation content by default. For example, assuming that the AI ​​generates a total of 4 product evaluation contents, only one or two of them can be displayed by default, etc., to avoid excessive occupation of the user evaluation content display area. In addition, the AI-generated content display sub-area can also respond to user interaction operations. For example, after the user clicks on the area to view it, the sub-area can be expanded and enlarged. At this time, the interface shown in (B) in Figure 3 can be displayed, which can display the details of multiple AI-generated product evaluation contents.

[0084] It should be noted that, in specific implementation, the AI ​​content generation model can not only be used to summarize various material contents to obtain product evaluation content, but also the AI ​​content generation model can extract representative user evaluation content from the user evaluation content corresponding to at least one associated product of the target product. In this way, the representative user evaluation content corresponding to the associated product can also be quoted based on the details page of the target product. For example, for the pendant shown in (A) in Figure 3, there are 0 specific user evaluation contents, but multiple product evaluation contents summarized by AI can be displayed on the product details page, and / or the representative user evaluation content corresponding to the associated product can be quoted. For example, in this example, the product evaluation content generated by AI can be 4, two of which can be evaluated from the dimensions of applicable occasions, craftsmanship, etc., and the third can directly quote the user's evaluation content of the same product, and so on. It should be noted here that when quoting or referring to user reviews of the same / similar products, you can only quote or refer to the reviews related to the product itself. If it involves evaluations of merchants, logistics, etc., you do not need to quote them. Of course, if they are the same / similar products from the same merchant, you can also quote or refer to the merchant's evaluations.

[0085] It should be noted that the embodiments of the present disclosure can be applied to a variety of e-commerce scenarios, for example, cross-border e-commerce scenarios. In cross-border e-commerce scenarios, in addition to generating product evaluation content, multilingual translation can also be performed. For example, when AI-generated evaluation content of the same product is displayed to users in different countries / regions, it can be translated into the corresponding language for easier reading.

[0086] The above introduces the specific implementation method of AI generating product evaluation content. In an optional manner, the AI ​​content generation model can also generate core decision attributes about the current product in the process of generating product evaluation content, wherein this core decision attribute can be at the leaf category granularity to guide users to evaluate. It should be noted here that in the prior art, evaluation guidance information is usually provided for some categories, including providing some core decision attributes and corresponding candidate items, so that users can quickly complete the evaluation of the product without having to enter the evaluation content about the specific core decision attributes word by word. However, the core decision attributes in the prior art are usually manually defined, so this function can usually only be supported on a few categories. In the embodiment of the present disclosure, the AI ​​content generation model can generate core decision attributes at the leaf category granularity for specific products, and provide corresponding candidate items to generate structured evaluation guidance information. In this way, more leaf categories can have structured evaluation guidance information, thereby helping to improve the user review rate of the product.

[0087] Specifically, since the user evaluation content of the products under the leaf category to which the target product belongs can be included when obtaining specific material content, the AI ​​content generation model can generate the core decision attributes of the leaf category granularity and the corresponding optional candidate attribute values ​​based on the information of the products under the leaf category to which the target product belongs. In this way, after receiving the request submitted by the user to evaluate the target product, structured evaluation guidance information can be provided, which includes the core decision attributes of the leaf category granularity and the corresponding optional candidate attribute values.

[0088] It's important to note that the core decision attributes used to guide user reviews are generated at the leaf category level. This means that different products within the same leaf category can share the same core decision attributes. This differs from the core decision attributes directly introduced into review content when AI-generated reviews are generated. The latter approach uses product-level core decision attributes, focusing more on the product's attributes and better aligning with user preferences.

[0089] In addition, in actual applications, in addition to the evaluation content, there is usually another feedback method, that is, the question-and-answer method between users such as "Ask Everyone". Usually, this question-and-answer feedback content is also very helpful for users' shopping decisions. However, there are also some products that may not have this kind of question-and-answer feedback content left by users, or the number is very small. Therefore, in the embodiment of the present disclosure, this kind of question-and-answer feedback content can also be generated by an AI content generation model. Among them, in order to make the generated question-and-answer feedback content more rigorous, the AI ​​content generation model can generate question-and-answer feedback content for the target product based only on the relevant information of the target product itself (including detailed description content, and / or conversation records of the customer service system corresponding to the target product, etc.), that is, it is not necessary to refer to the relevant evaluation or feedback of other related products, but to generate this kind of question-and-answer feedback content based on the relevant information of the current target product itself.

[0090] Regarding question-and-answer feedback, the AI ​​content generation model can directly generate specific questions and corresponding answers. Alternatively, if a user has already asked a question about the target product, the AI ​​content generation model can also generate answers to such user questions, and so on. For example, as shown in Figure 4, it shows the "Ask Everyone" interface of an electronic product, which displays two user questions and the answers generated by AI. As can be seen from Figure 4, when displaying AI-generated content, it is also possible to add tags such as "AI".

[0091] In summary, through the embodiments of the present disclosure, for new products or target products with a relatively low user review rate, relevant information of the target product itself and / or user review content corresponding to at least one associated product of the target product can be obtained as material content, and a pre-trained artificial intelligence AI content generation model can be called based on the material content to generate product review content for the target product through the AI ​​content generation model. This AI-generated product review content can be used for display on the target page related to the target product. In this way, the AI-generated product review content can be used as a supplement to the user review content, thereby helping users make shopping decisions and helping to improve indicators such as the conversion rate of pages such as product details pages.

[0092] Example 2

[0093] The second embodiment corresponds to the first embodiment and provides a method for displaying a product details page from the perspective of a client facing a consumer user. Referring to FIG5 , the method may include:

[0094] S501: In response to a request to display a target product's details page, obtain product review content generated for the target product by an AI content generation model based on source content, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user reviews, and the source content includes relevant information about the target product itself and / or user review content corresponding to at least one associated product of the target product;

[0095] S502: Displaying the product review content generated by the AI ​​content generation model based on the details page.

[0096] The associated products include the same / similar products of the target product, and / or products under the leaf category to which the target product belongs.

[0097] The AI ​​content generation model can be specifically used to summarize the product review content from the source content and / or extract representative user review content from the user review content corresponding to at least one associated product of the target product to serve as the product review content of the target product. Therefore, when displaying, the product review content summarized by the AI ​​content generation model can be displayed based on the details page of the target product, and / or representative user review content corresponding to the associated products extracted by the AI ​​content generation model can be cited.

[0098] Specifically, when displaying the product evaluation content generated by the AI ​​content generation model based on the details page, there can be multiple ways. For example, in one way, the product evaluation content generated by the AI ​​content generation model can be displayed directly in the user evaluation content display area of ​​the details page. Or, in another way, a separate AI-generated content display sub-area can be added to the user evaluation content display area of ​​the details page, and the product evaluation content generated by the AI ​​content generation model can be displayed in the AI-generated content display sub-area. In this way, the AI-generated evaluation content can be more clearly distinguished from the evaluation content published by the user for the current target product, which is convenient for the browser user to distinguish. In addition, regardless of which of the above display methods is used, an AI-generated mark can be added to the AI-generated evaluation content.

[0099] Example 3

[0100] This third embodiment corresponds to the first embodiment. From the perspective of a client facing consumer users, a method for displaying a product details page is provided for AI generation of "Ask Everyone" content. Referring to FIG6 , this method may include:

[0101] S601: In response to a request to display a target product's details page, obtaining question-and-answer feedback content generated by an AI content generation model for the target product based on source content, wherein the target product includes a newly released product and / or a product with less than a threshold amount of question-and-answer feedback content, and the source content includes detailed description information of the target product and / or conversation records related to the target product in a customer service system;

[0102] S602: Displaying the question-and-answer feedback content generated by the AI ​​content generation model in the question-and-answer feedback content display area of ​​the details page.

[0103] Example 4

[0104] This fourth embodiment also corresponds to the first embodiment and provides a method for displaying a product review editing interface from the perspective of a client facing a consumer user. Referring to FIG7 , the method may include:

[0105] S701: In response to a request to fill in user evaluation content for a target product, obtaining structured evaluation guidance information generated by an AI content generation model based on source content for a leaf category to which the target product belongs, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user evaluations, the structured evaluation guidance information includes core decision attributes at the leaf category granularity and corresponding optional candidate attribute values, and the source content includes user evaluation content for products under the leaf category to which the target product belongs;

[0106] S702: Displaying the structured evaluation guidance information so that the user can complete filling in the evaluation content based on the structured evaluation guidance information.

[0107] For the parts not described in detail in the above-mentioned embodiments 2 to 4, please refer to the description of embodiment 1 and other parts of this specification, and will not be repeated here.

[0108] It should be noted that the embodiments of the present disclosure may involve the use of user data. In actual applications, user-specific personal data may be used in the scenarios described herein within the scope permitted by applicable laws and regulations, subject to compliance with applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0109] Corresponding to the aforementioned method embodiment 1, the present disclosure embodiment further provides a device for generating product evaluation content, which may include:

[0110] a target product determining unit, configured to determine target products for which review content is to be supplemented, wherein the target products include newly released products and / or products for which the number of user reviews is less than a threshold;

[0111] a material content acquisition unit, configured to acquire material content, wherein the material content includes relevant information of the target product itself and / or user evaluation content corresponding to at least one associated product of the target product;

[0112] An evaluation content generation unit is used to call a pre-trained artificial intelligence (AI) content generation model based on the material content, so as to generate product evaluation content for the target product through the AI ​​content generation model, so as to be displayed in a target page related to the target product.

[0113] The relevant information of the target product itself includes: detailed description information of the target product, and / or conversation record information related to the target product in the customer service system.

[0114] The associated products include the same / similar products of the target product, and / or products under the leaf category to which the target product belongs.

[0115] Specifically, the product evaluation content includes multiple items, each used to evaluate the target product from different dimensions.

[0116] The AI ​​content generation model is specifically used to generate core decision attributes of the target product granularity based on the material content, so that the generated product evaluation content includes the core decision attributes and their attribute values.

[0117] Specifically, the attribute value corresponding to the core decision attribute may be a fine-grained attribute value expressed quantitatively.

[0118] In addition, the associated products include products under the leaf category to which the target product belongs; at this time, the AI ​​content generation model is also used to generate core decision attributes of the leaf category granularity and corresponding optional candidate attribute values ​​based on the information of the products under the leaf category to which the target product belongs, so as to provide structured evaluation guidance information after receiving a request submitted by the user to evaluate the target product.

[0119] In addition, the AI ​​content generation model is also used to generate question-and-answer feedback content for the target product based on the relevant information of the target product itself.

[0120] Corresponding to the second embodiment, the embodiment of the present disclosure further provides a device for displaying a product details page, which may include:

[0121] a product review content acquisition unit, configured to, in response to a request to display a target product details page, acquire product review content generated for the target product by the AI ​​content generation model based on source content, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user reviews, and the source content includes relevant information about the target product itself and / or user review content corresponding to at least one associated product of the target product;

[0122] A product review content display unit is used to display the product review content generated by the AI ​​content generation model based on the details page.

[0123] The associated products include the same / similar products of the target product, and / or products under the leaf category to which the target product belongs.

[0124] The AI ​​content generation model is specifically configured to summarize the product review content from the source content, and / or extract representative user review content from user review content corresponding to at least one associated product of the target product to serve as the product review content of the target product;

[0125] Specifically, the product evaluation content display unit can be used to: display the product evaluation content summarized by the AI ​​content generation model based on the details page of the target product, and / or quote representative user evaluation content corresponding to the related products extracted by the AI ​​content generation model.

[0126] Specifically, the product review content display unit can be used to:

[0127] In the user evaluation content display area of ​​the details page, the product evaluation content generated by the AI ​​content generation model is displayed.

[0128] Alternatively, the product review content display unit may also be used to:

[0129] A separate AI-generated content display sub-area is added to the user evaluation content display area of ​​the details page, and the product evaluation content generated by the AI ​​content generation model is displayed in the AI-generated content display sub-area.

[0130] Corresponding to the third embodiment, the embodiment of the present disclosure further provides a device for displaying a product details page, the device comprising:

[0131] A question-and-answer feedback content acquisition unit is configured to, in response to a request to display a target product's details page, acquire question-and-answer feedback content generated for the target product by the AI ​​content generation model based on source content, wherein the target product includes a newly released product and / or a product for which the amount of question-and-answer feedback content is less than a threshold, and the source content includes detailed description information of the target product and / or conversation records related to the target product in a customer service system;

[0132] The question-and-answer feedback content display unit is used to display the question-and-answer feedback content generated by the AI ​​content generation model in the question-and-answer feedback content display area of ​​the details page.

[0133] Corresponding to the fourth embodiment, the embodiment of the present disclosure further provides a device for displaying a product review editing interface, which may include:

[0134] a structured evaluation guidance information acquisition unit, configured to, in response to a request to fill in user evaluation content for a target product, acquire structured evaluation guidance information generated by an AI content generation model based on source content for a leaf category to which the target product belongs, wherein the target product includes a newly released product and / or a product with fewer than a threshold number of user evaluations, the structured evaluation guidance information includes core decision attributes at the leaf category granularity and corresponding optional candidate attribute values, and the source content includes user evaluation content for products under the leaf category to which the target product belongs;

[0135] The structured evaluation guidance information display unit is used to display the structured evaluation guidance information so as to complete the filling of the user evaluation content based on the structured evaluation guidance information.

[0136] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the aforementioned method embodiment are implemented.

[0137] And an electronic device comprising:

[0138] one or more processors; and

[0139] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in the aforementioned method embodiment.

[0140] A computer program product includes a computer program / computer executable instructions, which implement the steps of the method described in the above method embodiment when executed by a processor in an electronic device.

[0141] 8 exemplarily illustrates the architecture of an electronic device, which may include a processor 810, a video display adapter 811, a disk drive 812, an input / output interface 813, a network interface 814, and a memory 820. The processor 810, the video display adapter 811, the disk drive 812, the input / output interface 813, the network interface 814, and the memory 820 may be communicatively connected via a communication bus 830.

[0142] Among them, the processor 810 can be implemented by a general-purpose CPU (Central Processing Unit, processor), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., to execute relevant programs to implement the technical solutions provided by the present disclosure.

[0143] The memory 820 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 820 can store an operating system 821 for controlling the operation of the electronic device 800, and a basic input and output system (BIOS) for controlling the low-level operations of the electronic device 800. In addition, a web browser 823, a data storage management system 824, and a product evaluation content generation system 825, etc. can also be stored. The above-mentioned product evaluation content generation system 825 can be an application program that specifically implements the operations of the aforementioned steps in the embodiment of the present disclosure. In short, when the technical solution provided by the present disclosure is implemented by software or firmware, the relevant program code is stored in the memory 820 and is called and executed by the processor 810.

[0144] The input / output interface 813 is used to connect input / output modules to implement information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0145] The network interface 814 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WiFi, Bluetooth, etc.).

[0146] The bus 830 comprises a pathway for transmitting information between the various components of the device (eg, the processor 810 , the video display adapter 811 , the disk drive 812 , the input / output interface 813 , the network interface 814 , and the memory 820 ).

[0147] It should be noted that although the above device only shows a processor 810, a video display adapter 811, a disk drive 812, an input / output interface 813, a network interface 814, a memory 820, a bus 830, etc., in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will understand that the above device may also include only the components necessary to implement the disclosed solution, and does not necessarily include all the components shown in the figure.

[0148] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present disclosure can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling 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 certain parts of the embodiments of the present disclosure.

[0149] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on 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. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0150] The above is a detailed introduction to the product review content generation method and electronic device provided by the present disclosure. Specific examples are used herein to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only intended to help understand the method and core concept of the present disclosure. At the same time, for those skilled in the art, based on the concept of the present disclosure, there may be changes in the specific implementation methods and application scope. In summary, the contents of this specification should not be understood as limiting the present disclosure.

Claims

1. A method for generating product evaluation content, comprising: Determining a target product for which evaluation content needs to be supplemented, where the target product includes newly released products and / or products with the number of user evaluations less than a threshold; Obtaining material content, where the material content includes relevant information of the target product itself and / or user evaluation content corresponding to at least one associated product of the target product; Invoking a pre-trained artificial intelligence (AI) content generation model based on the material content, so as to generate product evaluation content for the target product through the AI content generation model for display on a target page related to the target product.

2. The method according to claim 1, wherein, The relevant information of the target product itself includes: detailed description information of the target product and / or conversation record information related to the target product in the customer service system.

3. The method according to claim 1 or 2, wherein The associated products include the same model / similar model products of the target product and / or products under the leaf category to which the target product belongs.

4. The method according to any one of claims 1 to 3, wherein, The product evaluation content is in multiple pieces, respectively used to evaluate the target product from different dimensions.

5. The method according to any one of claims 1 to 4, wherein The AI content generation model is specifically used to generate core decision attributes at the granularity of the target product according to the material content, so that the generated product evaluation content includes the core decision attributes and their attribute values.

6. The method according to claim 5, wherein, The attribute values corresponding to the core decision attributes are quantitative and fine-grained attribute values.

7. The method according to any one of claims 1 to 6, wherein The associated products include products under the leaf category to which the target product belongs; The AI content generation model is further used to generate core decision attributes at the granularity of the leaf category and corresponding optional candidate attribute values according to the information of the products under the leaf category to which the target product belongs, so as to provide structured evaluation guidance information after receiving a request from a user to evaluate the target product.

8. The method according to any one of claims 1 to 7, wherein, The AI content generation model is further used to generate question-and-answer style opinion feedback content for the target product according to the relevant information of the target product itself.

9. A method for displaying a product details page, comprising: In response to a request to display the details page of a target product, obtaining product evaluation content generated by an AI content generation model for the target product based on material content, where the target product includes newly released products and / or products with the number of user evaluations less than a threshold, and the material content includes relevant information of the target product itself and / or user evaluation content corresponding to at least one associated product of the target product; Displaying the product evaluation content generated by the AI content generation model based on the details page.

10. The method according to claim 9, wherein, The AI content generation model is specifically used to summarize the product evaluation content from the material content and / or extract representative user evaluation content from the user evaluation content corresponding to at least one associated product of the target product as the product evaluation content of the target product; The displaying the product evaluation content generated by the AI content generation model based on the details page includes: Display the product evaluation content summarized by the AI content generation model based on the details page of the target product, and / or cite the representative user evaluation content corresponding to the associated products extracted by the AI content generation model.

11. The method according to claim 9, wherein, The display of the product evaluation content generated by the AI content generation model based on the details page includes: In the user evaluation content display area on the details page, display the product evaluation content generated by the AI content generation model.

12. The method according to claim 9, wherein, The display of the product evaluation content generated by the AI content generation model based on the details page includes: Add a separate AI-generated content display sub-area in the user evaluation content display area of the details page, and display the product evaluation content generated by the AI content generation model in the AI-generated content display sub-area.

13. A method for displaying a product details page, including: In response to a request to display the details page of a target product, obtain the Q&A-style opinion feedback content generated by an AI content generation model for the target product based on the material content, where the target product includes newly released products and / or products with less than a threshold number of Q&A-style opinion feedback content, and the material content includes the detailed description information of the target product, and / or the conversation record information related to the target product in the customer service system; In the Q&A-style opinion feedback content display area on the details page, display the Q&A-style opinion feedback content generated by the AI content generation model.

14. A method for displaying a product evaluation editing interface, including: In response to a request to fill in user evaluation content for a target product, obtain the structured evaluation guidance information generated by an AI content generation model for the leaf category to which the target product belongs based on the material content, where the target product includes newly released products and / or products with less than a threshold number of user evaluations, and the structured evaluation guidance information includes the core decision attributes at the leaf category level and the corresponding optional candidate attribute values, and the material content includes the user evaluation content of the products under the leaf category to which the target product belongs; Display the structured evaluation guidance information so as to complete the filling of the user evaluation content based on the structured evaluation guidance information.

15. A computer-readable storage medium having a computer program stored thereon, wherein, When the program is executed by a processor, it implements the steps of the method according to any one of claims to 14.

16. An electronic device, including: One or more processors; And 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, they execute the steps of the method according to any one of claims to 14.

17. A computer program product comprising a computer program / computer-executable instructions, wherein, When the computer program / computer executable instructions are executed by the processor in the electronic device, they implement the steps of the method according to any one of claims to 14.

Images