Method, medium, device and program product for displaying product information and recommending products

Abstract

A method, medium, device and program product for displaying product information and recommending products, the method comprising: obtaining a plurality of product tags to be sorted; obtaining priority information of the plurality of product tags, the priority information being obtained by sorting the plurality of product tags based on a user portrait of a target user; obtaining product information of target products to be pushed to the target user corresponding to the plurality of product tags; and displaying the product information of the target products corresponding to the plurality of product tags to the target user according to the priority information.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, medium, device and program product for displaying product information and recommending products. Background Art

[0002] In e-commerce scenarios, when pushing products to users, product information related to certain product tags is usually displayed to help users quickly obtain the characteristics and advantages of the product. However, there are many types of product tags, and the current product information display method usually displays product information corresponding to several product tags in a fixed order, which cannot meet the personalized needs of different users. Summary of the invention

[0003] In a first aspect, an embodiment of the present application provides a method for displaying product information, the method comprising: obtaining multiple product tags to be sorted; obtaining priority information of the multiple product tags, the priority information being obtained by sorting the multiple product tags based on a user portrait of a target user; obtaining product information of target products to be pushed to the target user corresponding to the multiple product tags respectively; and displaying the product information of the target products corresponding to the multiple product tags respectively to the target user according to the priority information.

[0004] In a second aspect, an embodiment of the present application provides a product recommendation method, the method comprising: obtaining a product recommendation request from a target user; determining a product to be recommended in response to the product recommendation request; obtaining multiple items of product information of the product, the multiple items of product information corresponding to multiple product tags respectively; based on priority information of the multiple product tags, displaying multiple items of product information corresponding to the multiple product tags respectively to the target user, the priority information being obtained by sorting the multiple product tags based on a user portrait of the target user.

[0005] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present application.

[0006] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present application when executing the computer program.

[0007] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in any embodiment of the present application.

[0008] In an embodiment of the present application, product information of target products corresponding to multiple product tags is displayed to target users according to priority information of multiple product tags. Since the priority information is obtained by sorting multiple product tags based on the user portrait of the target user, that is, the priority information can reflect the personalized needs of the user, the present application realizes customization of the display order of product information of multiple product tags for users based on user needs, so that the display order of product information of multiple product tags is more in line with the personalized needs of users.

[0009] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings herein are incorporated into the specification and constitute a part of the present application. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solutions of the present application.

[0011] Figure 1 It is a schematic diagram of an application scenario of an embodiment of the present application.

[0012] Figure 2 It is a flowchart of the method for displaying product information of an embodiment of the present application.

[0013] Figure 3 It is a schematic diagram of priority information of multiple product tags under different product categories in an embodiment of the present application.

[0014] Figure 4 It is a schematic diagram of the priority information before and after adjustment of an embodiment of the present application.

[0015] Figure 5 It is a schematic diagram of priority information under different designated pages in an embodiment of the present application.

[0016] Figure 6 It is a schematic diagram of the system architecture of an embodiment of the present application.

[0017] Figure 7 It is a flow chart of the product recommendation method of an embodiment of the present application.

[0018] Figure 8 It is a block diagram of a device for displaying commodity information according to an embodiment of the present application.

[0019] Fig. 9 It is a block diagram of a product recommendation device according to an embodiment of the present application.

[0020] Fig.10 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0022] The terms used in this application are only for the purpose of describing specific embodiments, and are not intended to limit the application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a variety of.

[0023] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0024] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application and to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and understandable, the technical solutions in the embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0025] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0026] In e-commerce scenarios, when pushing products to users, product information related to certain product tags is usually displayed to help users quickly obtain the characteristics and advantages of the product. Product tags include but are not limited to product price tags, discount tags, logistics tags, sales tags, user evaluation tags, inventory tags, tags used to indicate whether the product is new (referred to as new product indication tags), tags related to the product's industry certificates (referred to as certificate tags), and tags related to the product's return and exchange policies (referred to as return and exchange tags). Each product tag corresponds to a type of product information. For example, the price tag corresponds to the price information of the product; the discount tag corresponds to the discount information of the product, such as full-discount information, discount information, gift information, etc.; the logistics label corresponds to the logistics information of the product, such as logistics time, estimated delivery time, delivery method, etc.; the sales label corresponds to the sales information of the product, such as sales value or sales ranking information; the user evaluation label corresponds to the user evaluation information of the product, such as the praise rate, the number of user evaluations, etc.; the inventory label corresponds to the inventory information of the product, such as the remaining inventory; the new product indication label corresponds to the shelf time and freshness of the product, such as "new products of the month", "new products of the season", etc.; the certificate label corresponds to the certificate information of the product, such as patent certificate, safety certification certificate, certificate of origin, etc.; the return and exchange label corresponds to the return and exchange policy of the product, such as "7-day no-reason return", "freight insurance", etc. Figure 1 A schematic diagram of an application scenario of some embodiments is shown. In the application scenario, a server 10 and a client 20 are included. The server 10 can push product information to the client 20 for display. The product information displayed by the client 20 includes product information corresponding to multiple product tags. In this embodiment, the multiple product tags include price tags, discount tags, new product indication tags, and sales tags. It can be understood that this is only an exemplary description. In other examples, the product tags may also include other tags.

[0027] The current product information display method usually displays product information corresponding to several product labels in a fixed order. For example, the product information corresponding to the price label is fixedly displayed before the product information corresponding to the discount label, and the product information corresponding to the new product indicator label is displayed after the product information corresponding to the discount label. However, different users may pay attention to different types of product information, and the above label display method cannot meet the personalized needs of different users.

[0028] Based on this, this application provides a method for displaying product information, see Figure 2 , the method comprising:

[0029] Step S12: obtaining multiple product labels to be sorted;

[0030] Step S14: obtaining priority information of multiple product tags, where the priority information is obtained by sorting the multiple product tags based on the user profile of the target user;

[0031] Step S16: Obtaining product information of target products to be pushed to target users that correspond to the above multiple product tags;

[0032] Step S18: displaying the product information of the target product corresponding to the above-mentioned multiple product tags to the target user according to the priority information.

[0033] This application sorts multiple product tags based on the user portrait of the target user to obtain priority information of the multiple product tags, and displays the product information of the target product corresponding to the multiple product tags to the target user according to the priority information, thereby customizing the display order of the product information of the multiple product tags for the user based on the user's needs, so that the display order of the product information of the multiple product tags is more in line with the personalized needs of the user. The specific implementation method of this application is illustrated below.

[0034] In step S12, the multiple product labels to be sorted can be determined based on the target product to be pushed to the target user, and different categories of target products can have different product labels. For example, the multiple product labels to be sorted for food target products can include taste labels, business ingredient labels, and origin labels, and the multiple product labels to be sorted for electronic target products can include certificate labels, function labels, and energy consumption labels. Alternatively, the multiple product labels to be sorted for different categories of target products can also be the same, based on which, the multiple product labels to be sorted can be the full range of product labels on the e-commerce platform.

[0035] In step S14, multiple product tags can be sorted based on the user portrait of the target user to obtain priority information of the above multiple product tags. The user portrait of the target user is a virtual model constructed based on the user information and behavior data of the target user to describe the characteristics and preferences of the target user. The user information may include but is not limited to some or all of the following: the user's age, gender, occupation, the user group category to which the user belongs (such as individual users, retailer users, wholesaler users, manufacturer users, etc.), the user's life cycle on the e-commerce platform (such as new users, active users, returning users, lost users, etc.), the user's membership level on the e-commerce platform, the user's registration area, delivery address, etc. The behavior data includes the target user's behavior operations on the e-commerce platform within a preset time period, such as browsing, clicking, adding to cart, collecting, purchasing, returning, sharing, etc. Based on the user portrait of the target user, the preferences (such as product preferences, logistics preferences, after-sales service preferences, transaction method preferences, etc.) and personalized needs of the target user can be determined. For example, if the target user is a wholesaler user, the target user may prefer low-priced products of the same type; for another example, if the target user has purchased electronic products with "long battery life" performance many times in the past period of time, the target user may prefer electronic products with higher battery life. Therefore, multiple product tags can be sorted based on the user portrait of the target user to obtain priority information of multiple product tags.

[0036] The priority information obtained in the above manner can represent the target user's interest in the product information corresponding to multiple label categories. Continuing with the previous example, the target user who prefers low-priced products may have a higher interest in the product information corresponding to the price tag. Therefore, for such users, a higher priority information can be set for the price tag; and the target user who prefers electronic products with longer battery life may have a higher interest in the product information corresponding to the product function tag. Therefore, for such users, a higher priority information can be set for the product function tag.

[0037] Furthermore, the product information that the same user pays attention to for products in different product categories may be different. Figure 3 For fresh products (such as steak), users may pay more attention to logistics efficiency, while for clothing products (such as T-shirts), users may pay more attention to product discount information. Therefore, the user portrait and the target product category to which the target product belongs can be combined to sort the above multiple product tags to obtain priority information of the above multiple product tags. On this basis, the priority information of the above multiple product tags is the priority information of the multiple product tags under the target product category. The priority information of the multiple product tags under the target product category is used to characterize the target user's interest in the multiple label categories of the target product in the target product category. Continue to see Figure 3, assuming that multiple product tags include discount tags, new product indication tags, logistics tags and sales volume tags, the priority information of the above tags under the food category (hereinafter referred to as priority information 1) and the priority information of the above tags under the electronic category (hereinafter referred to as priority information 2) can be obtained respectively. Since users pay more attention to logistics efficiency for fresh products and pay more attention to discount information for clothing products, priority information 1 can be the priority of logistics tags, discount tags, sales volume tags and new product indication tags in descending order, while priority information 2 can be the priority of discount tags, new product indication tags, logistics tags and sales volume tags in descending order. In the above manner, different priority information can be used for multiple product tags to be sorted under different product categories, which improves the matching degree of priority information and product categories, and at the same time improves the flexibility of label sorting.

[0038] In some embodiments, the priority information may be obtained by pre-sorting multiple product tags by the large language model based on the user portrait of the target user. Further, in an embodiment where the priority information is obtained based on both the user portrait and the product category, the priority information may be obtained by pre-sorting multiple product tags by the large language model based on the user portrait of the target user and the target product category.

[0039] Since the sorting of the large language model takes a long time, in order to reduce the impact of the sorting process of the large language model on the product information display process, the priority information can be obtained by the large language model in advance in an offline manner and stored locally. When it is necessary to display product information, the priority information stored locally can be directly obtained, and the product information can be displayed based on the obtained priority information, without waiting for the large language model to output the sorting results of multiple product tags, which improves the efficiency of the product information display process and thus improves the user experience.

[0040] In some embodiments, user needs may change over time, so the priority information of the above-mentioned multiple product tags can also be updated regularly. Specifically, the user portrait of the target user can be updated at a preset time interval, and the priority information regenerated based on the updated user portrait can be obtained. In the above manner, the priority information obtained can be more matched with the user's needs in the recent period of time. In the example where the priority information is obtained by the large language model based on the user portrait and the target product category, the user portrait of the target user can be updated at a preset time interval, the priority information regenerated by the large language model based on the updated user portrait and the target product category can be obtained, and the priority information stored locally can be updated based on the priority information regenerated by the large language model. In this way, on the one hand, the priority information obtained can be more matched with the user's needs in the recent period of time. On the other hand, since the priority information is pre-acquired and stored locally by the large language model, there is no need to wait for the large language model to output the sorting results of multiple product tags when displaying product information, which improves the efficiency of the product information display process.

[0041] In the above example, the user portrait and the target product category mainly reflect the long-term needs of the user, so the priority information obtained mainly matches the long-term needs of the user. However, the user's immediate needs may be different from the long-term needs. For example, in the long run, users prefer electronic products with longer battery life, that is, the priority of the functional label of the product is higher; but the user currently uses the keyword "same-day delivery" when searching for electronic products, indicating that the user is currently more concerned about logistics efficiency, so a higher priority should be set for the logistics efficiency label. Therefore, in order to make the obtained priority information more consistent with the user's immediate needs, the locally stored priority information can also be adjusted according to the real-time information obtained. Among them, the real-time information obtained may include the real-time input information of the target user and / or the information of the designated page (such as search page, recommendation page, promotion page, etc.) used to display the target product. The real-time input information can reflect the search needs of the target user, and the information of the designated page used to display the target product can reflect the scene in which the target user browses the product information. Therefore, both of the above information can reflect the immediate needs of the target user to a certain extent.

[0042] In some embodiments, real-time input information of a target user may be obtained, the real-time input information includes at least one product tag, and the priority information stored locally may be adjusted based on the at least one product tag included in the real-time input information. For example, the priority of a product tag included in the real-time input information may be higher than the priority of a product tag not included in the real-time input information. In this way, the influence of the user's immediate needs on the result of obtaining the priority information can be enhanced, so that the obtained priority information better matches the user's immediate needs. Figure 4 , the real-time input information is "new women's clothing", which includes a new product indication label (as shown in the "new product" in the figure). It can be seen that before the adjustment, the priority information stored locally is the discount label, the new product indication label and the logistics label, and the priority is reduced in turn, so that the displayed product information is the product information corresponding to the discount label ("30 off for purchases over 300"), the product information corresponding to the new product indication label ("new products of the month"), and the product information corresponding to the logistics label ("free shipping"). After the adjustment, the priority information is the new product indication label, the discount label and the logistics label, and the priority is reduced in turn, so that the displayed product information is the product information corresponding to the new product indication label ("new products of the month"), the product information corresponding to the discount label ("30 off for purchases over 300"), and the product information corresponding to the logistics label ("free shipping").

[0043] Alternatively, in some other embodiments, the target product is a product to be displayed on a specified page. The type of the specified page can be obtained, and the type of the specified page is related to the target user's browsing intention for the target product. The priority information stored locally is adjusted based on the type of the specified page. For example, a correspondence between the type of the specified page and the preset product tag can be pre-established, and the priority of the preset product tag corresponding to the type of the specified page can be set higher than the priority of other product tags. In this way, the influence of the user's immediate needs on the acquisition result of the priority information can be enhanced, so that the acquired priority information is more in line with the user's immediate needs. See Figure 5 When the designated page is a promotion page, the priority information is the discount tag, new product indication tag, logistics tag and sales tag, with the priority decreasing in turn; when the designated page is a search page, the priority information is the sales tag, discount tag, new product indication tag and logistics tag, with the priority decreasing in turn.

[0044] In step S16, the product information of the target products to be pushed to the target users corresponding to the above-mentioned multiple product tags can be obtained. Here, the product tag can be regarded as the field name or the key of the key-value pair, and the product information corresponding to the product tag can be regarded as the field value or the value of the key-value pair. For example, assuming that multiple product tags include a logistics tag, the product information corresponding to the logistics tag can be information such as "same-day delivery" or "Logistics efficiency TOP 5"; for another example, assuming that multiple product tags include a discount tag, the product information corresponding to the discount tag can be information such as "30 off for purchases over 300" or "9.5% off".

[0045] In step S18, the product information of the target product corresponding to the multiple product tags can be displayed according to the priority information determined in the above steps. For example, the method of the present application can be executed by the server 10, and the server 10 can send the priority information and the product information corresponding to the multiple product tags to the client 20, so that the client 20 displays the product information of the target product corresponding to the multiple product tags based on the priority information.

[0046] Further, a preset number of target product tags to be displayed can be determined from multiple product tags according to the priority information. Among them, the preset number is less than the total number of multiple product tags. Then, the product information of the target product corresponding to the preset number of target product tags can be displayed to the target user. For example, assuming that the total number of multiple product tags is 100, the target product tags with the top 3 priorities (that is, the preset number is equal to 3) can be selected according to the priority information, and the product information corresponding to these three target product tags can be displayed. For example, assuming that the target product tags with the top 3 priorities include logistics tags, discount tags, and sales tags, and the priorities of logistics tags, discount tags, and sales tags decrease in sequence, then the product information corresponding to the logistics tags (such as "same-day delivery"), the product information corresponding to the discount tags (such as "30 minus 300"), and the product information corresponding to the sales tags (such as "top 10 sales") can be displayed in sequence.

[0047] The solution of the present application is described below with reference to a specific embodiment.

[0048] In the cross-border e-commerce scenario with a high diversity of users and products, how to accurately display the selling points of users' favorite products to different users has become a key to user experience. Although the existing recommendation system has made progress in recommending products, there is still room for optimization in the detailed label display of individual products. Specifically, when there are many selling points of a product, how to quickly display the product labels that users are most concerned about. Based on this, this application has introduced a set of innovative solutions: an intelligent label sorting and display system. The system uses identity recognition, product classification, and product labels as basic data. Relying on a large language model, it sorts product labels in an intelligent way. It not only customizes the display content according to the user's identity, but also displays the most attractive product labels under different product categories, thereby improving user experience and purchase conversion rate. The overall system diagram is as follows: Figure 6 As shown, the following are the specific implementation details of this solution:

[0049] Step 1: Maintain basic data such as product categories and product label data. Classify and maintain products on the e-commerce platform, establish a product category system, and ensure that most products can be accurately classified, thereby providing a basis for subsequent label analysis and sorting. Define and maintain product labels, such as minimum order quantity (MOQ), page views, sales volume, company information, product certification, customizability, new products, return guarantee, delivery time guarantee, etc., to ensure that each product has complete and accurate label information. These product labels will be displayed to users as the core selling points of the products.

[0050] Step 2: User identification. By collecting basic information and behavioral data of users, and conducting data analysis, artificial intelligence, search engines, etc. on basic information, website visit records, order information, etc., we build user portraits (such as identifying users as retailers, wholesalers, or traders) and extract user identity characteristics and preferences. Only after clarifying the user's identity and preferences can we provide the user with the most effective information.

[0051] Step 3: Intelligent tag sorting using a large language model. Use a large language model to analyze user portraits and product tags, determine the user's interest in each product tag under the current product category, intelligently sort the product tags, and generate priority information based on user preferences. Since the time required to generate priority information in real time may be too long, resulting in a poor user experience, the intelligent sorting process can be produced offline and updated regularly.

[0052] Step 4: Dynamically display product tags and their corresponding product information. Based on the priority information obtained by the large language model, dynamically adjust the display order of product tags and their corresponding product information on the product page to ensure that the most important and user-attracting product tags are displayed first, thereby improving user experience and purchase intention.

[0053] This application has the following advantages:

[0054] (1) Personalized tag sorting: Compared with traditional recommendation systems and tag display systems, this application can dynamically adjust the display order of product tags for a single product based on user portraits and product categories. This solves the problem of fixed and single product tags in existing systems, and improves user browsing efficiency and experience.

[0055] (2) Intelligent optimization: Utilize the advanced natural language processing capabilities of the large language model to accurately determine and sort user preferences. Maintain a high degree of matching by regularly updating user portraits and product label weights. It is more flexible and accurate than systems that rely on fixed rules and historical data, and ensures that the system can adapt to changes in user behavior and preferences through regular updates.

[0056] (3) Multi-dimensional data analysis: This application takes both user profiles and product categories into consideration. Compared with systems that rely solely on historical behavior data, this multi-dimensional analysis method can provide a more comprehensive understanding of user needs.

[0057] See also Figure 7 The present application also provides a product recommendation method, the method comprising:

[0058] Step S22: Obtaining a product recommendation request from a target user;

[0059] Step S24: determining the product to be recommended in response to the product recommendation request;

[0060] Step S26: obtaining multiple items of product information of the product to be recommended, wherein the multiple items of product information correspond to multiple product tags respectively;

[0061] Step S28: Based on the priority information of the multiple product tags, multiple items of product information corresponding to the multiple product tags are displayed to the target user, wherein the priority information is obtained by sorting the multiple product tags based on the user portrait of the target user.

[0062] In step S22, the server 10 may obtain a product recommendation request from the target user, which may be sent via a client 20 installed on a client device, including but not limited to a mobile phone, a tablet computer, a laptop computer, a PC, etc. The client 20 may generate a product recommendation request and send the product recommendation request to the server 10 when the target user performs a search operation or enters a specified page.

[0063] In step S24, a commodity recommendation algorithm may be used to determine commodities to be recommended, and the number of commodities to be recommended may be greater than or equal to one.

[0064] In step S26, for each product to be recommended, multiple items of product information of the product can be obtained, and each item of product information corresponds to a product label. For example, product labels include but are not limited to price tags, discount tags, logistics tags, sales tags, user evaluation tags, inventory tags, etc. The price tag corresponds to the price information of the product; the discount tag corresponds to the discount information of the product, such as full-reduction information, discount information, gift information, etc.; the logistics tag corresponds to the logistics information of the product, such as logistics time, estimated delivery time, delivery method, etc.; the sales tag corresponds to the sales information of the product, such as sales value or sales ranking information; the user evaluation tag corresponds to the user evaluation information of the product, such as the praise rate, the number of user evaluations, etc.; the inventory tag corresponds to the inventory information of the product, such as the remaining inventory.

[0065] In step S28, based on the priority information of the multiple product tags, multiple items of product information corresponding to the multiple product tags can be displayed to the target user. For example, assuming that the priority information of the multiple product tags is from high to low: price tag, discount tag, logistics tag, user evaluation tag, then the order of display of the various product information displayed to the target user is: product information corresponding to the price tag, product information corresponding to the discount tag, product information corresponding to the logistics tag, and product information corresponding to the user evaluation tag. The specific implementation method of this step can be found in the aforementioned embodiment, which will not be repeated here.

[0066] By adopting the above scheme, the present application can customize the display order of multiple product information of recommended products for target users according to the personalized needs of target users when recommending products to target users, so that the display order of product information is more in line with the personalized needs of users.

[0067] See also Figure 8 The present application also provides a device for displaying commodity information, the device comprising:

[0068] A first acquisition module 202 is used to acquire multiple product labels to be sorted;

[0069] A second acquisition module 204 is used to acquire priority information of the multiple product tags, wherein the priority information is obtained by sorting the multiple product tags based on the user portrait of the target user, and the priority information is used to represent the interest of the target user in the product information corresponding to the multiple tag categories respectively;

[0070] The third acquisition module 206 is used to acquire the commodity information of the target commodity to be pushed to the target user corresponding to the multiple commodity tags respectively;

[0071] The first display module 208 is used to display the product information of the target product corresponding to the multiple product tags to the target user according to the priority information.

[0072] The functions or modules included in the device provided in the present application can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0073] See also Fig. 9 The present application also provides a product recommendation device, the device comprising:

[0074] The fourth acquisition module 302 is used to obtain a product recommendation request from a target user;

[0075] A determination module 304, configured to determine a product to be recommended in response to a product recommendation request;

[0076] A fifth acquisition module 306 is used to acquire multiple items of product information of the product to be recommended, where the multiple items of product information correspond to multiple product tags respectively;

[0077] The second display module 308 is used to display multiple items of product information corresponding to the multiple product tags to the target user based on the priority information of the multiple product tags, and the priority information is obtained by sorting the multiple product tags based on the user portrait of the target user.

[0078] An embodiment of the present application further provides a computer device, which comprises at least a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any of the foregoing embodiments is implemented.

[0079] Fig.10 A more specific hardware structure diagram of a computer device provided in an embodiment of the present application is shown, and the device may include: a processor 402, a memory 404, an input / output interface 406, a communication interface 408, and a bus 410. The processor 402, the memory 404, the input / output interface 406, and the communication interface 408 are connected to each other in communication within the device through the bus 410.

[0080] The processor 402 can be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing relevant programs to implement the technical solutions provided in the embodiments of the present application. The processor 402 can also include a graphics card, which can be a Nvidia titan X graphics card or a 1080Ti graphics card, etc.

[0081] The memory 404 can be implemented in the form of a read-only memory (ROM), a random access memory (RAM), a static storage device, a dynamic storage device, etc. The memory 404 can store an operating system and other application programs. When the technical solution provided in the embodiment of the present application is implemented by software or firmware, the relevant program code is stored in the memory 404 and is called and executed by the processor 402.

[0082] The input / output interface 406 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0083] The communication interface 408 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0084] The bus 410 comprises a pathway for transmitting information between the various components of the device, such as the processor 402 , the memory 404 , the input / output interface 406 , and the communication interface 408 .

[0085] It should be noted that, although the above device only shows the processor 402, the memory 404, the input / output interface 406, the communication interface 408 and the bus 410, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiment of the present application, and does not necessarily include all the components shown in the figure.

[0086] An embodiment of the present application provides a computer program product, including a computer program, which implements the method described in any embodiment of the present application when executed by a processor.

[0087] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the foregoing embodiments.

[0088] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computer device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0089] Each embodiment in the present application is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. The device embodiment described above is merely schematic, wherein the modules described as separate components may or may not be physically separated, and the functions of each module can be implemented in the same one or more software and / or hardware when implementing the embodiment scheme of the present application. It is also possible to select some or all of the modules according to actual needs to achieve the purpose of the embodiment scheme. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0090] The above is only a specific implementation of the embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the embodiment of the present application. These improvements and modifications should also be regarded as the protection scope of the embodiment of the present application.

Claims

1. A method for displaying commodity information, the method comprising: Get multiple product tags to be sorted; Obtaining priority information of the multiple product tags, where the priority information is obtained by sorting the multiple product tags based on a user profile of a target user; Acquire product information of target products to be pushed to the target user corresponding to the multiple product tags respectively; According to the priority information, the product information of the target product corresponding to the multiple product tags is displayed to the target user.

2. According to the method of claim 1, the priority information is used to represent the target user's interest in the product information corresponding to the multiple tag categories.

3. According to the method according to claim 2, the priority information of the multiple product tags is the priority information of the multiple product tags under the target product category, and the priority information of the multiple product tags under the target product category is used to characterize the target user's interest in the multiple tag categories of the target product in the target product category.

4. The method according to claim 3, wherein obtaining priority information of the plurality of product tags comprises: Get priority information of local storage; The priority information stored locally is obtained by pre-sorting the multiple product tags based on the user portrait of the target user and the target product category by a pre-trained large language model.

5. The method according to claim 4, further comprising: Updating the user profile of the target user at a preset time interval; The priority information regenerated by the large language model based on the updated user portrait and the target product category is obtained, and the locally stored priority information is updated based on the priority information regenerated by the large language model.

6. According to the method of claim 1, the priority information of the plurality of product tags is acquired in advance by a large language model based on the user profile of the target user and stored locally; the method further comprises: Acquire real-time input information of the target user; The real-time input information includes at least one product tag; The locally stored priority information is adjusted based on at least one product tag included in the real-time input information.

7. According to the method of claim 1, the priority information of the plurality of product tags is obtained in advance by a large language model based on the user profile of the target user and stored locally, and the target product is a product to be displayed on a designated page; the method further comprises: Get the type of the specified page; The type of the designated page is related to the target user's browsing intention for the target product; The locally stored priority information is adjusted based on the type of the designated page.

8. The method according to claim 1, wherein displaying the product information of the target product corresponding to the multiple product tags to the target user according to the priority information comprises: According to the priority information, determining a preset number of target product tags to be displayed from the multiple product tags; The preset number is less than the total number of the plurality of product labels; The product information of the target products corresponding to the preset number of target product labels is displayed to the target user.

9. A product recommendation method, the method comprising: Get the product recommendation request from the target user; Determining a product to be recommended in response to the product recommendation request; Acquire multiple items of product information of the product, where the multiple items of product information correspond to multiple product tags respectively; Based on the priority information of the multiple product tags, multiple pieces of product information corresponding to the multiple product tags are displayed to the target user, and the priority information is obtained by sorting the multiple product tags based on the user portrait of the target user.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 9.

11. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 9 when executing the computer program.

12. A computer program product, comprising a computer program, which implements the method according to any one of claims 1 to 9 when executed by a processor.

Images