User review information processing method for commodity object, and electronic device

Abstract

A user review information processing method for a commodity object, and an electronic device. The method comprises: in response to a request of a target user for viewing user review content with regard to a target commodity, inputting a plurality of pieces of user review content associated with the target commodity into a target algorithm model for processing, so as to generate target text content, wherein the target text content is used for performing inductive and conclusive expression on the plurality of pieces of user review content; and returning the target text content to a client, such that the target text content is presented when the user review information is presented. Therefore, a user can be helped to more efficiently realize more complete and more comprehensive understanding of user review content, such that the user review content can more effectively help the user to make a purchasing decision.

Description

Method and electronic device for processing user evaluation information of commodity objects

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on May 31, 2023, with application number 202310641306.4 and application name “User evaluation information processing method and electronic device for commodity objects”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of information processing technology, and in particular to a method and electronic device for processing user evaluation information of a commodity object. Background Art

[0003] When users browse and purchase products through a product information service system, product reviews posted by other users often provide valuable reference information for helping users make purchasing decisions. For example, after browsing product details and finding interest, users may use user reviews to make further decisions. However, in practice, for popular or high-selling products, the number of user reviews can be quite large, and users may spend a long time reviewing them. Consequently, users may often exit or close the website after viewing only a few reviews. This can lead to a biased impression of the product due to incomplete review content. Furthermore, some reviews that are truly useful to the current user may not be seen by the user because they are ranked relatively low, resulting in them not being able to truly help the user make a purchasing decision. Therefore, how to help users improve the efficiency of viewing user reviews and obtain more accurate and comprehensive information about user reviews has become a technical problem that needs to be solved by those skilled in the art.

[0004] Summary of the Invention

[0005] This application provides a method and electronic device for processing user evaluation information of product objects, which can help users more efficiently achieve a more complete and comprehensive understanding of user evaluation content, so that the user evaluation content can more effectively help users make shopping decisions.

[0006] This application provides the following solutions:

[0007] A method for processing user evaluation information of a product object, comprising:

[0008] In response to a target user's request to view user evaluation content of a target product, a target text content is generated by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing, wherein the target text content is used to summarize the multiple user evaluation contents;

[0009] The target text content is returned to the client so that the target text content can be displayed when the user evaluation information is displayed.

[0010] The step of inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing to generate target text content includes:

[0011] By inputting multiple user reviews associated with the target product into a target algorithm model for processing, information on the sentiment type expressed in the user reviews, information on the advantages and disadvantages of the target product, information on the commonalities or similarities between different user reviews, and / or information on the matching relationship between the target product and the needs / preferences of the target user is obtained;

[0012] The target text content is generated by processing the acquired information.

[0013] The step of inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing to generate target text content includes:

[0014] The target text content is generated by inputting a plurality of user evaluation contents associated with the target product and the personalized information of the target user into a target algorithm model for processing.

[0015] A method for processing user evaluation information of a product object, comprising:

[0016] Receive a request from a target user to view user evaluation content of a target product;

[0017] A user evaluation content display page is displayed, wherein the user evaluation content display page includes target text content, and the target text content is generated by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing, and is used to summarize and express the multiple user evaluation contents.

[0018] Among them, also include:

[0019] Before displaying the target text content, an interactive option is provided in the user evaluation content display page so that the user can confirm whether to display the target text content, and after receiving the confirmation message, the display of the target text content is triggered.

[0020] A method for processing user evaluation information of a product object, comprising:

[0021] In response to a request from a target user to fill in user evaluation information for a target product object, obtaining basic evaluation content provided by the target user for the target product object;

[0022] The basic evaluation content is submitted to the server, and the target text content is obtained for display, wherein the target text content is generated by the server after inputting the basic evaluation content into the target algorithm model for processing, so as to determine the evaluation text content for publication based on the target text content.

[0023] The basic evaluation content includes: the emotion type information expressed by the target user for the target product.

[0024] The basic evaluation content includes: the rating information input or selected by the target user for the target product object through multiple rating items displayed in the user evaluation content editing interface.

[0025] The basic evaluation content also includes: the evaluation text content input by the target user for the target product through the user evaluation content editing interface.

[0026] Among them, also include:

[0027] After the target text content is displayed, in response to a refresh request for the target text content, new target text content is acquired and displayed.

[0028] Among them, also include:

[0029] After the target text content is displayed, in response to a request to use the target text content, the target text content is displayed in an input control for inputting evaluation text content, so that the evaluation text content is determined and published according to the target text content.

[0030] A method for processing user evaluation information of a product object, comprising:

[0031] In response to a request for assisting in generating a user review body, obtaining basic review content submitted by a target user for a target product;

[0032] Generating target text content by inputting the basic evaluation content into a target algorithm model for processing;

[0033] The target text content is returned to the client so that the evaluation body content is determined based on the target text content for publication.

[0034] A device for processing user evaluation information of a commodity object, comprising:

[0035] a target text content generating unit, configured to generate target text content by inputting a plurality of user evaluation contents associated with the target product into a target algorithm model for processing in response to a target user's request to view user evaluation contents of the target product, wherein the target text content is used to summarize the plurality of user evaluation contents;

[0036] The target text content returning unit is used to return the target text content to the client so that the target text content can be displayed when displaying the user evaluation information.

[0037] A device for processing user evaluation information of a commodity object, comprising:

[0038] a request receiving unit, configured to receive a request from a target user to view user evaluation content of a target product;

[0039] A display unit is used to display a user evaluation content display page, wherein the user evaluation content display page includes target text content, and the target text content is generated by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing, and is used to summarize and express the multiple user evaluation contents.

[0040] A device for processing user evaluation information of a commodity object, comprising:

[0041] a basic evaluation content receiving unit, configured to respond to a request initiated by a target user to fill in user evaluation information for a target product object, and obtain basic evaluation content provided by the target user for the target product object;

[0042] The target text content display unit is used to submit the basic evaluation content to the server and obtain the target text content for display, wherein the target text content is the text content generated by the server after inputting the basic evaluation content into the target algorithm model for processing, so as to determine the evaluation text content for publication based on the target text content.

[0043] A device for processing user evaluation information of a commodity object, comprising:

[0044] A basic evaluation content acquisition unit, configured to acquire basic evaluation content submitted by a target user for a target product in response to a request for assisting in generating a user evaluation body content;

[0045] a target text content generating unit, configured to generate target text content by inputting the basic evaluation content into a target algorithm model for processing;

[0046] The target text content returning unit is used to return the target text content to the client so as to determine the evaluation text content according to the target text content for publication.

[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] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0052] Through the embodiments of the present application, when a user needs to view user reviews of a target product, and the target product is associated with multiple user reviews, the multiple user reviews can be input into a target algorithm model for processing, generating target text content that summarizes and summarizes the multiple user reviews, and presenting this target text content to the user. In this way, the user only needs to view the target text content generated by this model to understand other users' overall evaluation of the current product. Therefore, the user can more efficiently achieve a more complete and comprehensive understanding of the user reviews, thereby allowing the user reviews to more effectively help the user make shopping decisions.

[0053] In addition, when users need to evaluate a certain product object, they can use AI big models and other capabilities to generate target text content based on the basic evaluation content input by the user, so that the user can complete the input of the evaluation text content based on this target text content. In this way, users do not have to spend a lot of time thinking about how to write the evaluation content, nor do they need to enter a long evaluation text word for word. Therefore, it can help users improve efficiency and reduce the time cost of users. In addition, for the platform, since the target text content generated by the model may be fuller and richer in content, it is conducive to improving the quality of user evaluation content, providing more valuable reference information for more users, and thus helping to improve users' trust and satisfaction with the platform.

[0054] Of course, any product implementing the present application 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 application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

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

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

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

[0059] FIG4 is a flow chart of a second method provided in an embodiment of the present application;

[0060] FIG5 is a flow chart of a third method provided in an embodiment of the present application;

[0061] FIG6 is a schematic diagram of a second interface provided in an embodiment of the present application;

[0062] FIG7 is a schematic diagram of a third interface provided in an embodiment of the present application;

[0063] FIG8 is a flowchart of a fourth method provided in an embodiment of the present application;

[0064] FIG9 is a schematic diagram of a first device provided in an embodiment of the present application;

[0065] FIG10 is a schematic diagram of a second device provided in an embodiment of the present application;

[0066] FIG11 is a schematic diagram of a third device provided in an embodiment of the present application;

[0067] FIG12 is a schematic diagram of a fourth device provided in an embodiment of the present application;

[0068] FIG13 is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0070] In order to help users improve their browsing efficiency of user evaluation content of products, and at the same time, when there are a large number of user evaluation content items, they can also have a more comprehensive and complete understanding of such user evaluation content in a short time, the embodiment of the present application can apply the capabilities of AI (Artificial Intelligence) large-scale parameter models (referred to as "AI big models") to scenarios that help users view user evaluation content of products. Among them, the so-called AI big model refers to a model that uses a neural network model to be pre-trained on a large-scale data set containing a huge amount of data. This model usually has a strong model understanding ability for text information, image information, etc., and also has content production capabilities. The specific content produced can include text, images, videos, voice, etc. Since this AI big model has a strong model understanding ability, it has been applied in many fields. From this perspective, the embodiment of the present application can belong to the application of this AI big model in scenarios related to the display of user evaluation content of commodity objects.

[0071] Specifically, in an embodiment of the present application, when a user needs to view the user evaluation content of a target product, the user can perform model understanding on multiple user evaluation contents associated with the target product based on the above-mentioned AI big model. Based on the model understanding results, the multiple target evaluation contents can be summarized, and the AI ​​big model produces target text content for summarizing the multiple user evaluation contents. For example, it is possible to identify and summarize the user's emotional expression information such as positive, negative or neutral evaluation of the product, or it is possible to identify and summarize the characteristics, advantages, disadvantages and other information of the product mentioned by the user in the review; or it is possible to perform commonality or similarity analysis on multiple user evaluation contents, so as to classify and summarize them. Furthermore, it is possible to summarize the matching relationship with the user's preferences based on the current target user's preferences or some basic attributes (including the group to which he belongs, etc.), and so on. In short, one or more paragraphs of summarizing text content can be generated, and the text content in each paragraph can be a coherent expression that conforms to the natural language grammar to facilitate user understanding. By providing this target text content to users, users can quickly browse the user evaluation content through this target text content. Moreover, due to its summarizing nature, after seeing this target text content, it is equivalent to having read all the user evaluation content and drawn a conclusion. This can help users improve their browsing efficiency of user evaluation content and have a more complete and comprehensive understanding of the user evaluation content, thereby better helping users make purchasing decisions.

[0072] From the perspective of system architecture, the embodiments of the present application can provide the above functions in the commodity information service system. Specifically, referring to FIG1 , the specific system may include a client and a server, wherein the client may exist in the form of an application (App) or a page such as Web, H5, etc., and mainly runs on the user's terminal device, including mobile devices such as mobile phones. The server mainly runs in the server, and specifically may include a cloud server or an independent server, etc. Among them, the client is mainly used for displaying the front-end page and interacting with the user, and the server can provide specific data services. In the embodiments of the present application, the AI ​​large model can be called to summarize the content of multiple user reviews and generate text content for return to the client for display, etc.

[0073] The specific implementation scheme provided in the embodiments of this application is introduced in detail below.

[0074] Example 1

[0075] First, from the perspective of the server, this embodiment 1 provides a method for processing user evaluation information of a product object. Referring to FIG2 , the method may include:

[0076] S201: In response to a target user's request to view user evaluation content of a target product, a target text content is generated by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing. The target text content is used to summarize and express the multiple user evaluation contents.

[0077] Specifically, the target product can be the product that the user is currently browsing. Typically, a "review" information card can be provided on the product details page. By default, the information card can display summary information about some user review content, for example, usually one or two. After the user clicks on the information card, a specific user review content details page can be displayed, through which the complete user review content can be viewed. However, as described in the background technology section, for some product objects, the number of corresponding user review content may be very large. In this case, the user needs to scroll through multiple screens to view them. Moreover, the user may no longer have the patience to continue reading after viewing several screens, and thus cannot obtain relevant reference information from the content that is not displayed later.

[0078] In the embodiment of the present application, after the user initiates a request to view the user evaluation content of a product, the server can also call the target algorithm model (for example, the aforementioned AI big model, etc., in this specification, the AI ​​big model is mainly used as an example for introduction). In this way, the AI ​​big model can convert multiple user evaluation contents associated with the target product into the model's understanding, and then produce the target text content by summarizing the understood user evaluation content. In other words, just like someone has read all the user evaluation content and drawn a conclusion, the AI ​​big model can "read" all the user evaluation content for the user and directly provide the user with the conclusion drawn after reading.

[0079] Of course, in a specific implementation, in order to avoid interfering with the user's review content through the normal mode, it is also possible to adopt a method in which the user confirms whether to view the content produced by this model. After the user confirms, the above-mentioned target text content is generated and displayed. For example, in a specific implementation, as shown in the accompanying figure on the left side of Figure 3, a message such as "This product has 2000+ user reviews. Do you want me to help you quickly browse?" can be displayed at the top of the user review content display page. At the same time, options such as "later" and "OK" can be provided to the user. After the user selects "OK", the above-mentioned target text content is generated, and so on.

[0080] Specifically, in the process of modeling the multiple user reviews associated with the target product, various information can be obtained, such as the sentiment type information expressed in the user reviews (including judgments about positive, negative, or neutral evaluations), the advantages and disadvantages of the target product, the commonalities or similarities between different user reviews, and / or the matching relationship between the target product and the needs / preferences of the target user, etc. Specifically, when generating the target text content, a whole paragraph of text content can be generated, or multiple paragraphs of text content can be generated by summarizing and summarizing from multiple aspects or perspectives, etc.

[0081] It should be noted here that when model understanding is performed on user evaluation content, the user-submitted user evaluation content may include scoring information about some rating items, user-entered evaluation content information, and may also include user-uploaded photos of the actual goods received, product image content, etc. Therefore, the specific model understanding process can be a model understanding of the above multimodal information. In this way, through the fusion of this multimodal information, it is conducive to obtaining more accurate summary results, and at the same time, it can also reduce or eliminate the impact of some user evaluation content that is not accurate. For example, suppose that in a certain user evaluation content, the evaluation text content describes the effect of wearing a product well, but from the user-uploaded wear effect picture, the effect is not very good. Therefore, when generating the specific target text content, the evaluation text content and the wear effect picture can be combined to give a more appropriate conclusion, etc.

[0082] Furthermore, when generating the target text content, it can also incorporate personalized information about the current target user. Specific personalized information can include user-focused factors when selecting products. For example, for clothing products, some users may be more concerned with fabric comfort, others with price, and still others with quality, etc. Therefore, based on the user's focus, personalized processing can be performed when generating the target text content. For example, for users who are concerned with fabric comfort, more or more information about fabric characteristics and user reviews about comfort can be provided, and so on. Furthermore, since the same product may be suitable for some groups but less so for others, this personalized information can also include information about the demographic group to which the current user belongs. For example, this demographic group can be categorized by location, occupation, skin type, etc. Thus, when generating the target text content, a focus can be placed on summarizing reviews provided by users who belong to the same or similar demographic group as the current user. For example, user reviews of a down jacket might indicate that it's more suitable for the colder north and might be too thick for southerners. If the user happens to be from the south, this information can be reflected when generating the target text, for example: "This jacket has a high filling volume and provides good warmth, but it might be too thick for southerners." Another example is a cosmetics product. User reviews show that users with dry skin generally give it positive reviews, while users with oily skin generally give it less positive reviews. Given that the user has dry skin, the target text might include: "It's very moisturizing, so it's a good buy for those with dry skin," etc.

[0083] S202: Return the target text content to the client so that the target text content can be displayed when displaying the user evaluation information.

[0084] After generating specific target text content, it can be provided to the client, which can then display it in the user review content display interface. For example, as shown in the figure on the right side of Figure 3, the target text content generated for the current product can be displayed, which may include five paragraphs, summarizing the user reviews from five aspects, etc. This allows users to more efficiently and quickly understand other users' evaluations of the current product, allowing the user reviews to more effectively help users make shopping decisions.

[0085] In summary, through the embodiments of the present application, when a user needs to view user reviews of a target product, and the target product is associated with multiple user reviews, a target text content that summarizes and summarizes the multiple user reviews can be generated by modeling the multiple user reviews, and this target text content can be displayed to the user. In this way, the user only needs to view the target text content generated by this model to understand other users' overall evaluation of the current product. Therefore, the user can more efficiently achieve a more complete and comprehensive understanding of the user reviews, thereby allowing the user reviews to more effectively help the user make shopping decisions.

[0086] Example 2

[0087] The second embodiment corresponds to the first embodiment and provides a method for processing user evaluation information of a product object from the perspective of a client. Referring to FIG4 , the method may include:

[0088] S401: receiving a request from a target user to view user evaluation content of a target product;

[0089] S402: Displaying a user evaluation content display page, wherein the user evaluation content display page includes target text content, and the target text content is generated by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing, and is used to summarize and express the multiple user evaluation contents.

[0090] Specifically, before displaying the target text content, an interactive option may be provided in the user evaluation content display page so that the user can confirm whether to display the target text content, and upon receiving the confirmation message, the display of the target text content is triggered.

[0091] For details not described in the second embodiment, please refer to the description of the first embodiment and other parts of this specification, which will not be repeated here.

[0092] Example 3

[0093] In the above embodiments 1 and 2, when a user needs to view user reviews about a product, the AI ​​large model can be used to summarize the user reviews and generate target text content for the user's reference. Furthermore, in actual applications, there is also a situation where, due to limited expressiveness or a desire not to spend too much time, a user may only rate some required rating items when posting a review for a product they have already purchased. The body of the review may be very simple, making it difficult for other users to provide an effective reference. On the platform side, users are generally encouraged to describe their experience with the product in as much detail and specificity as possible, which has a positive effect on enhancing user trust in the platform. Therefore, in the third embodiment of the present application, the AI ​​large model can also be used to help users complete the input of user reviews for specific products, thereby producing higher-quality user reviews in a shorter time, while reducing reliance on the user's personal language skills.

[0094] Specifically, the third embodiment of the present application first provides a method for processing user evaluation information of a product object from the perspective of a client. Referring to FIG5 , the method may specifically include:

[0095] S501: In response to a request initiated by a target user to fill in user evaluation information for a target product object, basic evaluation content provided by the target user for the target product object is obtained.

[0096] After placing an order for a product and confirming receipt, a product review option is usually provided to the user. The user can use this option to enter an interface for filling in user review information for the product, that is, the user review content editing interface described in this article.

[0097] In this user review content editing interface, the system typically also provides some scoring items for users to rate. For example, as shown in Figure 6(A), specific scoring items may include description consistency (i.e., whether the actual product matches the information described in the product details page, or the degree of consistency), merchant service (usually referring to the merchant's delivery speed, etc.), logistics service (usually referring to logistics distribution efficiency, etc.), and other aspects. Users can rate based on their actual experience. For example, multiple score levels can be provided for each rating item, and users can choose which score level to give to a specific rating item. The higher the score level obtained by the rating item, the higher the score, and the higher the user's satisfaction with the rating item, etc. In addition, in the above editing interface, users can also be provided with an option for providing a "comprehensive evaluation". Through this option, users can give "good review", "medium review", "bad review" and other options to express emotional types for specific product objects, and users can make choices through this option. Furthermore, in the above editing interface, an input box for inputting the evaluation text content can usually be provided for the user. In addition to scoring the above scoring items, the user can also input specific evaluation text content.

[0098] Therefore, in the application embodiment, the so-called basic evaluation content may include the above-mentioned scoring result information for multiple scoring items, so that the AI ​​big model can generate text content based on this scoring information. Alternatively, the specific basic evaluation content may also be simple information about the expression of emotional types, including good reviews, medium reviews, bad reviews, etc. Alternatively, the specific basic evaluation content may also include the evaluation text content entered by the user. In this way, the AI ​​big model can further produce text content based on the scoring information of the specific scoring items, the emotional type information and / or the evaluation text content already entered by the user.

[0099] S502: Submit the basic evaluation content to the server and obtain the target text content for display, wherein the target text content is the text content generated by the server after inputting the basic evaluation content into the target algorithm model for processing, so as to determine the evaluation text content for publication based on the target text content.

[0100] After receiving the above-mentioned basic evaluation content, the AI ​​big model can assist in generating a paragraph of text content based on the basic evaluation content input by the user. In other words, the user can only give positive or negative emotional information or some rating items to the target product, and then the AI ​​big model will assist in generating a paragraph of text content to be used as the main content of the evaluation or as a reference. Alternatively, after simply filling in some evaluation text content, the AI ​​big model can assist in rewriting it, so that the actual published evaluation text content is fuller and can bring more reference value to other users, while not causing excessive occupation of user time costs, etc.

[0101] Of course, in a specific implementation, in order to avoid interfering with the process of the user actually inputting the user evaluation content, the above-mentioned process of generating the target text content can be performed after receiving the user's confirmation operation. That is to say, an operation option for asking the user can be provided in the above-mentioned editing interface. For example, as shown at 61 in Figure 6(B), a dialogue content of "Would you like me to rewrite it a little?" can be provided in the editing interface, and options such as "later" and "OK" can be provided. If the user selects "OK", it means that the user confirms that the AI ​​large model needs to help rewrite it, and then the step of generating the target text content can be triggered.

[0102] In the above-mentioned manner, the user can first enter the evaluation content editing interface through the "Evaluation" entry provided for the specific order / product object in the order list page, and after providing some basic evaluation content, initiate a request for AI-assisted generation of evaluation content through the operation options in the evaluation content editing interface. Alternatively, in another manner, in order to further improve efficiency, it is also possible to directly provide an "Evaluation" entry in the order list page and other pages, and directly provide "good review", "bad review" and other operation options for expressing emotional types, or directly provide operation options for scoring rating items. In this way, the user can directly make a simple basic evaluation through the operation option, and then trigger AI-assisted generation of evaluation content without having to enter the evaluation content editing interface to trigger it again, so that the user can more efficiently obtain AI-assisted generated user evaluation content, etc.

[0103] Specifically, when generating the target text content, it can be generated by a large AI model through model understanding of the basic evaluation information already entered by the user. Of course, during the generation process, some descriptive information of the product itself can also be combined. In addition, when generating the specific target text content, the user's idiomatic expressions and modal particles can be simulated based on the user's historical user evaluation content, so that the generated target text content is more acceptable to the user, etc.

[0104] After the target text content is generated, it can be displayed in the aforementioned editing interface. For example, as shown at 71 in FIG7(A), when the evaluation text entered by the user is "very suitable for me, diverse users, and high quality", it can be rewritten through the AI ​​large model into: "I recently bought this skirt and I am really satisfied with it. This skirt fits my figure perfectly - not too tight or too loose, this skirt is just right! The quality of the skirt is also very good. The material of this skirt is very thick and I can wear it for a long time. All in all, I will definitely recommend this product."

[0105] After displaying the target text content, the user can also be provided with options such as "Refresh" and "Use It". If the user is not satisfied with the currently generated target text content, the user can select the "Refresh" option. At this time, the model can regenerate the target text content. If "Use It" is selected, the target text content can be displayed in the input control for inputting the evaluation text content, so that the evaluation text content can be determined and published based on the target text content. For example, assuming that the user clicks the "Use It" option for the target text content displayed in Figure 7 (A), the text content can be filled in the input box in the interface as shown at 72 in Figure 7 (B), and the evaluation text content that the user has previously entered will be replaced. Of course, the user can also use the input box to make some edits and polishes to the target text content, etc., and then submit it.

[0106] Through this embodiment three, when a user needs to evaluate a certain commodity object, the AI ​​big model and other capabilities can be used to generate target text content based on the basic evaluation content input by the user, so that the user can complete the input of the evaluation text content based on this target text content. In this way, the user does not have to spend a lot of time to conceive how to write the evaluation content, nor does he need to enter a long evaluation text word for word. Therefore, it can help users improve efficiency and reduce the time cost of users. In addition, for the platform, since the target text content generated by the model may be fuller and richer in content, it is conducive to improving the quality of user evaluation content, providing more valuable reference information for more users, and thus also conducive to improving users' trust and satisfaction with the platform.

[0107] Example 4

[0108] This fourth embodiment corresponds to the third embodiment and provides a method for processing user evaluation information of a product object from the perspective of a server. Referring to FIG8 , the method may include:

[0109] S801: In response to a request for assisting in generating a user review body, obtaining basic review content submitted by a target user for a target product;

[0110] S802: generating target text content by inputting the basic evaluation content into a target algorithm model for processing;

[0111] S803: Return the target text content to the client, so as to determine the evaluation text content according to the target text content for publication.

[0112] For the parts not described in detail in the fourth embodiment, please refer to the description in the third embodiment, which will not be repeated here.

[0113] 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 scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of 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.).

[0114] Corresponding to the first embodiment, the embodiment of the present application further provides a device for processing user evaluation information of a commodity object. Referring to FIG9 , the device may include:

[0115] A target text content generating unit 901 is configured to generate target text content in response to a target user's request to view user evaluation content of a target product by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing, wherein the target text content is used to summarize the multiple user evaluation contents;

[0116] The target text content returning unit 902 is configured to return the target text content to the client so that the target text content can be displayed when displaying the user evaluation information.

[0117] Specifically, the target text content generating unit can be used to:

[0118] By inputting multiple user reviews associated with the target product into a target algorithm model for processing, information on the sentiment type expressed in the user reviews, information on the advantages and disadvantages of the target product, information on the commonalities or similarities between different user reviews, and / or information on the matching relationship between the target product and the needs / preferences of the target user is obtained;

[0119] The target text content is generated by processing the acquired information.

[0120] In addition, the target text content generating unit can be specifically used to:

[0121] The target text content is generated by inputting a plurality of user evaluation contents associated with the target product and the personalized information of the target user into a target algorithm model for processing.

[0122] Corresponding to the second embodiment, this embodiment of the present application further provides a device for processing user evaluation information of a commodity object. Referring to FIG10 , the device may include:

[0123] The request receiving unit 1001 is used to receive a request from a target user to view user evaluation content of a target product;

[0124] Display unit 1002 is used to display a user evaluation content display page, wherein the user evaluation content display page includes target text content, and the target text content is generated by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing, and is used to summarize and express the multiple user evaluation contents.

[0125] The device may further include:

[0126] The interactive option providing unit is used to provide interactive options in the user evaluation content display page before displaying the target text content, so that the user can confirm whether to display the target text content, and trigger the display of the target text content after receiving the confirmation message.

[0127] Corresponding to the third embodiment, the embodiment of the present application further provides a device for processing user evaluation information of a commodity object. Referring to FIG11 , the device may include:

[0128] The basic evaluation content receiving unit 1101 is configured to respond to a request from a target user to fill in user evaluation information for a target product object and obtain basic evaluation content provided by the target user for the target product object;

[0129] The target text content display unit 1102 is used to submit the basic evaluation content to the server and obtain the target text content for display, wherein the target text content is the text content generated by the server after inputting the basic evaluation content into the target algorithm model for processing, so as to determine the evaluation text content for publication based on the target text content.

[0130] The basic evaluation content includes: the emotion type information expressed by the target user for the target product.

[0131] Alternatively, the basic evaluation content includes: rating information input or selected by the target user for the target product object through multiple rating items displayed in the user evaluation content editing interface.

[0132] The basic evaluation content may further include: the evaluation text content input by the target user for the target product through the user evaluation content editing interface.

[0133] In addition, the device may further include:

[0134] The refresh display unit is used to, after displaying the target text content, respond to a refresh request for the target text content, reacquire and display new target text content.

[0135] The text quoting unit is used to display the target text content in an input control for inputting the evaluation text content in response to a request for using the target text content after displaying the target text content, so as to determine the evaluation text content according to the target text content and publish it.

[0136] Corresponding to the fourth embodiment, the embodiment of the present application further provides a device for processing user evaluation information of a commodity object. Referring to FIG12 , the device may include:

[0137] The basic evaluation content acquisition unit 1201 is used to obtain the basic evaluation content submitted by the target user for the target product in response to the request for assisting in generating the user evaluation text content;

[0138] A target text content generating unit 1202 is configured to generate target text content by inputting the basic evaluation content into a target algorithm model for processing;

[0139] The target text content returning unit 1203 is configured to return the target text content to the client so as to determine the evaluation text content based on the target text content for publication.

[0140] In addition, an embodiment of the present application 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 any one of the methods in the aforementioned method embodiments are implemented.

[0141] And an electronic device comprising:

[0142] one or more processors; and

[0143] 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 any one of the aforementioned method embodiments.

[0144] 13 exemplarily shows the architecture of an electronic device. For example, device 1300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, an aircraft, etc.

[0145] 13 , device 1300 may include one or more of the following components: a processing component 1302 , a memory 1304 , a power component 1306 , a multimedia component 1308 , an audio component 1310 , an input / output (I / O) interface 1312 , a sensor component 1314 , and a communication component 1316 .

[0146] The processing component 1302 generally controls the overall operation of the device 1300, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 1302 may include one or more processors 1320 to execute instructions to complete all or part of the steps of the method provided by the technical solution of the present disclosure. In addition, the processing component 1302 may include one or more modules to facilitate interaction between the processing component 1302 and other components. For example, the processing component 1302 may include a multimedia module to facilitate interaction between the multimedia component 1308 and the processing component 1302.

[0147] The memory 1304 is configured to store various types of data to support operations on the device 1300. Examples of such data include instructions for any application or method operating on the device 1300, contact data, phone book data, messages, pictures, videos, etc. The memory 1304 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0148] The power supply component 1306 provides power to the various components of the device 1300. The power supply component 1306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 1300.

[0149] The multimedia component 1308 includes a screen that provides an output interface between the device 1300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1308 includes a front camera and / or a rear camera. When the device 1300 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0150] The audio component 1310 is configured to output and / or input audio signals. For example, the audio component 1310 includes a microphone (MIC) that is configured to receive external audio signals when the device 1300 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 1304 or transmitted via the communication component 1316. In some embodiments, the audio component 1310 also includes a speaker for outputting audio signals.

[0151] I / O interface 1312 provides an interface between processing component 1302 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to, a home button, volume buttons, a start button, and a lock button.

[0152] Sensor assembly 1314 includes one or more sensors for providing various aspects of device 1300 status assessment. For example, sensor assembly 1314 can detect the open / closed state of device 1300, the relative positioning of components, such as the display and keypad of device 1300. Sensor assembly 1314 can also detect changes in the position of device 1300 or a component of device 1300, the presence or absence of user contact with device 1300, the orientation or acceleration / deceleration of device 1300, and changes in the temperature of device 1300. Sensor assembly 1314 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 1314 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 1314 can also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0153] The communication component 1316 is configured to facilitate wired or wireless communication between the device 1300 and other devices. The device 1300 can access a wireless network based on a communication standard, such as WiFi, or a mobile communication network such as 2G, 3G, 4G / LTE, 5G, etc. In an exemplary embodiment, the communication component 1316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1316 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0154] In an exemplary embodiment, the device 1300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described methods.

[0155] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1304 including instructions. The instructions can be executed by a processor 1320 of the device 1300 to perform the method provided by the technical solution of the present disclosure. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0156] Through the description of the above embodiments, it can be seen that 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 this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which 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 of the present application or certain parts of the embodiments.

[0157] 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.

[0158] The above describes in detail the method for processing user evaluation information of commodity objects and the electronic device provided by this application. Specific examples are used herein to illustrate the principles and implementation methods of this application. The description of the above embodiments is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, 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 this application.

Claims

1. A method for processing user evaluation information of a commodity object, It is characterized in that include: In response to a target user's request to view user evaluation content of a target product, a plurality of user evaluation contents associated with the target product are input into a target algorithm model for processing to generate target text content, wherein the target text content is used to summarize the plurality of user evaluation contents; The target text content is returned to the client so that the target text content can be displayed when the user evaluation information is displayed.

2. The method according to claim 1, It is characterized in that The step of inputting a plurality of user evaluation contents associated with the target product into a target algorithm model for processing to generate target text content includes: By inputting multiple user evaluation contents associated with the target product into the target algorithm model for processing, the sentiment type information expressed by the user evaluation contents, the advantages and disadvantages information of the target product, the commonality or similarity information between different user evaluation contents, and / or the matching relationship information between the target product and the needs / preferences of the target user are obtained; The target text content is generated by processing the acquired information.

3. The method according to claim 1, It is characterized in that The step of inputting a plurality of user evaluation contents associated with the target product into a target algorithm model for processing to generate target text content includes: The target text content is generated by inputting a plurality of user evaluation contents associated with the target commodity and the personalized information of the target user into a target algorithm model for processing.

4. A method for processing user evaluation information of a commodity object, It is characterized in that include: Receive a request from a target user to view user evaluation content of a target product; A user evaluation content display page is displayed, wherein the user evaluation content display page includes target text content, and the target text content is generated by inputting multiple user evaluation contents associated with the target product into a target algorithm model for processing, and is used to summarize and express the multiple user evaluation contents.

5. The method according to claim 4, It is characterized in that Also includes: Before displaying the target text content, an interactive option is provided in the user evaluation content display page so that the user can confirm whether to display the target text content, and after receiving the confirmation message, the display of the target text content is triggered.

6. A method for processing user evaluation information of a commodity object, It is characterized in that include: In response to a request initiated by a target user to fill in user evaluation information for a target commodity object, obtaining basic evaluation content provided by the target user for the target commodity object; The basic evaluation content is submitted to the server, and the target text content is obtained for display, wherein the target text content is the text content generated by the server after inputting the basic evaluation content into the target algorithm model for processing, so as to determine the evaluation text content for publication according to the target text content.

7. The method according to claim 6, It is characterized in that The basic evaluation content includes: the emotion type information expressed by the target user for the target product.

8. The method according to claim 6, It is characterized in that The basic evaluation content includes: the rating information input or selected by the target user for the target commodity object through a plurality of rating items displayed in the user evaluation content editing interface.

9. The method according to claim 6, It is characterized in that The basic evaluation content also includes: the evaluation text content input by the target user for the target product through the user evaluation content editing interface.

10. The method according to claim 6, It is characterized in that Also includes: After the target text content is displayed, in response to a refresh request for the target text content, new target text content is reacquired and displayed.

11. The method according to claim 6, It is characterized in that Also includes: After the target text content is displayed, in response to a request to use the target text content, the target text content is displayed in an input control for inputting evaluation text content, so that the evaluation text content is determined and published according to the target text content.

12. A method for processing user evaluation information of a commodity object, It is characterized in that include: In response to a request for assisting in generating a user evaluation text content, obtaining basic evaluation content submitted by a target user for a target product; The target text content is generated by inputting the basic evaluation content into the target algorithm model for processing; The target text content is returned to the client so that the evaluation text content is determined according to the target text content for publication.

13. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the steps of the method described in any one of claims 1 to 12 are implemented.

14. An electronic device, It is characterized in that include: one or more processors; as well as 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 any one of claims 1 to 12.

Images