Online shopping system and commodity brief introduction information display method

By introducing a product introduction model in the online shopping system, using intelligent introduction controls to generate concise product introduction information, the information overload problem is solved and the user's shopping experience and transaction efficiency are improved.

CN120338915APending Publication Date: 2025-07-18ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510397846.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-28
Publication Date
2025-07-18

AI Technical Summary

Technical Problem

In the existing online shopping system, the product details page information is overloaded, making it difficult for users to quickly and efficiently obtain core selling points and key elements, affecting browsing efficiency and shopping experience.

Method used

Introduce product introduction model in the shopping system, and refine and process detailed information through intelligent introduction controls, generate concise introduction information, and display the core selling points and key elements of the product.

Benefits of technology

Users can quickly and accurately understand the core selling points and key elements of the product without viewing the detailed information one by one, simplify the operation process, and improve shopping efficiency and transaction rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120338915A_ABST
    Figure CN120338915A_ABST
Patent Text Reader

Abstract

One or more embodiments of the invention provide an online shopping system and a commodity brief introduction information display method. The method comprises the following steps: displaying an intelligent brief introduction control for a target commodity in a commodity related interface; in response to triggering of the intelligent brief introduction control, brief introduction information of the target commodity is obtained and displayed, and the brief introduction information is obtained by reasoning detailed information of the target commodity through a commodity brief introduction model. Through the scheme, the user can quickly and accurately know the core selling point and the key elements of the target commodity without checking detailed information one by one or even opening a detailed page, so that the user operation is simplified, and the commodity transaction is promoted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] One or more embodiments of this specification relate to the field of online shopping, and in particular, to an online shopping system and a method for displaying product profile information. Background Art

[0002] Consumers can view product-related information through online shopping websites and then place orders to complete online shopping. Online shopping websites usually display product-related information on the product details page for users to view.

[0003] At present, a wide variety and large quantity of product-related information, such as parameter specifications, user reviews, promotional activities, after-sales services, etc., are usually displayed on the details page, resulting in cluttered page content and lack of emphasis, which is not conducive to users' efficient viewing and quick transactions. Summary of the Invention

[0004] In view of this, one or more embodiments of this specification provide the following technical solutions:

[0005] According to the first aspect of one or more embodiments of this specification, a method for displaying product profile information is proposed, including:

[0006] Displaying an intelligent profile control for a target product in a product-related interface;

[0007] In response to the intelligent profile control being triggered, obtaining and displaying the profile information of the target product, where the profile information is obtained by a product profile model reasoning about the detailed information of the target product.

[0008] According to the second aspect of one or more embodiments of this specification, an online shopping system is proposed, including a shopping client and a shopping server, where:

[0009] The shopping server is used to call a product profile model to reason about the detailed information of a target product to obtain the profile information of the target product;

[0010] The shopping client is used to display an intelligent profile control for the target product in a product-related interface, and, in response to the intelligent profile control being triggered, obtain and display the profile information.

[0011] According to the third aspect of one or more embodiments of this specification, an electronic device is proposed, including: a processor; a memory for storing processor-executable instructions; where the processor realizes the steps of the method as described in the first aspect by running the executable instructions.

[0012] According to a fourth aspect of one or more embodiments of this specification, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0013] According to a fifth aspect of one or more embodiments of this specification, a computer program product is provided, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0014] As can be seen from the above embodiments, this specification proposes an online shopping system and an information display solution implemented by a shopping client in the system. In this solution, the shopping client will display an intelligent profile control for a target product in the product-related interface; then, in response to the intelligent profile control being triggered, the profile information of the target product is obtained and displayed, and the profile information is inferred from the detailed information of the target product by a product profile model.

[0015] This solution realizes the refined processing of detailed information by leveraging the powerful information extraction function of the product profile model. It can be understood that, compared with the detailed information of the target product, the profile information is more concise (i.e., less data volume), and can more intuitively and prominently reflect the core selling points and key elements of the product. Based on this, users can quickly and accurately learn the core selling points and key elements of the target product without having to view the detailed information one by one or even open the details page, which helps to simplify user operations and promote product transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of the architecture of an online shopping system provided by an exemplary embodiment.

[0017] Figure 2 is a flowchart of a method for displaying product profile information provided by an exemplary embodiment.

[0018] Figures 3 to 6 are schematic diagrams of various display effects of intelligent profile controls provided by various exemplary embodiments.

[0019] Figure 7 is a schematic diagram of the display effect of a profile information provided by an exemplary embodiment.

[0020] Figure 8 is a schematic diagram of the structure of a device provided by an exemplary embodiment.

[0021] Figure 9 is a block diagram of a device for displaying product profile information provided by an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Consumers can view product - related information through an online shopping website and then place an order to complete online shopping. Online shopping websites usually display product - related information on the product detail page for users to view.

[0023] At present, a wide variety and large quantity of product - related information, such as parameter specifications, user reviews, promotional activities, after - sales services, etc., are usually displayed on the detail page, resulting in cluttered page content, lack of focus, and being unfavorable for users to view efficiently and complete transactions quickly.

[0024] For example, when a user searches for a smartphone, the product detail page may display dozens of technical parameters, hundreds of user reviews, and various preferential information simultaneously. Users have to spend a lot of time screening and reading to find the core selling points they care about, such as camera performance or battery life. This information overload phenomenon not only reduces the user's browsing efficiency but also may lead to decision - making fatigue and affect the shopping experience.

[0025] To solve the aforementioned technical problems in the related technologies, this specification proposes an online shopping system and a display solution for product brief information implemented by a shopping client in the system. That is, by leveraging the powerful information extraction function of a product brief model (especially a large model), the detailed information of a product is summarized and processed, and the refined brief information is displayed to consumers so that users can quickly and accurately learn the core selling points and key elements of the target product. The following will explain this solution in combination with the accompanying drawings and related embodiments.

[0026] Figure 1 is a schematic diagram of the architecture of an online shopping system provided by an exemplary embodiment. As Figure 1 shown, the system may include a server 11, a network 10, and several electronic devices, such as mobile phones 13, 14, 15, etc.

[0027] The server 11 may be a physical server containing an independent host, or the server 11 may be a virtual server hosted by a host cluster. During operation, the server 11 may run the server - side program of an application to implement the related functions of the application. For example, when the server 11 runs the program of the online shopping service, it can be implemented as the service - side of the online shopping service (hereinafter referred to as the shopping service - side).

[0028] A mobile phone is just one of the types of electronic devices that users can use. In fact, users (i.e., consumers with online shopping needs) can obviously also use electronic devices such as the following types: PC (Personal Computer), tablet devices, laptop computers, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.). One or more embodiments of this specification do not limit this. During operation, the electronic device can run a program on the client side of a certain application to implement the related functions of the application. For example, when the electronic device runs a program for an online shopping service, it can be implemented as a client of the online shopping service (hereinafter referred to as a shopping client). Among them, the application program of the above shopping client can be started and run on the electronic device. Exemplarily, the program can be a native application program installed on the electronic device, or the program can also be in the form of a mini program, a quick application, or other similar forms. Of course, when using web technologies such as HTML5 or similar, relevant functions can be implemented through the page displayed by the browser. Here, the browser can be an independent browser application or a browser module embedded in some applications.

[0029] It can be understood that from a hardware perspective, the online shopping system includes terminal devices (i.e., the aforementioned electronic devices, such as mobile phones 13 to 15, etc.) and servers (such as the aforementioned server 11); from a software perspective, the online shopping system includes a shopping client (such as the client-side program of the online shopping service running on mobile phone 13) and a shopping server (such as the server-side program of the online shopping service running on server 11).

[0030] It should be noted that the product profile model described in the embodiments of this specification can be deployed and run in the aforementioned server, that is, managed by the shopping server; or, the online shopping system can also include a model server. In this case, the product profile model can be deployed and run in this model server, that is, managed by the model management server in this server, and the aforementioned shopping server only needs to call this model through the network. For details, see the following embodiments.

[0031] In addition, for the network 10 for the interaction between electronic devices such as mobile phone 13 and server 11, communication can be specifically implemented by using a wired or wireless network based on the communication methods supported by the corresponding electronic devices. This specification does not limit this. For example, if mobile phone 13 usually only supports wireless communication, then wireless network can be used to implement communication; while a PC can communicate with server 11 in a wired or wireless manner, which will not be elaborated here.

[0032] This specification proposes an online shopping system, which includes a shopping client and a shopping server, where:

[0033] The shopping server is used to call a product profile model to infer the detailed information of a target product, so as to obtain the profile information of the target product;

[0034] The shopping client is used to display an intelligent profile control for the target product in a product-related interface, and, in response to the intelligent profile control being triggered, obtain and display the profile information.

[0035] It should be noted that the target product can be any product sold on an online shopping platform. The embodiments of this specification do not limit the type of the product (such as physical products, virtual products or services, etc.), price, seller, etc. In other words, for various products sold on an online shopping platform, the information display solution described in this solution can be used to obtain and display their profile information for corresponding consumers to view.

[0036] In addition, the detailed information of the target product described in the embodiments of this specification is information that introduces / describes the product in detail from multiple dimensions. These information can help consumers comprehensively understand the product so that they can make a purchase decision. The embodiments of this specification do not limit the specific dimensions, content, form (such as text, voice, and / or video), and data volume of the detailed information.

[0037] In one embodiment, the detailed information may include basic description information, evaluation information, and / or logistics information of the target commodity, etc. Among them, the basic description information is used to introduce the basic situation of the commodity, such as basic product information (brand, name, category, etc.), design-related information (such as size, weight, material, color, style, etc.), function description information (such as core function, technical parameters, additional functions, etc.), scenario description information (applicable scenarios, applicable populations, etc.), performance and experience information (such as performance performance, usage experience, etc.), accessory and packaging information (such as attached accessories, product packaging, etc.), after-sales service information (such as warranty policy, return and exchange policy, customer service support, etc.), price and promotion information (such as price, promotion activities, discounts, coupons, gifts, etc.). The evaluation information and logistics information are related information of the target commodity that has been sold before the current moment (hereinafter referred to as the sold target commodity). Among them, the evaluation information is the evaluation of the sold target commodity by consumers who purchased the sold target commodity, and this information can reflect the satisfaction degree of the purchased consumers with the commodity, such as the score, evaluation content, recommendation level, etc. for each SKU (Stock Keeping Unit). The logistics information is information used to introduce the statistical results of logistics information related to the delivery, transportation, receipt, etc. of the sold target commodity, such as the place of dispatch, selected logistics agency, dispatch duration, receipt duration, etc., or it can also be the predicted results of the place of dispatch, logistics agency, dispatch duration, receipt duration, etc. based on historical logistics information, which will not be elaborated here.

[0038] In addition, it should be noted that a commodity described in an embodiment of this specification may include one or more SKUs. For example, a mobile phone may include multiple SKUs according to combinations of colors and configurations. The mobile phones corresponding to these SKUs are all regarded as a mobile phone described in this solution.

[0039] Generally, the above detailed information will be displayed on the detail page of the target commodity; and consumers need to perform corresponding viewing operations in the client to enter the above detail page and view the displayed detailed information one by one in order to comprehensively and accurately understand the target commodity, and the browsing efficiency is relatively low, which is not conducive to quick transactions. This solution uses a commodity profile model to summarize and refine the detailed information of the target commodity into profile information and display it to the user, so that the user can know the key information of the commodity without viewing the detailed information one by one, thereby promoting transactions.

[0040] Figure 2 is a flowchart of a method for displaying commodity profile information provided by an exemplary embodiment. This method is applied to the aforementioned online shopping system and specifically applied to the shopping client in this system. As Figure 2 shown, this method includes the following steps 202-204.

[0041] Step 202: Display an intelligent summary control for the target product in the product-related interface.

[0042] This solution provides a one-key simplification function for the detailed information of the target product, that is, by displaying an intelligent summary control for the product in the product-related interface of the target product, the user (i.e., the consumer) can obtain the summary information refined by the product summary model with one key by simply triggering the control, so as to quickly obtain the key information of the product.

[0043] In one embodiment, according to different forms of the product-related interface, the shopping client can display the intelligent summary control of the product in multiple ways.

[0044] For example, the product-related interface can be a live broadcast interface for the target product. At this time, the intelligent summary control can be displayed in this interface. It can be understood that due to the high real-time nature of the live broadcast program, and the host may speak quickly when introducing the target product, or may not explain some selling points clearly, so it may cause the key information that the user is interested in to flash by during the live broadcast program, which is not conducive to the user's accurate understanding of the product and is not conducive to transactions. In response to this, this solution directly displays the intelligent summary control in the live broadcast interface, so that during the process of the user watching the live broadcast program, if they want to view some key information carefully, they can directly trigger the control and view the immediately displayed summary information, without having to enter the product details page through operations and view the relevant information by themselves, effectively simplifying the user's operation.

[0045] In addition, the shopping client can detect the target product displayed in the live broadcast interface according to the host's behavior or keywords, or can also determine the target product being explained at this time according to the live broadcast rhythm information pre-specified by the host party (that is, which product is explained in which time period). In fact, during the live broadcast program, the shopping client can always display the intelligent summary control in the live broadcast interface, and determine what the host is explaining at this time when the user triggers the control, and determine it as the target product. Or, considering that the host may not always explain the product during the live broadcast and the boundary between adjacent products may not be clear, in order to avoid abnormal situations such as being unable to determine the target product or displaying errors when the user triggers the intelligent summary control when the host is not explaining any product (such as performing talents unrelated to the product), it is also possible to detect the target product being explained in real time, and display the corresponding intelligent summary control for each detected target product in the live broadcast interface (for example, when there are multiple different products placed in the interface at the same time, these products can be determined as target products, and the corresponding intelligent summary controls for various products can be displayed at the positions corresponding to various products in the interface). In this way, it can be ensured that when the user triggers the intelligent summary control, the control corresponds to a clear target product.

[0046] Taking a dress as an example of the target product, as Figure 3 shown in the live broadcast interface. At this time, the host is wearing the dress 31. By performing live broadcast actions, broadcasting live broadcast voices and other behaviors, the host can introduce and explain the relevant information of the dress to the user so that the user can place an order after understanding. On this basis, an intelligent introduction control (i.e., the control 32 with the words "one-key selling points" displayed) can be displayed at the lower right of the right side of the live broadcast interface for the user to click and trigger. At this time, when the user clicks the control 32, the intelligent introduction control can be triggered to further display the introduction information of the dress for viewing.

[0047] For another example, the product-related interface can also be a product list interface. At this time, the interface can be divided into label areas corresponding to various products to be displayed, and the relevant information of each product can be displayed in the label area corresponding to each product. On this basis, the shopping client can display the intelligent introduction control for the target product in the label area corresponding to the target product. It can be understood that directly displaying the intelligent introduction controls corresponding to various products in the product list interface enables the user to directly trigger the control in this interface to quickly view the introduction information of the target product, and can trigger other controls to view the introduction information of the corresponding target product after exiting the display interface of the introduction information, thus effectively simplifying the user's product comparison operation, significantly improving the operation efficiency when the user compares product information, facilitating the user to make a quick decision and promoting transactions.

[0048] The shopping client can display the product list interface in response to the product list viewing operation implemented by the user in the live broadcast interface. At this time, the list of various products for sale in this live broadcast program is displayed in this interface, such as the product list on the host's / shelf of this live broadcast program or the window product list. At this time, the above-mentioned products for sale are used as the target products. Continuing from the previous embodiment, assuming that the user clicks the window control 34 in the lower right corner of the live broadcast interface (the "5" on the control indicates that there are a total of 5 products for sale in the host's window product list at this time), then it can jump to Figure 4 the window product list interface 41 shown, and the relevant information of 5 products for sale such as G1 - G5 is displayed in this interface in sequence. Taking product G2 as an example, the main product picture 43 (which can be a static picture or a dynamic video, etc.) is displayed on the left side of its corresponding label area 42, text information such as name, price, and sold quantity, as well as controls such as one-key add to shopping cart and one-key order are displayed in the middle, and the intelligent introduction control for this product (i.e., the control 44 with the words "one-key selling points" displayed) is displayed on the right side. At this time, when the user clicks the control 44, the intelligent introduction control can be triggered to further display the introduction information of product G2 and view it.

[0049] Alternatively, the shopping client can also display the product list interface in response to the product search operation performed by the user. At this time, the list displayed on this interface is the list of various products for sale found in this search, that is, the search result list. At this time, the aforementioned products for sale are used as target products. Among them, the user can perform the aforementioned product query operation on any interface. For example, the user can enter keywords, input voice, or import a local picture, etc. in the search box on the home page of the shopping client to perform a search. After that, the shopping client can display the aforementioned search result list in the search result interface, and display the intelligent profile controls corresponding to the various products for sale found in this interface. For example Figure 5 shows a schematic diagram of a search result interface. Assume that the user enters the keyword "AAA" in the search box 51 to perform a search, and the shopping client searches for at least AA1 to AA4 products for sale, and Figure 5 displays the relevant information of various products for sale in sequence in the shown search result interface. Taking the product AA1 as an example, its relevant information includes the main product picture 52 of this product (which can be a static picture or a dynamic video, etc.) and other information 53 (such as text information such as name, price, and the number of products sold, as well as controls such as one-click add to shopping cart and one-click order). At the same time, intelligent profile controls corresponding to various products for sale are also displayed in this interface (such as the control with a "lightning" logo). For example, this control can be displayed floating above the main product picture (as shown by the controls of AA1 and AA2), or this control can be displayed in the blank area below the main picture (as shown by the controls of AA3 and AA4).

[0050] For another example, the intelligent profile control for the target product can also be displayed in the details interface of the target product. Continuing from the previous embodiment, assume that the user clicks on the relevant information of any product in Figure 4 and Figure 5 to trigger the interface to jump to Figure 6 the details interface of this product shown. At this time, the intelligent profile control for this product (used as the target product) can also be displayed at a suitable position in this interface (such as the blank area on the right side of the basic information 61) (such as the control 62 with a "lightning" logo). In this way, even if the user has entered the details page of the target product, there is no need to view the detailed information one by one by himself, and the user can directly click on this control 62 to directly trigger the intelligent profile control to further display and view the profile information of product G2.

[0051] It should be noted that the display method of the intelligent profile control described in the previous embodiment is only exemplary. In fact, the intelligent profile control can be displayed at any suitable position in the product-related interface, and the embodiments of this specification do not limit this. Exemplarily, a new layer can be created above the original content of the product-related interface, and the intelligent profile control can be displayed in this layer to avoid interfering with the original content.

[0052] In one embodiment, when presenting the intelligent profile control, a floating presentation method can be adopted, that is, the intelligent profile control is presented in a floating manner on top of the commodity-related interface. Exemplarily, a new transparent page or a new layer can be created on top of the commodity-related interface, and the intelligent profile control is presented at the corresponding position in this page or layer. By adopting this presentation method, not only does it not require modifying the original content in the commodity-related interface, but also the intelligent profile control is prominently presented on the top layer, so there will be no occlusion, facilitating user perception and operation.

[0053] In one embodiment, considering that the one-key simplification function corresponding to the intelligent profile control is a brand-new function proposed in this specification, and users (especially those who have never used this function) may not be aware of the specific functions and effects of this function. Therefore, in order to facilitate users to know this function and thus promote its use, the shopping client can also present function prompt information for the intelligent profile control in the commodity-related interface for users to view. Exemplarily, as Figure 3 shown, when presenting the control 32, function prompt information 33 for this space can also be presented nearby, such as text prompt information like "Click here to view the core selling points of the commodity".

[0054] In addition, in addition to using text (such as Figure 3 and Figure 4 shown "one-key selling points") or special patterns (such as Figure 5 and Figure 6 shown "lightning" logo), the intelligent profile control can also be prominently presented by means of dynamic special effects, special colors or shapes, etc., so that users can intuitively see this control and promote users to use the one-key simplification function corresponding to the control, which will not be elaborated here.

[0055] Step 204, in response to the intelligent profile control being triggered, obtain and present the profile information of the target commodity, where the profile information is obtained by the commodity profile model reasoning about the detailed information of the target commodity.

[0056] When an intelligent profile control for the target commodity is presented in the commodity-related interface, if a user wants to view the profile information of this commodity, it can be achieved by triggering this control. For example, each intelligent profile control as Figures 3 to 6 shown can be clicked. In response to this control being triggered by the user, the shopping client will obtain the profile information generated by the commodity profile model reasoning about the detailed information, and present this information to the user for viewing. Among them, compared with the detailed information, the profile information can more intuitively and prominently reflect the core selling points and key elements of the target commodity, so that users can know.

[0057] As can be seen from the above embodiments, this specification proposes an online shopping system and an information display solution implemented by a shopping client in the system. In this solution, the shopping client displays an intelligent brief control for a target commodity on a commodity-related interface; then, in response to the triggering of the intelligent brief control, it obtains and displays the brief information of the target commodity, which is obtained by a commodity brief model reasoning about the detailed information of the target commodity.

[0058] This solution realizes the refined processing of detailed information by leveraging the powerful information extraction function of the commodity brief model. It can be understood that, compared with the detailed information of the target commodity, the brief information is more concise (i.e., less data volume) and can more intuitively and prominently reflect the core selling points and key elements of the commodity. Based on this, users can quickly and accurately learn the core selling points and key elements of the target commodity without having to view the detailed information one by one or even open the details page, which helps to simplify user operations and promote commodity transactions.

[0059] Among them, the commodity brief model can reason about the detailed information at different times to obtain the corresponding brief information and display it to the user. Correspondingly, the shopping client can also obtain the detailed information in different ways.

[0060] In one embodiment, the shopping server may pre-call the product introduction model to infer the detailed information of at least one product for sale in the online shopping platform to obtain the corresponding introduction information, and place the information in the introduction information set (such as using the SKU of the product as an index); thereafter, the corresponding shopping client may display the intelligent introduction control for the product in the product-related interface of the above-mentioned various products for sale. Assuming that any of the users triggers the intelligent introduction control for any of the products in the product-related interface displayed by the shopping client used by himself, the product is taken as the target product, and at this time, the shopping client may query the detailed information of the product from the above-mentioned introduction information set (such as querying according to the SKU of the product). The above-mentioned introduction information set may be maintained by the shopping server, and at this time, it is queried after the shopping client initiates a query request, and the corresponding query result (i.e., the introduction information of the target product obtained by the query) is returned to the shopping client for display. Alternatively, given that the smart introduction control for the target product is displayed in the product-related interface corresponding to the product, the shopping server can also, after determining the various products for sale corresponding to the interface, query the introduction information of these products for sale in the full introduction information set maintained by itself (the set may include introduction information of various products for sale in the online shopping platform) and send it to the shopping client (such as sending it together with detailed information of various products), and the shopping client caches this information locally (these detailed information constitute a component introduction information set); based on this, after the user triggers the smart introduction control corresponding to any of the products to be received (taken as the target product), the shopping client can query the introduction information of the product in the above-mentioned introduction information cached locally and display it.

[0061] It can be understood that this method obtains detailed information of the goods for sale in advance and calls the product introduction model to generate corresponding introduction information, so that the shopping client only needs to perform a simple query operation (request a shopping server query or a local query) after the user triggers the smart introduction control to quickly obtain the introduction information and display it. The pre-inference and caching technology realizes a rapid response to the user's triggered operation, significantly shortens the waiting time for the introduction information after the user triggers the smart introduction control, and helps to improve the user experience.

[0062] Of course, since the detailed information of the target commodity may change (especially logistics information, evaluation information, etc.), the brief information inferred and generated by the commodity brief model based on the detailed information is not fixed. Therefore, in order to improve the timeliness of the brief information displayed by the foregoing method as much as possible and reduce the possible interference to online services, the shopping server can periodically update the foregoing brief information set. For example, it can update the foregoing set during off-peak periods of the online shopping service (such as 3:00 am to 8:00 am every day, etc.) (that is, call the commodity brief model to infer and calculate the latest brief information based on the latest detailed information and place it in the foregoing set). Of course, the shorter the update period of the foregoing brief information set, the stronger the timeliness of the brief information, but the greater the consumption of relevant computing resources (such as the resources required for the shopping server to maintain the set, the resources required to run the commodity brief model, etc.). Therefore, the update period can be reasonably set according to actual situations, and the embodiments of this specification do not limit this.

[0063] In another embodiment, the commodity brief model can also be temporarily called for inference. For example, the shopping client can, in response to the intelligent brief control being triggered, determine the detailed information of the target commodity, and then call the commodity brief model to infer the detailed information and obtain the brief information of the target commodity output after the model's inference. Among them, in view of the fact that when the intelligent brief control is triggered, the shopping client may have received the detailed information sent by the shopping server (such as the commodity-related interface is the detail interface of the target commodity), or may not have received this information yet (such as the commodity-related interface is the search result display interface, and the target commodity is one of the searched commodities). Therefore, when the shopping client calls the commodity brief model, it can either initiate a brief information acquisition request containing the detailed information to the shopping server, so that the latter directly includes the detailed information in the request in the inference instruction and sends it to the commodity brief model for inference; or, it can also only initiate a brief information acquisition request containing the description information of the detailed information (such as the unique identifier of the target commodity in the online shopping platform) to the shopping server. In this case, the latter needs to first query the detailed information of the target commodity from the commodity database (such as the local database of the shopping server or the remote database it has the right to access) according to this description information, and then initiate an inference instruction containing this information to the commodity brief model. Of course, in view of the fact that whether the shopping client has obtained the detailed information when the intelligent brief control is triggered, this information is usually stored in the commodity database accessible by the shopping server, so the shopping client can also not need to pay attention to whether it has obtained the detailed information itself, and only needs to directly initiate a brief information acquisition request containing the foregoing description information in response to the trigger of the intelligent brief control, thus simplifying the trigger response logic of the shopping client. Further, if the commodity brief model is deployed locally on the shopping server (such as deployed in Figure 1In the server 11 shown, the server can directly initiate the foregoing inference instruction; while if the product profile model is deployed on other servers (such as deployed in the server 12 shown in Figure 1 ), the shopping server can call the model through the model call interface opened to the public by the other server (that is, initiate the inference instruction to it). Of course, when permissions permit, the shopping client can also directly call the product profile model (such as directly accessing the model management server), which will not be elaborated herein.

[0064] It can be seen that this method does not require pre-generated profile information, but generates profile information temporarily using the latest detailed information in response to the triggering of the intelligent profile control. It can be understood that on the one hand, the detailed information used for inference has better real-time performance, so the generated and displayed profile information is more accurate and effective; on the other hand, there is no need for the shopping server or the shopping client to maintain and manage pre-generated profile information and other information, which helps to reduce the data processing pressure on both and save the corresponding storage space.

[0065] As can be seen from the foregoing embodiments, whether pre-generated profile information before the intelligent profile control is triggered or temporarily generated profile information in response to the triggering of the intelligent profile control, it is necessary to call the product profile model to infer the detailed information. According to the type of the product profile model, different methods can be used to call the model.

[0066] In one embodiment, the product profile model can be an LLM (Large Language Model), which is a deep learning model trained based on a large amount of text data and can understand and generate natural language; this model can infer based on the detailed information in text form and output the profile information in text form. Or, the product profile model can also be a VLM (Vision-Language Model), which is a multi-modal model that combines vision and language and can handle association tasks between images and texts, such as image description, visual question answering, etc.; this model can infer based on detailed information in text (such as natural language, code, structured speech, etc.), image, and / or video form and output profile information in text, image, and / or video form. Among them, the foregoing LLM or VLM used as the product profile model in the embodiments of this specification can be pre-trained using sample detailed information and sample profile information on a standard LLM or standard VLM with the ability to generate basic information. The specific training process can refer to the records in related technologies and will not be elaborated herein.

[0067] When the product profile model is an LLM or a VLM, the shopping client or the shopping server can generate a profile prompt based on the detailed information of the target product, and input the prompt into the product profile model for inference to generate and output the corresponding profile information. At this time, the profile prompt can be regarded as the aforementioned inference instruction.

[0068] Exemplarily, the following are three profile prompts that can be used:

[0069] 1. Combining the product detailed information given below, briefly introduce this product to consumers of xxx? <Detailed information of xxx>

[0070] 2. Combining the product detailed information given below, briefly explain the key selling points of this product to consumers of xxx? <Detailed information of xxx>

[0071] 3. Combining the product detailed information given below, explain to consumers of xxx why they should choose to purchase this product? <Detailed information of xxx>

[0072] It can be understood that with the powerful information refinement and speech generation capabilities of the LLM or VLM, this solution can quickly generate accurate and comprehensive profile information for introducing the target product to users. Additionally, it should be noted that for the profile information in various forms such as text, images, or videos output by the VLM, appropriate formats and orders can be adopted for display so that users can view it.

[0073] In another embodiment, the product profile model can also be generated according to pre-created data reduction rules. For example, data reduction rules can be refined based on standard detailed information and profile information (to improve the accuracy of the rules, different data reduction rules can be refined according to data types), and then the product profile model can be constructed by writing code according to the above rules. Exemplarily, the above data reduction rules can be generated based on keywords, that is, used to extract keywords from the detailed information as the corresponding profile information. By this means, the generation logic of the above profile information can be simplified, the generation speed of the profile information can be accelerated, and the resource consumption in the information generation process can be reduced.

[0074] After obtaining the profile information of the target product through the foregoing method, the shopping client can display the information to the user so that they can quickly understand the target product by viewing the information.

[0075] In one embodiment, when presenting the brief introduction information, it can be presented by jumping to a new interface (different from the aforementioned product-related interface) to present the information more comprehensively. Alternatively, for the convenience of user operation, the brief introduction information can also be presented in a floating manner on top of the product-related interface. For example, it can be presented in a floating manner in some areas of the product-related interface through pop-up windows, sidebars, etc., and when the user triggers to close the information (such as clicking the close button or clicking on other areas of the product-related interface, etc.), the information will retract - the remaining interface after retraction is still the product-related interface, and the user can continue to view the content of this interface.

[0076] In one embodiment, when the shopping client presents the brief introduction information, at least part of the brief introduction information can be configured to be triggerable and presented; further, in response to any triggerable brief introduction information being triggered while being presented, the detailed information corresponding to the any triggerable brief introduction information can be presented so that users can further fully understand the detailed information when they have the need. Alternatively, in response to any triggerable brief introduction information being triggered while being presented, similar products of the target product can be presented in the product recommendation interface associated with the any triggerable brief introduction information (that is, recommend similar products related to the any triggerable brief introduction information to the user), so that when the user is not satisfied with the target product, they can turn to view other similar products, which helps to increase the overall transaction volume of the platform.

[0077] Let's assume that the target product is a mobile phone. The brief introduction information presented by the shopping client in response to the intelligent brief introduction control being triggered can be seen Figure 7 (illustrated only by text information). As Figure 7 shown, some keywords in the brief introduction information can be configured to be triggerable brief introduction information. For example, keywords such as "multiple color options", "xx chip", "triple camera system", etc. are bolded and underlined so that users can quickly and accurately view them; at the same time, corresponding hyperlinks are set for these keywords so that users can jump to a new page after clicking. For example, when the user clicks on "multiple color options", they can jump to the color rendering effect part of the mobile phone details page to quickly view the visual effects of multiple colors of this mobile phone. Another example is that when the user clicks on "triple camera system", the shopping client can request the server to search for other mobile phone products in the online shopping system that support the triple camera system and jump to the corresponding product recommendation interface to present the search results to the user. Of course, whether to further display detailed information, jump to the product recommendation interface or display other content after any triggerable brief introduction information is triggered can be distinguished by the display effect of the triggerable brief introduction information, such as different font colors, font sizes, font borders, setting explanatory text for this information, etc., which will not be elaborated here.

[0078] And / or. In another embodiment, when the shopping client displays the profile information, it may also display the profile information and its corresponding triggerable controls at the same time; further, in response to any triggerable control being triggered, a processing flow for the target product associated with the control may be started. It can be understood that by viewing the profile information, the user may or may not be more interested in the target product. At this time, the user may need to perform some subsequent processing on the product. This solution displays the above triggerable controls while displaying the detailed information, enabling the user to quickly start subsequent processing during the process of viewing the profile information, further simplifying the user operation and enhancing their shopping experience.

[0079] Among them, the above subsequent processing can have various forms. Exemplarily, in the case where the user has not purchased the target product, in response to any triggerable control being triggered, the shopping client can collect the target product, add the target product to the shopping cart, generate an order for the target product (i.e., place an order to purchase the product), or recommend similar products of the target product to the user (such as displaying similar products of the target product in the product recommendation interface). In the case where the user has already purchased the target product, then in response to any triggerable control being triggered, the historical orders of the user for the target product can be displayed, a return service can be applied for the historical order, or a price protection service can be applied for the historical order.

[0080] As Figure 7 shown, when the user triggers the collection control 73, the target product can be collected; when the user triggers the add-to-cart control 74, the target product can be added to the user's shopping cart. When the user triggers the place-order control 75, it can jump to the place-order interface to generate an order for purchasing the target product. When the user triggers the recommendation control 76, it can jump to the product recommendation interface to display similar products of the target product to the user for selection. When the user triggers the historical order control 77, it can jump to the historical order viewing interface to display the detailed information of the historical orders in which the user has purchased the target product. When the user triggers the return control 78, it can jump to the return interface for the historical order of the target product to start the return process. When the user triggers the collection control 79, it can jump to the price protection interface for the historical order of the target product to apply for the price protection service.

[0081] Of course, the above subsequent processing instructions are for illustrative purposes, and in the implementation of the solution, it can be flexibly adjusted according to the actual situation, and the embodiments of this specification do not limit this. In addition, for the aforementioned similar products recommended, the product profile model can also be called to further analyze the similarities and differences between the target product and each similar product, and output purchase suggestions to the user, such as how much money can be saved, how many days shorter the delivery time is, how many more years the warranty period is, etc., which will not be elaborated here.

[0082] In one embodiment, in view of the fact that there may be some questions about the target product during the user's viewing of the profile information, the product profile model can be invoked to answer the user's questions at this time. For example, the shopping client can also display an intelligent question control for the target product; further, in response to the triggering of the intelligent question control, the question raised by the user can be obtained, and the product profile model can be invoked to answer the question based on the detailed information. In this way, the text analysis and generation capabilities of the product profile model can be further fully utilized to efficiently answer relevant questions about the target product for the user, not only solving the consumer's problems earlier, but also reducing the occupation of customer service resources, which helps to improve the user's shopping experience and the overall efficiency of the online shopping system.

[0083] The foregoing embodiments may need to obtain relevant information of the user, such as historical orders, etc. 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 for analysis, stored data, displayed data, etc.) involved in this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for the user to choose to authorize or refuse.

[0084] Figure 8 is a schematic structural diagram of a device provided by an exemplary embodiment. Please refer to Figure 8 , at the hardware level, the device includes a processor 802, an internal bus 804, a network interface 806, a memory 808, and a non-volatile memory 810. Of course, there may also be other hardware required for other functions. One or more embodiments of this specification can be implemented in a software manner. For example, the processor 802 reads the corresponding computer program from the non-volatile memory 810 into the memory 808 and then runs it. Of course, in addition to the software implementation manner, one or more embodiments of this specification do not exclude other implementation manners, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, and can also be hardware or a logic device.

[0085] Please refer to Figure 9 , the display device for product profile information can be applied to a device as shown in Figure 8 to implement the technical solution of this specification. Among them, the display device for product profile information can include:

[0086] A control display unit 901, configured to display an intelligent profile control for a target product in a product-related interface;

[0087] An information display unit 902, configured to obtain and display the profile information of the target product in response to the triggering of the intelligent profile control, where the profile information is obtained by a product profile model reasoning about the detailed information of the target product.

[0088] Optionally, the control display unit 901 is specifically configured to perform one of the following:

[0089] Display an intelligent profile control for the target product in the live broadcast interface of the target product;

[0090] Display an intelligent profile control for the target product in the label area corresponding to the target product in the product list interface;

[0091] Display an intelligent profile control for the target product in the details interface of the target product.

[0092] Optionally, the control display unit 901 is specifically configured to:

[0093] Display the product list interface in response to a product search operation performed by the user; or,

[0094] Display the product list interface in response to a product list viewing operation performed by the user in the live broadcast interface.

[0095] Optionally, it further includes a prompt information display unit 903, configured to:

[0096] Display function prompt information for the intelligent profile control in the product-related interface.

[0097] Optionally, the detailed information of the target product includes the basic description information, evaluation information, and / or logistics information of the product.

[0098] Optionally, the information display unit 902 is specifically configured to:

[0099] Determine the detailed information of the target product, call the product profile model to reason about the detailed information, and obtain the profile information of the target product output after the model's reasoning; or,

[0100] Query the profile information of the target product from the profile information set, where the profile information is obtained by pre-calling the product profile model to reason about the detailed information and is placed in the profile information set.

[0101] Optionally, the product profile model is a large language model LLM or a vision language model VLM, and the information display unit 902 is specifically configured to:

[0102] Generate a profile prompt based on the detailed information of the target product, and input the profile prompt into the product profile model.

[0103] Optionally, the information display unit 902 is specifically configured to:

[0104] Configure at least part of the profile information to be triggerable and display it. In response to any triggerable profile information being triggered during display, display the detailed information corresponding to the triggered profile information or display similar products of the target product in the product recommendation interface associated with the triggered profile information; and / or,

[0105] Simultaneously display the profile information and its corresponding triggerable control. In response to any triggerable control being triggered, initiate a processing flow for the target product associated with the triggered control.

[0106] Optionally, the information display unit 902 is specifically configured to:

[0107] In the case where the user has not purchased the target product, in response to any triggerable control being triggered, favorite the target product, add the target product to the shopping cart, generate an order for the target product, or recommend similar products of the target product to the user;

[0108] In the case where the user has purchased the target product, in response to any triggerable control being triggered, display the user's historical order for the target product, apply for a return service or a price protection service for the historical order.

[0109] Optionally, it further includes an intelligent question unit 904, which is used to:

[0110] Display an intelligent question control for the target product;

[0111] In response to the intelligent question control being triggered, obtain the question raised by the user, and call the product profile model to answer the question based on the detailed information.

[0112] Based on the same concept as the above method, this specification also provides a computer-readable storage medium, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0113] Based on the same concept as the above method, this specification also provides a computer program product, including computer programs / instructions. When the computer programs / instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

Claims

1. A method for displaying product profile information, characterized in that, Including: Displaying an intelligent brief control for a target product in a product-related interface; In response to the intelligent brief control being triggered, obtaining and displaying the brief information of the target product, where the brief information is obtained by a product brief model reasoning about the detailed information of the target product.

2. The method according to claim 1, wherein The displaying an intelligent brief control for a target product in the product-related interface includes one of the following: Displaying an intelligent brief control for the target product in a live broadcast interface for the target product; Displaying an intelligent brief control for the target product in a label area corresponding to the target product in a product list interface; Displaying an intelligent brief control for the target product in a detail interface of the target product.

3. The method according to claim 2, wherein When the intelligent brief control is displayed in the label area, displaying the product list interface includes: Displaying the product list interface in response to a product search operation performed by the user; or, Displaying the product list interface in response to a product list viewing operation performed by the user in the live broadcast interface.

4. The method according to claim 1, characterized in that, Further including: Displaying function prompt information for the intelligent brief control in the product-related interface.

5. The method according to claim 1, wherein The detailed information of the target product includes the basic description information, evaluation information, and / or logistics information of the product.

6. The method according to claim 1, characterized in that, The obtaining the brief information of the target product includes: Determining the detailed information of the target product, invoking the product brief model to reason about the detailed information, and obtaining the brief information of the target product output after the model's reasoning; or, Querying the brief information of the target product from a brief information set, where the brief information is obtained by pre-invoking the product brief model to reason about the detailed information and is placed in the brief information set.

7. The method according to claim 6, wherein The product brief model is a large language model (LLM) or a vision-language model (VLM). The invoking the product brief model to reason about the detailed information includes: Generating a brief prompt word based on the detailed information of the target product and inputting the brief prompt word into the product brief model.

8. The method according to claim 1, wherein The displaying the brief information of the target product includes: Configuring at least part of the brief information as triggerable brief information for display. In response to any triggerable brief information being triggered, displaying the detailed information corresponding to the any triggerable brief information or displaying similar products of the target product in a product recommendation interface associated with the any triggerable brief information; and / or, Simultaneously displaying the brief information and its corresponding triggerable control. In response to any triggerable control being triggered, starting a processing flow for the target product associated with the any triggerable control.

9. The method according to claim 8, wherein When simultaneously displaying the brief information and its corresponding triggerable control, the starting a processing flow for the target product associated with the any triggerable control in response to any triggerable control being triggered includes: In the case where the user has not purchased the target product, in response to any triggerable control being triggered, collecting the target product, adding the target product to the shopping cart, generating an order for the target product, or recommending similar products of the target product to the user; In the case where the user has purchased the target product, in response to any triggerable control being triggered, display the user's historical order for the target product, apply for a return service for the historical order, or apply for a price protection service for the historical order.

10. The method according to claim 1, wherein It further includes: Display an intelligent question control for the target product; In response to the intelligent question control being triggered, obtain the question raised by the user, and call the product profile model to answer the question based on the detailed information.

11. An online shopping system, characterized in that, It includes a shopping client and a shopping server, where: The shopping server is used to call the product profile model to reason about the detailed information of the target product to obtain the profile information of the target product; The shopping client is used to display an intelligent profile control for the target product in the product-related interface, and, in response to the intelligent profile control being triggered, obtain and display the profile information.

12. An electronic device, characterized in that, It includes: A processor; A memory for storing instructions executable by the processor; wherein, the processor implements the steps of the method according to any one of claims 1-10 by running the executable instructions.

13. A computer-readable storage medium, characterized in that, Stored thereon are computer instructions, which when executed by the processor implement the steps of the method according to any one of claims 1-10.

14. A computer program product, characterized in that, It includes a computer program / instructions, which when executed by the processor implement the steps of the method according to any one of claims 1-10.