Commodity display page generation method and device and electronic equipment

Abstract

The invention discloses a commodity display page generation method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining original detail description information of a target commodity; according to different information types, performing type recognition processing on the original detail description information to obtain recognition results of different types of description information, and forming recognized description information; according to identification results of the different types of description information, the identified description information is classified and listed into different information modules formed according to predefined information categories; according to the target display object of the target commodity and the attribute of the target commodity, determining a corresponding target display frame according to a predefined display strategy; and according to the target display frame, filling a display position in the target display frame with the target information selected from the corresponding information module to form a target display page. According to the scheme provided by the invention, the quality of the description information in the commodity display page can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a method and device for generating a product display page, an electronic device and a computer readable storage medium. BACKGROUND

[0002] In the current e-commerce environment, product detail information has gradually become the core link connecting users and products, and can directly affect the purchase decision and conversion rate of users. However, due to the lack of professional visual design, each merchant tends to display all information of the product in a "big and complete" manner when configuring product detail description information, usually stacking information such as text and pictures in disorder, resulting in that the obtained product detail information is unclear in focus and the overall information structure is chaotic, which seriously affects the quality of product display and user experience.

[0003] Therefore, how to improve the quality of description information in the product display page has become a technical problem to be solved. SUMMARY

[0004] The present application provides a method and device for generating a product display page, an electronic device and a computer readable storage medium, which can improve the quality of description information in the product display page. The specific scheme is as follows: In a first aspect, the present application provides a method for generating a product display page, which comprises: obtaining original detail description information of a target product; performing type identification processing on the original detail description information according to different information types to obtain identification results of description information of different types, forming identified description information; according to the identification results of description information of different types, classifying the identified description information into different information modules formed according to pre-defined information categories; according to a target display object of the target product and the intrinsic attributes of the target product, determining a corresponding target display framework according to a pre-defined display strategy; and according to the target display framework, filling target information selected from the corresponding information module into a display position in the target display framework to form a target display page.

[0005] Optionally, the method further comprises: obtaining a target region to which the target display object of the target product belongs; obtaining a target industry attribute of the target product; and determining the corresponding target display framework according to the target region, the target industry attribute and the pre-defined display strategy.

[0006] Optionally, the determining the corresponding target display framework according to the target region, the target industry attribute, and the predefined display strategy comprises: determining a display position order corresponding to each display position included in the predefined display framework according to the target region, the target industry attribute, and the predefined display strategy; and sorting each display position included in the predefined display framework according to the display position order to obtain the corresponding target display framework.

[0007] Optionally, before the filling the target information selected from the information module into the display position in the target display framework to form the target display page, the method further comprises: performing preset processing on non-text description information in the description information after recognition corresponding to each information module to obtain updated description information after recognition; and taking the updated description information after recognition as the target information selected from the information module.

[0008] Optionally, the non-text description information comprises view description information and table description information, and the performing preset processing on the non-text description information in the description information after recognition corresponding to the information module to obtain updated description information after recognition comprises: selecting target view description information with a clarity greater than a preset clarity from the view description information to obtain processed view description information; fusing parameter description information belonging to commodity attributes in the table description information to obtain processed table description information; and replacing the view description information in the description information after recognition corresponding to the information module with the processed view description information, and replacing the table description information in the description information after recognition corresponding to the information module with the processed table description information.

[0009] Optionally, the description information after recognition comprises target description information after recognition in an image form, and the method further comprises: performing original information type identification processing on the target description information after recognition to obtain first target description information after recognition with an original information type of a table type, second target description information after recognition with an original information type of a text type, and third target description information after recognition with an original information type of an image type; updating the first target description information after recognition in the description information after recognition from a picture type to a table type, and updating the second target description information after recognition from a picture type to a text type to obtain updated description information after recognition.

[0010] Optionally, the target display page includes target detailed description information obtained based on the original detailed description information and basic display information of the target commodity, and the method further includes: determining target metadata belonging to both the basic display information and the target detailed description information; removing the target metadata from the target detailed description information or the basic display information to obtain an updated target display page.

[0011] Optionally, the original detailed description information is description information provided for a first region; before filling the target information selected from the information modules in the display positions in the target display framework to form a target display page, the method further includes: determining first description information to be converted locally from the identified description information; converting the first description information locally according to a local configuration mode corresponding to other regions except the first region to obtain first description information provided for the other regions; and adding the first description information provided for the other regions to the identified description information to obtain updated identified description information.

[0012] Optionally, the first description information is a size table; and converting the first description information locally according to a local configuration mode corresponding to other regions except the first region to obtain first description information provided for the other regions includes: converting the size table in the identified description information according to a size configuration mode adopted by the other regions to obtain a size table provided for the other regions.

[0013] Optionally, the first description information is commodity accessory information in a commodity picture; and converting the first description information locally according to a local configuration mode corresponding to other regions except the first region to obtain first description information provided for the other regions includes: converting the commodity accessory information of the target commodity in the commodity picture in the identified description information according to an accessory configuration mode adopted by users of the other regions for the target commodity to obtain a commodity picture provided for the other regions.

[0014] Optionally, determining the display position corresponding to each display position in the predefined display framework based on the target region, the target industry attribute, and the predefined display strategy includes: obtaining target historical interaction data of the target display object for the description information corresponding to each display position in the predefined display framework from the target display object's historical interaction data; and determining the display position corresponding to each display position in the predefined display framework based on the target region, the target industry attribute, the target historical interaction data, and the predefined display strategy.

[0015] Secondly, embodiments of this application provide a device for generating a product display page. The device includes: an acquisition unit for acquiring original detailed description information of a target product; an identification unit for performing type identification processing on the original detailed description information according to different information types to obtain identification results of different types of description information, forming identified description information; an inclusion unit for classifying and including the identified description information into different information modules formed according to predefined information categories based on the identification results of the different types of description information; a determination unit for determining a corresponding target display framework based on the target display object of the target product and the inherent attributes of the target product, according to a predefined display strategy; and a forming unit for filling the display positions therein with target information selected from the corresponding information modules according to the target display framework, forming a target display page.

[0016] Thirdly, this application also provides an electronic device, including: a processor; and a memory for storing a data processing program, wherein the electronic device, after being powered on and running the program through the processor, performs the method described in the first aspect.

[0017] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a data processing program that is executed by a processor to perform the method described in the first aspect.

[0018] Compared with the prior art, this application has the following advantages: The product display page generation method provided in this application includes the following steps: obtaining the original detailed description information of the target product; performing type identification processing on the original detailed description information according to different information types to obtain identification results of different types of description information, forming identified description information; classifying the identified description information into different information modules according to predefined information categories based on the identification results of the different types of description information; determining the corresponding target display framework according to the target display object of the target product and the inherent attributes of the target product, and according to a predefined display strategy; and filling the display positions in the target display framework with the target information selected from the corresponding information modules to form the target display page. It can be seen that the product display page generation method provided in this application performs type identification processing on the original detailed description information of the target product. This allows for the identification of the type of each piece of information in the original detailed description information, thereby obtaining identified description information labeled with the information type. Then, according to the front-end display requirements, the identified description information is placed into different information modules. This avoids a complex and chaotic structure and blurred focus when displaying description information. Next, for the target display object of the target product, a target display frame is specifically determined according to a predefined display strategy to match the inherent attributes of the target display object and the target product. Content is then backfilled based on this target display frame, filling the display positions with the target information selected from the corresponding information modules. Because the target display frame matches the inherent attributes of the target display object and the target product, the resulting target display page also matches the inherent attributes of the target display object and the target product. Therefore, after content backfilling, the quality of the descriptive information on the product display page can be improved.

[0019] Furthermore, the product display page generation method provided in this application applies AI capabilities throughout the entire process, forming an intelligent closed loop from the supply of original detailed description information to the output of the target display page, thereby improving the generation efficiency of product display pages. Attached Figure Description

[0020] Figure 1 This is a system architecture diagram of the product display page generation method provided in the embodiments of this application.

[0021] Figure 2 This is a flowchart of the method for generating a product display page provided in the embodiments of this application.

[0022] Figure 3 This is a schematic diagram illustrating the processing of the original details page in the product display page generation method provided in this application embodiment.

[0023] Figure 4This is a schematic diagram of the material refining stage in the product display page generation method provided in the embodiments of this application.

[0024] Figure 5 This is a schematic diagram of the front-end supply stage in the product display page generation method provided in the embodiments of this application.

[0025] Figure 6 This is a schematic diagram of the target display page for displaying the target product on the front end in the product display page generation method provided in this application embodiment.

[0026] Figure 7 This is a structural block diagram of an example of a product display page generation device provided in the embodiments of this application.

[0027] Figure 8 This is a structural block diagram of an example of an electronic device for generating product display pages provided in the embodiments of this application. Detailed Implementation

[0028] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0029] It should be noted that the terms "first," "second," "third," etc., in the claims, specification, and drawings of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. Such data are interchangeable where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown or described herein. Furthermore, the terms "comprising," "having," and their variations are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0030] It should be understood that in the embodiments of this application, "at least one" means one or more, and "more than one" means two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the related objects before and after it are in an "or" relationship. "Contains A, B and / or C" means containing any one, two, or three of A, B, and C.

[0031] It should be understood that in the embodiments of this application, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0032] Based on the reasons mentioned in the background art, the first embodiment of this application provides a method for generating a product display page to improve the quality of the description in the product display page. To more clearly demonstrate the method for generating a product display page provided in this application embodiment, the application scenarios of the method are first introduced.

[0033] The product display page generation method provided in this application embodiment can be applied to instant e-commerce platforms (which may be cross-border e-commerce platforms). For example, in an instant e-commerce platform, when it is detected that a target display object clicks on the product card of a target product (i.e., opens the product display page for the target product), the product display page generation method provided in this application embodiment can be used to generate the target product's target display page. Specifically, in response to detecting that a target display object has opened the product display page for a target product, the original detailed description information of the target product uploaded by the merchant can be obtained. Then, according to different information types, the original detailed description information can be processed... The description information is processed for type identification to obtain identification results for different types of description information, forming identified description information. Then, based on the identification results of the different types of description information, the identified description information is categorized and included in different information modules formed according to predefined information categories. Next, based on the target display object of the target product and the attributes of the target product itself, a corresponding target display framework is determined according to a predefined display strategy. Finally, based on the target display framework, the target information selected from the corresponding information modules is filled into the display positions to form a target display page. After that, the target display page can be sent to the terminal held by the target display object.

[0034] The product display page generation method provided in this application embodiment can also be applied to offline shopping scenarios. For example, in offline shopping venues (such as supermarkets, department stores, convenience stores, etc.), target products are placed. When a target display object scans the QR code or barcode on the outer packaging of the target product used to display the product display page, the product display page of the target product can be generated using the product display page generation method provided in this application embodiment. Specifically, in response to detecting the target display object's scanning operation of the target product's QR code or barcode, the original detailed description information of the target product uploaded by the merchant can be obtained. Then, according to different information types, the original detailed description information of the target product can be processed. The detailed description information undergoes type identification processing to obtain identification results for different types of description information, forming identified post-description information. Then, based on the identification results for the different types of description information, the identified post-description information is categorized and placed into different information modules formed according to predefined information categories. Next, based on the target display object of the target product and the inherent attributes of the target product, a corresponding target display framework is determined according to a predefined display strategy. Finally, based on the target display framework, the target information selected from the corresponding information modules is filled into the display positions within it to form a target display page. The target display page can then be sent to the terminal held by the target display object.

[0035] It should be noted that the application scenarios given above are merely examples. Those skilled in the art can apply the product display page generation method provided in the embodiments of this application to other scenarios according to actual needs. This application will not provide detailed examples of each scenario.

[0036] To facilitate understanding of the product display page generation method provided in the embodiments of this application, the following is combined with... Figure 1 This application describes the system architecture of a product display page generation method provided in an embodiment. The product display page generation system 100 may include a client 101, a server 102, and a network 103. The client 101 can connect to the server 102 via the network.

[0037] Client 101 can be any device with computing hardware capable of supporting and executing the software application tools corresponding to the method for generating product display pages. Client 101 can be an electronic device with display and data processing capabilities, such as a mobile phone, tablet, desktop computer, or laptop. The target display object can open the product display page for the target product on client 101. In response to detecting the opening operation, client 101 can send a request message to server 102 to obtain the product display page for the target product, and upon receiving the target display page for the target product returned by server 102, the target display page is displayed.

[0038] Server 102 possesses high-speed central processing unit (CPU) computing power, long-term reliable operation, powerful input / output (I / O) external data throughput capabilities, and better scalability. Server 102 can be a single server or a server cluster. When server 102 receives a request message from client 101 requesting access to the product display page of the target product, it performs type identification processing on the original detailed description information according to different information types, obtaining identification results for different types of description information, forming identified description information. Then, based on the identification results of the different types of description information, it categorizes the identified description information and includes it in different information modules formed according to predefined information categories. Next, based on the target display object of the target product and the inherent attributes of the target product, it determines the corresponding target display framework according to a predefined display strategy. Finally, based on the target display framework, it fills the display positions with the target information selected from the corresponding information modules to form the target display page. Then, server 102 sends the target display page to client 101.

[0039] Network 103 can be a wireless network or a wired network. For example, a wireless network could be a wireless local area network (WLAN), a local area network (LAN), a cellular network, a 2G network, a 3G network, a 4G network, or a 5G network. Additionally, different clients 101 can connect to other clients 101 or to the server 102 using their own Bluetooth network or hotspot network.

[0040] It should be noted that, Figure 1 The schematic diagram of the product display page generation system shown is merely an example. The product display page generation system 100 described in this application embodiment is intended to more clearly illustrate the technical solutions of this application embodiment and does not constitute a limitation on the technical solutions provided in this application embodiment.

[0041] The technical solution of this application will be described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0042] The following, combined with Figures 2-6 This application describes a method for generating a product display page, which is applied to a server.

[0043] like Figure 2 The diagram shows a flowchart of the method for generating a product display page provided in this application, including the following steps S101 to S105.

[0044] Step S101: Obtain the original detailed description information of the target product.

[0045] This step is used to obtain the original detailed description information of the target product when there is a need to display a product display page (i.e., the target display page) for the target product.

[0046] The target product refers to the product to be displayed on the target display page to the user. The target product can be any online product displayed on the instant e-commerce platform or any offline product displayed in an offline shopping venue.

[0047] The original detailed description information of the target product can be information provided by the merchant selling or producing the target product. It can be understood as a collection of product materials used to describe the product's attributes, performance, appearance, material, usage scenarios, after-sales service, etc. Taking an instant e-commerce platform as an example, when a merchant publishes the target product on the platform, they will upload the corresponding original detailed description information of the target product to the platform's product information database.

[0048] Step S102: Based on different information types, perform type identification processing on the original detailed description information to obtain the identification results of different types of description information, and form the identified description information.

[0049] This step is used to classify the original detailed description information of the target product, thereby obtaining the type of each piece of description information in the original detailed description information.

[0050] The original product details description information is typically HTML (Hypertext Markup Language) text, meaning it is in string format. This includes strings representing product information, company information, logistics and transportation information, size information, etc. Figure 3The diagram illustrates the processing of the original details page in the product display page generation method provided in this application embodiment, specifically including a material cleaning stage and a material processing stage. In the material cleaning stage, before performing type recognition processing on the original details description information, the original details description information can be structured (e.g., through structured scripting), thereby placing strings representing product information, company information, logistics and transportation information, size information, etc., in their respective positions. Then, type recognition processing is performed on the structured original details description information to obtain recognition results for different types of description information, forming the recognized description information. In a specific implementation, the structured original details description information can be input into a trained type recognition model. The type recognition model performs type recognition processing on the original details description information, outputting recognition results for different types of description information, forming the recognized description information.

[0051] In one optional implementation, before performing type identification processing on the original detailed description information, redundant material can be removed from the original detailed description information to obtain updated original detailed description information; type identification processing is then performed on the updated original detailed description information to obtain identification results for different types of description information, forming identified description information. This method is used to perform data cleaning on the original detailed description information before performing type identification processing, filtering out redundant information to obtain high-quality original detailed description information.

[0052] In practical applications, merchants typically aim to showcase comprehensive product information for their target goods. Therefore, the original product details provided often contain a large amount of diverse information, including redundant materials—materials not needed for the final display on the front-end page. These redundant materials may include, but are not limited to, at least one of the following: repetitive content and low-value content. For example, the content uploaded by the merchant for the target product might include multiple duplicate images, information unrelated to the product (such as external links), or videos shorter than a preset duration. In this method, before performing type identification processing on the original product details, redundant materials are removed. This ensures that the updated original product details do not contain repetitive or low-value content, improving the quality of the original product details before type identification processing and providing a solid foundation for generating a high-quality target display page.

[0053] Different information types can be categorized into different classes according to different classification dimensions. Based on the classification dimension of information presentation format, different information types can include, but are not limited to, view-based information types, text-based information types, table-based information types, and question-and-answer information types. View-based information types can include image-based information types and video-based information types. Based on this, by performing type recognition processing on the original detailed description information according to different information types, recognition results such as view-based description information, text-based description information, table-based description information, and question-and-answer description information can be obtained, thus forming recognized description information. That is, the formed recognized description information can include, but is not limited to, view-based description information, text-based description information, table-based description information, and question-and-answer description information. Based on the classification dimension of whether the information is text, different information types can include text-based information types and non-text-based information types. Based on this, by performing type recognition processing on the original detailed description information according to different information types, recognition results such as text-based description information and non-text-based description information can be obtained, thus forming recognized description information. That is, the formed recognized description information can include both text-based and non-text-based description information. The text-based description information may include at least one of the following: the product title of the target product, the usage scenario of the target product, the after-sales service of the target product, and the development history of the brand to which the target product belongs; the non-text-based description information includes, but is not limited to, at least one of the following: view-based description information, table-based description information, etc., and view-based description information includes image-based description information and video-based description information.

[0054] In practical applications, some merchants often provide image-based information when providing original product detail descriptions, such as size charts, product introductions, and merchant introductions. This means that text-based or table-based descriptions, which are not image-based, are also placed as images within the original product detail descriptions. In this case, after the identified description information is generated, the target identified description information presented as images can be processed to identify its original information type, resulting in a first target identified description information of table type, a second target identified description information of text type, and a third target identified description information of image type. The first target identified description information is then updated from image type to table type, and the second target identified description information is updated from image type to text type, resulting in updated identified description information. This avoids information that should belong to table type or text type being classified as image-based description information, achieving efficient, comprehensive, and accurate classification of each piece of description information in the identified description information into its appropriate information type.

[0055] In this embodiment, the image class description information can be classified according to different image types to obtain recognized image class description information. The recognized image class description information may specifically include, but is not limited to, at least one of the following: product detail images displaying the target product from multiple angles; model display images showing the target product; scene display images combining usage scenarios; size charts showing size measurement methods; customization images showing customization processes; SKU (Stock Keeping Unit) charts; merchant customization capability charts; factory scene images; exhibition images; production flow charts; company information charts; and product attribute charts. The tabular description information may specifically include, but is not limited to, at least one of the following: size tables displaying the various sizes corresponding to the target product; and product parameter tables displaying the configuration information of the target product.

[0056] like Figure 3 As shown, the image class description information after recognition can be input into a trained multimodal generation model, and the image class description information can be classified by the multimodal generation model.

[0057] Step S103: Based on the identification results of the different types of descriptive information, classify the identified descriptive information and include it in different information modules formed according to predefined information categories.

[0058] This step integrates the identified descriptive information according to the display requirements of the front-end page, thereby placing each piece of information in the identified descriptive information into different information modules. This facilitates accurate filling of information content according to each information module during the subsequent front-end page display.

[0059] Different information modules, formed according to predefined information categories, are the modules used for front-end display. These information display modules include, but are not limited to, product attribute modules, size modules, product customization modules, company modules, logistics and transportation modules, user feedback modules, product accessory modules, merchant description modules, and SKU (Stock Keeping Unit) image modules. For example, merchant qualifications and certificates from the merchant introduction dimension can be placed in the merchant description module; images that differ only in color while having identical details can be placed in the SKU image module; scene display images, model display images, and product detail images can be placed in the basic image module; and size charts from image information and size tables from table information can be placed in the size module.

[0060] In this way, based on the recognition results of the different types of descriptive information, the recognized descriptive information can be categorized into different information modules formed according to predefined information categories. For example... Figure 3 As shown, in the material processing stage, the identification description information can be input into the trained module attribution model. The module attribution model is pre-set with different information modules formed according to predefined information categories, so that each description information in the identification description information can be divided into the corresponding information modules through the module attribution model.

[0061] In one optional implementation, information category feature data corresponding to each piece of descriptive information in the identified descriptive information can be extracted based on the recognition results of the different types of descriptive information. Each piece of descriptive information is then categorized and placed into different information modules formed according to predefined information categories based on the information category feature data. The information category feature data can be vector-type data used to characterize the information category to which the corresponding identified descriptive information belongs.

[0062] In this way, the classification table of the identified description information can be included in modules such as product attribute module, size module, product customization module, company module, logistics and transportation module, user feedback module, and product accessories module.

[0063] Optionally, before classifying the identified description information into different information modules formed according to predefined information categories, the identified description information can be pre-processed to obtain updated identified description information. Then, based on the identification results of the different types of description information, the identified description information can be classified into different information modules formed according to predefined information categories. Alternatively, after classifying the identified description information into different information modules formed according to predefined information categories, for each information module, the non-textual description information in the identified description information corresponding to the information module can be pre-processed to obtain updated identified description information. The updated identified description information is then used as the target information selected in the information module.

[0064] In this specific implementation, the non-text description information can be specifically divided into at least one of the following based on the information type it corresponds to: view description information (video description information and image description information) and table description information.

[0065] Subsequently, for the view class description information, target view class description information with a resolution greater than a preset resolution can be filtered from the view class description information to obtain processed view class description information. After obtaining view class description information such as size diagrams, product detail images, display images, and product introduction videos, a pre-trained image processing model can be used to determine whether each view class description information meets the requirements (such as resolution requirements).

[0066] In a specific example, such as Figure 4The diagram shown illustrates the material finishing stage in the product display page generation method provided in this application embodiment. For the size image, a pre-trained image processing model can be used to determine whether the sharpness of the measured subject in the size image is greater than a preset sharpness. If not, the size image is removed or the sharpness of the measured subject in the size image is adjusted until the sharpness of the measured subject in the size image is greater than the preset sharpness. A pre-trained image processing model can also be used to determine whether the size measurement method of the size image conforms to the standard. If not, the size image is removed or adjusted until the size measurement method of the size image conforms to the standard. For the product customization image, a pre-trained image processing model can be used to determine whether the sharpness of the product subject in the product customization image is greater than a preset sharpness. If not, the product customization image is removed or the sharpness of the product subject in the product customization image is adjusted until the sharpness of the product subject in the product customization image is greater than the preset sharpness. A pre-trained image processing model can also be used to determine whether the customization process displayed in the product customization image matches the text used to describe the customization process. If the product customization image and the text description information used to describe the customization process are consistent, then the customized product image is removed or the customization process shown in the customized product image is adjusted according to the text description information used to describe the customization process until the customization process shown in the customized product image is consistent with the text description information used to describe the customization process. For product detail images, a pre-trained image processing model can be used to determine whether the product detail image matches the name of the labeled detail part (e.g., if the collar part is shown but the labeled detail part is named "sleeve", then the product detail image and the labeled detail part do not match). If they do not match, then the product detail image is removed or the labeled detail part name is modified until the product detail image and the labeled detail part name match. For display images, a pre-trained image processing model can be used to determine whether the visual focus of the display image is the target product (e.g., if the target product is a top but the visual focus of the model display image is pants, then the visual focus is not the target product). If not, then the display image is removed or the image layout or color contrast of the display image is adjusted so that the visual focus of the display image is the target product.

[0067] Furthermore, it can be determined whether the category matching degree between the view class description information and the information category it is included in is greater than a preset category matching degree. If not, the view class description information is reclassified and included in the updated information category, so that the category matching degree between the view class description information and the updated information category it is included in is greater than the preset category matching degree. Specifically, the view class description information and the information category it is included in can be input into the image processing model, and the image processing model can determine whether the category matching degree between the view class description information and the information category it is included in is greater than the preset category matching degree.

[0068] For the aforementioned table-type description information, the parameter-type description information belonging to product attributes within the table-type description information can be merged to obtain processed table-type description information. For example... Figure 4 As shown, the parameter description information belonging to the product attributes in the table-type description information can be input into the language processing model, so that the parameters can be fused through the language processing model to obtain the processed table-type description information.

[0069] The product attributes refer to the fabric composition or material properties of the target product. The parameter-based description information of these product attributes can be understood as the composition distribution data of the target product. For clothing, product attributes may include fabric material, and the parameter-based description information could be 100% cotton, or 80% polyester fiber & 20% spandex, etc. For shoes, product attributes may include upper material and sole material, and the parameter-based description information could be genuine leather, rubber, knitted, etc. In this way, the parameter-based description information belonging to product attributes in the tabular description information can be merged to obtain a product parameter table, resulting in processed tabular description information. This avoids the data distribution being too messy due to the parameter-based description information belonging to product attributes being scattered in different locations, improving data integration.

[0070] Subsequently, the view class description information in the identified description information corresponding to the information module can be replaced with the processed view class description information, and the table class description information in the identified description information corresponding to the information module can be replaced with the processed table class description information.

[0071] Optionally, the target product is a product displayed on a cross-border e-commerce platform. That is, the target product is a product displayed to users in different regions. Region refers to a country or area, where country refers to the country where the user is located, and area refers to the region to which the user is divided according to geographical area, cultural customs, etc.

[0072] It's important to note that different users, especially those from different regions, often have different cultural customs and consumption habits. For example, in terms of weight, China commonly uses grams and kilograms, while the United States commonly uses pounds and ounces; in terms of volume, China commonly uses milliliters and liters, while the United States commonly uses gallons; the same pair of shoes might be labeled as size 38 in China but size 8 in the United States; and some countries traditionally pair T-shirts with shorts, while others pair them with jeans.

[0073] To cater to the cultural customs and consumption habits of users in different regions, after obtaining the identified description information, it can be first determined whether the original detailed description information is provided for each region to be displayed on the cross-border e-commerce platform (such as China, the United States, Europe, etc.). If the original detailed description information is provided for each region to be displayed on the cross-border e-commerce platform, then there is no need to localize the information in the original detailed description information. If the original detailed description information is provided for a first region (such as China), then some information in the original detailed description information needs to be localized to adapt to users in different regions.

[0074] It should be noted that the localization conversion here includes both language conversion (e.g., if the original details are presented in Chinese, they can be converted to English, French, Korean, Japanese, etc.) and presentation preference conversion. Specifically, a first description information to be localized can be determined from the identified description information; according to the localization configuration of the first description information in other regions besides the first region (e.g., China) (e.g., the United States, Europe, etc.), the first description information is localized to obtain first description information provided for the other regions; the first description information provided for the other regions is added to the identified description information to obtain the updated identified description information.

[0075] Taking localization conversion, including the conversion of presentation preferences, as an example, the localized configuration methods corresponding to the first description information in regions other than the first region are used to indicate the presentation preferences of users in those other regions for the first description information. After localizing the first description information to obtain the first description information provided for the other regions, the first description information provided for the other regions is also added to the identified description information. In this way, the information in the identified description information is applied to users in various regions, which facilitates selective display based on the user's region when showing the information to the user later, thereby increasing the user's willingness to purchase.

[0076] In this embodiment of the application, the first description information can be input into a pre-trained localization conversion model for implementing local conversion, so that the first description information can be localized through the localization conversion model to obtain the first description information provided for the other regions.

[0077] In one specific example, the first descriptive information is a size chart. The size chart includes the sizes of the target product and the standardized parameters corresponding to each size. These standardized parameters are typically physical dimensions or specifications. For clothing, sizes typically include S, M, L, XL, etc., and the standardized parameters refer to the specific dimensions of the clothing under each size. For example, a size M short-sleeved shirt has a length of 68cm, a chest circumference of 100cm, and a shoulder width of 45cm. For shoes, sizes typically include 36, 37, 38, 39, 40, 41, 42, etc., and the standardized parameters refer to the specific dimensions of the shoes under each size. For example, a size 38 shoe has a length of 240mm. The step of converting the first description information to a localized configuration method corresponding to each region other than the first region, to obtain first description information for those other regions, may include the following steps: converting the size table in the identified description information according to the size configuration method adopted in those other regions, to obtain a size table for those other regions. The size configuration method is used to indicate the size preferences of users in those other regions for the target product. In a specific example, such as... Figure 4 As shown, a pre-trained language processing model can be used to convert the size chart in the recognized description information to size charts for other regions. For example, if a merchant providing the target product only provides a size chart applicable to country A, the language processing model can convert the size chart for country A to size charts for country B, country C, etc. Thus, when showing the target product to users in country B, the size chart for country B is displayed, and when showing the target product to users in country C, the size chart for country C is displayed.

[0078] In another specific example, the first descriptive information is the accessory information of the product in the product image. The step of localizing the first descriptive information according to the localized configuration methods corresponding to different regions other than the first region to obtain the first descriptive information provided for those other regions may include the following steps: converting the accessory information of the target product in the product image of the identified descriptive information according to the accessory configuration methods used by users in those other regions for the target product, to obtain a product image provided for those other regions. The accessory configuration method is used to indicate the accessory matching preferences of users in those other regions for the target product. In this specific example, a pre-trained accessory conversion model can be used to convert the accessory information of the target product in the product image of the identified descriptive information to obtain a product image provided for those other regions. For example, if the target product is a women's vest, and the merchant providing the product shows it paired with a long skirt in the product image based on the styling habits of users in country A, while in country B women typically wear vests with shorts and in country C women typically wear vests with trousers, then an accessory conversion model can be used to convert the long skirt in the product image to a product image showing a vest paired with shorts based on the styling habits of country B, and a product image showing a vest paired with trousers based on the styling habits of country C. Thus, when showing the target product to users in country B, the product image showing a vest paired with shorts based on the styling habits of country B is displayed; when showing the target product to users in country C, the product image showing a vest paired with trousers based on the styling habits of country C is displayed. This configuration allows for the localization of the first description information in the identified description information according to the presentation preferences of users in different regions. This ensures that the converted first description information conforms to the habits of users in different regions. Consequently, when displaying the target product to users in different regions, the page can select the description information corresponding to the user's region for presentation. This avoids user misunderstanding and confusion, effectively enhances user trust, facilitates quick decision-making, and increases users' willingness to purchase the target product.

[0079] Step S104: Based on the target display object of the target product and the attributes of the target product itself, determine the corresponding target display frame according to the predefined display strategy.

[0080] The target display audience is the user viewing the target product. This step is used to determine the target display frame when displaying the target product to a target display audience. The target display frame indicates the display position of each display slot included in the predefined display frame.

[0081] Specifically, the target region of the target product's target display object can be obtained; the target industry attribute of the target product can be obtained; and a corresponding target display framework can be determined based on the target region, the target industry attribute, and a predefined display strategy. Determining the corresponding target display framework based on the target region, the target industry attribute, and the predefined display strategy includes: determining the display position corresponding to each display position included in the predefined display framework based on the target region, the target industry attribute, and the predefined display strategy; and sorting the display positions included in the predefined display framework according to the display positions to obtain the corresponding target display framework.

[0082] This step is used to personalize the sorting of each display position in the predefined display framework based on the target region to which the target display object belongs and the target industry attribute of the target product, so as to intelligently arrange the information filled in each display position.

[0083] The target industry attribute of the target product is used to indicate the industry classification to which the target product belongs. In this embodiment, the target industry attribute of the target product can be identified by a pre-trained industry category recognition model. The target industry attribute of the target product includes, but is not limited to, at least one of the following: apparel industry, home appliance industry, home furnishing industry, beauty industry, maternal and infant industry, food industry, and office supplies industry. For example, shirts, short sleeves, trousers, dresses, leather shoes, and sneakers belong to the apparel industry; refrigerators, washing machines, televisions, and air conditioners belong to the home appliance industry; sofas, wardrobes, and shoe cabinets belong to the home furnishing industry; skin care products, face masks, sunscreens, and cosmetics belong to the beauty industry; milk powder and diapers belong to the maternal and infant industry; snacks, grains, oils, rice, and noodles belong to the food industry; and printers, office chairs, and filing cabinets belong to the office supplies industry.

[0084] The target region to which the target display object belongs is used to characterize the country or region to which the target display object belongs. The country to which the target display object belongs refers to the country where the target display object is located, and the region to which the target display object belongs refers to the area to which the target display object is divided according to geographical regions, cultural customs, etc. When the target region to which the target display object belongs is used to characterize the country to which the target display object belongs, the target region to which the target display object belongs can be one of China, the United States, the United Kingdom, Norway, South Korea, etc. When the target region to which the target display object belongs is used to characterize the region to which the target display object belongs, a coarse-grained division based on continental plates can be at least one of Asia, Europe, the Americas, Australia, Africa, etc., and a fine-grained division based on specific regions can be at least one of East China, South China, North China, Central China, Northeast China, Northwest China, Southwest China, etc. For ease of explanation, this embodiment of the application will use the target region to which the target display object belongs to characterize the country to which the target display object belongs as an example for explanation.

[0085] In one specific implementation, the target language parameter set locally by the target display object can be obtained, and the target region to which the target display object belongs can be determined based on the target language parameter. The target language parameter can represent at least one of Chinese, English, Japanese, Korean, Russian, and French. If the target language parameter represents Chinese, the target region to which the target display object belongs can be determined to be China; if the target language parameter represents English, the target region to which the target display object belongs can be determined to be the United Kingdom or the United States; if the target language parameter represents Japanese, the target region to which the target display object belongs can be determined to be Japan; and if the target language parameter represents French, the target region to which the target display object belongs can be determined to be France.

[0086] In another specific implementation, the current geographical location of the target display object can be obtained, and the target region to which the target display object belongs can be determined based on the current geographical location of the target display object. For example, if the current geographical location of the target display object is office building A, and office building A belongs to country B, then the target region to which the target display object belongs can be determined to be country B.

[0087] Users in different regions typically pay varying degrees of attention to different information about the same product. For example, users in region A tend to focus more on the product's origin, users in region B on the material, users in region C on the seller's qualifications, and users in region D on logistics and transportation information. Furthermore, the weight of different information varies across products from different industries. This information weight represents the degree of influence of the corresponding information on the user; a higher weight indicates a stronger influence, and a lower weight indicates a weaker influence. For instance, users in the clothing industry pay more attention to size, making size information the highest-weighted information in the clothing sector; users in the home appliance industry focus more on energy consumption, making energy consumption information the highest-weighted information in the home appliance sector; users in the furniture industry focus more on materials, making material information the highest-weighted information in the furniture sector; and users in the food industry focus more on the origin of the ingredients, making the origin of the ingredients the highest-weighted information in the food sector.

[0088] In a specific implementation, a content ranking model can be used to determine the display position of each display slot within a predefined display framework. This content ranking model pre-learns the display strategies for each display slot under different regional and industry attributes. Thus, by inputting the target region and target industry attribute into the content ranking model, it can infer the display position of the target product's target industry attribute when displayed to target users in the target region. Therefore, for the same product, the display positions of each slot in the target display framework generated for target users in different target regions may differ, with the display slots corresponding to information modules that receive higher attention from target users in those regions occupying relatively higher positions. Similarly, for target products with different target industry attributes, the display positions of each slot in the target display framework generated for users in the same region may differ, with the display slots corresponding to information modules with higher information weight in the product's industry attribute occupying relatively higher positions. In other words, this application embodiment can not only avoid generating the same product description information for users in different regions for the same product, but also avoid generating the same product description information for users in the same region for products of different industry categories.

[0089] Step S105: Based on the target display framework, fill the display positions therein with the target information selected from the corresponding information modules to form the target display page.

[0090] This step is used to generate a target display page for the target product based on the target display object.

[0091] like Figure 5 The diagram shown illustrates the front-end supply stage in the product display page generation method provided in this application embodiment. The display positions of each display slot within a predefined display framework can be intelligently arranged according to the target industry attributes of the target product, the target region to which the target display object of the target product belongs, and a predetermined differentiated display strategy, forming a target display framework. The display slots within this framework are then filled with target information selected from corresponding information modules to form the target display page.

[0092] Optionally, the target display page includes not only the target detailed description information formed based on the original detailed description information, but also the basic display information of the target product. There may be overlap in content between the two; for example, both the basic display information and the target detailed description information may include multi-angle images of the target product. In this case, target metadata that belongs to both the basic display information and the target detailed description information can be identified. The target metadata is then removed from either the target detailed description information or the basic display information to obtain the updated target display page. This avoids wasting interface space by repeatedly displaying the same information on the screen, thus improving screen efficiency.

[0093] Then, the target display page can be sent to the terminal held by the target display object so that the target display page can be displayed on the terminal held by the target display object.

[0094] like Figure 6 The diagram shows the interface of the target product display page displayed on the front end in the product display page generation method provided in this application embodiment, including interface (a) and interface (b). Interface (a) is the target product display page displayed to user 1 whose region is region A. In this interface, the display position 201 displaying size information is the first position, the display position 202 displaying product display information is the second position, and the display position 203 displaying supplier description information is the third position. Interface (b) is the target product display page displayed to user 2 whose region is region B. In this interface, the display position 205 displaying size information is the second position, the display position 204 displaying product display information is the first position, and the display position 206 displaying supplier description information is the third position. It can be seen that for the same target product, the display positions in the target product display page displayed on the front end interface of users in different regions are different.

[0095] Because the ranking of the content description information is determined by combining the target region of the target display object and the target industry attribute of the target product, the final ranking of the description information on the target display page conforms to both the viewing needs of users in the target region and the importance ranking of information within the target industry attribute. This not only avoids generating identical product display pages for users in different regions for the same product, but also avoids generating identical product display pages for users in the same region for products from different industry categories, thereby improving the quality of the description information on the product display page. As a result, when viewing the target product's target display page, users can quickly obtain the description information they are most interested in, effectively enhancing user trust, facilitating quick decision-making, and increasing users' willingness to purchase the target product.

[0096] In addition to determining the display position of each display slot in the predefined display framework based on the target region and target industry attributes, as described above, this application can also sort the display slots in the predefined display framework for personalized experiences for different users. Specifically, determining the display position of each display slot in the predefined display framework based on the target region, target industry attributes, and predefined display strategy can be achieved through the following steps: obtaining target historical interaction data of the target display object regarding the descriptive information corresponding to each display slot in the predefined display framework from the target display object's historical interaction data; and determining the display position of each display slot in the predefined display framework based on the target region, target industry attributes, target historical interaction data, and predefined display strategy.

[0097] This step is used to personalize the sorting of each display position based on the target region, target industry attributes, and the target display object's preference for the descriptive information corresponding to each display position included in the predefined display framework, so as to realize the intelligent arrangement of each display position in the display framework.

[0098] Specifically, historical interaction data of the target display object for multiple products can be obtained within a preset time period (e.g., the most recent week or the most recent month), and target historical interaction data of the target display object for the descriptive information corresponding to each display position included in the predefined display framework can be obtained from this data. The target historical interaction data may include, but is not limited to, at least one of the following: viewing frequency, dwell time, and search count for the descriptive information corresponding to each display position. The target historical interaction data is used to characterize the target display object's preference for the descriptive information of the corresponding display position. For example, if the target display object has a long dwell time on the display position corresponding to size information, it indicates that the target display object focuses on the size information of the product; if the target display object searches for merchant qualifications frequently, it indicates that the target display object focuses on the qualifications of the merchant providing the product.

[0099] In this way, the target historical interaction data, the target region, and the target industry attributes are used to jointly determine the display position of each display position included in the predefined display framework. As a result, the target display object's preferred display position will be located in a relatively prominent position, enabling personalized display of the target product and further enhancing the user's willingness to purchase the target product.

[0100] The product display page generation method provided in this application includes the following steps: obtaining the original detailed description information of the target product; performing type identification processing on the original detailed description information according to different information types to obtain identification results of different types of description information, forming identified description information; classifying the identified description information into different information modules according to predefined information categories based on the identification results of the different types of description information; determining the corresponding target display framework according to the target display object of the target product and the inherent attributes of the target product, and according to a predefined display strategy; and filling the display positions in the target display framework with the target information selected from the corresponding information modules to form the target display page. It can be seen that the product display page generation method provided in this application performs type identification processing on the original detailed description information of the target product. This allows for the identification of the type of each piece of information in the original detailed description information, thereby obtaining identified description information labeled with the information type. Then, according to the front-end display requirements, the identified description information is placed into different information modules. This avoids a complex and chaotic structure and blurred focus when displaying description information. Next, for the target display object of the target product, a target display frame is specifically determined according to a predefined display strategy to match the inherent attributes of the target display object and the target product. Content is then backfilled based on this target display frame, filling the display positions with the target information selected from the corresponding information modules. Because the target display frame matches the inherent attributes of the target display object and the target product, the resulting target display page also matches the inherent attributes of the target display object and the target product. Therefore, after content backfilling, the quality of the descriptive information on the product display page can be improved.

[0101] Furthermore, the product display page generation method provided in this application applies AI capabilities throughout the entire process, forming an intelligent closed loop from the supply of original detailed description information to the output of the target display page, thereby improving the generation efficiency of product display pages.

[0102] Corresponding to the product display page generation method provided in the first embodiment of this application, the second embodiment of this application also provides a product display page generation apparatus, such as... Figure 7As shown, the product display page generation device 400 includes: an acquisition unit 401, used to acquire the original detailed description information of the target product; an identification unit 402, used to perform type identification processing on the original detailed description information according to different information types, to obtain identification results of different types of description information, and to form identified description information; an inclusion unit 403, used to classify and include the identified description information into different information modules formed according to predefined information categories according to the identification results of the different types of description information; a determination unit 404, used to determine the corresponding target display framework according to the target display object of the target product and the attributes of the target product itself, and according to a predefined display strategy; and a formation unit 405, used to fill the display positions therein with the target information selected from the corresponding information modules according to the target display framework, and to form the target display page.

[0103] Optionally, the determining unit 404 is specifically used to: obtain the target region to which the target display object of the target product belongs; obtain the target industry attribute of the target product; and determine the corresponding target display framework based on the target region, the target industry attribute, and a predefined display strategy.

[0104] Optionally, the determining unit 404 is specifically used to: determine the display position corresponding to each display position included in the predefined display framework according to the target region, the target industry attribute and the predefined display strategy; sort the display positions included in the predefined display framework according to the display position to obtain the corresponding target display framework.

[0105] Optionally, the product display page generation device 400 further includes a processing unit, which is specifically used for: for each information module, performing preset processing on the non-textual description information in the recognition description information corresponding to the information module to obtain updated recognition description information; and using the updated recognition description information as the target information selected in the information module.

[0106] Optionally, the non-textual description information includes view-type description information and table-type description information. The processing unit is specifically used to: filter target view-type description information with a clarity greater than a preset clarity from the view-type description information to obtain processed view-type description information; fuse parameter-type description information belonging to product attributes in the table-type description information to obtain processed table-type description information; replace the view-type description information in the identified description information corresponding to the information module with the processed view-type description information, and replace the table-type description information in the identified description information corresponding to the information module with the processed table-type description information.

[0107] Optionally, the post-identification description information includes target post-identification description information presented in image form; the processing unit is further configured to: perform original information type identification processing on the target post-identification description information to obtain first target post-identification description information of table type, second target post-identification description information of text type, and third target post-identification description information of image type; update the first target post-identification description information from image type to table type and the second target post-identification description information from image type to text type in the post-identification description information to obtain updated post-identification description information.

[0108] Optionally, the target display page includes target detailed description information obtained based on the original detailed description information and basic display information of the target product. The processing unit is further configured to: determine target metadata that belongs to both the basic display information and the target detailed description information; remove the target metadata from the target detailed description information or the basic display information to obtain an updated target display page.

[0109] Optionally, the original detailed description information is description information provided for the first region, and the processing unit is further configured to: determine first description information to be localized from the identified description information; perform localization conversion on the first description information according to the localization configuration method corresponding to the first description information in other regions besides the first region, to obtain first description information provided for the other regions; add the first description information provided for the other regions to the identified description information to obtain updated identified description information.

[0110] Optionally, the first description information is a size chart, and the processing unit is further specifically used to: convert the size chart in the identified description information according to the size configuration method adopted in the other regions, so as to obtain a size chart provided for the other regions.

[0111] Optionally, the first description information is the product accessory information in the product image, and the processing unit is further specifically used to: convert the product accessory information of the target product in the product image in the identified description information according to the accessory configuration method adopted by users in other regions for the target product, so as to obtain a product image provided for the other regions.

[0112] Optionally, the determining unit 404 is specifically used to: obtain target historical interaction data of the target display object for the description information of each display position included in the predefined display framework from the historical interaction data of the target display object; and determine the display position corresponding to each display position included in the predefined display framework according to the target region, the target industry attribute, the target historical interaction data and the predefined display strategy.

[0113] Corresponding to the product display page generation method provided in the first embodiment of this application, the third embodiment of this application also provides an electronic device for generating product display pages.

[0114] like Figure 8 The diagram shown is a structural block diagram of an example of an electronic device for generating a product display page, provided in an embodiment of this application.

[0115] In this embodiment, an optional hardware structure of the electronic device 500 may be as follows: Figure 8 As shown, it includes: at least one processor 501, at least one memory 502 and at least one communication bus 505; the memory 502 contains a program 503 and data 504.

[0116] Bus 505 can be a communication device for transmitting data between components within electronic device 500, such as an internal bus (e.g., CPU-memory bus, where the processor is the central processing unit, or CPU for short) or an external bus (e.g., a universal serial bus port or a peripheral component interconnection fast port).

[0117] Additionally, the electronic device also includes at least one network interface 506 and at least one peripheral interface 507. The network interface 506 provides wired or wireless communication with an external network 508 (e.g., the Internet, intranet, local area network, mobile communication network, etc.). In some embodiments, the network interface 506 may include any number of network interface controllers (NICs), radio frequency (RF) modules, repeaters, transceivers, modems, routers, gateways, any combination of wired network adapters, wireless network adapters, Bluetooth adapters, infrared adapters, near field communication (NFC) adapters, cellular network chips, etc.

[0118] Peripheral interface 507 is used to connect to peripherals, such as peripheral 1 in the figure. Figure 8 509 in the middle), peripheral 2 ( Figure 8510 in the middle) and peripheral 3 ( Figure 8 (511 in the original text). Peripherals are peripheral devices, which may include, but are not limited to, cursor control devices (such as mice, touchpads, or touchscreens), keyboards, displays (such as cathode ray tube displays, liquid crystal displays), monitors or light-emitting diode displays, video input devices (such as cameras or input interfaces coupled to video files), etc.

[0119] The processor 501 may be a CPU, an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0120] Memory 502 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage device.

[0121] The processor 501 calls the program and data stored in the memory 502 to execute the following steps: obtaining the original detailed description information of the target product; performing type recognition processing on the original detailed description information according to different information types to obtain the recognition results of different types of description information, forming the recognized description information; classifying the recognized description information into different information modules according to predefined information categories based on the recognition results of the different types of description information; determining the corresponding target display framework according to the target display object of the target product and the attributes of the target product itself, based on a predefined display strategy; and filling the display positions in the target display framework with the target information selected from the corresponding information modules to form the target display page.

[0122] Corresponding to the product display page generation method provided in the first embodiment of this application, the fourth embodiment of this application provides a computer-readable storage medium storing a program for generating a product display page. This program is executed by a processor and performs the following steps: obtaining the original detailed description information of the target product; performing type identification processing on the original detailed description information according to different information types to obtain identification results for different types of description information, forming identified description information; classifying and listing the identified description information into different information modules formed according to predefined information categories based on the identification results of the different types of description information; determining a corresponding target display framework according to the target display object of the target product and the inherent attributes of the target product, based on a predefined display strategy; and filling the display positions within the target display framework with target information selected from the corresponding information modules to form a target display page.

[0123] It should be noted that for a detailed description of the apparatus, electronic device and computer-readable storage medium provided in the second, third and fourth embodiments of this application, please refer to the relevant description of the first embodiment of this application, which will not be repeated here.

[0124] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0125] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0126] 1. Computer-readable media includes both permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined in this application, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0127] 2. Those skilled in the art will understand that embodiments of this application can provide methods, systems, or computer program products. Therefore, embodiments of this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] 3. This application embodiment may involve the use of user data. In practical applications, user-specific personal data may be used within the scope permitted by applicable laws and regulations of the country in which the application is located (e.g., with the user's explicit consent and effective notification to the user, etc.). Furthermore, 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. The collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0129] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.

Claims

1. A method for generating a product display page, characterized in that, The method includes: Obtain the original detailed description information of the target product; Based on different information types, the original detailed description information is subjected to type identification processing to obtain the identification results of different types of description information, thus forming the identified description information; Based on the identification results of the different types of descriptive information, the identified descriptive information is categorized and included in different information modules formed according to predefined information categories; Based on the target audience of the target product and the attributes of the target product itself, determine the corresponding target display framework according to the predefined display strategy; Based on the target display framework, the target information selected from the corresponding information modules is filled into the display positions therein to form the target display page.

2. The method according to claim 1, characterized in that, The step of determining the corresponding target display framework based on the target display audience of the target product and the inherent attributes of the target product, according to a predefined display strategy, includes: Obtain the target region to which the target display object of the target product belongs; Obtain the target industry attributes of the target product; Based on the target region, the target industry attributes, and the predefined display strategy, determine the corresponding target display framework.

3. The method according to claim 1, characterized in that, The step of determining the corresponding target display framework based on the target region, the target industry attributes, and predefined display strategies includes: Based on the target region, the target industry attributes, and the predefined display strategy, determine the display position corresponding to each display position included in the predefined display framework; The display positions included in the predefined display frame are sorted according to the display position to obtain the corresponding target display frame.

4. The method according to claim 1, characterized in that, Before filling the display positions in the target display framework with the target information selected from the corresponding information modules to form the target display page, the method further includes: For each information module, the non-textual description information in the post-identification description information corresponding to the information module is pre-processed to obtain the updated post-identification description information; The updated post-identification description information is used as the target information selected in the information module.

5. The method according to claim 4, characterized in that, The non-textual description information includes view-type description information and table-type description information. The step of pre-processing the non-textual description information in the recognized description information corresponding to the information module to obtain updated recognized description information includes: Target view class description information with a resolution greater than a preset resolution is filtered from the view class description information to obtain the processed view class description information; The parameter description information belonging to product attributes in the table-type description information is merged to obtain the processed table-type description information; Replace the view class description information in the identified description information corresponding to the information module with the processed view class description information, and replace the table class description information in the identified description information corresponding to the information module with the processed table class description information.

6. The method according to claim 1, characterized in that, The post-identification description information includes target post-identification description information presented in image form; the method further includes: The target recognition description information is processed by original information type identification to obtain the first target recognition description information with original information type of table, the second target recognition description information with original information type of text, and the third target recognition description information with original information type of image. The first target identification description information is updated from image type to table type, and the second target identification description information is updated from image type to text type to obtain the updated identification description information.

7. The method according to claim 1, characterized in that, The target display page includes detailed target description information obtained based on the original detailed description information and basic display information of the target product. The method further includes: Determine the target metadata that belongs to both the basic display information and the target detailed description information; The target metadata is removed from the target's detailed description information or the basic display information to obtain the updated target display page.

8. The method according to claim 1, characterized in that, The original detailed description information is description information provided for the first region; before filling the display positions in the target display framework with the target information selected from the corresponding information modules to form the target display page, the method further includes: Determine the first description information to be localized from the identified description information; Based on the localization configuration methods corresponding to the first description information in other regions besides the first region, the first description information is localized to obtain the first description information provided for the other regions. The first description information provided for the other regions is added to the post-identification description information to obtain the updated post-identification description information.

9. The method according to claim 8, characterized in that, The first description information is a size chart; the step of performing localized conversion on the first description information according to the localized configuration methods corresponding to other regions besides the first region to obtain first description information provided for the other regions includes: According to the size configuration method adopted in other regions, the size table in the identified description information is converted to obtain a size table provided for other regions.

10. The method according to claim 8, characterized in that, The first descriptive information is the product accessory information in the product image; the step of performing localized conversion on the first descriptive information according to the localized configuration methods corresponding to the first descriptive information in other regions besides the first region to obtain the first descriptive information provided for the other regions includes: Based on the accessory configuration methods adopted by users in other regions for the target product, the accessory information of the target product in the product image in the identified description information is converted to obtain product images provided for the other regions.

11. The method according to claim 3, characterized in that, The step of determining the display position corresponding to each display position in the predefined display framework based on the target region, the target industry attributes, and the predefined display strategy includes: Obtain target historical interaction data from the target display object's historical interaction data for the description information corresponding to each display position included in the predefined display framework. Based on the target region, the target industry attributes, the target historical interaction data, and the predefined display strategy, determine the display position corresponding to each display position included in the predefined display framework.

12. A device for generating a product display page, characterized in that, The device includes: The acquisition unit is used to acquire the original detailed description information of the target product; The identification unit is used to perform type identification processing on the original detailed description information according to different information types, to obtain the identification results of different types of description information, and to form the identified description information; The inclusion unit is used to classify and include the identified description information into different information modules formed according to predefined information categories based on the identification results of the different types of description information; The determination unit is used to determine the corresponding target display framework based on the target display object of the target product and the attributes of the target product itself, according to a predefined display strategy. The forming unit is used to fill the display positions therein with target information selected from the corresponding information modules according to the target display framework, thereby forming a target display page.

13. An electronic device, characterized in that, include: processor; as well as A memory for storing a data processing program, which, when the electronic device is powered on and runs through the processor, performs the method as described in any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The system contains a data processing program that is executed by a processor to perform the method as described in any one of claims 1-11.

Images