Commodity information generation method, apparatus and device, and computer program product

Abstract

The embodiment of the invention provides a commodity information generation method and device, equipment and a computer program product. The method comprises the steps of obtaining a generation request of commodity information, wherein the generation request at least comprises category description corresponding to the commodity information and at least one knowledge item description; based on category description and at least one knowledge item description in the generation request, determining a commodity category matched with the generation request and concept attributes under each knowledge item under the commodity category; circle product analysis is carried out based on the commodity category and the concept attribute, commodity preliminary information is obtained, and the commodity preliminary information at least comprises recommended commodities corresponding to the generation request and crowd portraits corresponding to the recommended commodities; and based on the preliminary information of the commodity, generating commodity information corresponding to the generation request, the commodity information at least comprising description information of the commodity and a promotion document of the commodity. According to the embodiment of the invention, manpower and material resources required for generating the commodity information are reduced, and the generation quality and efficiency of the commodity information are improved.

Description

Technical Field

[0001] The present invention relates to the field of network technology, and in particular to a method, device, equipment and computer program product for generating commodity information. Background Art

[0002] Product information or product information (concept board) is used to convert product ideas into text and pictures so that consumers can understand and respond. For merchants / brands, the traditional product information design process is: market insight-concept co-creation (creative workshop)-desktop research-qualitative interviews-quantitative research. The process often requires collecting a lot of information and conducting long-term brainstorming operations. Especially for industries with fast response and multiple products such as food and clothing, a large number of concept boards need to be produced in a short time. This requires a lot of manpower and material resources to generate corresponding product information. Summary of the invention

[0003] The embodiments of the present invention provide a method, device, equipment and computer program product for generating commodity information, which can efficiently generate commodity information and reduce the human and material resources required for commodity information.

[0004] In a first aspect, an embodiment of the present invention provides a method for generating commodity information, comprising:

[0005] Obtaining a request for generating product information, wherein the request at least includes: a category description corresponding to the product information and at least one knowledge item description;

[0006] Based on the category description and at least one knowledge item description in the generation request, determining a commodity category that matches the generation request and a concept attribute under each knowledge item under the commodity category;

[0007] Perform circle product analysis based on the product category and the concept attribute to obtain preliminary product information, wherein the preliminary product information at least includes: a recommended product corresponding to the generation request and a crowd portrait corresponding to the recommended product;

[0008] Based on the preliminary product information, product information corresponding to the generation request is generated, and the product information at least includes: product description information and product promotion copy.

[0009] In a second aspect, an embodiment of the present invention provides a device for generating commodity information, including:

[0010] A first acquisition module is used to acquire a request for generating product information, wherein the request at least includes: a category description corresponding to the product information and at least one knowledge item description;

[0011] A first determination module, configured to determine a commodity category that matches the generation request and a concept attribute under each knowledge item under the commodity category based on a category description and at least one knowledge item description in the generation request;

[0012] A first processing module is used to perform circle product analysis based on the product category and the concept attribute to obtain preliminary product information, wherein the preliminary product information at least includes: a recommended product corresponding to the generation request and a crowd portrait corresponding to the recommended product;

[0013] The first processing module is used to generate product information corresponding to the generation request based on the preliminary product information, and the product information at least includes: product description information and product promotion copy.

[0014] In a third aspect, an embodiment of the present invention 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 generating product information in the above-mentioned first aspect.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, wherein the computer program enables a computer to implement the method for generating commodity information in the first aspect when executed.

[0016] In a fifth aspect, an embodiment of the present invention provides a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, causes the one or more processors to execute the steps in the method for generating product information shown in the first aspect above.

[0017] In a sixth aspect, an embodiment of the present invention provides a method for generating commodity information, comprising:

[0018] Displaying an interactive interface for generating product information, wherein the interactive interface includes a request interactive interface;

[0019] In response to an interactive operation input by a user through the request interactive interface, a request for generating product information is obtained, wherein the request for generating product information includes at least: a category description corresponding to the product information and at least one knowledge item description;

[0020] Displaying a commodity category that matches the commodity information and a concept attribute under each knowledge item under the commodity category, wherein the commodity category and the concept attribute are determined by analyzing and processing the category description and at least one knowledge item description in the generation request;

[0021] Displaying preliminary product information corresponding to the generation request, wherein the preliminary product information is obtained by performing a circle product analysis based on the product category and the concept attribute; wherein the preliminary product information at least includes: a recommended product corresponding to the generation request and a crowd portrait corresponding to the recommended product;

[0022] The product information corresponding to the generation request is displayed, wherein the product information is determined based on the analysis and processing of the preliminary product information, wherein the product information at least includes: product description information and product promotion copy.

[0023] In a seventh aspect, an embodiment of the present invention provides a device for generating commodity information, including:

[0024] A second display module, used to display an interactive interface for generating product information, wherein the interactive interface includes a request interactive interface;

[0025] A second processing module is configured to obtain a request for generating product information in response to an interactive operation input by a user through the request interactive interface, wherein the request for generating product information includes at least: a category description corresponding to the product information and at least one knowledge item description;

[0026] The second display module is used to display the commodity category adapted to the commodity information and the concept attribute under each knowledge item under the commodity category, wherein the commodity category and the concept attribute are determined by analyzing and processing the category description and at least one knowledge item description in the generation request;

[0027] The second display module is used to display preliminary product information corresponding to the generation request, wherein the preliminary product information is obtained by performing circle product analysis based on the product category and the concept attribute; wherein the preliminary product information at least includes: recommended products corresponding to the generation request and crowd portraits corresponding to the recommended products;

[0028] The second display module is used to display the product information corresponding to the generation request, wherein the product information is determined based on the analysis and processing of the preliminary product information, wherein the product information at least includes: product description information and product promotion copy.

[0029] In an eighth aspect, an embodiment of the present invention 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 generating product information in the above-mentioned sixth aspect.

[0030] In a ninth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, wherein the computer program enables a computer to implement the method for generating commodity information in the sixth aspect when executed.

[0031] In the tenth aspect, an embodiment of the present invention provides a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, causes the one or more processors to execute the steps in the method for generating product information shown in the sixth aspect above.

[0032] The method, apparatus, device and computer program product for generating product information provided in the present embodiment obtain a request for generating product information, and determine the product category that matches the generation request and the conceptual attributes under each knowledge item under the product category based on the category description and at least one knowledge item description in the generation request; then, a circle product analysis is performed based on the product category and the conceptual attributes to obtain preliminary product information, and product information corresponding to the generation request is generated based on the preliminary product information, so that the generation operation of product information can be realized efficiently and automatically, which not only reduces the human and material resources required for product information, but also greatly improves the generation quality and efficiency of product information, thereby effectively ensuring the practicality of the method. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A schematic diagram of a scenario of a method for generating commodity information provided by an embodiment of the present invention;

[0035] Figure 2 A flowchart of a method for generating commodity information provided by an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of a process for determining a commodity category that matches the generation request and a conceptual attribute under each knowledge item under the commodity category provided by an embodiment of the present invention;

[0037] Figure 4 A schematic diagram of a process for performing circle product analysis based on the product category and the concept attribute to obtain preliminary product information provided by an embodiment of the present invention;

[0038] Figure 5 A schematic diagram of a method for generating commodity information provided by an embodiment of the present invention;

[0039] Figure 6 A schematic diagram of the principle of a method for generating commodity information provided by an application embodiment of the present invention;

[0040] Figure 7 A schematic diagram of the structure of a device for generating commodity information provided by an embodiment of the present invention;

[0041] Figure 8 For Figure 7 A schematic diagram showing the structure of an electronic device corresponding to the device for generating commodity information provided in the embodiment;

[0042] Fig. 9 A schematic diagram of the structure of a device for generating commodity information provided by an embodiment of the present invention;

[0043] Fig.10 For Fig. 9 A schematic diagram of the structure of an electronic device corresponding to the device for generating commodity information provided in an embodiment is shown. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "an", and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two, but does not exclude the situation of including at least one.

[0046] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0047] 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 determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0048] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a product or system. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the product or system including the elements.

[0049] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0050] Definition of terms:

[0051] Product information / product information: concept board, used to convert product ideas into text and pictures so that consumers can understand and respond. The product information / product information obtained can be used to guide the generation of products.

[0052] Knowledge points: Through an expert team or a professional team, vertical knowledge items and knowledge points of a certain industry are sorted out to form a category-knowledge item-knowledge point system. A category can correspond to one or more knowledge items, and a knowledge item can correspond to one or more knowledge points (or called concept attributes).

[0053] Large Language Model: Large Language Model, referred to as LLM, usually refers to an artificial intelligence model that is trained with a large amount of data and can handle complex tasks.

[0054] In order to facilitate understanding of the specific implementation process and implementation effect of the method, device, equipment and computer program product for generating commodity information in this embodiment, the relevant technology is briefly described below:

[0055] For merchants / brands on e-commerce platforms, the traditional product information design process is: market insight-concept co-creation (often achieved by creative workshops)-desktop research-qualitative interviews-quantitative research. The product information design process often requires collecting a large amount of data and conducting long-term brainstorming operations. Especially for industries with fast response and multiple products such as food and clothing, it is necessary to produce a large number of concept boards or product information in a short time. However, the above product information generation method has the following problems:

[0056] (1) The time period is long. In a rapidly changing business environment, it is difficult to track trends and verify the validity of product information. It may take a long time to produce a concept, and after this time, the generated product information may no longer be popular.

[0057] (2) The initial data collection, collation, and analysis work is cumbersome and time-consuming;

[0058] (3) The above method requires a lot of manpower and material resources to generate the corresponding product information, and artificial brainstorming has great limitations. Because each individual has limitations in knowledge and thinking, it is often easy to miss or ignore some conceptual information during the workshop brainstorming process.

[0059] In order to solve the technical problems existing in the above-mentioned related technologies, this embodiment provides a method, device, equipment and computer program product for generating commodity information. Figure 1 As shown, the execution subject of the method for generating product information can be a device 200 for generating product information, and the device 200 for generating product information can be implemented as a local server, a server in the cloud, or a preset device. In the case where the device 200 for generating product information is implemented as a server in the cloud, the method for generating product information can be executed in the cloud, and a number of computing nodes (cloud servers) can be deployed in the cloud, and each computing node has computing, storage and other processing resources. In the cloud, multiple computing nodes can be organized to provide a certain service. Of course, a computing node can also provide one or more services. The way to provide the service in the cloud can be to provide a service interface to the outside, and the user calls the service interface to use the corresponding service. The service interface includes software development kits (Software Development Kit, referred to as SDK), application programming interfaces (Application Programming Interface, referred to as API), and other forms.

[0060] The device 200 for generating product information is connected to the client 100 in communication, wherein the client 100 is used for users to perform applications so as to trigger the generation operation of product information. The client 100 can be any computing device with a certain ability to generate product information. When implemented specifically, the client 100 can be a mobile phone, a personal computer PC, a tablet computer, a setting application, etc. In addition, the basic structure of the client 100 can include: at least one processor. The number of processors depends on the configuration and type of the client. The client 100 can also include a memory, which can be volatile, such as a random access memory (RAM), or non-volatile, such as a read-only memory (ROM), flash memory, etc., or can also include both types. The memory usually stores an operating system (OS), one or more application programs, and can also store program data, etc. In addition to the processing unit and the memory, the client 100 also includes some basic configurations, such as a network card chip, an IO bus, a display component, and some peripheral devices, etc. Optionally, some peripheral devices can include, for example, a keyboard, a mouse, an input pen, a printer, etc. Other peripheral devices are well known in the art and will not be described in detail here.

[0061] The device 200 for generating commodity information refers to a device that can generate commodity information in a network virtual environment, and generally refers to a device that uses the network to perform information planning and commodity information generation operations. In physical implementation, the device 200 for generating commodity information can be any device that can provide computing services and can perform corresponding commodity information generation operations, 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 generating commodity information mainly includes a processor, a hard disk, a memory, a system bus, etc., which is similar to a general computer architecture.

[0062] In the above embodiment, the client 100 is connected to the device 200 for generating product information through a network, and the network connection can be a wireless or wired network connection. If the client 100 can be connected to the device 200 for generating product information through a communication, the network standard of the mobile network can be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), WiMax, 5G, 6G, etc.

[0063] In the embodiment of the present application, the client 100 is used by the user to generate a request for generating product information, wherein the request for generating product information can be generated through human-computer interaction or voice interaction. After obtaining the request for generating product information, the request for generating product information can be sent to the device for generating product information 200, so that the device for generating product information 200 can perform a corresponding operation for generating product information based on the request for generating product information.

[0064] The device 200 for generating product information is used to obtain a generation request for product information through the client 100, wherein the obtained generation request includes at least: a category description and at least one knowledge item description corresponding to the product information, the category description may correspond to at least one category, the knowledge item description may correspond to at least one knowledge item, and the above-mentioned category may correspond to one or more knowledge items. After obtaining the generation request, the category description and at least one knowledge item description in the generation request may be analyzed and processed to determine the product category that matches the generation request and the conceptual attributes under each knowledge item under the product category.

[0065] After obtaining the product categories that match the generation request and the conceptual attributes of each knowledge item under the product category, circle product analysis can be performed based on the product categories and conceptual attributes to obtain preliminary product information. The preliminary product information at least includes: recommended products corresponding to the generation request, and crowd portraits corresponding to the recommended products. The number of recommended products corresponding to the generation request can be one or more. After obtaining the preliminary product information, the preliminary product information can be analyzed and processed to generate product information corresponding to the generation request. The generated product information at least includes: product description information and product promotion copy. The generated product information is used to guide the production or generation operation of the product, thereby ensuring the accuracy and reliability of the generation of product information.

[0066] In this embodiment, by determining the product category that is compatible with the generation request and the conceptual attributes of each knowledge item under the product category, a circle product analysis is performed based on the product category and the conceptual attributes to obtain preliminary product information, and then the product information corresponding to the generation request can be generated based on the preliminary product information, thereby efficiently and automatically realizing the generation operation of the product information. This not only reduces the human and material resources required for the product information, but also greatly improves the generation quality and efficiency of the product information, thereby effectively ensuring the practicability of the method.

[0067] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the case where there is no conflict between the embodiments, the following embodiments and the features in the embodiments can be combined with each other. In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0068] Figure 2 A flowchart of a method for generating commodity information provided by an embodiment of the present invention; Figure 2 As shown, this embodiment provides a method for generating product information. The execution subject of the method is a device for generating product information. Specifically, the device for generating product information can be implemented as software, or a combination of software and hardware. When the device for generating product information is implemented as hardware, it can be various electronic devices that can realize the generation operation of product information, including but not limited to personal computers, servers, databases, etc. When the device for generating product information is implemented as software, it can be installed in the electronic devices listed above. Based on the above-mentioned device for generating product information, the generation operation of product information can be realized. Specifically, the method for generating product information can include:

[0069] Step S201: obtaining a request for generating product information, wherein the request at least includes: a category description corresponding to the product information and at least one knowledge item description.

[0070] Step S202: Based on the category description in the generation request and at least one knowledge item description, determine the commodity category and the concept attributes under each knowledge item under the commodity category that are compatible with the generation request.

[0071] Step S203: Perform circle product analysis based on product categories and concept attributes to obtain preliminary product information, which at least includes: recommended products corresponding to the generation request and population portraits corresponding to the recommended products.

[0072] Step S204: Generate product information corresponding to the generation request based on the preliminary product information, where the product information at least includes: product description information and product promotion copy.

[0073] The specific implementation process and effects of each of the above steps are described in detail below:

[0074] Step S201: obtaining a request for generating product information, wherein the request at least includes: a category description corresponding to the product information and at least one knowledge item description.

[0075] When a user has a demand for generating product information, the device for generating product information may obtain a request for generating product information, wherein the request for generating product information includes at least a description of a category corresponding to the product information and at least one knowledge item description.

[0076] For example, the request for generating product information can be implemented as "I want to develop a beverage with a sweet and sour taste", the above "beverage" can be the category description corresponding to the product information, and the above "sweet and sour taste" can be at least one knowledge item description. Alternatively, the request for generating product information can be implemented as "I want to develop a biscuit for the elderly with a spleen-strengthening function", the above "biscuit" can be the category description corresponding to the product information, and the above "for the elderly, spleen-strengthening function" can be at least one knowledge item description.

[0077] Specifically, this embodiment does not limit the specific implementation method for obtaining the generation request of product information. In some instances, the generation request of product information can be obtained through human-computer interaction operations. In this case, obtaining the generation request of product information may include: displaying a human-computer interaction interface corresponding to the product information; determining the execution operation input by the user in the human-computer interaction interface; and obtaining the generation request of product information based on the execution operation. This effectively ensures the stability and reliability of obtaining the generation request of product information.

[0078] In other instances, the request for generating product information can be obtained not only through human-computer interaction operations, but also through a preset device. In this case, obtaining the request for generating product information may include: determining a preset device (for example, a client) that is communicatively connected to a device for generating product information, wherein the request for generating product information is stored or generated in the preset device; and actively or passively obtaining the request for generating product information through the preset device, thereby also ensuring the accuracy and reliability of obtaining the request for generating product information.

[0079] Step S202: Based on the category description in the generation request and at least one knowledge item description, determine the commodity category and the concept attributes under each knowledge item under the commodity category that are compatible with the generation request.

[0080] Since the generation request is often a description text composed of natural language, in order to accurately perform the generation operation of product information, the category description and at least one knowledge item description in the generation request can be analyzed and processed, so as to determine the product category that matches the product information and the conceptual attributes under each knowledge item under the product category. Specifically, a product category can correspond to one or more knowledge items, and a knowledge item can correspond to one or more conceptual attributes. For example, when the product is "bottled beverages", the determined product category can be implemented as "beverages", and the knowledge items can include: "flavors, raw materials, and processes of beverages", etc. The conceptual attributes under the above-mentioned "flavor" knowledge item can include: orange flavor, apple flavor, peach flavor, pineapple flavor, etc.

[0081] In some instances, the product categories and the conceptual attributes of each knowledge item under the product categories can be obtained by adapting the generation request through a preset knowledge base. At this time, based on the category description and at least one knowledge item description in the generation request, determining the product categories and the conceptual attributes of each knowledge item under the product categories that are adapted to the generation request can include: obtaining a preset knowledge base, wherein the preset knowledge base includes multiple standard product categories, multiple standard knowledge items under each standard product category, and existing conceptual attributes under each standard knowledge item; adapting the category description and at least one knowledge item description in the generation request based on the preset knowledge base to obtain the product categories and the conceptual attributes of each knowledge item under the product categories that are adapted to the generation request.

[0082] Among them, a preset knowledge base is pre-configured for determining product categories and conceptual attributes under each knowledge item under the product category. The preset knowledge base includes multiple standard product categories, multiple standard knowledge items under each standard product category, and existing conceptual attributes under each standard knowledge item. Specifically, the preset knowledge base can be stored in a preset area. When it is necessary to determine the product category that is compatible with the product information and the conceptual attributes under each knowledge item under the product category, the preset knowledge base can be obtained by accessing the preset area.

[0083] After obtaining the preset knowledge base, the category description and at least one knowledge item description in the generation request can be adapted based on the preset knowledge base, so that the commodity category adapted to the commodity information and the concept attributes under each knowledge item under the commodity category can be obtained. In some instances, the commodity category adapted to the commodity information and the concept attributes under each knowledge item under the commodity category can be determined by a pre-trained neural network model. At this time, adapting the category description and at least one knowledge item description in the generation request based on the preset knowledge base to obtain the commodity category adapted to the generation request and the concept attributes under each knowledge item under the commodity category can include: obtaining a pre-trained neural network model; inputting the preset knowledge base and the generation request into the neural network model, and using the neural network model to analyze and process the preset knowledge base and the category description and at least one knowledge item in the generation request, so that the commodity category adapted to the commodity information and the concept attributes under each knowledge item under the commodity category output by the neural network model can be obtained, which effectively ensures the accuracy and reliability of determining the concept attributes under the commodity category and each knowledge item.

[0084] In other instances, the commodity categories and conceptual attributes of each knowledge item under the commodity categories that are compatible with the commodity information can be determined not only by a pre-trained neural network model, but also by information adaptation through a preset knowledge base. In this case, adapting the category description and at least one knowledge item description in the generation request based on the preset knowledge base to obtain the commodity categories and conceptual attributes of each knowledge item under the commodity categories that are compatible with the generation request can include: determining the associated categories of the commodity information and at least one associated knowledge item under the associated categories based on the category description and at least one knowledge item description in the generation request; matching the associated categories and at least one associated knowledge item based on the preset knowledge base to obtain the commodity categories and conceptual attributes of each knowledge item under the commodity categories that are compatible with the generation request.

[0085] Specifically, in order to accurately determine the commodity category that matches the commodity information and the conceptual attributes of each knowledge item under the commodity category, after obtaining the request for generating the commodity information, the associated category of the commodity information and at least one associated knowledge item under the associated category may be determined based on the category description in the generation request and at least one knowledge item description. In some instances, the associated category may refer to a category that matches the category description, and the associated knowledge item may refer to a knowledge item that matches the knowledge item description. At this time, based on the category description in the generation request and at least one knowledge item description, determining the associated category of the commodity information and at least one associated knowledge item under the associated category may include: determining a description category corresponding to the commodity information and at least one description knowledge item under the description category based on the category description in the generation request and at least one knowledge item description; determining the description category as an associated category of the commodity information, and determining at least one description knowledge item as at least one associated knowledge item under the associated category.

[0086] After obtaining the generation request, the description category corresponding to the product information and at least one description knowledge item under the description category can be determined based on the category description in the generation request and at least one knowledge item description. The description category can be determined by analyzing and identifying the category description in the generation request, and the description knowledge item can be determined by analyzing and identifying at least one knowledge item description. After determining the description category corresponding to the product information and at least one description knowledge item under the description category, the description type can be determined as an associated category of the product information, and at the same time, at least one description knowledge item can be determined as at least one associated knowledge item under the associated category, which effectively ensures the accuracy and reliability of determining the associated knowledge items and associated categories.

[0087] In some other instances, associated categories may include not only categories that match the category description, but also categories that are similar to the category description. Similarly, associated knowledge items may include not only knowledge items that match the knowledge item description, but also knowledge items that are similar to the knowledge item description. In this case, determining the associated categories of the product information and at least one associated knowledge item under the associated categories based on the category description and at least one knowledge item description in the generation request may include: determining a description category corresponding to the product information and at least one description knowledge item under the description category based on the category description and at least one knowledge item description in the generation request; determining an approximate category corresponding to the description category and an approximate knowledge item corresponding to the description knowledge item; determining the description category and the approximate category as associated categories of the product information, and determining at least one description knowledge item and the approximate knowledge item as at least one associated knowledge item under the associated category.

[0088] After obtaining the generation request, the description category corresponding to the product information and at least one description knowledge item under the description category can be determined based on the category description and at least one knowledge item description in the generation request. Since the associated categories include the description categories and approximate categories corresponding to the generation request, and the associated knowledge items include at least one description knowledge item and approximate knowledge items under the description category corresponding to the generation request, in order to accurately determine the associated categories and the associated knowledge items, after determining the description categories and the description knowledge items, the approximate categories corresponding to the description categories and the approximate knowledge items corresponding to the description knowledge items can be determined.

[0089] Among them, the approximate categories can be determined by the similarity between categories, and correspondingly, the approximate knowledge items can be determined by the similarity between knowledge items. At this time, determining the approximate categories corresponding to the description categories and the approximate knowledge items corresponding to the description knowledge items may include: obtaining the similarity between the description categories and other categories, and the similarity between the description knowledge items and other knowledge items; determining the first threshold corresponding to the description category and the second threshold corresponding to the description knowledge item; when the similarity between categories is greater than or equal to the first threshold, the category corresponding to the similarity between categories is determined as the approximate category corresponding to the description category; when the similarity between categories is less than the first threshold, the category corresponding to the similarity between categories is ignored. Similarly, when the similarity between knowledge items is greater than or equal to the second threshold, the knowledge item corresponding to the similarity between knowledge items is determined as the approximate knowledge item corresponding to the description knowledge item; when the similarity between knowledge items is less than the second threshold, the knowledge item corresponding to the similarity between knowledge items is ignored, which effectively ensures the accuracy and reliability of determining the approximate knowledge items and the approximate categories.

[0090] After determining the approximate categories corresponding to the description categories and the approximate knowledge items corresponding to the description knowledge items, the description categories and the approximate categories can be determined as associated categories of the product information, and at least one description knowledge item and the approximate knowledge item can be determined as at least one associated knowledge item under the associated categories. Then, the associated categories and the at least one associated knowledge item can be matched based on the preset knowledge base, so that the product categories that are compatible with the generated request and the conceptual attributes of each knowledge item under the product category can be obtained, which effectively ensures the accuracy and reliability of determining the product categories that are compatible with the product information and the conceptual attributes of each knowledge item under the product category.

[0091] Step S203: Perform circle product analysis based on product categories and concept attributes to obtain preliminary product information, which at least includes: recommended products corresponding to the generation request and population portraits corresponding to the recommended products.

[0092] After obtaining the product category and concept attributes, circle product analysis operations can be performed based on the product category and concept attributes to obtain preliminary product information, wherein the obtained preliminary product information includes at least: recommended products corresponding to the generation request, population portraits corresponding to the recommended products, and the number of recommended products obtained is one or more.

[0093] In some instances, the product circle analysis operation can be implemented through a pre-trained large language model. At this time, performing product circle analysis based on product categories and conceptual attributes to obtain preliminary product information may include: obtaining a pre-trained large language model; inputting product categories and conceptual attributes into the large language model for product circle analysis, and obtaining preliminary product information output by the large language model, which effectively ensures the accuracy and reliability of determining the preliminary product information.

[0094] Step S204: Generate product information corresponding to the generation request based on the preliminary product information, where the product information at least includes: product description information and product promotion copy.

[0095] Since the preliminary information of the goods often includes the recommended goods corresponding to the generation request and the crowd portrait corresponding to the recommended goods, in order to obtain the goods information used to guide the production operation of the goods, after obtaining the preliminary information of the goods, the preliminary information of the goods can be analyzed and processed to generate the goods information corresponding to the generation request, and the goods information can at least include: description information of the goods and promotional copy of the goods. For example, when the goods are food, the description information of the goods can include at least one of the following: taste description information, raw material description information, process description information, design description information, packaging description information, etc., and the promotional copy of the goods can include "advantage promotion copy of food", "featured promotion copy of food", etc.

[0096] It should be noted that product information may include not only product description information and product promotion copy, but also other information, such as: population portrait information corresponding to the product, scene information corresponding to the product, etc. Technical personnel in this field may flexibly configure or adjust the information included in the product information according to specific application scenarios or application requirements.

[0097] In some instances, product information can be determined by analyzing and processing a pre-trained large language model. At this time, based on the preliminary product information, generating product information corresponding to the generation request may include: obtaining a pre-trained large language model; using the large language model to analyze and process the preliminary product information, and obtaining the product information corresponding to the generation request output by the large language model, thereby effectively ensuring the stable reliability of the generation of the product information.

[0098] The method for generating product information provided in the present embodiment obtains a request for generating product information, and determines the product category and the conceptual attributes under each knowledge item under the product category that are compatible with the generation request based on the category description in the generation request and at least one knowledge item description; then, a circle product analysis is performed based on the product category and the conceptual attributes to obtain preliminary product information, and the product information corresponding to the generation request is generated based on the preliminary product information, thereby efficiently and automatically realizing the generation operation of product information. This not only reduces the human and material resources required for product information, but also greatly improves the generation quality and efficiency of product information, thereby effectively ensuring the practicability of the method.

[0099] Figure 3 A flowchart of determining a commodity category and a concept attribute under each knowledge item under the commodity category that are compatible with a request generation method according to an embodiment of the present invention; based on the above embodiment, refer to the attached Figure 3 As shown, the commodity category and the concept attributes under each knowledge item under the commodity category that are adapted to the generation request can be determined not only by a preset knowledge base, but also by a large language model used to analyze and process the generation request. At this time, based on the category description and at least one knowledge item description in the generation request, determining the commodity category and the concept attributes under each knowledge item under the commodity category that are adapted to the generation request may include:

[0100] Step S301: Obtain a large language model for analyzing and processing the generation request, wherein the large language model is obtained by training based on sample data.

[0101] Step S302: parse the category description and at least one knowledge item description in the generation request using a large language model to obtain a commodity category that matches the generation request and concept attributes under each knowledge item under the commodity category.

[0102] Among them, a large language model for analyzing and processing generation requests is pre-trained and can be stored in a preset area or a preset device. When it is necessary to determine the product category and concept attributes, the large language model can be obtained through the preset area or the preset device, and then the large language model is used to parse the category description and at least one knowledge item description in the generation request, so as to obtain the product category output by the large language model that is compatible with the product information and the concept attributes of each knowledge item under the product category, thereby effectively ensuring the accuracy and reliability of determining the product category and concept attributes.

[0103] In some other examples, since the commodity categories and concept attributes can be determined not only by analyzing and processing the generation request through the large language model, but also by analyzing and processing the generation request through the preset knowledge base, in order to ensure the accuracy and reliability of determining the commodity categories and concept attributes, different methods can be selected in different scenarios to determine the commodity categories that are compatible with the commodity information and the concept attributes under each knowledge item under the commodity category. At this time, before obtaining the large language model for analyzing and processing the generation request, the method in this embodiment may also include: when the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base, and the commodity category and the concept attributes under each knowledge item under the commodity category that are compatible with the generation request are not obtained, it is allowed to obtain the large language model for analyzing and processing the generation request; when the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base, and the commodity category and the concept attributes under each knowledge item under the commodity category that are compatible with the generation request are obtained, it is prohibited to obtain the large language model for analyzing and processing the generation request.

[0104] Among them, no matter in which application scenario, the preset knowledge base can be used to analyze and process the generation request in priority to determine the product category that is compatible with the product information and the conceptual attributes of each knowledge item under the product category; since the data in the preset knowledge base is often limited in number, when it is impossible to determine the product category that is compatible with the product information and the conceptual attributes of each knowledge item under the product category based on the preset knowledge base, the large language model can be used to analyze and process the generation request to determine the product category corresponding to the product information and the conceptual attributes of each knowledge item under the product category.

[0105] In order to be able to stably obtain product categories and conceptual attributes in any scenario, before obtaining the large language model used to analyze and process the generation request, the result information of the adaptation processing of the generation request based on the preset knowledge base can be obtained, and the result information is identified as: when the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base, and the product categories adapted to the generation request and the conceptual attributes of each knowledge item under the product category are not obtained, in order to ensure the accuracy and reliability of the determination of the product categories and conceptual attributes, it is allowed to obtain the large language model used to analyze and process the generation request, so as to use the large language model to parse the category description and at least one knowledge item description in the generation request to obtain the product categories adapted to the generation request and the conceptual attributes of each knowledge item under the product category.

[0106] Correspondingly, the result information is identified as follows: when the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base, the product category and the concept attributes of each knowledge item under the product category that are adapted to the generation request can be obtained, and there is no need to confirm the product category and the concept attributes again. At this time, it is prohibited to obtain the large language model used to analyze and process the generation request, that is, there is no need to use the large language model to parse and process the category description and at least one knowledge item description in the generation request, which can avoid waste of resources in the process of generating product information.

[0107] In other instances, in order to stably obtain concept attributes that meet personalized needs, users can also perform supplementary operations on concept attributes according to needs. At this time, the method in this embodiment may also include: obtaining an attribute supplement request; determining a supplementary concept attribute corresponding to the generated request based on the attribute supplement request; and determining the supplementary concept attribute and the concept attribute determined using the large language model as the target concept attributes under each knowledge item under the product category.

[0108] Specifically, since the data in the preset knowledge base is limited in number, in the process of adapting the category description and at least one knowledge item description in the generation request based on the preset knowledge base, only a limited number of commodity categories and concept attributes under each knowledge item under the commodity category that are adapted to the generation request can be obtained, or the commodity categories and concept attributes under each knowledge item under the commodity category that are adapted to the commodity information cannot be obtained. In order to obtain concept attributes that meet the needs of different users, the user can apply the needs to perform attribute supplementation operations. At this time, the commodity information generation device can obtain the attribute supplementation request. In some instances, the attribute supplementation request can be obtained through human-computer interaction operations; after obtaining the attribute supplementation request, the supplementary concept attributes corresponding to the generation request can be determined based on the attribute supplementation request, and then the supplementary concept attributes and the concept attributes determined using the large language model can be determined as the target concept attributes under each knowledge item under the commodity category.

[0109] It should be noted that when there are overlapping attributes between the supplementary concept attributes and the concept attributes determined by the large language model, the supplementary concept attributes and the concept attributes determined by the large language model can be deduplicated first, and then the deduplicated supplementary concept attributes and the concept attributes determined by the large language model can be determined as the target concept attributes under each knowledge item under the product category. This not only ensures the accuracy and reliability of the determination of the target concept attributes, but also retains the user's personalized understanding.

[0110] In this embodiment, a large language model used to analyze and process the generation request is obtained, and the large language model is used to parse the category description and at least one knowledge item description in the generation request to obtain the commodity category and the conceptual attributes of each knowledge item under the commodity category that are compatible with the generation request. This effectively ensures the accuracy and reliability of the determination of the conceptual attributes.

[0111] Figure 4 A flowchart of performing circle product analysis based on product categories and concept attributes to obtain preliminary product information is provided in an embodiment of the present invention; based on the above embodiment, refer to the attached Figure 4 As shown, for the circle product analysis operation, it can be implemented not only through the pre-trained large language model, but also in combination with the circle product guidance parameters. At this time, the circle product analysis is performed based on the product category and concept attributes, and the preliminary information of the product can include:

[0112] Step S401: obtaining circle product orientation parameters for realizing circle product analysis, where the circle product orientation parameters include at least one of the following: sales orientation parameters and innovation orientation parameters.

[0113] Among them, when performing the product circle operation of the product, the product circle operation can be implemented based on different reference dimensions, for example: sales dimension and innovation dimension, that is, the corresponding product information can be generated by considering the sales situation of the product, or the corresponding product information can be generated by considering the innovation situation of the product. Since different reference dimensions can generate different preliminary product information, in order to ensure the accuracy and reliability of the determination of the preliminary product information, the product circle guidance parameters used to implement the product circle analysis operation can be obtained. The product circle guidance parameters may include at least one of the following: sales guidance parameters, innovation guidance parameters. The above-mentioned product circle guidance parameters can be obtained through human-computer interaction operations, or the product circle guidance parameters can be stored in the preset device. At this time, the product circle guidance parameters are obtained by accessing the preset device.

[0114] Step S402: sort the commodity categories and concept attributes to obtain sorting information of the concept attributes.

[0115] After obtaining the commodity categories and the concept attributes under each knowledge item under the commodity categories that are compatible with the commodity information, the commodity categories and the concept attributes can be sorted to obtain the sorting information of the concept attributes. In some examples, the concept attributes can be sorted based on the dimension of the growth rate of the total commodity transaction amount. At this time, sorting the commodity categories and the concept attributes to obtain the sorting information of the concept attributes can include: obtaining the commodity historical data corresponding to the commodity categories and the concept attributes; determining the growth rate of the total commodity transaction amount corresponding to the concept attribute based on the commodity historical data; sorting the commodity categories and the concept attributes in reverse order based on the growth rate of the total commodity transaction amount to obtain the sorting information of the concept attributes.

[0116] In order to efficiently sort the commodity categories and conceptual attributes, the commodity historical data corresponding to the commodity categories and conceptual attributes can be obtained. The commodity historical data may include at least one of the following: the number of commodity transactions, the commodity transaction amount, the number of commodity orders, the number of commodity transaction users, etc. within the historical time period. The commodity historical data can be obtained by accessing the e-commerce platform. After obtaining the commodity historical data, the commodity historical data can be analyzed and counted to determine the growth rate of the total commodity transaction amount corresponding to the conceptual attribute, wherein one commodity information can correspond to a growth rate of the total commodity transaction amount, and different commodity information can correspond to different growth rates of the total commodity transaction amount. After obtaining the growth rate of the total commodity transaction amount, the commodity categories and conceptual attributes can be sorted in reverse order based on the growth rate of the total commodity transaction amount, that is, the commodity categories and conceptual attributes can be sorted in reverse order from large to small according to the growth rate of the total commodity transaction amount, so that the sorting information of the conceptual attribute can be stably obtained.

[0117] In other instances, the normalization operation can be combined with the sorting operation of commodity categories and conceptual attributes. In this case, sorting the commodity categories and conceptual attributes and obtaining the sorting information of the conceptual attributes may include: obtaining commodity historical data corresponding to the commodity categories and conceptual attributes; determining the growth rate of the total commodity transaction amount corresponding to the conceptual attribute based on the commodity historical data; normalizing the commodity categories and conceptual attributes to obtain normalized categories and normalized attributes; and then sorting the normalized categories and normalized attributes in reverse order based on the growth rate of the total commodity transaction amount to obtain the sorting information of the conceptual attributes. This also ensures the accuracy and reliability of obtaining the sorting information of the conceptual attributes.

[0118] Step S403: Based on the sorting information of the concept attributes and the circle product orientation parameters, determine the focus concept attributes for implementing circle product analysis in the concept attributes.

[0119] After obtaining the ranking information and circle product orientation parameters of the concept attributes, the focus concept attributes for realizing circle product analysis can be determined in the concept attributes based on the ranking information and the circle product orientation parameters of the concept attributes; in some instances, the focus concept attributes can be implemented as the concept attributes ranked in the top few in the ranking information, and the concept attributes ranked in the top 3 in the ranking information can be determined as the focus concept attributes; or, the concept attributes ranked in the top 5 in the ranking information can be determined as the focus concept attributes, which effectively ensures the accuracy and reliability of the determination of the focus concept attributes.

[0120] In other instances, different circle product orientation parameters can obtain different numbers of focus concept attributes. At this time, based on the sorting information of the concept attributes and the circle product orientation parameters, determining the focus concept attributes for realizing circle product analysis in the concept attributes may include: determining the quantity information corresponding to the focus concept attributes based on the circle product orientation parameters; obtaining the front concept attributes that meet the quantity information based on the sorting information of the concept attributes; and determining the front concept attributes as the focus concept attributes for realizing circle product analysis.

[0121] Specifically, in order to accurately determine the focus concept attributes used to implement the circle product analysis, the quantity information corresponding to the focus concept attributes can be determined based on the circle product orientation parameters, wherein the quantity information corresponding to the focus concept attributes can be determined by a preset mapping relationship, and the above preset mapping relationship can be flexibly adjusted or configured according to the specific application scenario or application requirements. For example: when the circle product orientation parameter is a sales orientation parameter, the quantity information corresponding to the focus concept attribute can be 30%*N, wherein N is the total number of concept attributes involved in the sorting; when the circle product orientation parameter is an innovation orientation parameter, the quantity information corresponding to the focus concept attribute can be 80%*N, wherein N is the total number of concept attributes involved in the sorting, thus effectively realizing that different quantity information can be determined based on different circle product orientation parameters.

[0122] After obtaining the quantity information corresponding to the concept attribute of interest, the leading concept attribute that satisfies the quantity information can be obtained based on the sorting information of the concept attribute. For example, when the number of concept attributes is 100 and the quantity information is 30, the concept attributes in the top 30 can be obtained based on the sorting information of the concept attributes. At this time, the concept attributes in the top 30 are the leading concept attributes that satisfy the quantity information. Alternatively, when the number of concept attributes is 100 and the quantity information is 80, the concept attributes in the top 80 can be obtained based on the sorting information of the concept attributes. At this time, the concept attributes in the top 80 are the leading concept attributes that satisfy the quantity information. After obtaining the leading concept attribute that satisfies the quantity information, the leading concept attribute can be directly determined as the concept attribute of interest for realizing the product collection operation, thereby effectively achieving the accurate reliability of determining the concept attribute of interest.

[0123] Step S404: Determine preliminary product information based on the associated product information corresponding to the focus concept attribute.

[0124] After obtaining the focus concept attribute, the associated product information corresponding to the focus concept attribute can be determined. The associated product information can include at least one of the following: the product name, product category, product consumer group, etc. corresponding to the focus concept attribute, and then the preliminary product information can be determined based on the associated product information. In some instances, the associated product information corresponding to the focus concept attribute can be directly determined as the preliminary product information, or the preliminary product information can be obtained through a large language model. At this time, based on the associated product information corresponding to the focus concept attribute, determining the preliminary product information can include: obtaining a large language model, wherein the large language model is obtained by training based on sample data; using the large language model to diverge the associated product information corresponding to the focus concept attribute to obtain the preliminary product information.

[0125] Specifically, in order to accurately determine the preliminary information of the product, after obtaining the focus concept attribute, the related product information corresponding to the focus concept attribute can be determined first, and then the focus concept attribute and the related product information corresponding to the focus concept attribute can be input into the large language model for divergent processing, so that the preliminary information of the product can be obtained stably.

[0126] In some other instances, in order to improve the practicality of the method, the method in this embodiment can also generate generation reasons corresponding to the preliminary information of the product, and can display the generation reasons. At this time, the method in this embodiment can also include: in the process of using a large language model to perform divergent processing on the related product information corresponding to the focus concept attribute, generating generation reasons corresponding to the preliminary information of the product; and displaying the generation reasons and the preliminary information of the product in association.

[0127] Specifically, in the process of using the large language model to diverge the related product information corresponding to the focus concept attribute, not only can the preliminary product information be obtained, but also the generation reasons corresponding to the preliminary product information can be generated based on the reasoning ability of the large language model. The generation reasons and the preliminary product information can then be displayed in association, so that the user can not only view the preliminary product information, but also the generation reasons of the preliminary product information simultaneously, which can ensure the accuracy of the generation of the preliminary product information.

[0128] In this embodiment, by obtaining the circle product guidance parameters used to implement the circle product analysis, the product categories and concept attributes are sorted to obtain the sorting information of the concept attributes, and then based on the sorting information of the concept attributes and the circle product guidance parameters, the focus concept attributes used to implement the circle product analysis can be determined in the concept attributes, and the preliminary information of the product can be determined based on the related product information corresponding to the focus concept attributes, thereby effectively ensuring the accuracy and reliability of the determination of the preliminary information of the product. When the product information is determined based on the preliminary information of the product, the accuracy of the determination of the product information is also improved.

[0129] Figure 5 A schematic diagram of a method for generating commodity information provided by an embodiment of the present invention; Figure 5As shown, this embodiment provides a method for generating product information. The execution subject of the method is a device for generating product information. Specifically, the device for generating product information can be implemented as software, or a combination of software and hardware. When the device for generating product information is implemented as hardware, it can be various electronic devices that can realize the generation operation of product information, including but not limited to personal computers, servers, databases, etc. When the device for generating product information is implemented as software, it can be installed in the electronic devices listed above. Based on the above-mentioned device for generating product information, the generation operation of product information can be realized. Specifically, the method for generating product information can include:

[0130] Step S501: displaying an interactive interface for generating product information, wherein the interactive interface includes a request interactive interface.

[0131] When a user has a demand for generating product information, the device for generating product information may display an interactive interface for generating product information. The interactive interface may include a request interactive interface, which may be implemented as a text input interface for users to perform interactive operations.

[0132] Step S502: In response to an interactive operation input by a user through a request interactive interface, a request for generating product information is obtained, wherein the request for generating product information includes at least a description of a category corresponding to the product information and at least one description of a knowledge item.

[0133] When a user has a demand for generating product information, the user can input an interactive operation through the request interactive interface, and thereby obtain a request for generating product information based on the interactive operation. For example, the user can input an interactive operation in the request interactive interface, and can obtain through the interactive operation "Help me design a novel, fun and interesting lollipop suitable for children and students, with 0 sugar and 0 additives, which must be healthy and burden-free", in this way, the request for generating product information can be obtained stably.

[0134] Step S503: displaying the commodity categories that match the commodity information and the concept attributes of each knowledge item under the commodity category, wherein the commodity categories and the concept attributes are determined by analyzing and processing the category description and at least one knowledge item description in the generation request.

[0135] After obtaining the request for generating product information, the request for generating product information can be analyzed and processed to obtain product categories that are compatible with the product information and conceptual attributes under each knowledge item under the product category, and the product categories and conceptual attributes under each knowledge item can be displayed. For example, when the request for generating product information is "help me design a novel, fun and interesting lollipop suitable for children and students, with 0 sugar and 0 additives, which must be healthy and burden-free", the following product categories (flavors, functions, raw materials, etc.) and conceptual attributes under each knowledge item under the product category can be obtained by analyzing and processing the request for generating product information. When the product category is a raw material category, the obtained conceptual attributes can include "cod"; when the product category is a function category, the obtained conceptual attributes can include "0 additives" and "healthy"; in the display interface, not only product categories and conceptual attributes can be displayed, but also other relevant information can be displayed, such as packaging design information, scene information, applicable population, etc., and technicians in this field can flexibly configure or adjust the content in the display interface according to specific application scenarios or application requirements.

[0136] Step S504: Display preliminary product information corresponding to the generation request, where the preliminary product information is obtained by performing circle product analysis based on product categories and conceptual attributes; wherein the preliminary product information at least includes: recommended products corresponding to the generation request and population portraits corresponding to the recommended products.

[0137] Among them, the recommended products included in the preliminary information of the products can be one or more, and the name information, monthly sales and similar comparison information of the recommended products can be displayed in the display interface. In addition, the analyzed product category and concept attributes corresponding to the generated request can be displayed at the top of the preliminary information of the products.

[0138] Step S505: displaying the product information corresponding to the generation request, wherein the product information is determined based on the analysis and processing of the preliminary product information, wherein the product information at least includes: product description information and product promotion copy.

[0139] After obtaining the preliminary information of the product, the product information corresponding to the generation request can be determined based on the preliminary information of the product, and the product information can be displayed. The displayed product information can at least include the description information of the product and the promotional copy of the product. The description information of the product can include at least one of the following: a description of the innovative taste of the product, a description of the selected raw materials of the product, a description of the special process of the product, etc. The promotional copy of the product is used for the promotional copy of the production and sales of the product, which effectively ensures the accuracy and reliability of the determination of the product information.

[0140] The specific implementation methods and implementation effects of the above steps in this embodiment are the same as those in the above Figure 2-Figure 4 The specific implementation method and implementation effect of steps S201 to S204 in the illustrated embodiment are similar, and the details may be referred to the above statements, which will not be repeated here.

[0141] In addition, the sample identification method in this embodiment may also include the above Figure 2-Figure 4 For the method of the embodiment shown in the figure, the part not described in detail in this embodiment can be referred to Figure 2-Figure 4 The implementation process and technical effects of this technical solution refer to Figure 2-Figure 4 The description in the illustrated embodiment will not be repeated here.

[0142] For specific applications, refer to the attached Figure 6 As shown, this application embodiment provides a method for generating product concepts, which can help merchants quickly generate product concepts during the creative stage of product concepts, and can solve the defects in the creativity dimension and resource investment dimension of merchants in the traditional process of product concept creative operation. Among them, the defects in the creativity dimension include: 1) Due to the limitations of the number of participants and the time for co-creation, the number of ideas is relatively limited; 2) Due to the limitations of the creativity and expression of the participants, the generation quality of product concepts cannot be guaranteed; the defects in the resource investment dimension include: 1) It takes a long time from consumer insight to the final refinement of product concepts; 2) The investment cost of manpower and resources is relatively high.

[0143] Specifically, the method may include the following steps:

[0144] Step 1: Obtain a request for generating a product concept, and use the large language model (LLM) to parse the request input by the user to obtain a category description and at least one knowledge item description corresponding to the product concept included in the request.

[0145] Among them, the obtained category description and at least one knowledge item description can be obtained by performing inference operations on the generation request input by the user through the large language model LLM. Specifically, the category description is used to determine the adaptation category corresponding to the product concept, and the knowledge item description is used to determine the knowledge item corresponding to the adaptation category. For example: when the adaptation category is the "food" category, the knowledge item corresponding to the adaptation category may include at least one of the following: taste, function, and scene; when the adaptation category is the "clothing" category, the knowledge item corresponding to the adaptation category may include at least one of the following: style and design.

[0146] Step 2: Based on the category description in the generation request and at least one knowledge item description, determine the commodity category and the knowledge points under each knowledge item under the commodity category (corresponding to the concept attributes in the above embodiment) that match the generation request.

[0147] In some instances, the knowledge points under each knowledge item can be obtained by performing a knowledge point matching operation on a preset knowledge base. At this time, based on the category description in the generation request and at least one knowledge item description, determining the commodity category that is compatible with the commodity concept and the knowledge points under each knowledge item under the commodity category may include: obtaining a preset knowledge base, wherein the preset knowledge base stores a plurality of standard commodity categories, standard knowledge items under each standard commodity category, and standard knowledge points under the standard knowledge items; and then performing a knowledge point matching operation in the preset knowledge base based on the category description in the generation request and at least one knowledge item description, thereby obtaining the commodity category that is compatible with the generation request and the knowledge points under each knowledge item under the commodity category.

[0148] In other instances, the commodity categories that match the commodity concepts and the knowledge points under each knowledge item under the commodity categories can be determined by means of synonyms. At this time, the knowledge points under each knowledge item can be obtained by performing knowledge point matching operations on a preset knowledge base. Specifically, based on the category description in the generation request and at least one knowledge item description, determining the commodity categories that match the commodity concepts and the knowledge points under each knowledge item under the commodity categories can include: obtaining a preset knowledge base, wherein the preset knowledge base stores a plurality of standard commodity categories, standard knowledge items under each standard commodity category, and standard knowledge points under the standard knowledge items; then, based on the category description in the generation request and at least one knowledge item description, determining the description category and description knowledge point corresponding to the generation request; determining a similar category corresponding to the description category and a similar knowledge point corresponding to the description knowledge point; performing knowledge point matching operations in the preset knowledge base based on the description category, the similar category, the description knowledge point, and the similar knowledge point, so that the commodity categories that match the generation request and the knowledge points under each knowledge item under the commodity category can be obtained.

[0149] In some other instances, when the preset knowledge base cannot match the product category that is compatible with the generation request and the knowledge points under each knowledge item under the product category, in order to accurately generate the product concept, the large language model can be used to infer the product category that is compatible with the generation request and the knowledge points under each knowledge item under the product category. At this time, the method in this embodiment may include: when the preset knowledge base cannot match the knowledge point corresponding to the generation request, the large language model can be obtained, and then the large language model is used to perform inference operations on the generation request to obtain the product category that is compatible with the generation request and the knowledge points under each knowledge item under the product category.

[0150] Step 3: Perform a knowledge point supplement operation on the knowledge points under each knowledge item obtained to obtain filled knowledge points, and determine the obtained knowledge points and filled knowledge points as target knowledge points corresponding to the generation request.

[0151] Among them, when the knowledge points obtained under each knowledge item do not meet the user's needs, the user-defined knowledge points can be supplemented, that is, the human-computer interaction interface is displayed to obtain the knowledge point supplement operation entered by the user in the human-computer interaction interface; based on the knowledge point supplement operation, the filling knowledge points are obtained, and then the knowledge points obtained in the above steps and the filling knowledge points are determined as the target knowledge points corresponding to the generation request, so that the user's personalized understanding can be retained.

[0152] Step 4: Normalize the target knowledge points under each knowledge item under the product category to obtain normalized knowledge points.

[0153] Step 5: Use each knowledge item and normalized knowledge point under the product category to perform data insight operations and obtain data insight results.

[0154] Specifically, after obtaining each knowledge item and normalized knowledge point under the product category, you can first obtain a pre-trained large language model, and then input each knowledge item and normalized knowledge point into the large language model for data insight operations, so as to obtain data insight results, which are used to implement circle product analysis operations.

[0155] In other instances, in order to accurately obtain data insight results, the normalized knowledge points can be sorted during the data insight process. At this time, the commodity categories and the commodity historical data corresponding to each normalized knowledge point can be obtained first. The commodity historical data can include historical data within the site and / or external data. The commodity historical data is used to determine the growth rate of the total commodity transaction amount of the normalized knowledge point; the normalized knowledge points are sorted in reverse order using the growth rate of the total commodity transaction amount to obtain the sorting information of the concept attributes; the sorting information of the concept attributes and the preset circle product orientation parameters are used to determine the knowledge points of interest for realizing circle product analysis, wherein the preset circle product orientation parameters can include at least one of the following: sales orientation parameters, innovation orientation parameters, and the above-mentioned circle product orientation parameters. The parameters can correspond to the quantiles used to select the focus knowledge points, and then the focus knowledge points used to realize circle product analysis can be determined based on the quantiles and the sorting information of the concept attributes, that is, the top N knowledge points can be queried and calculated, and then the preliminary information of the products can be determined based on the related product information corresponding to the focus knowledge points. Specifically, after obtaining the data insight results, the semantic understanding and completion capabilities of the large language model can be used to diverge and complete the data insight results, so as to obtain the preliminary information of the products and the corresponding associative reasons. The preliminary information of the products can at least include: the recommended products corresponding to the generated request, the population portraits corresponding to the recommended products, etc., so that the quantiles in all knowledge points can be used to distinguish and obtain different data insight results.

[0156] For example, in the food category, from the perspective of sales, the top three flavors of products with the highest sales volume or sales effect can be selected and listed, such as peach-flavored beverages, apple-flavored beverages, and strawberry-flavored beverages, etc. The preliminary product information can include the corresponding crowd portraits of the above peach-flavored beverages, apple-flavored beverages, and strawberry-flavored beverages. In the clothing category, from the perspective of innovation, the top three styles of clothing with the highest degree of innovation can be selected and listed, such as black casual clothing, black formal clothing, and white casual clothing, etc. The obtained preliminary product information can include the corresponding crowd portraits of the above black casual clothing, black formal clothing, and white casual clothing.

[0157] Step 6: Based on the data insight results, generate a product concept corresponding to the generation request, and the product concept at least includes: product description information, product promotion copy, and product population portrait description.

[0158] After obtaining the data insight results, a complete product concept can be obtained based on the data insight results. Specifically, the semantic organization ability of the large language model can be used to expand the final product concept, that is, the data insight results can be inferred into a complete descriptive sentence. The product concept can include at least one of the following: selling point copywriting information, specific design details of various products, specific usage scenarios and suitable population portrait descriptions, etc., and then the product concept can be used to guide the generation or manufacturing operations of the product, and can improve the effect of product promotion.

[0159] Since the large language model has the following advantages: it can quickly organize the required information and can diverge information association operations (the amount of knowledge learned by AI far exceeds that of individuals), in the process of using the large language model for data reasoning, it can automatically and interactively output product concepts and bring merchants a new agile and efficient experience. The generation method of the product concept realizes a generation process from input parsing, knowledge point matching, data insight operation, knowledge point completion to product concept, thereby providing users with divergent innovation capabilities for product concepts. Specifically, in the knowledge point matching stage, the large language model based on multi-level semantic embedding can be used to identify multi-dimensional features related to the user's input intent. These features are contextually understood through a generative decoder, thereby ensuring that the rich information of the generated request can be fully mined and presented. At the same time, the integration of dynamic knowledge can be promoted based on the on-site data and off-site data mined by the preset neural network model, so that the product category and at least one knowledge point under the product category can be stably obtained, and then the product concept can be generated based on at least one knowledge point, which can ensure the accuracy and reliability of the generation of the product concept; in the data insight stage, the knowledge points can be normalized and sorted based on the comparative learning model, and then the user interests and market trends can be further analyzed in depth to obtain more accurate top knowledge points, popular products and target user portraits at the front end of the sorting; in addition, by capturing the user behavior characteristics (purchase behavior, add-to-cart behavior, collection behavior), product categories, various knowledge points under the product category and market trends unique to the e-commerce field, the product concept can be generated based on the above captured information, which not only meets the corresponding generation needs of the product concept, but also gives the product concept a higher innovation ability and market adaptability, which can bring unique competitive advantages to the e-commerce platform, thus realizing a virtuous cycle from product concept generation to market feedback and promoting rapid product iteration and updating.

[0160] The technical solution provided by the present application embodiment uses a large language model to efficiently and automatically generate product concepts, wherein the large language model can be obtained by independent training based on data in a specific field, which can improve the reliability of the output of product concepts in specific fields (for example, the e-commerce field) and specific industries, and reduce the "hallucination" phenomenon; and thus can not only make the generated product concepts more reasonable and accurate, so that the generated product concepts conform to industry trends; but also the product concept generation process is more divergent, and obtains more creative and inspiring product concepts, and, in the process of generating product concepts, users can also perform information supplement operations according to needs, which makes the product concept generation operation more flexible, convenient, accurate and reliable, thereby greatly improving the quality and efficiency of product concepts, and further improving the practicality of the method.

[0161] Figure 7 A schematic diagram of a device for generating commodity information provided by an embodiment of the present invention; Figure 7 As shown, this embodiment provides a device for generating commodity information, which is used to perform the above Figure 2 The method for generating commodity information shown in the figure, specifically, the device for generating commodity information may include:

[0162] A first acquisition module 11 is used to acquire a request for generating product information, wherein the request at least includes: a category description corresponding to the product information and at least one knowledge item description;

[0163] A first determination module 12 is used to determine a commodity category and a concept attribute under each knowledge item under the commodity category that matches the generation request based on the category description and at least one knowledge item description in the generation request;

[0164] The first processing module 13 is used to perform circle product analysis based on product categories and concept attributes to obtain preliminary product information, which at least includes: recommended products corresponding to the generation request and crowd portraits corresponding to the recommended products;

[0165] The first processing module 13 is used to generate product information corresponding to the generation request based on the preliminary product information, and the product information at least includes: product description information and product promotion copy.

[0166] In some instances, when the first determination module 12 determines the product category and the concept attributes under each knowledge item under the product category that are compatible with the generation request based on the category description and at least one knowledge item description in the generation request, the first determination module 12 is used to execute: obtaining a preset knowledge base, wherein the preset knowledge base includes multiple standard product categories, multiple standard knowledge items under each standard product category, and existing concept attributes under each standard knowledge item; adapting the category description and at least one knowledge item description in the generation request based on the preset knowledge base to obtain the product category and the concept attributes under each knowledge item under the product category that are compatible with the generation request.

[0167] In some instances, when the first determination module 12 adapts the category description and at least one knowledge item description in the generation request based on a preset knowledge base to obtain a product category that is adapted to the generation request and conceptual attributes under each knowledge item under the product category, the first determination module 12 is used to execute: determining an associated category of the product information and at least one associated knowledge item under the associated category based on the category description and at least one knowledge item description in the generation request; matching the associated category and at least one associated knowledge item based on the preset knowledge base to obtain a product category that is adapted to the generation request and conceptual attributes under each knowledge item under the product category.

[0168] In some instances, when the first determination module 12 determines an associated category of the product information and at least one associated knowledge item under the associated category based on the category description and at least one knowledge item description in the generation request, the first determination module 12 is used to perform: determining a description category corresponding to the product information and at least one description knowledge item under the description category based on the category description and at least one knowledge item description in the generation request; determining the description category as an associated category of the product information, and determining at least one description knowledge item as at least one associated knowledge item under the associated category.

[0169] In some instances, when the first determination module 12 determines an associated category of the product information and at least one associated knowledge item under the associated category based on the category description and at least one knowledge item description in the generation request, the first determination module 12 is used to perform: determining a description category corresponding to the product information and at least one description knowledge item under the description category based on the category description and at least one knowledge item description in the generation request; determining an approximate category corresponding to the description category and an approximate knowledge item corresponding to the description knowledge item; determining the description category and the approximate category as associated categories of the product information, and determining at least one description knowledge item and the approximate knowledge item as at least one associated knowledge item under the associated category.

[0170] In some instances, when the first determination module 12 determines the commodity category and the conceptual attributes of each knowledge item under the commodity category that are compatible with the generation request based on the category description and at least one knowledge item description in the generation request, the first determination module 12 is used to execute: obtaining a large language model for analyzing and processing the generation request, wherein the large language model is obtained by training based on sample data; using the large language model to parse the category description and at least one knowledge item description in the generation request to obtain the commodity category and the conceptual attributes of each knowledge item under the commodity category that are compatible with the generation request.

[0171] In some instances, before obtaining the large language model for analyzing and processing the generation request, the first processing module 13 in this embodiment is used to perform the following steps: when the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base, and the product category and the conceptual attributes of each knowledge item under the product category that are adapted to the generation request are not obtained, it is allowed to obtain the large language model for analyzing and processing the generation request; when the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base, and the product category and the conceptual attributes of each knowledge item under the product category that are adapted to the generation request are obtained, it is prohibited to obtain the large language model for analyzing and processing the generation request.

[0172] In some examples, the first acquisition module 11, the first determination module 12 and the first processing module 13 in this embodiment are used to perform the following steps:

[0173] A first acquisition module 11 is used to acquire an attribute supplement request;

[0174] A first determination module 12, configured to determine a supplementary concept attribute corresponding to the generation request based on the attribute supplementation request;

[0175] The first processing module 13 is used to determine the supplementary concept attributes and the concept attributes determined by using the large language model as the target concept attributes under each knowledge item under the commodity category.

[0176] In some instances, when the first processing module 13 performs circle product analysis based on product categories and concept attributes to obtain preliminary product information, the first processing module 13 is used to execute: obtaining circle product guidance parameters for implementing circle product analysis, the circle product guidance parameters include at least one of the following: sales guidance parameters, innovation guidance parameters; sorting the product categories and concept attributes to obtain sorting information of the concept attributes; determining the focus concept attributes for implementing circle product analysis in the concept attributes based on the sorting information of the concept attributes and the circle product guidance parameters; and determining preliminary product information based on the associated product information corresponding to the focus concept attributes.

[0177] In some instances, when the first processing module 13 sorts the commodity categories and conceptual attributes to obtain sorting information of the conceptual attributes, the first processing module 13 is used to execute: obtaining commodity historical data corresponding to the commodity categories and conceptual attributes; determining the growth rate of the total commodity transaction amount corresponding to the conceptual attributes based on the commodity historical data; sorting the commodity categories and conceptual attributes in reverse order based on the growth rate of the total commodity transaction amount to obtain sorting information of the conceptual attributes.

[0178] In some examples, when the first processing module 13 determines the focus concept attribute for realizing circle product analysis in the concept attribute based on the sorting information of the concept attribute and the circle product orientation parameter, the first processing module 13 is used to execute: based on the circle product orientation parameter, determine the quantity information corresponding to the focus concept attribute; based on the sorting information of the concept attribute, obtain the front concept attribute that meets the quantity information; determine the front concept attribute as the focus concept attribute for realizing circle product analysis.

[0179] In some instances, when the first processing module 13 determines preliminary product information based on the associated product information corresponding to the focus concept attribute, the first processing module 13 is used to execute: obtaining a large language model, wherein the large language model is obtained by training based on sample data; and using the large language model to perform divergent processing on the associated product information corresponding to the focus concept attribute to obtain preliminary product information.

[0180] In some instances, the first processing module 13 in this embodiment is used to perform the following steps: in the process of using a large language model to perform divergent processing on the related product information corresponding to the focus concept attribute, generating a generation reason corresponding to the preliminary product information; and displaying the generation reason and the preliminary product information in association.

[0181] Figure 7 The device shown can perform Figure 2-Figure 4 , Figure 6 For the method of the embodiment shown in the figure, the part not described in detail in this embodiment can be referred to Figure 2-Figure 4 , Figure 6 The implementation process and technical effects of this technical solution refer to Figure 2-Figure 4 , Figure 6 The description in the illustrated embodiment will not be repeated here.

[0182] In one possible design, Figure 7 The structure of the device for generating product information shown can be implemented as an electronic device, which can be a controller, a personal computer, a server, or other devices. Figure 8 As shown, the electronic device may include: a first processor 21 and a first memory 22. The first memory 22 is used to store the corresponding electronic device executing the above Figure 2-Figure 4 , Figure 6 The program of the method for generating commodity information provided in the illustrated embodiment, the first processor 21 is configured to execute the program stored in the first memory 22 .

[0183] The program includes one or more computer instructions, wherein the one or more computer instructions can implement the following steps when executed by the first processor 21: obtaining a request for generating product information, the generation request at least including: a category description corresponding to the product information and at least one knowledge item description; determining a product category that matches the generation request and concept attributes under each knowledge item under the product category based on the category description and at least one knowledge item description in the generation request; performing circle product analysis based on the product category and concept attributes to obtain preliminary product information, the preliminary product information at least including: recommended products corresponding to the generation request and a population portrait corresponding to the recommended products; generating product information corresponding to the generation request based on the preliminary product information, the product information at least including: product description information and product promotion copy.

[0184] Furthermore, the first processor 21 is also used to execute the aforementioned Figure 2-Figure 4 , Figure 6 All or part of the steps in the illustrated embodiments.

[0185] 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.

[0186] In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions used by electronic devices, which includes instructions for executing the above Figure 2-Figure 4 , Figure 6 A program involved in the method for generating product information in the illustrated embodiment.

[0187] In addition, an embodiment of the present invention provides a computer program product, including: a computer-readable storage medium storing computer instructions, when the computer instructions are executed by one or more processors, causing the one or more processors to execute the above Figure 2-Figure 4 , Figure 6 The steps in the method for generating commodity information in the method embodiment are shown.

[0188] Fig. 9 A schematic diagram of a device for generating commodity information provided by an embodiment of the present invention; Fig. 9 As shown, this embodiment provides a device for generating commodity information, which is used to perform the above Figure 5 The method for generating commodity information shown in the figure, specifically, the device for generating commodity information may include:

[0189] A second display module 31 is used to display an interactive interface for generating product information, wherein the interactive interface includes a request interactive interface;

[0190] The second processing module 32 is used to obtain a request for generating product information in response to an interactive operation input by a user through the request interactive interface, wherein the request for generating product information includes at least: a category description corresponding to the product information and at least one knowledge item description;

[0191] The second display module 31 is used to display the commodity categories and the concept attributes of each knowledge item under the commodity categories that are compatible with the commodity information. The commodity categories and the concept attributes are determined by analyzing and processing the category description and at least one knowledge item description in the generation request;

[0192] The second display module 31 is used to display preliminary information of the product corresponding to the generation request, where the preliminary information of the product is obtained by performing circle product analysis based on the product category and concept attribute; wherein the preliminary information of the product at least includes: the recommended product corresponding to the generation request and the crowd portrait corresponding to the recommended product;

[0193] The second display module 31 is used to display the commodity information corresponding to the generation request, where the commodity information is determined based on the analysis and processing of the preliminary commodity information, wherein the commodity information at least includes: description information of the commodity and promotion copy of the commodity.

[0194] Fig. 9 The device shown can perform Figure 5-Figure 6 For the method of the embodiment shown in the figure, the part not described in detail in this embodiment can be referred to Figure 5-Figure 6 The implementation process and technical effects of this technical solution refer to Figure 5-Figure 6 The description in the illustrated embodiment will not be repeated here.

[0195] In one possible design, Fig. 9 The structure of the device for generating product information shown can be implemented as an electronic device, which can be a controller, a personal computer, a server, or other devices. Fig.10 As shown, the electronic device may include: a second processor 41 and a second memory 42. The second memory 42 is used to store the corresponding electronic device executing the above Figure 5-Figure 6 The second processor 41 is configured to execute the program stored in the second memory 42 for the method of generating commodity information provided in the illustrated embodiment.

[0196] The program includes one or more computer instructions, wherein the one or more computer instructions can implement the following steps when executed by the second processor 41: displaying an interactive interface for generating product information, wherein the interactive interface includes a request interactive interface; in response to an interactive operation input by a user through the request interactive interface, obtaining a request for generating product information, wherein the request for generating product information includes at least: a category description corresponding to the product information and at least one knowledge item description; displaying product categories that are compatible with the product information and concept attributes under each knowledge item under the product category, wherein the product category and the concept attributes are determined by analyzing and processing the category description and at least one knowledge item description in the generation request; displaying preliminary product information corresponding to the generation request, wherein the preliminary product information is obtained by performing circle product analysis based on the product category and the concept attributes; wherein the preliminary product information includes at least: a recommended product corresponding to the generation request and a crowd portrait corresponding to the recommended product; displaying product information corresponding to the generation request, wherein the product information is determined by analyzing and processing the preliminary product information, wherein the product information includes at least: product description information and product promotion copy.

[0197] Furthermore, the second processor 41 is also used to execute the aforementioned Figure 5-Figure 6 All or part of the steps in the illustrated embodiments.

[0198] The structure of the electronic device may further include a second communication interface 43 for the electronic device to communicate with other devices or a communication network.

[0199] In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions used by electronic devices, which includes instructions for executing the above Figure 5-Figure 6 A program involved in the method for generating product information in the illustrated embodiment.

[0200] In addition, an embodiment of the present invention provides a computer program product, including: a computer-readable storage medium storing computer instructions, when the computer instructions are executed by one or more processors, causing the one or more processors to execute the above Figure 5-Figure 6 The steps in the method for generating commodity information in the method embodiment are shown.

[0201] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0202] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0203] 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 combining hardware and software. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0204] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0205] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable device so that a series of operation steps are executed 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 the functions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in the blocks or multiple blocks. In a typical configuration, the computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0206] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0207] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 embodiments of the present invention.

Claims

1. A method for generating commodity information, characterized in that: include: Obtaining a request for generating product information, wherein the request at least includes: a category description corresponding to the product information and at least one knowledge item description; Based on the category description and at least one knowledge item description in the generation request, determining a commodity category that matches the generation request and a concept attribute under each knowledge item under the commodity category; Perform circle product analysis based on the product category and the concept attribute to obtain preliminary product information, wherein the preliminary product information at least includes: a recommended product corresponding to the generation request and a crowd portrait corresponding to the recommended product; Based on the preliminary product information, product information corresponding to the generation request is generated, and the product information at least includes: product description information and product promotion copy.

2. The method according to claim 1, characterized in that: Based on the category description and at least one knowledge item description in the generation request, determining a commodity category adapted to the generation request and a concept attribute under each knowledge item under the commodity category, including: Acquire a preset knowledge base, wherein the preset knowledge base includes a plurality of standard commodity categories, a plurality of standard knowledge items under each standard commodity category, and an existing concept attribute under each standard knowledge item; Based on the preset knowledge base, the category description and at least one knowledge item description in the generation request are adapted to obtain a commodity category adapted to the generation request and concept attributes under each knowledge item under the commodity category.

3. The method according to claim 2, characterized in that Adapting the category description and at least one knowledge item description in the generation request based on the preset knowledge base to obtain a commodity category adapted to the generation request and a concept attribute under each knowledge item under the commodity category, including: Determine, based on the category description and at least one knowledge item description in the generation request, an associated category of the product information and at least one associated knowledge item under the associated category; The associated categories and at least one associated knowledge item are matched based on the preset knowledge base to obtain a commodity category that matches the generation request and a concept attribute under each knowledge item under the commodity category.

4. The method according to claim 3, characterized in that Determining an associated category of the product information and at least one associated knowledge item under the associated category based on the category description and at least one knowledge item description in the generation request includes: Determine, based on the category description and at least one knowledge item description in the generation request, a description category corresponding to the product information and at least one description knowledge item under the description category; The description category is determined as an associated category of the product information, and the at least one description knowledge item is determined as at least one associated knowledge item under the associated category.

5. The method according to claim 3, characterized in that: Determining, based on the category description and at least one knowledge item description in the generation request, an associated category of the product information and at least one associated knowledge item under the associated category, includes: Determine, based on the category description and at least one knowledge item description in the generation request, a description category corresponding to the product information and at least one description knowledge item under the description category; Determine an approximate category corresponding to the description category and an approximate knowledge item corresponding to the description knowledge item; The description category and the similar category are determined as associated categories of the product information, and the at least one description knowledge item and the similar knowledge item are determined as at least one associated knowledge item under the associated category.

6. The method according to claim 2, characterized in that Based on the category description and at least one knowledge item description in the generation request, determining a commodity category adapted to the generation request and a concept attribute under each knowledge item under the commodity category, including: Acquire a large language model for analyzing and processing the generation request, wherein the large language model is obtained by training based on sample data; The large language model is used to parse the category description and at least one knowledge item description in the generation request to obtain a commodity category that matches the generation request and concept attributes under each knowledge item under the commodity category.

7. The method according to claim 6, characterized in that Before obtaining the large language model for analyzing and processing the generation request, the method further includes: When the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base, and no commodity category or concept attributes under each knowledge item under the commodity category that matches the generation request is obtained, it is allowed to obtain a large language model for analyzing and processing the generation request; When the category description and at least one knowledge item description in the generation request are adapted based on the preset knowledge base to obtain the product category adapted to the generation request and the conceptual attributes of each knowledge item under the product category, it is prohibited to obtain the large language model used to analyze and process the generation request.

8. The method according to claim 7, characterized in that The method further comprises: Get attribute supplement request; determining, based on the attribute supplementation request, a supplementary concept attribute corresponding to the generation request; The supplementary concept attributes and the concept attributes determined by using the large language model are determined as target concept attributes under each knowledge item under the commodity category.

9. The method according to any one of claims 1 to 8, characterized in that: Based on the product category and the concept attribute, a circle product analysis is performed to obtain preliminary product information, including: Acquire a circle product orientation parameter for realizing circle product analysis, wherein the circle product orientation parameter includes at least one of the following: a sales orientation parameter and an innovation orientation parameter; Sorting the commodity categories and the concept attributes to obtain sorting information of the concept attributes; Based on the ranking information of the concept attributes and the circle product orientation parameters, determining the focus concept attributes for implementing circle product analysis from the concept attributes; The preliminary information of the product is determined based on the related product information corresponding to the focus concept attribute.

10. The method according to claim 9, characterized in that Sorting the commodity categories and the concept attributes to obtain sorting information of the concept attributes includes: Acquire commodity historical data corresponding to the commodity category and the conceptual attribute; Determine the growth rate of the total transaction amount of the commodity corresponding to the concept attribute based on the commodity historical data; The commodity categories and the concept attributes are sorted in reverse order based on the growth rate of the total commodity transaction amount to obtain sorting information of the concept attributes.

11. The method according to claim 9, characterized in that Based on the sorting information of the concept attributes and the circle product orientation parameters, determining the focus concept attributes for implementing circle product analysis from the concept attributes includes: Based on the circle product orientation parameter, determining the quantity information corresponding to the attribute of the concept of interest; Based on the sorting information of the concept attributes, obtaining the front concept attributes that satisfy the quantity information; The front concept attribute is determined as a focus concept attribute for implementing circle product analysis.

12. The method according to claim 9, characterized in that Determining the preliminary information of the product based on the related product information corresponding to the focus concept attribute includes: Acquire a large language model, wherein the large language model is obtained by training based on sample data; The large language model is used to perform divergent processing on the related product information corresponding to the focus concept attribute to obtain the preliminary product information.

13. The method according to claim 12, characterized in that The method further comprises: In the process of using the large language model to perform divergent processing on the related product information corresponding to the focus concept attribute, generating a generation reason corresponding to the preliminary product information; The generation reason and the preliminary information of the product are displayed in association with each other.

14. A method for generating commodity information, characterized in that: include: Displaying an interactive interface for generating product information, wherein the interactive interface includes a request interactive interface; In response to an interactive operation input by a user through the request interactive interface, a request for generating product information is obtained, wherein the request for generating product information includes at least: a category description corresponding to the product information and at least one knowledge item description; Displaying a commodity category that matches the commodity information and a concept attribute under each knowledge item under the commodity category, wherein the commodity category and the concept attribute are determined by analyzing and processing the category description and at least one knowledge item description in the generation request; Displaying preliminary product information corresponding to the generation request, wherein the preliminary product information is obtained by performing a circle product analysis based on the product category and the concept attribute; wherein the preliminary product information at least includes: a recommended product corresponding to the generation request and a crowd portrait corresponding to the recommended product; The product information corresponding to the generation request is displayed, wherein the product information is determined based on the analysis and processing of the preliminary product information, wherein the product information at least includes: product description information and product promotion copy.

15. A device for generating commodity information, characterized in that: include: A first acquisition module is used to acquire a request for generating product information, wherein the request at least includes: a category description corresponding to the product information and at least one knowledge item description; A first determination module, configured to determine a commodity category that matches the generation request and a concept attribute under each knowledge item under the commodity category based on a category description and at least one knowledge item description in the generation request; A first processing module is used to perform circle product analysis based on the product category and the concept attribute to obtain preliminary product information, wherein the preliminary product information at least includes: a recommended product corresponding to the generation request and a crowd portrait corresponding to the recommended product; The first processing module is used to generate product information corresponding to the generation request based on the preliminary product information, and the product information at least includes: product description information and product promotion copy.

16. A device for generating commodity information, characterized in that: include: A second display module, used to display an interactive interface for generating product information, wherein the interactive interface includes a request interactive interface; A second processing module is configured to obtain a request for generating product information in response to an interactive operation input by a user through the request interactive interface, wherein the request for generating product information includes at least: a category description corresponding to the product information and at least one knowledge item description; The second display module is used to display the commodity category adapted to the commodity information and the concept attribute under each knowledge item under the commodity category, wherein the commodity category and the concept attribute are determined by analyzing and processing the category description and at least one knowledge item description in the generation request; The second display module is used to display preliminary product information corresponding to the generation request, wherein the preliminary product information is obtained by performing circle product analysis based on the product category and the concept attribute; wherein the preliminary product information at least includes: recommended products corresponding to the generation request and crowd portraits corresponding to the recommended products; The second display module is used to display the product information corresponding to the generation request, wherein the product information is determined based on the analysis and processing of the preliminary product information, wherein the product information at least includes: product description information and product promotion copy.

17. An electronic device, characterized in that: 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 1-14.

18. A computer storage medium, characterized in that: Used to store a computer program, which enables a computer to implement the method of any one of claims 1 to 14 when executed.

19. A computer program product, characterized in that include: A computer program, when executed by a processor of an electronic device, causes the processor to execute the steps of any one of the methods of claims 1 to 14.

Images