Product structured information determination method and apparatus, and device

Abstract

The embodiments of the present disclosure provide a product structured information determination method and apparatus, and a device. The product structured information determination method comprises: acquiring category information and attribute items of products in a first e-commerce platform; determining at least one second e-commerce platform different from the first e-commerce platform and product information of products in the second e-commerce platform; on the basis of the category information and the attribute items, determining optional attribute items corresponding to the products in the second e-commerce platform; and on the basis of the product information and the optional attribute items, determining structured information of the products in the second e-commerce platform, wherein the structured information at least comprises a target attribute item. By means of the technical solution provided in the present embodiment, structured information of products in an external platform is effectively determined on the basis of category information and attribute items of products in an internal platform, thereby improving the accuracy of determining structured information of products, and also ensuring the practicability of the method.

Description

Method, device and equipment for determining product structured information

[0001] This disclosure claims priority to a Chinese patent application filed with the Patent Office of China on November 30, 2023, with application number 202311631051X and application name “Method, device and apparatus for determining product structured information,” the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0002] The present disclosure relates to the field of information processing, and in particular to a method, device, and apparatus for determining structured information of a product. Background Art

[0003] In e-commerce application scenarios, the structured information of products is of great significance. Currently, this information is often extracted using the Named Entity Recognition (NER) algorithm. However, due to the large variety of e-commerce platforms and the large differences in product expressions across different platforms, using the same NER algorithm model to extract structured information can easily reduce the accuracy of extracting product structured information.

[0004] Summary of the Invention

[0005] The embodiments of the present disclosure provide a method, apparatus, and device for determining product structured information, which can improve the accuracy of extracting product structured information.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for determining product structured information, comprising:

[0007] Obtain category information and attribute items of products on the first e-commerce platform;

[0008] Determine at least one second e-commerce platform different from the first e-commerce platform and product information of the products on the second e-commerce platform; based on the category information and attribute items, determine the optional attribute items corresponding to the products on the second e-commerce platform; based on the product information and optional attribute items, determine the structured information of the products on the second e-commerce platform, wherein the structured information includes at least the target attribute item.

[0009] In a second aspect, an embodiment of the present disclosure provides a device for determining product structured information, including:

[0010] The first acquisition module is used to obtain category information and attribute items of goods on the first e-commerce platform; the first determination module is used to determine at least one second e-commerce platform different from the first e-commerce platform and the product information of the goods on the second e-commerce platform; the first determination module is used to determine the optional attribute items corresponding to the goods on the second e-commerce platform based on the category information and attribute items; the first processing module is used to determine the structured information of the goods on the second e-commerce platform based on the product information and optional attribute items, and the structured information includes at least the target attribute items.

[0011] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method for determining the structured information of a product in the first aspect above.

[0012] In a fourth aspect, an embodiment of the present disclosure provides a computer storage medium for storing a computer program, wherein the computer program enables a computer to implement the method for determining product structured information in the first aspect when executed.

[0013] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when the computer instructions are executed by one or more processors, causes the one or more processors to execute the steps in the method for determining product structured information shown in the first aspect above.

[0014] The technical solution provided in this embodiment obtains the category information and attribute items of the goods in the first e-commerce platform; determines the product information of at least one second e-commerce platform different from the first e-commerce platform and the goods in the second e-commerce platform; and then determines the optional attribute items corresponding to the goods in the second e-commerce platform based on the category information and attribute items; and determines the structured information of the goods in the second e-commerce platform based on the product information and optional attribute items. It effectively realizes the determination of the structured information of the goods in the off-site platform based on the category information and attribute items of the goods in the on-site platform, and then facilitates the corresponding processing operations based on the structured information of the goods. This not only improves the accuracy of determining the structured information of the goods, but also ensures the practicality of the method, which is conducive to market promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] FIG1 is a schematic diagram of a scenario of a method for determining product structured information provided by an embodiment of the present disclosure;

[0017] FIG2 is a flow chart of a method for determining product structured information provided by an embodiment of the present disclosure;

[0018] FIG3 is a schematic diagram of a process for determining structured information of a product on the second e-commerce platform based on the product information and optional attribute items provided by an embodiment of the present disclosure;

[0019] FIG4 is a flow chart of another method for determining product structured information provided by an embodiment of the present disclosure;

[0020] FIG5 is a flow chart of another method for determining product structured information provided by an embodiment of the present disclosure;

[0021] FIG6 is a schematic diagram showing the principle of a method for determining product structured information according to an embodiment of the present disclosure;

[0022] FIG7 is a second schematic diagram of the principle of a method for determining product structured information provided by an application embodiment of the present disclosure;

[0023] FIG8 is a first schematic diagram of generating prompt information provided by an application embodiment of the present disclosure;

[0024] FIG9 is a second schematic diagram of generating prompt information provided by an application embodiment of the present disclosure;

[0025] FIG10 is a third schematic diagram of generating prompt information provided by an application embodiment of the present disclosure;

[0026] FIG11 is a schematic diagram of the structure of a device for determining product structured information provided by an application embodiment of the present disclosure;

[0027] FIG12 is a schematic structural diagram of an electronic device corresponding to the apparatus for determining structured information of a commodity provided by the embodiment shown in FIG11 . DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0029] The terms used in the embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit the present disclosure. The singular forms "a," "an," and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two, but does not exclude the inclusion of at least one.

[0030] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0031] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0032] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or system. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or system comprising the element.

[0033] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0034] Definition of terms:

[0035] Named Entity Recognition (NER) refers to the technology of automatically identifying and classifying entities appearing in text in the field of natural language processing. It can identify named entities, such as names of people, places, and organizations, and label them with corresponding categories.

[0036] CPV: Category, Property, Value, represents the category, property and property value of the product.

[0037] Category: This refers to the classification of products, which refers to a collection of products with certain common characteristics. It can be divided into multiple categories according to the granularity of classification. For example, in the category of clothing-men's clothing-jackets, clothing is a first-level category, men's clothing is a second-level category, and jackets is a sub-category.

[0038] Attribute: It is the characteristic of a product. The attribute value is the specific content of the attribute. For example, the attributes of a product include color, size, collar type, sleeve type, etc. The attribute values ​​of color attribute include red, pink, brown, etc.

[0039] Product word: refers to the name of a brand or product, usually used in the business field to refer to a specific product or service. For example, dress, pajamas, excavator, etc. are all product words.

[0040] Large Language Models (LLMs): These are natural language processing models based on deep learning. These models utilize neural networks for training and can automatically learn the patterns and characteristics of natural language, enabling them to perform tasks such as language modeling, text generation, machine translation, and speech recognition. These models typically require large amounts of data and computing resources to train, hence the term "large" language models.

[0041] ChatGPT: A natural language processing model based on the Transformer architecture that can generate and understand natural language text.

[0042] To facilitate understanding of the specific implementation process and effects of the method, apparatus, and device for determining product structured information in this embodiment, the following briefly describes the relevant technologies:

[0043] With the rapid development of e-commerce platforms, various types of e-commerce platforms have emerged rapidly. For any e-commerce platform, the structured information of products on the e-commerce platform is of great significance. For example, the structured information of products on off-site platforms can help operations and merchants identify external demand, quickly capture and explore opportunity markets and selling points. The obtained opportunity markets and selling points are an important basis for operations to carry out category planning, which can guide the website's product supply and delivery strategies.

[0044] Currently, the structured information of products is often obtained by extracting products from off-site platforms using named entity recognition (NER) algorithms, and trend attributes and selling points can be identified. However, due to the large variety of e-commerce platforms, the expression of products on different e-commerce platforms varies greatly. In order to accurately obtain the structured information of products on each e-commerce platform, different e-commerce platforms can be configured with different NER algorithm models. Since any NER algorithm model has limited understanding of off-site products, if the same NER algorithm model is used to extract structured information, since the NER algorithm model can only accurately extract information from products on the on-site platform, the information that can be extracted from products on off-site platforms is limited and the semantic understanding is poor, this can easily reduce the accuracy of determining the structured information of products.

[0045] Alternatively, if different NER algorithm models are used to extract structured information, the training efficiency of the NER algorithm model is low. In addition, for each NER algorithm model, data collection, labeling, and model training operations are required. If the trained NER algorithm model does not meet expectations, all model training and data processing processes are still required, which makes the data extraction efficiency relatively low.

[0046] To address the above technical issues, this embodiment provides a method, device, and apparatus for determining product structured information. Referring to FIG1 , the method for determining product structured information is performed by a device 200 for determining product structured information. The device 200 is communicatively connected to a client 100. It should be noted that the device 200 for determining product structured information can be implemented as a personal computer, a tablet computer, a local server, or a cloud server. When the device 200 for determining product structured information is implemented as a cloud server, the method for determining product structured information can be executed in the cloud. Several computing nodes (cloud servers) can be deployed in the cloud, each of which has processing resources such as computing and storage. In the cloud, multiple computing nodes can be organized to provide a certain service. Of course, a single computing node can also provide one or more services. The cloud can provide the service by providing a service interface to the outside world, and users can call the service interface to use the corresponding service. Service interfaces include software development kits (SDKs) and application programming interfaces (APIs).

[0047] The client 100 is used by users (e.g., operations personnel on an e-commerce platform) to perform operations to determine product structured information. The client 100 can be any computing device with sufficient data transmission capabilities. Specifically, the client 100 can be a mobile phone, a personal computer (PC), a tablet computer, a configuration application, and the like. Furthermore, the basic structure of the client 100 may include at least one processor. The number of processors depends on the configuration and type of the client 100. The client 100 may also include memory, which can be volatile, such as random access memory (RAM), non-volatile, such as read-only memory (ROM), flash memory, or both. The memory typically stores an operating system (OS), one or more application programs, and may also store program data. In addition to the processing unit and memory, the client 100 also includes some basic configurations, such as a network card chip, an I / O bus, a display component, and some peripheral devices. Optionally, some peripheral devices may include, for example, a keyboard, a mouse, a stylus, a printer, and the like. Other peripheral devices are well known in the art and will not be described in detail here.

[0048] The device 200 for determining product structured information refers to a device capable of performing product structured information determination operations within a network virtual environment. It typically refers to a device that utilizes a network to perform information planning and product structured information determination operations. Physically, the device 200 for determining product structured information can be any device capable of providing computing services, responding to product structured information determination requests, and performing product structured information determination operations based on these requests. For example, it can be a cluster server, a conventional server, a cloud server, a cloud host, a virtual center, etc. The device 200 for determining product structured information primarily comprises a processor, a hard drive, memory, a system bus, and other components, similar to a general-purpose computer architecture.

[0049] In the above embodiment, the client 100 is connected to the device 200 for determining product structured information through a network, and the network connection may be a wireless or wired network connection. If the client 100 can be communicatively connected to the device 200 for determining product structured information, the network standard of the mobile network can be any one of 2G (GSM (Global System for Mobile Communications), 2.5G (GPRS (General Packet Radio Service), 3G (WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division Synchronous Code Division Multiple Access), CDMA2000 (Code Division Multiple Access 2000), UTMS (Universal Mobile Telecommunications System), 4G (LTE (Long Term Evolution), 4G+ (LTE+ (Long Term Evolution Advanced)), WiMax (Worldwide Interoperability for Microwave Access), 5G (fifth generation global system for mobile communications), 6G (fifth generation global system for mobile communications), etc.

[0050] When a user requests to determine product structured information, the client 100 may generate or obtain a request for determining the product structured information. In some instances, the request for determining the product structured information may be obtained based on a human-computer interaction operation. In this case, the client 100 may display a human-computer interaction interface, obtain the interaction operation input by the user in the human-computer interaction interface, and obtain and determine the request for determining the product structured information based on the interaction operation. Alternatively, the request for determining the product structured information may be obtained via a preset interface or a third device. In this case, obtaining the request for determining the product structured information may include: obtaining a communication interface on the client 100; or actively or passively transmitting the request for determining the product structured information based on a third device in communication with the communication interface. After obtaining the request for determining the product structured information, in order to accurately determine the product structured information, the request for determining the product structured information may be sent to the product structured information determination device 200, so that the product structured information determination device 200 performs the product structured information determination operation.

[0051] The device 200 for determining product structured information is used to obtain a determination request for product structured information sent by the client 100, and then obtain the category information and attribute items of the product in the first e-commerce platform (i.e., the in-site platform) based on the determination request for the product structured information, wherein the product in the first e-commerce platform may refer to all products that can be displayed on the display page, and the category information of the product may be a secondary category, a tertiary category or a leaf category, etc. In some instances, the category information of the product may preferably be a leaf category.

[0052] In order to accurately determine the structured information of products in a second e-commerce platform (i.e., an off-site platform) other than the first e-commerce platform, it is possible to first determine at least one second e-commerce platform different from the first e-commerce platform and the title information and description information of the products in the second e-commerce platform. The products in the second e-commerce platform may refer to all products that can be displayed on the display page, the title information may refer to the name information of the product, and the description information may refer to the information used to provide a detailed description of the product on the second e-commerce platform, so that users can quickly understand the situation of the product through the description information.

[0053] After obtaining the category information and attribute items of the goods in the first e-commerce platform, the category information and attribute items can be analyzed and processed to determine the optional attribute items corresponding to the goods in the second e-commerce platform. Then, the title information, description information and optional attribute items can be analyzed and processed to determine the structured information of the goods in the second e-commerce platform, and the structured information at least includes the target attribute items; thereby effectively realizing the accurate determination of the structured information of the goods in the second e-commerce platform based on the category information and attribute items of the goods in the first e-commerce platform, thereby improving the accuracy of determining the structured information of the goods, and then based on the obtained structured information of the goods, the opportunity market or selling point mining operation can be carried out, further improving the practicality of the method.

[0054] Some embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. The following embodiments and features thereof may be combined with one another unless they conflict with each other. Furthermore, the sequence of steps in the following method embodiments is provided for illustrative purposes only and is not intended to be a strict limitation.

[0055] FIG2 is a flow chart of a method for determining product structured information provided by an embodiment of the present disclosure; Referring to FIG2 , this embodiment provides a method for determining product structured information, the execution subject of which is a device for determining product structured information. It can be understood that the device for determining product structured information can be implemented as software, or a combination of software and hardware. Specifically, when the device for determining product structured information is implemented as hardware, it can be various electronic devices with a product structured information determination operation, including but not limited to personal computers, servers, etc. When the device for determining product structured information is implemented as software, it can be installed in the electronic devices listed above. Moreover, in different application scenarios, the device for determining product structured information can be configured in different application platforms. Based on the above-mentioned device for determining product structured information, the method for determining product structured information that can be implemented by this embodiment may include:

[0056] Step S201: Obtain category information and attribute items of products on the first e-commerce platform.

[0057] Step S202: Determine at least one second e-commerce platform different from the first e-commerce platform and product information of products on the second e-commerce platform.

[0058] Step S203: Based on the category information and attribute items, determine the optional attribute items corresponding to the product in the second e-commerce platform.

[0059] Step S204: Based on the product information and the optional attribute items, determine the structured information of the product in the second e-commerce platform, where the structured information at least includes the target attribute item.

[0060] The following is a detailed description of the specific implementation process and results of each of the above steps:

[0061] Step S201: Obtain category information and attribute items of products on the first e-commerce platform.

[0062] When a user needs to determine product structured information, in order to implement the product structured information determination operation, the category information and attribute items of the product on the first e-commerce platform can be obtained. The products on the first e-commerce platform may refer to all products that can be displayed on the display page of the first e-commerce platform. The category information of the product may refer to the secondary category, tertiary category, or sub-category of the product, etc. The attribute items may refer to the attribute information corresponding to the name or title of the product. For example, if the name of the product is "Red Puff Sleeve Dress", the attribute items may include: "Color Attribute" corresponding to "Red", "Sleeve Type Attribute" corresponding to "Puff Sleeve", and "Product Type Attribute" corresponding to "Dress". If the title of the product is "Blue Cotton Clothes", the attribute items may include: "Color Attribute" corresponding to "Blue", "Material Attribute" corresponding to "Cotton", and "Product Type Attribute" corresponding to "Clothes", etc.

[0063] Specifically, this embodiment does not limit the specific method of obtaining the category information and attribute items of the goods on the first e-commerce platform. In some instances, the category information and attribute items of the goods on the first e-commerce platform can be stored in a preset area in the first e-commerce platform, and the category information and attribute items of the goods on the first e-commerce platform can be obtained by accessing the preset area.

[0064] In other instances, the category information and attribute items of the goods on the first e-commerce platform can be obtained not only by accessing the preset area, but also by extracting information from the first e-commerce platform. At this time, obtaining the category information and attribute items of the goods on the first e-commerce platform may include: obtaining the display interface on the first e-commerce platform; performing information extraction operations on the display interface to obtain the goods on the first e-commerce platform; and then determining the category information and attribute items corresponding to the goods on the first e-commerce platform, thereby effectively ensuring the accuracy and reliability of the determination of the category information and attribute items of the goods on the first e-commerce platform.

[0065] Step S202: Determine at least one second e-commerce platform different from the first e-commerce platform and product information of products on the second e-commerce platform.

[0066] In the field of e-commerce, there are often multiple e-commerce platforms. In this case, the e-commerce field can be configured with a first e-commerce platform and at least one second e-commerce platform different from the first e-commerce platform. For the operation and maintenance personnel of the first e-commerce platform, the first e-commerce platform can be an on-site platform, and the second e-commerce platform can be an off-site platform. In order to accurately determine the structured information of goods in other e-commerce platforms (i.e., off-site platforms) based on the category information and attribute items of goods in the first e-commerce platform (i.e., the on-site platform), after obtaining the category information and attribute items of goods in the first e-commerce platform, at least one second e-commerce platform different from the first e-commerce platform and the product information of the goods in the second e-commerce platform can be determined. It should be noted that when there are multiple e-commerce platforms, the product information of the goods in each e-commerce platform can be obtained; when there is only one e-commerce platform, the product information of the goods in the current second e-commerce platform can be obtained. In addition, the products in the second e-commerce platform may be some or all of the products that can be displayed in the display interface of the platform, and the product information may be the sum of all information associated with the products. In some instances, the product information may include the title information of the product and the description information of the product. The title information of the above-mentioned product may be the name information of the product, and the category to which the product belongs can be determined through the title information of the product. The description information of the product may be detailed introduction information, promotional information, etc. used to describe the product.

[0067] In some instances, when product information includes title information and description information, the title information and description information of the product can be obtained by extracting information from a second e-commerce platform. At this time, determining the title information and description information of the product on the second e-commerce platform can include: after determining at least one second e-commerce platform different from the first e-commerce platform, obtaining the product category corresponding to the product on the second e-commerce platform; extracting information on the products that can be displayed on the display interface of the second e-commerce platform according to the product category, and obtaining the title information and description information of the product on the second e-commerce platform.

[0068] In some other instances, the title information and description information of the product can be obtained not only through information extraction technology, but also through a second e-commerce platform. At this time, determining the title information and description information of the product on the second e-commerce platform may include: determining the communication interface corresponding to the second e-commerce platform, and actively or passively obtaining the title information and description information of the product stored in the second e-commerce platform through the communication interface of the second e-commerce platform, thereby effectively ensuring the accuracy and reliability of the determination of the title information and description information of the product.

[0069] Step S203: Based on the category information and attribute items, determine the optional attribute items corresponding to the product in the second e-commerce platform.

[0070] Since the first e-commerce platform and the second e-commerce platform are different e-commerce platforms, the products on different e-commerce platforms may have corresponding attribute expressions. In order to accurately determine the structured information of the products on the second e-commerce platform, the product categories and attribute system of the first e-commerce platform can be used to determine the optional attribute items corresponding to the products on the second e-commerce platform. Specifically, after obtaining the category information and attribute items, the category information and attribute items can be analyzed and processed to determine the optional attribute items corresponding to the products on the second e-commerce platform, wherein the optional attribute items are the range corresponding to the attribute items that can be determined for the products on the second e-commerce platform.

[0071] In some instances, optional attribute items can be obtained by analyzing and processing category information and attribute items based on a pre-trained machine learning model or neural network model. At this time, determining the optional attribute items corresponding to the products on the second e-commerce platform based on the category information and attribute items may include: obtaining a pre-trained machine learning model or neural network model; inputting the category information, attribute items and products on the second e-commerce platform into the machine learning model to obtain the optional attribute items corresponding to the products on the second e-commerce platform. It should be noted that the obtained optional attribute items may be the same as or different from the attribute items of the products on the first e-commerce platform.

[0072] In other instances, optional attribute items can be obtained not only by analyzing and processing category information and attribute items based on a machine learning model or a neural network model, but can also be obtained directly by analyzing and processing the category information and attribute items. In this case, based on the category information and attribute items, determining the optional attribute items corresponding to the goods on the second e-commerce platform may include: determining the target category corresponding to the goods on the second e-commerce platform in the category information; and determining the attribute items corresponding to the target category as the optional attribute items corresponding to the goods on the second e-commerce platform.

[0073] Specifically, since the first e-commerce platform is an in-site platform and the second e-commerce platform is an off-site platform, the category information of the goods on the first e-commerce platform obtained is more comprehensive than that on the off-site platform. At this time, it can be considered that the category of the goods on the second e-commerce platform can be at least a part of the category information of the goods on the first e-commerce platform. Therefore, in order to accurately obtain the optional attribute items corresponding to the goods on the second e-commerce platform, after obtaining the category information of the goods on the first e-commerce platform, the target category corresponding to the goods on the second e-commerce platform can be determined in the category information, that is, the target category corresponding to the goods on the second e-commerce platform is any one of the category information of the goods on the first e-commerce platform.

[0074] After determining the target category corresponding to the product on the second e-commerce platform, the attribute items corresponding to the target category can be determined as the optional attribute items corresponding to the product on the second e-commerce platform. At this time, the obtained optional attribute items corresponding to the product on the second e-commerce platform are part of the attribute items on the first e-commerce platform, thereby effectively ensuring the accuracy and reliability of the determination of the optional attribute items corresponding to the product on the second e-commerce platform.

[0075] Step S204: Based on the product information and the optional attribute items, determine the structured information of the product in the second e-commerce platform, where the structured information at least includes the target attribute item.

[0076] After obtaining the product information and optional attribute items, the product information and optional attribute items can be analyzed and processed to obtain the structured information of the product on the second e-commerce platform. In some instances, the structured information of the product on the second e-commerce platform can be obtained by analyzing and processing the product information and optional attribute items using a pre-trained machine learning model or neural network model. In this case, determining the structured information of the product on the second e-commerce platform based on the product information and optional attribute items may include: obtaining the pre-trained machine learning model or neural network model, inputting the product information and optional attribute items into the pre-trained machine learning model or neural network model, and obtaining the structured information of the product on the second e-commerce platform output by the machine learning model or neural network model, wherein the obtained structured information includes at least the target attribute items, thereby effectively ensuring the accuracy and reliability of determining the structural information of the product on the second e-commerce platform.

[0077] In some other instances, in order to improve the practicality of the method, after determining the structured information of the product in the second e-commerce platform, the method in this embodiment may also include: identifying whether the target attribute item exists in the first e-commerce platform; if the target attribute item does not exist in the first e-commerce platform, adding the target attribute item to the first e-commerce platform to obtain the updated attribute item of the product in the first e-commerce platform.

[0078] Since the first e-commerce platform and the second e-commerce platform are different e-commerce platforms, different e-commerce platforms may correspond to different attribute items, that is, the target attribute items of the products on the second e-commerce platform obtained may be included in the attribute items of the products on the first e-commerce platform, or the target attribute items of the products on the second e-commerce platform are not included in the attribute items of the products on the first e-commerce platform. Therefore, after obtaining the target attribute items of the products on the second e-commerce platform, the target attribute items of the products on the second e-commerce platform can be analyzed and compared with the attribute items of the products on the first e-commerce platform to identify whether the target attribute items exist in the first e-commerce platform. When the target attribute items do not exist in the first e-commerce platform, in order to make the attribute items in the first e-commerce platform more comprehensive, the target attribute items can be added to the first e-commerce platform, so that the updated attribute items of the products on the first e-commerce platform can be obtained. When the target attribute items exist in the first e-commerce platform, the attribute items of the products on the first e-commerce platform can be kept unchanged, thereby effectively realizing that the attribute items in the first e-commerce platform can be updated based on the structured information of the products on the off-site platform, thereby further improving the comprehensiveness of the attribute items of the products on the first e-commerce platform.

[0079] For example, the attribute items of a product on a first e-commerce platform may include: attribute a, attribute b, attribute c, and attribute d, and the target attribute items of a product on a second e-commerce platform may include: attribute a, attribute b, attribute e, and attribute f. As for attributes e and f of the product on the second e-commerce platform, since the above-mentioned attributes e and attribute f are not included in the first e-commerce platform, the above-mentioned target attribute items can be added to the first e-commerce platform, thereby obtaining the updated attribute items of the product on the first e-commerce platform. The updated attribute items may include: attribute a, attribute b, attribute c, attribute d, attribute e, and attribute f. As for attributes a and b of the product on the second e-commerce platform, since the above-mentioned attributes a and attribute b are included in the first e-commerce platform, the attribute items of the product on the first e-commerce platform can be kept unchanged.

[0080] In other instances, in order to further improve the practicality of the method, after determining the structured information of the goods in the second e-commerce platform, opportunity market mining operations can be performed based on the structured information of the goods in the second e-commerce platform. At this time, the method in this embodiment may also include: obtaining platform transaction data and attention attributes corresponding to the goods in the second e-commerce platform; based on the structured information, platform transaction data and attention attributes of the goods in the second e-commerce platform, determining the product adjustment plan corresponding to the first e-commerce platform.

[0081] After determining the structured information of the goods in the second e-commerce platform, the platform transaction data and attention attributes corresponding to the goods in the second e-commerce platform can be obtained, wherein the platform transaction data can be obtained by analyzing and processing the log information in the second e-commerce platform, and the attention attributes can be obtained by analyzing and processing the category information of the goods in the second e-commerce platform. At this time, obtaining the platform transaction data and attention attributes corresponding to the goods in the second e-commerce platform in this embodiment can include: obtaining the log information in the second e-commerce platform; performing information extraction operations on the log information to obtain the platform transaction data corresponding to the goods in the second e-commerce platform; determining the category information of the goods in the second e-commerce platform; and determining the attention attributes of the goods in the second e-commerce platform based on the category information, thereby effectively ensuring the accuracy and reliability of the acquisition of the platform transaction data and attention attributes.

[0082] As for platform transaction data and attention attributes, platform transaction data may include at least one of the following: platform transaction order data, platform transaction amount data, platform transaction status data, platform transaction evaluation data, etc., and attention attributes may refer to attribute information that can affect commodity transaction operations. It should be noted that different commodities may have different attention attributes. For example, for clothing commodities, attention attributes may include at least one of the following: brand, color, material, version, style, etc.; for electronic commodities, attention attributes may include at least one of the following: brand, color, size, model, configuration, etc.; for mechanical commodities, attention attributes may include at least one of the following: volume, weight, configuration, etc.

[0083] After obtaining the structured information, platform transaction data and attention attributes of the goods on the second e-commerce platform, the structured information, platform transaction data and attention attributes of the goods can be analyzed and processed to determine the product adjustment plan corresponding to the first e-commerce platform. In some instances, the product adjustment plan is obtained through a pre-trained machine learning model or neural network model. At this time, based on the structured information, platform transaction data and attention attributes of the goods on the second e-commerce platform, determining the product adjustment plan corresponding to the first e-commerce platform can include: obtaining a pre-trained machine learning model or neural network model, inputting the structured information, platform transaction data and attention attributes of the goods on the second e-commerce platform into the pre-trained machine learning model or neural network model, and obtaining the product adjustment plan corresponding to the first e-commerce platform output by the machine learning model or neural network model.

[0084] For example, taking "red puff sleeve dress" as a product on the second e-commerce platform, after determining the structured information of the product on the second e-commerce platform, the structured information of the product may include: product name (dress) and target attribute items (color, sleeve type, product type), and then the platform transaction data and attention attributes of "red puff sleeve dress" on the second e-commerce platform can be obtained. When the platform transaction data is a platform transaction order, the quantity and amount corresponding to the platform transaction order can be counted, and then the platform transaction order can be analyzed and compared with the preset threshold. When the quantity and amount corresponding to the platform transaction order are greater than or equal to the preset threshold, it means that the sales volume of the product on the second e-commerce platform is good and can meet the market demand, and then based on the structured information of the product on the second e-commerce platform, the platform The transaction data and attention attributes are used to generate a product adjustment plan corresponding to the first e-commerce platform. For example, when the sales volume of the "red puff sleeve dress" on the second e-commerce platform is high, a product adjustment plan for increasing the number of corresponding products can be generated. The product adjustment plan is used to indicate that the number of announcements or publicity and promotion information of the "red puff sleeve dress" product should be increased on the first e-commerce platform; when the sales volume of the "red puff sleeve dress" on the second e-commerce platform is low, a product adjustment plan for reducing the number of corresponding products can be generated. The product adjustment plan is used to indicate that the number of announcements or publicity and promotion information of the "red puff sleeve dress" product should be reduced on the first e-commerce platform. This is conducive to increasing the transaction volume and transaction rate of products on the first e-commerce platform, thereby helping to improve the stickiness of platform users and ensuring the flexibility and reliability of the method.

[0085] The method for determining the structured information of a product provided in this embodiment obtains the category information and attribute items of the product on a first e-commerce platform; determines the product information of at least one second e-commerce platform different from the first e-commerce platform and the product on the second e-commerce platform; and then determines the optional attribute items corresponding to the product on the second e-commerce platform based on the category information and attribute items; and determines the structured information of the product on the second e-commerce platform based on the product information and the optional attribute items. This effectively realizes the determination of the structured information of the product on an off-site platform based on the category information and attribute items of the product on the in-site platform, and then facilitates corresponding data processing operations based on the structured information of the product. This not only improves the accuracy of determining the structured information of the product, but also ensures the flexibility and reliability of the method, which is conducive to market promotion and application.

[0086] FIG3 is a schematic diagram of a process for determining structured information of a product on a second e-commerce platform based on product information and optional attributes, according to an embodiment of the present disclosure. Based on the above embodiment and with reference to FIG3 , the structured information of a product on the second e-commerce platform can be obtained not only through a pre-trained machine learning model or neural network model, but also through a large-scale language processing model. When the product information includes title information and description information, determining the structured information of a product on the second e-commerce platform based on the product information and optional attributes may include:

[0087] Step S301: Integrate the title information, description information, and optional attribute items to obtain a first prompt for input into a large-scale language processing model. The first prompt is used to determine the attribute items of the product.

[0088] Among them, in order to stably obtain the structured information of the goods in the second e-commerce platform through the large-scale language processing model, the prompt information for input into the large-scale language processing model can be obtained first. Therefore, after obtaining the title information, description information and optional attribute items, the title information, description information and optional attribute items can be integrated. Specifically, a preset template for integrating the title information, description information and optional attribute items can be obtained; the title information, description information and optional attribute items are integrated according to the preset template in a natural language manner, so that a first prompt Prompt for input into the large-scale language processing model can be obtained, and the first prompt Prompt is used to determine the attribute items of the product.

[0089] In some other instances, the first prompt can be obtained not only by integrating the title information, description information and optional attribute items, but also by combining the focus attributes of the product in the second e-commerce platform. At this time, integrating the title information, description information and optional attribute items to obtain the first prompt for input into the large-scale language processing model can include: obtaining the focus attributes corresponding to the product in the second e-commerce platform; integrating the title information, description information, optional attribute items and focus attribute items to obtain a first prompt for determining the product attribute items.

[0090] For the goods in the second e-commerce platform, the attribute items of the goods may not only be related to the title information, description information and optional attribute items of the goods, but also be related to the attention attributes of the goods in the second e-commerce platform. Therefore, in order to accurately obtain the prompt information used to determine the attribute items of the goods, the attention attributes corresponding to the goods in the second e-commerce platform may be obtained. It should be noted that different goods may have different attention attributes. Therefore, the attention attributes can be expressed through the product category. At this time, obtaining the attention attributes corresponding to the goods in the second e-commerce platform may include: obtaining the target category corresponding to the goods in the second e-commerce platform; based on the target category, determining the attention attributes corresponding to the goods in the second e-commerce platform, thereby effectively ensuring the accuracy and reliability of the determination of the attention attributes of the goods in the second e-commerce platform.

[0091] After obtaining the focus attributes corresponding to the products in the second e-commerce platform, the title information, description information, optional attribute items and focus attribute items can be integrated and processed. Specifically, the title information, description information, optional attribute items and focus attributes can be integrated in a natural language manner, so that the first prompt Prompt for input into the large-scale language processing model can be stably obtained.

[0092] Step S303: Process the first prompt using a large-scale language processing model to obtain target attribute items of the product on the second e-commerce platform.

[0093] After obtaining the first prompt, the first prompt can be processed using a large-scale language processing model, that is, the first prompt is input into the large-scale language processing model to obtain the target attribute items of the goods in the second e-commerce platform output by the large-scale language processing model, thereby effectively ensuring the accuracy and reliability of the determination of the target attribute items of the goods in the second e-commerce platform.

[0094] In some other instances, this embodiment can not only obtain the target attribute items of the goods in the second e-commerce platform, but also obtain the name information of the goods in the second e-commerce platform. Specifically, after determining at least one second e-commerce platform different from the first e-commerce platform and the product information of the goods in the second e-commerce platform, the method in this embodiment can also include: integrating the title information and the description information to obtain a second prompt for input into the large-scale language processing model, the second prompt is used to determine the name of the product; using the large-scale language processing model to process the second prompt to obtain the product name of the product in the second e-commerce platform.

[0095] Specifically, in order to accurately store and process the structured information of the product, while obtaining the structured information of the product, this embodiment can also obtain the product name of the product on the second e-commerce platform. Since the product name and the target attribute item belong to different information, the product name and the target attribute item can be generated by different prompt information, that is, the prompt information used to determine the attribute item of the product can be different from the prompt information used to determine the name information of the product. Similar to the implementation method of the above step S301, after obtaining the title information and description information, the title information and description information can be integrated. Specifically, a preset integration method for integrating the title information and description information can be obtained; the title information and description information are integrated according to the preset template in a natural language manner, so that a second prompt Prompt for input into the large-scale language processing model can be obtained. The second prompt Prompt is used to determine the name of the product.

[0096] After obtaining the second prompt, the second prompt can be processed using a large-scale language processing model, that is, the second prompt is input into the large-scale language processing model to obtain the product name of the product on the second e-commerce platform output by the large-scale language processing model, thereby effectively ensuring the accuracy and reliability of determining the product name of the product on the second e-commerce platform.

[0097] It should be noted that the large-scale language processing model used to process the first prompt and the large-scale language processing model used to process the second prompt are the same model. For the large-scale language processing model, the number of tasks that need to be processed can be one or more. When the number of tasks is one, that is, the number of prompt information input into the large-scale language processing model is one, the large-scale language processing model can directly analyze and process the prompt information, thereby completing the task processing operation; when the number of tasks is multiple, that is, the number of prompt information input into the large-scale language processing model is multiple, the large-scale language processing model can process multiple tasks synchronously or asynchronously, thereby completing the task processing operation.

[0098] Specifically, when a large-scale language processing model is used to perform synchronous processing operations on multiple tasks, multiple prompt information corresponding to the multiple tasks can be batch-inputted into the large-scale language processing model. The large-scale language processing model can synchronously process the multiple prompt information, thereby obtaining processing results corresponding to the multiple prompt information output by the large-scale language processing model. It should be noted that when the large-scale language processing model synchronously processes multiple prompt information, if the current prompt information has not obtained the processing result, the processing operation on the next prompt information is prohibited until the processing result corresponding to the previous prompt information is obtained. After the processing result corresponding to the previous prompt information is obtained, the processing result can be displayed, and the next prompt information can be processed. At the same time, the large-scale language processing model can be used to directly obtain the processing result and display the processing result.

[0099] When using a large-scale language processing model to perform asynchronous processing operations on multiple tasks, the prompt information corresponding to the multiple tasks can be asynchronously input into the large-scale language processing model, and the large-scale language processing model can asynchronously process the multiple prompt information. It should be noted that when the large-scale language processing model processes multiple prompt information in sequence, if the current prompt information has not obtained the processing result, the next prompt information can be directly processed. When the processing result corresponding to the previous prompt information is obtained, the user can be prompted through the message mechanism that the task processing result has been obtained, and whether the task processing result needs to be displayed can be determined based on the user's execution operation on the prompt information sent by the message mechanism. Specifically, when the user clicks on the prompt information sent by the message mechanism, the task processing result can be displayed; when the user does not click on the prompt information sent by the message mechanism, the task processing result is prohibited from being displayed, thereby effectively realizing the asynchronous processing operations of multiple tasks using a large-scale language processing model.

[0100] In this embodiment, by integrating the title information, description information and optional attribute items, a first prompt for input into a large-scale language processing model is obtained, and the title information and description information are integrated to obtain a second prompt for input into the large-scale language processing model. The first prompt is then processed by the large-scale language processing model to obtain the target attribute items of the product on the second e-commerce platform, and the second prompt is processed by the large-scale language processing model to obtain the product name of the product on the second e-commerce platform, thereby effectively achieving the accurate and reliable acquisition of the structured information and product name of the product on the second e-commerce platform, and further improving the practicality of the method.

[0101] FIG4 is a flow chart of another method for determining product structured information provided by an embodiment of the present disclosure. Based on the above embodiment, with reference to FIG4 , the structured information of a product may include not only target attribute items but also product selling point information. Product selling point information may refer to information such as unique features and characteristics of a product. Such features and characteristics may be inherent to the product or created by operation and maintenance personnel. In this case, in order to accurately obtain the structured information of the product, the method in this embodiment may further include:

[0102] Step S401: Integrate the title information and description information to obtain a third prompt for input into a large-scale language processing model, where the third prompt is used to determine the selling point information of the product.

[0103] Among them, when the structured information includes product selling point information, the product selling point information is associated with the title information and the description information. Therefore, in order to accurately determine the product selling point information, after obtaining the title information and the description information, the title information and the description information can be integrated. Specifically, a preset template for integrating the title information and the description information can be obtained; the title information and the description information are integrated according to the preset template in a natural language manner, so as to obtain a third prompt Prompt for input into the large-scale language processing model, and the third prompt Prompt is used to determine the selling point information of the product.

[0104] Step S402: Process the third prompt using a large-scale language processing model to obtain preliminary selling point information of the product on the second e-commerce platform.

[0105] After obtaining the third prompt, the third prompt can be processed using a large-scale language processing model, that is, the third prompt is input into the large-scale language processing model to obtain the preliminary selling point information of the product in the second e-commerce platform output by the large-scale language processing model. The number of preliminary selling point information obtained can be multiple.

[0106] Step S403: Obtain the attention attributes corresponding to the products in the second e-commerce platform.

[0107] Since the number of preliminary selling point information of products that can be obtained through large-scale language processing models is often multiple, in order to accurately determine the selling point information of products on the second e-commerce platform, the focus attributes corresponding to the products on the second e-commerce platform can be obtained. It should be noted that different products may correspond to different focus attributes. In some instances, the focus attributes can be obtained based on the category information of the products on the second e-commerce platform. At this time, obtaining the focus attributes corresponding to the products on the second e-commerce platform may include: obtaining a mapping relationship between a pre-configured product category and the focus attributes, and determining the category information of the products on the second e-commerce platform; determining the focus attributes corresponding to the products on the second e-commerce platform based on the mapping relationship and the category information of the products, thereby effectively ensuring the accuracy and reliability of the determination of the focus attributes.

[0108] Step S404: Based on the attention attributes and the preliminary selling point information, determine the target selling point information of the product on the second e-commerce platform.

[0109] Since the preliminary selling point information is obtained based on the title information and description information of the goods on the second e-commerce platform, the number of preliminary selling point information is often multiple. At this time, the selling point information obtained is relatively broad and not targeted. In order to accurately determine the target selling point information of the goods on the second e-commerce platform, the obtained preliminary selling point information can be filtered based on the focus attributes, so that the target selling point information of the goods on the second e-commerce platform can be determined. At this time, the number of target selling points can be one or more, and the obtained target selling point information can be part of the preliminary selling point information.

[0110] In some instances, determining the target selling point information of a product on the second e-commerce platform based on the focus attributes and preliminary selling point information may include: obtaining matching selling point information corresponding to the focus attributes in the preliminary selling point information; and determining the matching selling point information as the target selling point information of the product on the second e-commerce platform.

[0111] Specifically, after obtaining the preliminary selling point information, the attribute information corresponding to the preliminary selling point information can be determined; then, the attribute information corresponding to each preliminary selling point information is analyzed and compared with the attribute of interest. When matching attribute information that matches the attribute of interest exists, the matching selling point information corresponding to the attribute of interest is obtained. At this time, the matching selling point information can be a part of the preliminary selling point information. When the matching selling point information is obtained, it is determined as the target selling point information of the product on the second e-commerce platform, thereby ensuring the accuracy and reliability of the determination of the target selling point information. When there is no matching attribute information that matches the attribute of interest, the matching selling point information can be determined to be a null value, and the target selling point information obtained at this time can be the preliminary selling point information.

[0112] In other instances, the target selling point information can be obtained by analyzing and processing the focus attributes and preliminary selling point information through a pre-trained machine learning model or neural network model. At this time, based on the focus attributes and preliminary selling point information, determining the target selling point information of the goods on the second e-commerce platform can include: obtaining a pre-trained machine learning model or neural network model, inputting the focus attributes and preliminary selling point information into the machine learning model or neural network model, and obtaining the target selling point information of the goods on the second e-commerce platform output by the machine learning model or neural network model, thereby effectively ensuring the accuracy and reliability of the determination of the target selling point information.

[0113] In this embodiment, by integrating the title information and the description information, a third prompt for input into the large-scale language processing model is obtained, and then the third prompt is processed by the large-scale language processing model to obtain preliminary selling point information of the product on the second e-commerce platform, and the focus attributes corresponding to the product on the second e-commerce platform are obtained. Then, based on the focus attributes and the preliminary selling point information, the target selling point information of the product on the second e-commerce platform is determined. This effectively ensures the accuracy and reliability of the determination of the target selling point information, and then the opportunity market mining operation can be performed based on the target selling point information, further improving the practicality of the method.

[0114] FIG5 is a flow chart of another method for determining product structured information provided by an embodiment of the present disclosure. Based on any of the above embodiments, with reference to FIG5 , after determining the structured information of a product on the second e-commerce platform, the method in this embodiment can not only update and adjust the attribute items on the first e-commerce platform based on the attribute items on the second e-commerce platform, but also update and adjust the attribute values ​​on the first e-commerce platform based on the attribute values ​​on the second e-commerce platform. In this case, the method in this embodiment can further include:

[0115] Step S501: Acquire a first attribute value set corresponding to a target attribute item in a first e-commerce platform and a second attribute value set corresponding to the target attribute item in a second e-commerce platform.

[0116] Step S502: When the second attribute value set is a subset of the first attribute value set, the first attribute value set remains unchanged.

[0117] Step S503: When the second attribute value set is different from the first attribute value set, the first attribute value set is updated based on the second attribute value set to obtain an updated first attribute value set.

[0118] Among them, for the first e-commerce platform and the second e-commerce platform, the first e-commerce platform includes not only attribute items for configuring products, but also attribute value sets corresponding to the attribute items. For example, when the attribute item is "color", the attribute value set can be "red, green, blue, yellow, orange, etc."; when the attribute item is "material", the attribute value set can be "linen, silk, polyester, woolen cloth, knitted fabric, mulberry silk, etc.". Since the second e-commerce platform and the first e-commerce platform are different e-commerce platforms, different e-commerce platforms may correspond to different attribute value sets. Therefore, in order to be able to update the attribute value set included in the first e-commerce platform based on the attribute value set included in the second e-commerce platform, after determining the structured information of the products in the second e-commerce platform, the first attribute value set corresponding to the target attribute item in the first e-commerce platform and the second attribute value set corresponding to the target attribute item in the second e-commerce platform can be obtained.

[0119] After obtaining the first attribute value set and the second attribute value set, the first attribute value set and the second attribute value set can be analyzed and compared to obtain the inter-set relationship between the first attribute value set and the second attribute value set. When the inter-set relationship is that the second attribute value set is a subset of the first attribute value set, it means that the range corresponding to the first attribute value set is larger, and the range corresponding to the first attribute value set includes the second attribute value set, which further indicates that the attribute value set included in the first e-commerce platform is more comprehensive, and the first attribute value set can be kept unchanged.

[0120] When the relationship between the sets is that the second attribute value set is different from the first attribute value set (intersecting or not intersecting), it means that the first attribute value set and the second attribute value set intersect, or the first attribute value set and the second attribute value set do not intersect. In this case, the first attribute value set can be updated based on the second attribute value set, so as to obtain an updated first attribute value set. In some instances, updating the first attribute value set based on the second attribute value set to obtain the updated first attribute value set may include: obtaining the attribute value intersection between the first attribute value set and the second attribute value set, the attribute value intersection including the common attribute values ​​between the first attribute value set and the second attribute value set; determining the remaining attribute value set in the second attribute value set excluding the attribute value intersection; adding the attribute values ​​in the remaining attribute value set to the first attribute value set to obtain the updated first attribute value set.

[0121] Specifically, in order to be able to implement the update operation on the first attribute value set, the attribute value intersection between the first attribute value set and the second attribute value set can be obtained. It should be noted that when the first attribute value set and the second attribute value set intersect, there are one or more common attribute values ​​between the first attribute value set and the second attribute value set in the attribute value intersection; when the first attribute value set and the second attribute value set do not intersect, the attribute value intersection is an empty value, and then the attribute value intersection can be removed from the second attribute value set to obtain the remaining attribute value set in the second attribute value set excluding the attribute value intersection. Since the attribute values ​​included in the remaining attribute value set do not belong to the first attribute value set, the attribute values ​​in the remaining attribute value set can be added to the first attribute value set to obtain the updated first attribute value set. This effectively implements the update operation on the first attribute value set, further improves the stability and reliability of the use of the first e-commerce platform, and ensures a good user experience.

[0122] In this embodiment, by obtaining a first attribute value set corresponding to the target attribute item in the first e-commerce platform and a second attribute value set corresponding to the target attribute item in the second e-commerce platform, when the second attribute value set is a subset of the first attribute value set, the first attribute value set is kept unchanged; when the second attribute value set is different from the first attribute value set, the first attribute value set is updated based on the second attribute value set to obtain an updated first attribute value set, thereby effectively realizing that when the attribute value in the in-site platform does not include the attribute value in the off-site platform, the attribute value of the in-site platform is updated and adjusted based on the attribute value in the off-site platform; when the attribute value in the in-site platform includes the attribute value in the off-site platform, the attribute value in the in-site platform can be kept unchanged, thereby improving the comprehensive reliability of the attribute value in the in-site platform and further improving the practicality of the method.

[0123] In specific applications, referring to Figures 6 and 7 , taking the first e-commerce platform as an on-site platform and the second e-commerce platform as an off-site platform as an example, this application embodiment provides a method for understanding product structured information based on a large-scale model. The execution subject of the understanding method is an understanding system, which may include a data acquisition module, a data processing module, a category mapping module, an information extraction module, and an output module. Based on the above-mentioned understanding system, the method for understanding product structured information implemented in this embodiment may include the following steps:

[0124] Step 1: Use the data collection module to obtain the on-site data of on-site products in the on-site platform and the off-site data of off-site products in the off-site platform.

[0125] Among them, the in-site data of in-site products in the in-site platform may include: in-site categories, in-site attribute items and in-site attribute value sets corresponding to the in-site attribute items. Specifically, the in-site data can be obtained by collecting data through the data collection module in the in-site platform; the off-site data can be obtained by traversing the off-site platform step by step according to categories through information extraction technology. The off-site data of off-site products in off-site platforms (which can be excellent platforms in the industry, competing platforms, etc.) may include: off-site product titles and off-site product descriptions.

[0126] In addition, when the data acquisition module collects on-site data and off-site data, the on-site data and off-site data can be automatically collected according to a preset frequency (3 days / time, 1 time / month, etc.) or preset conditions (when the data increment of off-site data reaches a preset threshold), or can be passively collected in response to the user's triggering behavior. Technical personnel in this field can flexibly configure or adjust according to specific application scenarios or application requirements.

[0127] It should be noted that there can be multiple off-site platforms, and different off-site platforms can correspond to different off-site data. For example: off-site platform 1 can correspond to the off-site product title, the five-line characteristic description of the off-site product (five descriptive information used to describe the selling points of the off-site product), and other descriptions of the off-site product; off-site platform 2 can correspond to the off-site product title, custom attributes and descriptive information of the off-site product; off-site platform 3 can correspond to the off-site product title, descriptive information of the off-site product, and so on.

[0128] In some other instances, since the large-scale language model used to determine the structured information of a product often needs to obtain prompt information in English, and the on-site data and off-site data are often not in English, in order to accurately perform the operation of determining the structured information of the product, after obtaining the on-site data and off-site data, the on-site data and off-site data can be used as texts to be translated, and then the data processing module can be used to translate the on-site data and off-site data, thereby obtaining the on-site translation data and off-site translation data.

[0129] Specifically, at least one translation tool may be configured in the data processing module. When at least one translation tool is used to translate on-site data and off-site data, the translation results output by each translation tool may be obtained, and then the translation results may be evaluated. Specifically, the translation cost and translation accuracy corresponding to each translation tool may be obtained. Then, based on the translation cost and translation accuracy, a target translation tool may be selected from at least one translation tool, and the translation results output by the target translation tool may be used to determine the on-site translation data and off-site translation data after the translation operations on the on-site data and off-site data are performed.

[0130] Step 2: Use the category mapping module and on-site data to process off-site data to obtain optional attribute items corresponding to off-site products in the off-site platform.

[0131] In order to improve the accuracy of on-site and off-site attribute matching, you can first perform category mapping on-site data and off-site data, so as to use the on-site attribute items to limit the optional attribute range of off-site products. Specifically, after obtaining the product title of the off-site product in the off-site platform, you can use the category mapping module and the category information and attribute items of the on-site products in the on-site data to perform category mapping on the off-site products, and obtain the optional attribute items corresponding to the off-site products in the off-site platform.

[0132] In order to further improve the accuracy of determining optional attribute items, after obtaining the optional attribute items, the rationality of the obtained optional attribute items can be evaluated. In some instances, the optional attribute items can be displayed, and the execution operations input by the user on the displayed optional attribute items can be obtained. Based on the execution operations, it is determined whether the optional attribute items are reasonable; when it is determined that the optional attribute items are reasonable, the optional attribute items can be retained unchanged; when it is determined that the optional attribute items are unreasonable, the unreasonable optional attribute items can be deleted, thereby effectively realizing the evaluation of the optional attribute items and the rationality detection operations.

[0133] Step 3: Use the information extraction module to analyze and process off-site data and optional attribute items to generate a first prompt for determining the product word of the off-site product, a second prompt for determining the attribute value of the off-site product, and a third prompt for determining the selling point information of the off-site product.

[0134] After obtaining the off-site data, the information extraction module can be used to analyze and process the off-site data and optional attribute items to generate corresponding prompt information for different information extraction tasks, including the first prompt, the second prompt and the third prompt. The prompt information can then be input into the large-scale language processing model (which can be a pre-configured chatGPT model) to obtain the product structured information output by the large-scale language processing model. The product structured information can specifically include: product words, attribute values, selling point information, etc.

[0135] It should be noted that since product structured information can specifically include: product name information, attribute values, and selling point information, the product information extraction operation can be divided into the following three types of tasks for processing:

[0136] Attribute value extraction task: As shown in Figure 8, the corresponding prompt template is configured according to the task type. After obtaining the off-site product information and the optional attribute items corresponding to the off-site products, the category core attributes corresponding to the off-site products can be determined based on the category information of the off-site products. Then, the off-site product information, optional attribute items and category core attributes can be integrated with the prompt template in a natural language manner, so as to obtain the first prompt corresponding to the attribute value extraction task. The first prompt information is input into the large-scale language processing model for model extraction operation to obtain the attribute data output by the large-scale language processing model.

[0137] Selling point extraction task: As shown in Figure 9, the corresponding prompt template is configured according to the task type. After obtaining the off-site product information, the off-site product information can be integrated with the prompt template in a natural language manner, so as to obtain the second prompt corresponding to the selling point extraction task. The second prompt information is input into the large-scale language processing model for model extraction operation to obtain the preliminary selling point data output by the large-scale language processing model; after obtaining the preliminary selling point data, the important attributes corresponding to the off-site products can be determined, and then the preliminary selling point data can be filtered based on the important attributes to obtain the target selling point data.

[0138] Name extraction task: As shown in Figure 10, the corresponding prompt template is configured according to the task type. After obtaining the off-site product information, the off-site product information can be integrated with the prompt template in a natural language manner, so as to obtain the third prompt corresponding to the name extraction task. The third prompt information is input into the large-scale language processing model for model extraction operation to obtain the product word data output by the large-scale language processing model.

[0139] Step 4: Input the first prompt, the second prompt, and the third prompt into the large-scale language model to obtain the name information, attribute values, and selling point information of the off-site products output by the large-scale language model.

[0140] Step 5: After obtaining the selling point information of the off-site products, you can determine the category core attributes corresponding to the off-site products, filter the selling point information based on the category core attributes, and obtain the target selling point information corresponding to the off-site products.

[0141] Specifically, since the selling point information of off-site products is obtained by analyzing and processing the off-site products, the amount of selling point information obtained is large, that is, the selling points are numerous and general. In order to obtain clearer selling point information, the core attributes of the category of off-site products can be used to screen and filter the selling point information, so that clearer selling point information can be obtained. Then, product recommendations can be made based on the selling point information of off-site products, realizing the mining of opportunity markets.

[0142] Step 6: After obtaining the attribute values ​​of off-site products, you can analyze and compare the attribute values ​​of on-site products with the attribute values ​​of off-site products. When the attribute values ​​of off-site products are not stored in the on-site platform, you can update the attribute values ​​of off-site products and add them to the on-site platform, thereby realizing the update and adjustment of the attribute values ​​in the on-site platform.

[0143] Step 7: After obtaining the attribute items of off-site products, you can analyze and compare the attribute items of on-site products with the attribute items of off-site products. When the attribute items of off-site products are not stored in the on-site platform, you can update the attribute items of off-site products and add them to the on-site platform, thereby realizing the update and adjustment of the attribute items in the on-site platform.

[0144] In order to ensure the rationality of the update and adjustment operations, before the attribute items of off-site products are updated and added to the on-site platform, the attribute items of the off-site products can be displayed in the display interface, so that the operation and maintenance personnel can judge whether the attribute items displayed in the display interface are reasonable. When the attribute items are reasonable, the attribute items of the off-site products are allowed to be updated and added to the on-site platform; when the attribute items are unreasonable, the attribute items of the off-site products are prohibited from being updated and added to the on-site platform.

[0145] Step 8: When analyzing and processing each processing task using a large-scale language model, the task processing mode corresponding to each processing task can be determined, and analysis and processing operations are performed on each processing task based on the task processing model.

[0146] Among them, when using a large-scale language model to perform task processing operations, you can first configure the large-scale language model. At this time, you can obtain the large-scale model parameters (including: task scheduling configurations such as temperature value, concurrency number and qps (Query per Second) limit), and based on the above large-scale model parameters, you can obtain the corresponding large-scale language model.

[0147] In addition, when the large-scale language processing model corresponds to multiple processing tasks, in order to improve the quality and efficiency of task processing, the multiple processing tasks can be grouped and the task processing mode corresponding to each processing task can be determined. The task processing mode can include a synchronous processing mode and an asynchronous processing mode. When calling the large-scale language model to process multiple tasks synchronously, the task processing results can be directly obtained and parsed, and the obtained task processing results can be displayed and stored. When calling the large-scale language model to process multiple tasks asynchronously, the task processing results obtained by the large-scale language model can be obtained through a message mechanism and can be stored. It should be noted that when the task processing results are not obtained, the large-scale language model can perform corresponding processing operations on other tasks.

[0148] It should be noted that for large-scale language models, large-scale language models can be configured with calling interfaces for adapting various modules, providing a unified interface while supporting functions such as account management, quota management, and flow control, thereby effectively ensuring the stability and reliability of large-scale model use.

[0149] The technical solution provided by this application embodiment effectively realizes the accurate understanding of the structured information of products on the off-site platform based on the large language model and the product data on the on-site platform, ensuring the accuracy and reliability of the acquisition of product structured information. Compared with the existing technology, this solution has the following advantages: (1) universal generalization ability and powerful semantic understanding ability for different site data and task types. Specifically, the large model can be trained or configured based on training data and model parameters, and then the product information extraction operation for various task types and different sites can be realized according to different prompt templates, effectively expanding the scope of application of the method; (2) Training efficiency is improved. For large models, they can be configured through prompt templates and task scheduling without going through the entire model training process. Different information extraction tasks can correspond to the same large model, which greatly improves the quality and efficiency of model training and the efficiency of task processing. In particular, there is no need to train new models for new tasks. Through task scheduling and prompt construction, the processing operations of new tasks can be quickly supported. In addition, after obtaining the structured information of the product, opportunity market analysis operations or CPV system update and completion operations can be performed based on the structured information, further improving the practicality of the method and facilitating market promotion and application.

[0150] FIG11 is a schematic diagram of a structure of a device for determining product structured information provided by an embodiment of the present disclosure. Referring to FIG11 , this embodiment provides a device for determining product structured information. The device is configured to execute the method for determining product structured information shown in FIG2 . The device may include:

[0151] The first acquisition module 11 is used to obtain category information and attribute items of goods on the first e-commerce platform; the first determination module 12 is used to determine at least one second e-commerce platform different from the first e-commerce platform and the product information of the goods on the second e-commerce platform; the first determination module 12 is used to determine the optional attribute items corresponding to the goods on the second e-commerce platform based on the category information and attribute items; the first processing module 13 is used to determine the structured information of the goods on the second e-commerce platform based on the product information and the optional attribute items, and the structured information at least includes the target attribute items.

[0152] In some instances, when the first determination module 12 determines the optional attribute items corresponding to the products on the second e-commerce platform based on the category information and attribute items, the first determination module 12 is used to execute: determining the target category corresponding to the products on the second e-commerce platform in the category information; and determining the attribute items corresponding to the target category as the optional attribute items corresponding to the products on the second e-commerce platform.

[0153] In some instances, the product information includes title information and description information; when the first processing module 13 determines the structured information of the product in the second e-commerce platform based on the product information and optional attribute items, the first processing module 13 is used to perform: integrating the title information, description information and optional attribute items to obtain a first prompt for input into a large-scale language processing model, the first prompt being used to determine the attribute items of the product; using the large-scale language processing model to process the first prompt to obtain the target attribute items of the product in the second e-commerce platform.

[0154] In some instances, when the first processing module 13 integrates the title information, description information, and optional attribute items to obtain a first prompt for input into a large-scale language processing model, the first processing module 13 is used to execute: obtaining the focus attributes corresponding to the products in the second e-commerce platform; integrating the title information, description information, optional attribute items, and focus attribute items to obtain a first prompt for determining the product attribute items.

[0155] In some instances, when the first processing module 13 obtains the attention attributes corresponding to the products in the second e-commerce platform, the first processing module 13 is used to execute: obtaining the target category corresponding to the products in the second e-commerce platform; based on the target category, determining the attention attributes corresponding to the products in the second e-commerce platform.

[0156] In some instances, after determining at least one second e-commerce platform different from the first e-commerce platform and the product information of the product on the second e-commerce platform, the first processing module 13 in this embodiment is used to: integrate the title information and the description information to obtain a second prompt for input into a large-scale language processing model, the second prompt being used to determine the name of the product; and process the second prompt using the large-scale language processing model to obtain the product name of the product on the second e-commerce platform.

[0157] In some instances, the structured information also includes: product selling point information; the first processing module 13 in this embodiment is used to perform: integrating the title information and the description information to obtain a third prompt for input into the large-scale language processing model, the third prompt being used to determine the selling point information of the product; processing the third prompt using the large-scale language processing model to obtain preliminary selling point information of the product on the second e-commerce platform; obtaining the focus attributes corresponding to the product on the second e-commerce platform; and determining the target selling point information of the product on the second e-commerce platform based on the focus attributes and the preliminary selling point information.

[0158] In some instances, when the first processing module 13 determines the target selling point information of the product in the second e-commerce platform based on the focus attributes and the preliminary selling point information, the first processing module 13 is used to execute: obtaining matching selling point information corresponding to the focus attributes in the preliminary selling point information; and determining the matching selling point information as the target selling point information of the product in the second e-commerce platform.

[0159] In some instances, after determining the structured information of the goods in the second e-commerce platform, the first acquisition module 11 and the first processing module 13 in this embodiment are used to perform the following steps: the first acquisition module 11 is used to obtain a first attribute value set corresponding to the target attribute item in the first e-commerce platform and a second attribute value set corresponding to the target attribute item in the second e-commerce platform; the first processing module 13 is used to keep the first attribute value set unchanged when the second attribute value set is a subset of the first attribute value set; when the second attribute value set is different from the first attribute value set, update the first attribute value set based on the second attribute value set to obtain an updated first attribute value set.

[0160] In some instances, when the first processing module 13 updates the first attribute value set based on the second attribute value set to obtain the updated first attribute value set, the first processing module 13 is used to execute: obtaining the attribute value intersection between the first attribute value set and the second attribute value set, where the attribute value intersection includes the common attribute values ​​between the first attribute value set and the second attribute value set; determining the remaining attribute value set in the second attribute value set excluding the attribute value intersection; and adding the attribute values ​​in the remaining attribute value set to the first attribute value set to obtain the updated first attribute value set.

[0161] In some instances, after determining the structured information of the product in the second e-commerce platform, the first processing module 13 in this embodiment is used to perform: identifying whether the target attribute item exists in the first e-commerce platform; if the target attribute item does not exist in the first e-commerce platform, adding the target attribute item to the first e-commerce platform to obtain the updated attribute item of the product in the first e-commerce platform.

[0162] In some examples, after determining the structured information of the product in the second e-commerce platform, the first acquisition module 11 and the first processing module 13 in this embodiment are configured to perform the following steps:

[0163] The first acquisition module 11 is used to obtain platform transaction data and attention attributes corresponding to the products on the second e-commerce platform; the first processing module 13 is used to determine the product adjustment plan corresponding to the first e-commerce platform based on the structured information, platform transaction data and attention attributes of the products on the second e-commerce platform.

[0164] The device shown in FIG11 can execute the method of the embodiment shown in FIG1-FIG10. For the parts not described in detail in this embodiment, please refer to the relevant description of the embodiment shown in FIG1-FIG10. The execution process and technical effects of this technical solution can be found in the description of the embodiment shown in FIG1-FIG10, and will not be repeated here.

[0165] In one possible design, the structure of the device for determining product structured information shown in FIG11 can be implemented as an electronic device, which can be a mobile phone, tablet computer, server, or other device. As shown in FIG12 , the electronic device may include a first processor 21 and a first memory 22. The first memory 22 is used to store a program that enables the electronic device to execute the method for determining product structured information provided in the embodiments shown in FIG1-10 . The first processor 21 is configured to execute the program stored in the first memory 22.

[0166] The program includes one or more computer instructions, wherein, when the one or more computer instructions are executed by the first processor 21, the following steps can be implemented: obtaining category information and attribute items of goods on the first e-commerce platform; determining at least one second e-commerce platform different from the first e-commerce platform and product information of the goods on the second e-commerce platform; based on the category information and attribute items, determining the optional attribute items corresponding to the goods on the second e-commerce platform; based on the product information and the optional attribute items, determining the structured information of the goods on the second e-commerce platform, wherein the structured information includes at least the target attribute items.

[0167] Furthermore, the first processor 21 is also configured to execute all or part of the steps in the embodiments shown in the aforementioned FIG. 1 to FIG. 10 .

[0168] The structure of the electronic device may further include a first communication interface 23 for the electronic device to communicate with other devices or a communication network.

[0169] In addition, an embodiment of the present disclosure provides a computer storage medium for storing computer-executable instructions used by an electronic device, which includes a program for executing the method for determining product structured information in the method embodiments shown in Figures 1 to 10 above.

[0170] In addition, this embodiment adopts a computer program product, which includes: a computer program, when the computer program is executed by a processor of an electronic device, the processor executes the method for determining the structured information of a product in the method embodiments shown in Figures 1 to 10 above.

[0171] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0172] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by a combination of hardware and software. Based on this understanding, the above technical solution, or the part that contributes to the existing technology, can be embodied in the form of a computer product. The present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM (Compact Disc Read-Only Memory), optical storage, etc.) containing computer-usable program code.

[0173] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable device to produce a machine, so that the instructions executed by the processor of the computer or other programmable device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0174] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device that implements the functions specified in one or more processes of the flowchart and / or one or more blocks of the block diagram. These computer program instructions may also be loaded onto a computer or other programmable device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes of the flowchart and / or one or more blocks of the block diagram. In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interfaces, network interfaces and memory. Memory may include non-permanent memory in a computer-readable medium, random access memory (Random Access Memory, RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0175] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to 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 random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. According to the definition in this article, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present disclosure.

Claims

1. A method for determining product structured information, wherein: include: Obtain category information and attribute items of products on the first e-commerce platform; Determine at least one second e-commerce platform different from the first e-commerce platform and product information of products on the second e-commerce platform; Based on the category information and attribute items, determining optional attribute items corresponding to the products in the second e-commerce platform; Based on the product information and the optional attribute items, the structured information of the product in the second e-commerce platform is determined, and the structured information includes at least a target attribute item.

2. The method according to claim 1, wherein: Determining optional attribute items corresponding to the products in the second e-commerce platform based on the category information and attribute items includes: In the category information, determine the target category corresponding to the product in the second e-commerce platform; The attribute items corresponding to the target category are determined as optional attribute items corresponding to the products in the second e-commerce platform.

3. The method according to claim 1, wherein: The product information includes title information and description information; Determining structured information of the product in the second e-commerce platform based on the product information and the optional attribute items includes: Integrate the title information, description information, and optional attribute items to obtain a first prompt for input into a large-scale language processing model, wherein the first prompt is used to determine the attribute items of the product; The first prompt is processed using the large-scale language processing model to obtain target attribute items of the products in the second e-commerce platform.

4. The method according to claim 3, wherein: Integrating the title information, description information, and optional attribute items to obtain a first prompt for input into a large-scale language processing model, including: Acquire the attention attribute corresponding to the product in the second e-commerce platform; The title information, description information, optional attribute items and focus attribute items are integrated to obtain a first prompt for determining the commodity attribute items.

5. The method according to claim 4, wherein: Obtaining the concerned attributes corresponding to the product on the second e-commerce platform includes: Obtaining a target category corresponding to the product on the second e-commerce platform; Based on the target category, determine the focus attributes corresponding to the products in the second e-commerce platform.

6. The method according to any one of claims 3 to 5, wherein: After determining at least one second e-commerce platform different from the first e-commerce platform and product information of products on the second e-commerce platform, the method further includes: Integrate the title information and the description information to obtain a second prompt for input into a large-scale language processing model, wherein the second prompt is used to determine a name of the product; The second prompt is processed using the large-scale language processing model to obtain the product name of the product on the second e-commerce platform.

7. The method according to any one of claims 3 to 6, wherein: The structured information also includes: commodity selling point information; the method also includes: Integrate the title information and the description information to obtain a third prompt for input into a large-scale language processing model, wherein the third prompt is used to determine the selling point information of the product; Processing the third prompt using the large-scale language processing model to obtain preliminary selling point information of the product on the second e-commerce platform; Acquire the attention attribute corresponding to the product in the second e-commerce platform; Based on the focus attribute and the preliminary selling point information, target selling point information of the product in the second e-commerce platform is determined.

8. The method according to claim 7, wherein: Determining target selling point information of the product on the second e-commerce platform based on the focus attribute and the preliminary selling point information includes: In the preliminary selling point information, obtaining matching selling point information corresponding to the concerned attribute; The matching selling point information is determined as the target selling point information of the product in the second e-commerce platform.

9. The method according to any one of claims 1 to 8, wherein: After determining the structured information of the product in the second e-commerce platform, the method further includes: Acquire a first attribute value set corresponding to the target attribute item in the first e-commerce platform and a second attribute value set corresponding to the target attribute item in the second e-commerce platform; When the second attribute value set is a subset of the first attribute value set, the first attribute value set remains unchanged; When the second attribute value set is different from the first attribute value set, the first attribute value set is updated based on the second attribute value set to obtain an updated first attribute value set.

10. The method according to claim 9, wherein: Updating the first attribute value set based on the second attribute value set to obtain an updated first attribute value set includes: Acquire an attribute value intersection between the first attribute value set and the second attribute value set, wherein the attribute value intersection includes common attribute values ​​between the first attribute value set and the second attribute value set; Determine a remaining attribute value set in the second attribute value set excluding the attribute value intersection; The attribute values ​​in the remaining attribute value set are added to the first attribute value set to obtain an updated first attribute value set.

11. The method according to any one of claims 1 to 10, wherein: After determining the structured information of the product in the second e-commerce platform, the method further includes: Identify whether a target attribute item exists in the first e-commerce platform; If the target attribute item does not exist in the first e-commerce platform, the target attribute item is added to the first e-commerce platform to obtain the updated attribute item of the product in the first e-commerce platform.

12. The method according to any one of claims 1 to 11, wherein: After determining the structured information of the product in the second e-commerce platform, the method further includes: Acquire platform transaction data and attention attributes corresponding to the product on the second e-commerce platform; Based on the structured information of the goods in the second e-commerce platform, the platform transaction data and the focus attribute, a product adjustment plan corresponding to the first e-commerce platform is determined.

13. A device for determining product structured information, wherein: include: A first acquisition module, used to acquire category information and attribute items of commodities in a first e-commerce platform; A first determining module, configured to determine at least one second e-commerce platform different from the first e-commerce platform and product information of products on the second e-commerce platform; The first determination module is used to determine the product in the second e-commerce platform based on the category information and attribute items. The corresponding optional attribute items; The first processing module is used to determine the structured information of the product in the second e-commerce platform based on the product information and the optional attribute items, and the structured information at least includes a target attribute item.

14. An electronic device, wherein: include: A memory, a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method as described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 12 when executed by a processor.

16. A computer program product, characterized in that The method comprises a computer program, which implements the method according to any one of claims 1 to 12 when being executed by a processor.

Images