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

Abstract

Provided in the embodiments of the present disclosure are a product information generation method and apparatus, and a device and a computer program product. The method comprises: acquiring a generation request for product information, wherein the generation request at least comprises a category description corresponding to the product information, and at least one knowledge item description; on the basis of the category description and at least one knowledge item description in the generation request, determining a product category that matches the generation request, and a concept attribute under each knowledge item under the product category; on the basis of the product category and the concept attributes, performing product selection analysis, so as to obtain preliminary product information, wherein the preliminary product information at least comprises a recommended product corresponding to the generation request, and a user profile corresponding to the recommended product; and on the basis of the preliminary product information, generating product information corresponding to the generation request, wherein the product information at least comprises description information of a product and promotional copy for the product. The embodiment not only reduces manpower and material resources required for generating product information, but also improves the quality and efficiency of product information generation.

Description

Methods, apparatus, equipment and computer programs for generating product information Technical Field

[0001] This disclosure relates to the field of network technology, and in particular to a method, apparatus, device, and computer program product for generating product information. Background Technology

[0002] Product information, or concept boards, is used to translate product ideas into text and images, enabling consumers to understand and respond. For businesses / brands, the traditional product information design process involves: market insight – concept co-creation (creative workshops) – desk research – qualitative interviews – quantitative research. This process often requires collecting extensive data and lengthy brainstorming sessions, especially in fast-paced, multi-product industries like food and apparel, where a large number of concept boards need to be produced in a short time. This demands significant human and material resources to generate the corresponding product information. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and computer program product for generating product information, which can efficiently generate product information and reduce the human and material resources required to generate product information.

[0004] In a first aspect, embodiments of this disclosure provide a method for generating product information, including:

[0005] A request to generate product information, wherein the request includes at least: 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, determine the product category that matches the generation request and the conceptual attributes under each knowledge item of the product category;

[0007] Based on the product category and the conceptual attributes, a product circle analysis is performed to obtain preliminary product information. The preliminary product information includes at least: recommended products corresponding to the generation request and the user profile corresponding to the recommended products.

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

[0009] Secondly, embodiments of this disclosure provide a product information generation apparatus, comprising:

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

[0011] The first determining module is configured to determine, based on the category description and at least one knowledge item description in the generation request, a product category that matches the generation request and the conceptual attributes under each knowledge item of the product category.

[0012] The first processing module is configured to perform product segmentation analysis based on the product category and the conceptual attributes to obtain preliminary product information. The preliminary product information includes at least: recommended products corresponding to the generation request and the user profile corresponding to the recommended products.

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

[0014] Thirdly, embodiments of this disclosure provide an electronic device, including: a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the method for generating product information described in the first aspect is implemented.

[0015] Fourthly, embodiments of this disclosure provide a computer storage medium for storing a computer program that, when executed by a computer, implements the method for generating product information as described in the first aspect above.

[0016] Fifthly, embodiments of this disclosure provide a computer program product, including: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps in the product information generation method described in the first aspect above.

[0017] Sixthly, embodiments of this disclosure provide a method for generating product information, including:

[0018] Display an interactive interface for generating product information, the interactive interface including a request interaction interface;

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

[0020] Displays product categories that match the product information, as well as the conceptual attributes of each knowledge item under the product category. The product categories and the conceptual attributes are determined by analyzing and processing the category description and at least one knowledge item description in the generation request.

[0021] The system displays preliminary product information corresponding to the generation request. This preliminary product information is obtained through product segmentation analysis based on the product category and the conceptual attributes. The preliminary product information includes at least: recommended products corresponding to the generation request and a user profile of the recommended products.

[0022] Display product information corresponding to the generated request. The product information is determined based on the analysis and processing of the preliminary product information. The product information includes at least: product description information and product promotional copy.

[0023] In a seventh aspect, embodiments of this disclosure provide an apparatus for generating product information, comprising:

[0024] The second display module is configured to display an interactive interface for generating product information, the interactive interface including a request interaction interface;

[0025] The second processing module is configured to respond to the user's interactive operation input through the request interaction interface to obtain a request to generate product information. The request to generate 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 configured to display product categories adapted to the product information and conceptual attributes under each knowledge item of the product category. The product categories and conceptual attributes 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 configured to display preliminary product information corresponding to the generation request. The preliminary product information is obtained through product segmentation analysis based on the product category and the conceptual attributes. The preliminary product information includes at least: recommended products corresponding to the generation request and a user profile corresponding to the recommended products.

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

[0029] Eighthly, this disclosure provides an electronic device, including: 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 product information generation method in the sixth aspect above.

[0030] In a ninth aspect, embodiments of this disclosure provide a computer storage medium for storing a computer program that, when executed by a computer, implements the method for generating commodity information as described in the sixth aspect above.

[0031] In a tenth aspect, embodiments of this disclosure provide a computer program product, including: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps in the product information generation method described in the sixth aspect above.

[0032] The product information generation method, apparatus, device, and computer program product provided in this embodiment obtain a product information generation request, and based on the category description and at least one knowledge item description in the generation request, determine the product category and the conceptual attributes under each knowledge item of the product category that are compatible with the generation request; then, based on the product category and the conceptual attributes, perform product segmentation analysis to obtain preliminary product information, and generate product information corresponding to the generation request based on the preliminary product information. This can efficiently and automatically realize the product information generation operation, which can not only reduce the human and material resources required for product information generation, but also greatly improve the quality and efficiency of product information generation, thereby effectively ensuring the practicality of the method. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 is a schematic diagram of a scenario for a method of generating product information provided in an embodiment of this disclosure;

[0035] Figure 2 is a flowchart illustrating a method for generating product information according to an embodiment of this disclosure;

[0036] Figure 3 is a flowchart illustrating the process of determining the product category that matches the generation request and the conceptual attributes under each knowledge item of the product category, according to an embodiment of this disclosure.

[0037] Figure 4 is a flowchart illustrating the process of performing product segmentation analysis based on the product category and the conceptual attributes to obtain preliminary product information according to an embodiment of this disclosure.

[0038] Figure 5 is a schematic diagram of a method for generating product information provided in an embodiment of this disclosure;

[0039] Figure 6 is a schematic diagram illustrating the principle of a product information generation method provided in an application embodiment of this disclosure;

[0040] Figure 7 is a schematic diagram of a product information generation device provided in an embodiment of this disclosure;

[0041] Figure 8 is a schematic diagram of the electronic device corresponding to the product information generation device provided in the embodiment shown in Figure 7;

[0042] Figure 9 is a schematic diagram of a product information generation device provided in an embodiment of this disclosure;

[0043] Figure 10 is a schematic diagram of the electronic device corresponding to the product information generation device provided in the embodiment shown in Figure 9. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0045] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the disclosure. The singular forms “a” and “the” as used in the embodiments of this disclosure and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise, and “multiple” generally includes at least two, but does not exclude the inclusion of at least one.

[0046] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0047] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0048] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes that element.

[0049] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0050] Terminology definition:

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

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

[0053] Large Language Model (LLM) typically refers to an artificial intelligence model trained on a large amount of data that is capable of handling complex tasks.

[0054] To facilitate understanding of the specific implementation process and effects of the product information generation method, apparatus, device, and computer program product in this embodiment, the relevant technologies are 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 through creative workshops) - desk research - qualitative interviews - quantitative research. The product information design process often requires collecting a large amount of data and engaging in lengthy brainstorming sessions, especially in fast-paced industries like food and apparel that produce numerous product types, necessitating the generation of a large number of concept boards or product information within a short period. However, the above method of generating product information has the following problems:

[0056] (1) The time cycle is long. In the ever-changing business environment, it is difficult to track trends and verify the effectiveness of product information. It may take a long time to produce a concept. After the above time, the product information generated may no longer be popular.

[0057] (2) The preliminary data collection, organization, and analysis work is tedious and time-consuming;

[0058] (3) The above methods require a lot of manpower and resources to generate corresponding product information. However, artificial brainstorming has great limitations because each individual has limitations in knowledge and thinking. Therefore, it is easy to miss or ignore some conceptual information during the brainstorming process.

[0059] To address the technical problems existing in the aforementioned related technologies, this embodiment provides a method, apparatus, device, and computer program product for generating product information. Specifically, referring to Figure 1, the executing entity of the product information generation method can be a product information generation apparatus 200. This apparatus 200 can be implemented as a local server, a cloud server, or a pre-set device. When the product information generation apparatus 200 is implemented as a cloud server, the product information generation method can be executed in the cloud. Several computing nodes (cloud servers) can be deployed in the cloud, each with computing, storage, and other processing resources. In the cloud, multiple computing nodes can be organized to provide a certain service; of course, a single computing node can also provide one or more services. The cloud can provide this service by providing a service interface, which users call to use the corresponding service. Service interfaces include Software Development Kits (SDKs), Application Programming Interfaces (APIs), etc.

[0060] The product information generation device 200 is communicatively connected to the client 100. The client 100 is configured for user application to trigger the product information generation operation. The client 100 can be any computing device with a certain product information generation capability; specifically, it can be a mobile phone, personal computer (PC), tablet computer, application program, etc. Furthermore, the basic structure of the client 100 may include at least one processor. The number of processors depends on the client's configuration and type. The client 100 may also include memory, which can be volatile, such as Random Access Memory (RAM), or non-volatile, such as Read-Only Memory (ROM), flash memory, etc., or both types. The memory typically stores the operating system (OS), one or more applications, and may also store program data. In addition to the processing unit and memory, the client 100 also includes some basic configurations, such as a network interface card (NIC) chip, I / O bus, display components, and some peripheral devices. Optionally, some peripheral devices may include, for example, a keyboard, mouse, pen, printer, etc. Other peripheral devices are well known in the art and will not be described in detail here.

[0061] The product information generation device 200 refers to a device capable of generating product information in a network virtual environment. It typically refers to a device that utilizes a network for information planning and product information generation. Physically, the product information generation device 200 can be any device capable of providing computing services and performing corresponding product information generation operations, such as a cluster server, a conventional server, a cloud server, a cloud host, or a virtual data center. The product information generation device 200 mainly consists of a processor, hard disk, memory, and system bus, similar to a general computer architecture.

[0062] In this embodiment described above, the client 100 establishes a network connection with the product information generation device 200. This network connection can be wireless or wired. If the client 100 can establish a communication connection with the product information generation device 200, the mobile network standard 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 this embodiment, the client 100 is configured for user use to generate a product information generation request. This request can be generated through human-computer interaction or voice interaction. After receiving the product information generation request, it can be sent to the product information generation device 200, enabling the device to perform the corresponding product information generation operation based on the request.

[0064] The product information generation device 200 is configured to receive product information generation requests from a client 100. The product information generation process can be as follows: the obtained generation request includes at least: a category description corresponding to the product information and at least one knowledge item description. The category description can correspond to at least one category, and the knowledge item description can correspond to at least one knowledge item. Each category can correspond to one or more knowledge items. After receiving the generation request, the category description and at least one knowledge item description in the generation request can be analyzed and processed to determine the product category that matches the generation request and the conceptual attributes under each knowledge item within that product category.

[0065] After obtaining the product categories and conceptual attributes under each knowledge item that match the generation request, product segmentation analysis can be performed based on the product categories and conceptual attributes to obtain preliminary product information. This preliminary information includes at least: recommended products corresponding to the generation request and the corresponding user profiles for those products. There can be one or more recommended products corresponding to the generation request. After obtaining the preliminary product information, it can be analyzed and processed to generate product information corresponding to the generation request. The generated product information includes at least: product description information and promotional copy. This generated product information guides the production or generation operations of the product, thus ensuring the accuracy and reliability of the generated product information.

[0066] In this embodiment, by determining the product category and the conceptual attributes of each knowledge item under the product category that match the generation request, and performing product circle analysis based on the product category and conceptual attributes, preliminary product information is obtained. Then, product information corresponding to the generation request can be generated based on the preliminary product information, and the product information can be output. This efficiently and automatically realizes the product information generation operation. This not only reduces the human and material resources required for product information generation, but also greatly improves the quality and efficiency of product information generation, thus effectively ensuring the practicality of the method.

[0067] The following detailed description of some embodiments of this disclosure is provided in conjunction with the accompanying drawings. Where there is no conflict between the embodiments, the following embodiments and features can be combined with each other. Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0068] Figure 2 is a flowchart illustrating a method for generating product information according to an embodiment of this disclosure. Referring to Figure 2, this embodiment provides a method for generating product information. The executing entity of this method is a product information generating device. Specifically, the product information generating device can be implemented as software or a combination of software and hardware. When the product information generating device is implemented as hardware, it can be various electronic devices capable of generating product information, including but not limited to personal computers, servers, databases, etc. When the product information generating device is implemented as software, it can be installed in the aforementioned electronic devices. Based on the above-mentioned product information generating device, the product information generating operation can be realized. Specifically, the product information generating method may include:

[0069] Step S201: Obtain a request to generate product information. The request shall include at least: a category description corresponding to the product information and at least one knowledge item description.

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

[0071] Step S203: Perform product segmentation analysis based on product category and conceptual attributes to obtain preliminary product information. The preliminary product information includes at least: recommended products corresponding to the generated request and the user profile corresponding to the recommended products.

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

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

[0074] Step S201: Obtain a request to generate product information. The request shall include at least: a category description corresponding to the product information and at least one knowledge item description.

[0075] When a user has a need to generate product information, the product information generation device can obtain the product information generation request. The product information generation request includes at least: a category description corresponding to the product information and at least one knowledge item description.

[0076] For example, a request to generate product information could be implemented as "I want to develop a beverage with a sweet and sour flavor," where "beverage" can be a category description corresponding to the product information, and "with a sweet and sour flavor" can be at least one knowledge item description. Alternatively, a request to generate product information could be implemented as "I want to develop a biscuit for the elderly that has spleen-strengthening properties," where "biscuit" can be a category description corresponding to the product information, and "for the elderly that has spleen-strengthening properties" can be at least one knowledge item description.

[0077] Specifically, this embodiment does not limit the specific implementation method of obtaining the product information generation request. In some instances, the product information generation request can be obtained through human-computer interaction. In this case, obtaining the product information generation request may include: displaying the 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 product information generation request based on the execution operation. This effectively ensures the stability and reliability of obtaining the product information generation request.

[0078] In other instances, the request to generate product information can be obtained not only through human-computer interaction but also through a preset device. In this case, obtaining the request to generate product information may include: identifying a preset device (e.g., a client) that is communicatively connected to the device that generates product information, wherein the preset device stores or generates the request to generate product information; and actively or passively obtaining the request to generate product information through the preset device, thus ensuring the accuracy and reliability of obtaining the request to generate product information.

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

[0080] Since the request to generate product information is often a descriptive text composed of natural language, in order to accurately generate product information, the category description and at least one knowledge item description in the request can be analyzed and processed. This allows us to determine the product category that matches the product information, as well as the conceptual attributes under each knowledge item within that 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 beverage," the determined product category can be "beverage," and the knowledge items can include: "beverage flavor, ingredients, and processing," etc. The conceptual attributes under the "flavor" knowledge item can include: orange flavor, apple flavor, peach flavor, pineapple flavor, etc.

[0081] In some instances, product categories and the conceptual attributes of each knowledge item under a product category can be obtained by adapting the generation request to a preset knowledge base. In this case, determining the product category and the conceptual attributes of each knowledge item under the product category that are adapted to the generation request, based on the category description and at least one knowledge item description in the generation request, may 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; and 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 conceptual attributes of each knowledge item under the product category that are adapted to the generation request.

[0082] The system includes a pre-configured knowledge base for determining product categories and the conceptual attributes of each knowledge item under each product category. This 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 knowledge base can be stored in a pre-configured area. When it is necessary to determine the product category that matches the product information and the conceptual attributes of each knowledge item under the product category, the knowledge base can be obtained by accessing the pre-configured 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. This allows us to obtain the product category and the conceptual attributes of each knowledge item under the product category that match the product information. In some instances, the product category and the conceptual attributes of each knowledge item under the product category that match the product information can be determined by a pre-trained neural network model. 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 product category and the conceptual attributes of each knowledge item under the product category that match the generation request 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 category description and at least one knowledge item in the preset knowledge base and the generation request. This allows us to obtain the product category and the conceptual attributes of each knowledge item under the product category that match the product information, as output by the neural network model. This effectively ensures the accuracy and reliability of determining the product category and the conceptual attributes of each knowledge item.

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

[0085] Specifically, in order to accurately determine the product category and the conceptual attributes of each knowledge item under the product category that match the product information, after obtaining the product information generation request, the associated category of the product information and at least one associated knowledge item under the associated category can be determined based on the category description and at least one knowledge item description in the generation request. In some instances, the associated category can refer to the category that matches the category description, and the associated knowledge item can refer to the knowledge item description. In this case, determining the 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 can include: determining the description category corresponding to the product information and at least one descriptive 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 the associated category of the product information, and determining at least one descriptive 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 and at least one knowledge item description in the generation request. 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 the 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 the associated category of the product information, and at least one description knowledge item can be determined as at least one associated knowledge item under the associated category. This effectively ensures the accuracy and reliability of determining the associated knowledge item and associated category.

[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 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 may include: determining the 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 approximate category corresponding to the description category and the approximate knowledge item corresponding to the description knowledge item; determining the description category and the approximate category as the associated category 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 description knowledge item under the description category in the generation request. Since the associated category includes the description category and the approximate category corresponding to the generation request, and the associated knowledge item includes at least one description knowledge item and the approximate knowledge item under the description category corresponding to the generation request, in order to accurately determine the associated category and the associated knowledge item, after determining the description category and the description knowledge item, the approximate category corresponding to the description category and the approximate knowledge item corresponding to the description knowledge item can be determined.

[0089] In this process, similar categories can be determined using inter-category similarity, and similar knowledge items can be determined using inter-knowledge item similarity. Determining the similarity between the descriptive category and the similarity between the descriptive knowledge item and the descriptive knowledge item can include: obtaining the inter-category similarity between the descriptive category and other categories, and the inter-knowledge item similarity between the descriptive knowledge item and other knowledge items; determining a first threshold corresponding to the descriptive category and a second threshold corresponding to the descriptive knowledge item; when the inter-category similarity is greater than or equal to the first threshold, the category corresponding to the inter-category similarity is determined as the similar category corresponding to the descriptive category; when the inter-category similarity is less than the first threshold, the category corresponding to the inter-category similarity is ignored. Similarly, when the inter-knowledge item similarity is greater than or equal to the second threshold, the knowledge item corresponding to the inter-knowledge item similarity is determined as the similar knowledge item corresponding to the descriptive knowledge item; when the inter-knowledge item similarity is less than the second threshold, the knowledge item corresponding to the inter-knowledge item similarity is ignored. This effectively ensures the accuracy and reliability of determining similar knowledge items and similar categories.

[0090] After identifying the approximate categories corresponding to the descriptive categories and the approximate knowledge items corresponding to the descriptive knowledge items, the descriptive categories and approximate categories can be identified as the associated categories of the product information. At least one descriptive knowledge item and one approximate knowledge item can be identified as at least one associated knowledge item under the associated category. Then, the associated categories and at least one associated knowledge item can be matched based on a preset knowledge base to obtain the product category and the conceptual attributes under each knowledge item under the product category that are compatible with the generation request. This effectively ensures the accuracy and reliability of determining the product category and the conceptual attributes under each knowledge item under the product category that are compatible with the product information.

[0091] Step S203: Perform product segmentation analysis based on product category and conceptual attributes to obtain preliminary product information. The preliminary product information includes at least: recommended products corresponding to the generated request and the user profile corresponding to the recommended products.

[0092] After obtaining the product category and conceptual attributes, a product segmentation analysis can be performed based on the product category and conceptual attributes to obtain preliminary product information. The preliminary product information obtained includes at least: recommended products corresponding to the generation request, and the user profiles corresponding to the recommended products. The number of recommended products obtained is one or more.

[0093] In some instances, product segmentation analysis can be implemented using a pre-trained large language model. In this case, product segmentation analysis based on product category and conceptual attributes to obtain preliminary product information may include: acquiring the pre-trained large language model; inputting the product category and conceptual attributes into the large language model for product segmentation analysis; and obtaining the preliminary product information output by the large language model. This effectively ensures the accuracy and reliability of determining the preliminary product information.

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

[0095] Since preliminary product information often includes recommended products corresponding to the request and the target audience for those products, in order to obtain product information to guide production operations, the preliminary product information can be analyzed and processed after acquisition to generate product information corresponding to the request. This product information may include at least: product description information and product promotional copy. For example, when the product is food, the product description information may include at least one of the following: flavor description information, ingredient description information, processing description information, design description information, packaging description information, etc., and the product promotional copy may include "promotional copy highlighting the advantages of the food" or "promotional copy highlighting the unique features of the food," etc.

[0096] It should be noted that product information may include not only product descriptions and promotional copy, but also other information, such as the target audience profiles and the scenarios in which the product is used. Those skilled in the art can 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 through analysis and processing using a pre-trained large language model. In this case, generating product information corresponding to the generation request based on preliminary product information may include: obtaining a pre-trained large language model; using the large language model to analyze and process the preliminary product information to obtain the product information output by the large language model that corresponds to the generation request. This effectively ensures the stability and reliability of product information generation.

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

[0099] Figure 3 is a flowchart illustrating the process of determining the product category and the conceptual attributes under each knowledge item of the product category that are compatible with the generation request, according to an embodiment of this disclosure. Based on the above embodiment, referring to Figure 3, the product category and the conceptual attributes under each knowledge item of the product category that are compatible with 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. In this case, determining the product category and the conceptual attributes under each knowledge item of 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, may include:

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

[0101] Step S302: Use a large language model to parse the category description and at least one knowledge item description in the generation request to obtain the product category and the conceptual attributes of each knowledge item under the product category that are compatible with the generation request.

[0102] The system includes a pre-trained large language model for analyzing and processing generated requests. This large language model can be stored in a preset area or device. When it is necessary to determine the product category and conceptual attributes, the large language model can be obtained through the preset area or device. Then, the large language model is used to parse the category description and at least one knowledge item description in the generated request. This allows the system to obtain the product category and conceptual attributes under each knowledge item in the product category, which are adapted to the product information. This effectively ensures the accuracy and reliability of determining the product category and conceptual attributes.

[0103] In other instances, since product categories and conceptual attributes can be determined not only through large language models but also through pre-defined knowledge bases, different methods can be chosen in different scenarios to determine the product categories and conceptual attributes that match the product information. In this case, before obtaining the large language model used to analyze the generation request, the method in this embodiment may further include: if, based on the pre-defined knowledge base, the category description and at least one knowledge item description in the generation request are adapted, and no product category or conceptual attributes matching the generation request are obtained, then obtaining the large language model for analyzing the generation request is permitted; if, based on the pre-defined knowledge base, the category description and at least one knowledge item description in the generation request are adapted, and a product category and conceptual attributes matching the generation request are obtained, then obtaining the large language model for analyzing the generation request is prohibited.

[0104] In any application scenario, a pre-set knowledge base can be used first to analyze and process the generated request to determine the product category that matches the product information, as well as the conceptual attributes of each knowledge item under the product category. Since the data in the pre-set knowledge base is often limited, when it is not possible to determine the product category that matches the product information and the conceptual attributes of each knowledge item under the product category based on the pre-set knowledge base, a large language model can be used to analyze and process the generated request to determine the product category that corresponds to the product information and the conceptual attributes of each knowledge item under the product category.

[0105] To reliably obtain product categories and conceptual attributes in any scenario, before acquiring the large language model used to analyze and process the generated request, the result information of adapting the generated request based on a preset knowledge base can be obtained. This result information is marked as follows: when adapting the category description and at least one knowledge item description in the generated request based on the preset knowledge base fails to obtain a product category or conceptual attributes under each knowledge item within the product category, in order to ensure the accuracy and reliability of determining the product category and conceptual attributes, the large language model used to analyze and process the generated request is allowed. This large language model is then used to parse the category description and at least one knowledge item description in the generated request to obtain a product category and conceptual attributes under each knowledge item within the product category that are compatible with the generated request.

[0106] Correspondingly, if 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, and the product category and the conceptual attributes under each knowledge item under the product category are obtained, then there is no need to perform the confirmation operation of the product category and conceptual 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. This can avoid the waste of resources in the process of generating product information.

[0107] In other instances, in order to reliably obtain conceptual attributes that meet personalized needs, users can also supplement conceptual attributes according to their needs. In this case, the method in this embodiment may also include: obtaining an attribute supplementation request; determining supplementary conceptual attributes corresponding to the generation request based on the attribute supplementation request; and determining the supplementary conceptual attributes and the conceptual attributes determined by the large language model as target conceptual attributes under each knowledge item in the product category.

[0108] Specifically, since the data in the preset knowledge base is limited, during the adaptation operation of 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 product categories and conceptual attributes under each knowledge item of the product category that are adapted to the generation request can be obtained, or product categories and conceptual attributes under each knowledge item of the product category that are adapted to the product information cannot be obtained. In order to obtain conceptual attributes that meet the needs of different users, users can perform attribute supplementation operations based on their needs. At this time, the product information generation device can obtain the attribute supplementation request. In some instances, the attribute supplementation request can be obtained through human-computer interaction. After obtaining the attribute supplementation request, the supplementary conceptual attributes corresponding to the generation request can be determined based on the attribute supplementation request. Then, the supplementary conceptual attributes and the conceptual attributes determined by the large language model can be determined as the target conceptual attributes under each knowledge item of the product category.

[0109] It is important to note that when there is overlap between the supplementary conceptual attributes and the conceptual attributes determined by the large language model, the supplementary conceptual attributes and the conceptual attributes determined by the large language model can be deduplicated first. Then, the deduplicated supplementary conceptual attributes and the conceptual attributes determined by the large language model can be identified as the target conceptual attributes under each knowledge item in the product category. This not only ensures the accuracy and reliability of the target conceptual attributes but also preserves the user's personalized understanding.

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

[0111] Figure 4 is a flowchart illustrating the process of obtaining preliminary product information through product category and conceptual attributes analysis according to an embodiment of this disclosure. Based on the above embodiment, and referring to Figure 4, the product category analysis operation can be implemented not only through a pre-trained large language model but also by combining product category guidance parameters. In this case, obtaining preliminary product information through product category and conceptual attributes analysis can include:

[0112] Step S401: Obtain the product-oriented parameters used to implement product-oriented analysis. The product-oriented parameters include at least one of the following: sales-oriented parameters and innovation-oriented parameters.

[0113] When performing product segmentation, different reference dimensions can be used, such as sales and innovation. This means that product information can be generated based on sales performance or innovation. Since different reference dimensions generate different initial product information, to ensure the accuracy and reliability of the initial product information, product segmentation guidance parameters can be obtained. These parameters can include at least one of the following: sales guidance parameters and innovation guidance parameters. These parameters can be obtained through human-computer interaction, or they can be stored in a preset device, allowing access to the device to obtain the parameters.

[0114] Step S402: Sort the product categories and conceptual attributes to obtain the sorting information of the conceptual attributes.

[0115] After obtaining the product categories and conceptual attributes under each knowledge item that match the product information, the product categories and conceptual attributes can be sorted to obtain the sorting information of the conceptual attributes. In some instances, the conceptual attributes can be sorted based on the growth rate of total transaction volume. In this case, sorting the product categories and conceptual attributes to obtain the sorting information of the conceptual attributes can include: obtaining historical product data corresponding to the product categories and conceptual attributes; determining the growth rate of total transaction volume corresponding to the conceptual attributes based on the historical product data; and sorting the product categories and conceptual attributes in reverse order based on the growth rate of total transaction volume to obtain the sorting information of the conceptual attributes.

[0116] To efficiently sort product categories and conceptual attributes, historical product data corresponding to these categories and attributes can be obtained. This historical data may include at least one of the following: the number of transactions, transaction value, number of orders, and number of users transacting within a historical time period. This historical data can be obtained by accessing e-commerce platforms. After obtaining the historical data, it can be analyzed and statistically analyzed to determine the growth rate of the total transaction value corresponding to each conceptual attribute. Each product can have a unique growth rate for its total transaction value, and different product information may have different growth rates. After obtaining the growth rate, the product categories and conceptual attributes can be sorted in reverse order based on this growth rate, from highest to lowest, thus providing a stable ranking information for the conceptual attributes.

[0117] In other instances, normalization operations can be combined to achieve the sorting of product categories and conceptual attributes. In this case, sorting product categories and conceptual attributes to obtain the sorting information of conceptual attributes may include: obtaining historical product data corresponding to product categories and conceptual attributes; determining the growth rate of the total transaction volume of products corresponding to the conceptual attributes based on the historical product data; normalizing product 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 transaction volume of products to obtain the sorting information of conceptual attributes. This also ensures the accuracy and reliability of obtaining the sorting information of conceptual attributes.

[0118] Step S403: Based on the ranking information of concept attributes and the circle-product guidance parameters, determine the concept attributes of interest used to achieve circle-product analysis from the concept attributes.

[0119] After obtaining the ranking information of concept attributes and the circle quality guidance parameters, the concept attributes of interest used to carry out circle quality analysis can be determined based on the ranking information and the circle quality guidance parameters. In some instances, the concept attributes of interest can be defined as the top-ranked concept attributes in the ranking information. For example, the top 3 concept attributes in the ranking information can be identified as the concept attributes of interest. Alternatively, the top 5 concept attributes in the ranking information can be identified as the concept attributes of interest. This effectively ensures the accuracy and reliability of the identification of the concept attributes of interest.

[0120] In other instances, different circle-oriented parameters can yield different numbers of attention concept attributes. In this case, based on the ranking information of the concept attributes and the circle-oriented parameters, determining the attention concept attributes used to achieve circle-oriented analysis can include: determining the quantity information corresponding to the attention concept attributes based on the circle-oriented parameters; obtaining the preceding concept attributes that satisfy the quantity information based on the ranking information of the concept attributes; and determining the preceding concept attributes as the attention concept attributes used to achieve circle-oriented analysis.

[0121] Specifically, to accurately determine the key concept attributes used for circle-based product analysis, the quantity information corresponding to these attributes can be determined based on circle-based product guidance parameters. This quantity information can be determined through a preset mapping relationship, which can be flexibly adjusted or configured according to specific application scenarios or needs. For example, when the circle-based product guidance parameter is sales-oriented, the quantity information corresponding to the key concept attributes can be 30%*N, where N is the total number of concept attributes participating in the ranking. When the circle-based product guidance parameter is innovation-oriented, the quantity information corresponding to the key concept attributes can be 80%*N, where N is the total number of concept attributes participating in the ranking. This effectively allows for the determination of different quantity information based on different circle-based product guidance parameters.

[0122] After obtaining the quantity information corresponding to the concepts of interest, the preceding concepts of interest can be obtained based on the ranking information of the concepts of interest. For example, when the number of concepts of interest is 100 and the quantity information is 30, the top 30 concepts of interest can be obtained based on the ranking information. In this case, the top 30 concepts of interest are the preceding concepts of interest that satisfy the quantity information. Alternatively, when the number of concepts of interest is 100 and the quantity information is 80, the top 80 concepts of interest can be obtained based on the ranking information. In this case, the top 80 concepts of interest are the preceding concepts of interest that satisfy the quantity information. After obtaining the preceding concepts of interest that satisfy the quantity information, the preceding concepts of interest can be directly determined as the concepts of interest used for circle product operation. This effectively achieves the accuracy and reliability of determining the concepts of interest.

[0123] Step S404: Determine preliminary product information based on the associated product information corresponding to the concept attributes of interest.

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

[0125] Specifically, in order to accurately determine the preliminary information of the product, after obtaining the interest concept attribute, we can first determine the associated product information corresponding to the interest concept attribute, and then input the interest concept attribute and the associated product information corresponding to the interest concept attribute into the large language model for divergent processing. In this way, we can stably obtain the preliminary product information.

[0126] In some other instances, to improve the practicality of the method, the method in this embodiment can also generate a reason for generation corresponding to the preliminary information of the product and display the reason for generation. In this case, the method in this embodiment can also include: generating a reason for generation corresponding to the preliminary information of the product during the process of diverging the related product information corresponding to the concept attribute of interest using a large language model; and displaying the reason for generation and the preliminary information of the product in association.

[0127] Specifically, in the process of using a large language model to diverge the associated product information corresponding to the attributes of the concept of interest, not only can preliminary product information be obtained, but also the reasoning ability of the large language model can be used to generate a reason corresponding to the preliminary product information. Then, the reason for generation and the preliminary product information can be displayed together, so that users can not only view the preliminary product information, but also view the reason for generating the preliminary product information at the same time. This can ensure the accuracy of the generation of the preliminary product information.

[0128] In this embodiment, by acquiring the circle-product guidance parameters used to implement circle-product analysis, the product categories and conceptual attributes are sorted to obtain the sorting information of the conceptual attributes. Then, based on the sorting information of the conceptual attributes and the circle-product guidance parameters, the focus concept attributes used to implement circle-product analysis can be determined from the conceptual attributes. And based on the associated product information corresponding to the focus concept attributes, the preliminary product information can be determined. This effectively ensures the accuracy and reliability of determining the preliminary product information, and also improves the accuracy of determining the product information when determining the product information based on the preliminary product information.

[0129] Figure 5 is a schematic diagram of a method for generating product information provided in an embodiment of this disclosure; as shown in Figure 5, the process involves requesting an interaction interface in the interactive interface, obtaining conceptual attributes in the interactive interface, obtaining preliminary product information, and then obtaining product information.

[0130] This embodiment provides a method for generating product information. The execution subject of this method is a product information generating device. Specifically, the product information generating device can be implemented as software or a combination of software and hardware. When the product information generating device is implemented as hardware, it can be various electronic devices capable of generating product information, including but not limited to personal computers, servers, databases, etc. When the product information generating device is implemented as software, it can be installed in the aforementioned electronic devices. Based on the above-mentioned product information generating device, the product information generating operation can be realized. Specifically, the product information generating method can include:

[0131] Displays an interactive interface for generating product information, including a request interface.

[0132] When a user has a need to generate product information, the product information generation device can display an interactive interface for generating product information. The interactive interface can include a request interaction interface, which can be implemented as a text input interface for users to perform interactive operations.

[0133] In response to an interactive operation input by a user through a request interaction interface, a request to generate product information is obtained. The generation request includes at least: a category description corresponding to the product information and at least one knowledge item description.

[0134] When a user has a need to generate product information, the user can input an interactive operation through the request interaction interface. Based on the interactive operation, the user can obtain the product information generation request. For example, the user can input an interactive operation in the request interaction interface and obtain the request "Help me design a novel, fun, and interesting lollipop suitable for children and students, with zero sugar and zero additives, requiring health and no burden". In this way, the product information generation request can be obtained reliably.

[0135] Displays product categories that match the product information, as well as the conceptual attributes of each knowledge item under each product category. The product categories and conceptual attributes are determined by analyzing and processing the category description and at least one knowledge item description in the generation request.

[0136] After receiving a request to generate product information, the request can be analyzed and processed to obtain product categories and conceptual attributes under each knowledge item within those product categories. These product categories and their conceptual attributes can then be displayed. For example, if the request is "Design a novel, fun, and interesting lollipop suitable for children and students, with zero sugar and zero additives, requiring health and no burden," analysis can yield product categories (flavors, functions, ingredients, etc.) and conceptual attributes under each knowledge item within those categories. When the product category is the ingredient category, the obtained conceptual attributes might include "cod"; when the product category is the function category, the obtained conceptual attributes might include "zero additives" and "healthy." The display interface can not only show product categories and conceptual attributes but also other relevant information, such as packaging design information, scenario information, and target audience. Those skilled in the art can flexibly configure or adjust the content of the display interface according to specific application scenarios or requirements.

[0137] Displays preliminary product information corresponding to the request. This preliminary product information is obtained through product category and conceptual attribute analysis. The preliminary product information includes at least: recommended products corresponding to the request and the user profiles of the recommended products.

[0138] The preliminary product information can include one or more recommended products, and the name, monthly sales and comparison information of the recommended products can be displayed on the display interface. Furthermore, the product category and conceptual attributes corresponding to the generated request can be displayed at the top of the preliminary product information.

[0139] Displays product information corresponding to the request. The product information is determined based on the analysis and processing of preliminary product information. The product information includes at least: product description information and product promotional copy.

[0140] After obtaining preliminary product information, the product information corresponding to the request can be determined based on this information, and the product information can be displayed. The displayed product information may include at least the product description and promotional copy. The product description may include at least one of the following: a description of the product's innovative flavor, a description of the product's carefully selected ingredients, a description of the product's unique processing techniques, etc. The promotional copy is used to promote the production and sales of the product, thus effectively ensuring the accuracy and reliability of the determined product information.

[0141] In this embodiment, the specific implementation methods and effects of each step are similar to those of steps S201-S204 in the embodiments shown in Figures 2-4. For details, please refer to the above descriptions, which will not be repeated here.

[0142] In addition, the sample identification method in this embodiment may also include the method shown in the embodiments of Figures 2-4 above. For parts not described in detail in this embodiment, please refer to the relevant descriptions of the embodiments shown in Figures 2-4. The execution process and technical effects of this technical solution are described in the embodiments shown in Figures 2-4, and will not be repeated here.

[0143] In practical application, referring to Figure 6, this application embodiment provides a method for generating product concepts. This method can help merchants quickly generate product concepts during the creative stage and solve the shortcomings of traditional product concept creation processes in terms of creativity and resource input. The shortcomings in the creativity dimension include: 1) the number of ideas is limited due to the number of participants and the time available for co-creation; 2) the quality of product concept generation cannot be guaranteed due to the limitations of the participants' creativity and expression. The shortcomings in the resource input dimension include: 1) the time from consumer insight to the final refinement of the product concept is relatively long; 2) the cost of human resources and resources is relatively high.

[0144] As shown in Figure 6, the process includes parsing the user's input request into knowledge items; matching the parsed results with knowledge points; performing data insight operations using the knowledge points to obtain data insight results; knowledge point completion operations; and generating product concepts using a large language model. This implements a workflow from input parsing, knowledge point matching, data insight, information completion to product concept generation.

[0145] Specifically, the method may include the following steps:

[0146] Step 1: Obtain the product concept generation request. Use the Large Language Model (LLM) to parse the user-input generation request and obtain the category description corresponding to the product concept and at least one knowledge item description included in the generation request.

[0147] The obtained category description and at least one knowledge item description can be obtained by performing reasoning operations on the user input generation request through a large language model (LLM). Specifically, the category description is used to determine the appropriate category corresponding to the product concept, and the knowledge item description is used to determine the knowledge item corresponding to the appropriate category. For example, when the appropriate category is "food", the knowledge item corresponding to the appropriate category may include at least one of the following: flavor, function, and scenario; when the appropriate category is "clothing", the knowledge item corresponding to the appropriate category may include at least one of the following: style and design.

[0148] Step 2: Based on the category description and at least one knowledge item description in the generation request, determine the product category that matches the generation request, and the knowledge points under each knowledge item of the product category (corresponding to the concept attributes in the above embodiments).

[0149] In some instances, the knowledge points under each knowledge item can be obtained through knowledge point matching operations using a preset knowledge base. In this case, determining the product category and the knowledge points under each knowledge item that match the product concept based on the category description and at least one knowledge item description in the generation request can include: obtaining a preset knowledge base, which stores multiple standard product categories, standard knowledge items under each standard product category, and standard knowledge points under each standard knowledge item; and then performing knowledge point matching operations in the preset knowledge base based on the category description and at least one knowledge item description in the generation request, thereby obtaining the product category and the knowledge points under each knowledge item that match the generation request.

[0150] In other instances, synonyms can be used to determine the product category and the knowledge points under each knowledge item within the product category that match the product concept. In this case, the knowledge points under each knowledge item can be obtained through a knowledge point matching operation using a preset knowledge base. Specifically, based on the category description and at least one knowledge item description in the generation request, determining the product category and the knowledge points under each knowledge item within the product category that match the product concept can include: obtaining a preset knowledge base, which stores multiple standard product categories, standard knowledge items under each standard product category, and standard knowledge points under each standard knowledge item; then, based on the category description and at least one knowledge item description in the generation request, determining the description category and description knowledge points corresponding to the generation request; determining the similar categories corresponding to the description categories and the similar knowledge points corresponding to the description knowledge points; and performing a knowledge point matching operation in the preset knowledge base based on the description categories, similar categories, description knowledge points, and similar knowledge points, thereby obtaining the product category and the knowledge points under each knowledge item within the product category that match the generation request.

[0151] In some other instances, when no matching product category or knowledge points under each knowledge item of a product category can be found in the preset knowledge base, in order to accurately generate product concepts, a large language model can be used to infer and obtain the matching product category and knowledge points under each knowledge item of the product category. In this case, the method in this embodiment may include: when no matching knowledge points corresponding to the generation request can be found in the preset knowledge base, a large language model can be obtained, and then the large language model can be used to perform reasoning operations on the generation request to obtain the matching product category and knowledge points under each knowledge item of the product category.

[0152] Step 3: Perform knowledge point supplementation operations on the knowledge points under each obtained knowledge item to obtain fill knowledge points, and determine the obtained knowledge points and fill knowledge points as the target knowledge points corresponding to the generation request.

[0153] When the knowledge points obtained under each knowledge item do not meet the user's needs, user-defined knowledge points can be added. This involves displaying the human-computer interaction interface and obtaining the knowledge point addition operation input by the user in the human-computer interaction interface. Based on the knowledge point addition operation, the knowledge points to be filled are obtained. Then, the knowledge points obtained in the above steps and the filled knowledge points are determined as the target knowledge points corresponding to the generation request. This can preserve the user's personalized understanding.

[0154] Step 4: Normalize the target knowledge points under each knowledge item in the product category to obtain normalized knowledge points.

[0155] Step 5: Utilize the various knowledge items and normalized knowledge points under the product category to perform data insight operations and obtain data insight results.

[0156] Specifically, after obtaining the various knowledge items and normalized knowledge points under the product category, a pre-trained large language model can be obtained first. Then, the various knowledge items and normalized knowledge points can be input into the large language model for data insight operations, thereby obtaining data insight results. These data insight results are used to implement circle product analysis operations.

[0157] In other instances, to accurately obtain data insight results, normalized knowledge points can be sorted during the data insight process. This involves first acquiring historical data for product categories and corresponding normalized knowledge points. Historical product data can include on-site and / or off-site historical data. The growth rate of total transaction volume for each normalized knowledge point is then determined using this historical data. The normalized knowledge points are then sorted in reverse order using this growth rate to obtain the ranking information for concept attributes. This ranking information, along with preset product-oriented parameters, is used to determine the knowledge points to focus on for product-oriented analysis. These preset parameters can include at least one of the following: sales-oriented parameters, innovation-oriented parameters, etc. The parameters can be applied to the quantiles of the selected knowledge points. Then, based on the quantiles and the ranking information of the concept attributes, the knowledge points to be used for circle product analysis can be determined. That is, the top N knowledge points can be queried and calculated. Then, based on the associated product information corresponding to the knowledge points, the preliminary product information can be determined. 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, thereby obtaining the preliminary product information and the corresponding association reasons. The preliminary product information can include at least: the recommended products corresponding to the generated request, the user profile corresponding to the recommended products, etc. In this way, it is possible to distinguish based on the quantiles in all knowledge points and obtain different data insight results.

[0158] For example, in the food category, you can select the top three flavors with the highest sales volume or sales performance to list, such as peach-flavored drinks, apple-flavored drinks, and strawberry-flavored drinks. The initial product information can include the target audience profiles for each of these flavors. In the clothing category, you can select the top three styles of clothing with high innovation, such as black casual wear, black formal wear, and white casual wear. The initial product information can include the target audience profiles for each of these flavors.

[0159] Step 6: Based on the data insight results, generate a product concept corresponding to the generation request. This product concept shall include at least: product description information, product promotion copy, and product audience profile description.

[0160] After obtaining data insights, a complete product concept can be derived from them. Specifically, the semantic organization capabilities of a large language model can be used to expand the final product concept, that is, to reason the data insights into a complete descriptive statement. This 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 audience profiles, etc. Then, the product concept can be used to guide the product generation or manufacturing operations and improve the effectiveness of product promotion.

[0161] Because large language models offer the following advantages—rapidly organizing necessary information and enabling divergent information association (AI learns far more knowledge than an individual)—they can automatically and interactively output product concepts during data reasoning, providing merchants with a new, agile, and efficient experience. This product concept generation method implements a process from input parsing, knowledge point matching, data insight, and information completion to product concept generation, thereby providing users with the ability to creatively generate product concepts. Specifically, in the knowledge point matching stage, a large language model with multi-layered semantic embedding can identify multi-dimensional features related to the user's input intent. These features are then used for contextual understanding through a generative decoder, ensuring that the rich information in the generated request is fully mined and presented. Simultaneously, the integration of dynamic knowledge can be promoted by mining internal and external data based on a pre-set neural network model. This allows for the stable acquisition of product categories and at least one knowledge point within each category. Product concepts can then be generated based on this knowledge point, ensuring the accuracy and reliability of the generated product concepts. In the data insight phase, knowledge points can be normalized and ranked using a comparative learning model. Further in-depth analysis of user interests and market trends yields a more accurate list of top-ranked knowledge points, popular products, and target user profiles. Furthermore, by capturing e-commerce-specific user behavior characteristics (purchase behavior, add-to-cart behavior, favorites behavior), product categories, various knowledge points within those categories, and market trends, product concepts can be generated based on this captured information. This not only meets the generation requirements of product concepts but also endows them with higher innovation capabilities and market adaptability, thus providing e-commerce platforms with a unique competitive advantage. This achieves a virtuous cycle from product concept generation to market feedback, promoting rapid product iteration and updates.

[0162] The technical solution provided in this application embodiment uses a large language model to efficiently and automatically generate product concepts. This large language model can be independently trained based on domain-specific data, which improves the reliability of product concept generation in specific domains (e.g., e-commerce) and industries, reducing the "illusion" phenomenon. This not only makes the generated product concepts more reasonable and accurate, aligning with industry trends, but also makes the product concept generation process more divergent, yielding more creative and inspired product concepts. Furthermore, during the product concept generation process, users can supplement information as needed, making the product concept generation operation more flexible, convenient, accurate, and reliable. This significantly improves the quality and efficiency of product concepts, further enhancing the practicality of the method.

[0163] Figure 7 is a schematic diagram of a product information generation device provided in an embodiment of this disclosure; referring to Figure 7, this embodiment provides a product information generation device, which is configured to execute the product information generation method shown in Figure 2 above. Specifically, the product information generation device may include:

[0164] The first acquisition module 11 is configured to acquire a generation request for product information. The generation request includes at least: a category description corresponding to the product information and at least one knowledge item description.

[0165] The first determining module 12 is configured to determine the product category and the conceptual attributes under each knowledge item in the product category that are compatible with the generating request, based on the category description and at least one knowledge item description in the generating request.

[0166] The first processing module 13 is configured to perform product segmentation analysis based on product categories and conceptual attributes to obtain preliminary product information. The preliminary product information includes at least: recommended products corresponding to the generation request and the user profile corresponding to the recommended products.

[0167] The first processing module 13 is configured to generate product information corresponding to the generation request based on the preliminary product information. The product information includes at least: product description information and product promotion copy.

[0168] In some instances, when the first determining module 12 determines the product category and the conceptual attributes under each knowledge item in 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 determining module 12 is configured to perform the following: obtain 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; adapt 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 conceptual attributes under each knowledge item in the product category that are compatible with the generation request.

[0169] In some instances, when the first determining 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 the product category and the conceptual attributes under each knowledge item of the product category that are adapted to the generation request, the first determining module 12 is configured to perform the following: based on the category description and at least one knowledge item description in the generation request, determine the associated category of the product information and at least one associated knowledge item under the associated category; and match the associated category and at least one associated knowledge item based on the preset knowledge base to obtain the product category and the conceptual attributes under each knowledge item of the product category that are adapted to the generation request.

[0170] In some instances, when the first determining module 12 determines the 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 determining module 12 is configured to perform: determining the 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 the 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.

[0171] In some instances, when the first determining module 12 determines the 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 determining module 12 is configured to perform: determining the 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 approximate category corresponding to the description category and the approximate knowledge item corresponding to the description knowledge item; determining the description category and the approximate category as the associated category 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.

[0172] In some instances, when the first determining module 12 determines the product category and the conceptual attributes under each knowledge item in 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 determining module 12 is configured to perform: 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; and using the large language model to parse the category description and at least one knowledge item description in the generation request to obtain the product category and the conceptual attributes under each knowledge item in the product category that are compatible with the generation request.

[0173] In some instances, before obtaining the large language model used for analyzing and processing the generated request, the first processing module 13 in this embodiment is configured to perform the following steps: when adapting the category description and at least one knowledge item description in the generated request based on a preset knowledge base, and no product category or conceptual attributes under each knowledge item of the product category are obtained that are adapted to the generated request, obtaining the large language model used for analyzing and processing the generated request is permitted; when adapting the category description and at least one knowledge item description in the generated request based on a preset knowledge base, and a product category or conceptual attributes under each knowledge item of the product category are obtained that are adapted to the generated request, obtaining the large language model used for analyzing and processing the generated request is prohibited.

[0174] In some instances, the first acquisition module 11, the first determination module 12, and the first processing module 13 in this embodiment are configured to perform the following steps:

[0175] The first acquisition module 11 is configured to acquire attribute supplementation requests;

[0176] The first determining module 12 is configured to determine the supplementary conceptual attributes corresponding to the generation request based on the attribute supplementation request;

[0177] The first processing module 13 is configured to determine the supplementary conceptual attributes and the conceptual attributes determined by the large language model as the target conceptual attributes under each knowledge item of the product category.

[0178] In some instances, when the first processing module 13 performs product circle analysis based on product categories and conceptual attributes to obtain preliminary product information, the first processing module 13 is configured to perform the following: obtain product circle guidance parameters for implementing product circle analysis, the product circle guidance parameters including at least one of the following: sales guidance parameters, innovation guidance parameters; sort the product categories and conceptual attributes to obtain sorting information of the conceptual attributes; based on the sorting information of the conceptual attributes and the product circle guidance parameters, determine the concept attributes of interest for implementing product circle analysis in the conceptual attributes; and determine the preliminary product information based on the associated product information corresponding to the concept attributes of interest.

[0179] In some instances, when the first processing module 13 sorts the product categories and conceptual attributes to obtain the sorting information of the conceptual attributes, the first processing module 13 is configured to perform: obtaining historical product data corresponding to the product categories and conceptual attributes; determining the growth rate of the total transaction amount of the products corresponding to the conceptual attributes based on the historical product data; and sorting the product categories and conceptual attributes in reverse order based on the growth rate of the total transaction amount of the products to obtain the sorting information of the conceptual attributes.

[0180] In some instances, when the first processing module 13 determines the concept attributes of interest for implementing circle quality analysis based on the ranking information of concept attributes and circle quality guidance parameters, the first processing module 13 is configured to perform the following: determine the quantitative information corresponding to the concept attributes of interest based on the circle quality guidance parameters; obtain the preceding concept attributes that satisfy the quantitative information based on the ranking information of concept attributes; and determine the preceding concept attributes as the concept attributes of interest for implementing circle quality analysis.

[0181] In some instances, when the first processing module 13 determines preliminary product information based on the associated product information corresponding to the concept attribute of interest, the first processing module 13 is configured to perform: 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 concept attribute of interest to obtain preliminary product information.

[0182] In some instances, the first processing module 13 in this embodiment is configured to perform the following steps: during the process of divergent processing of the associated product information corresponding to the concept attributes of interest using a large language model, generating a reason for generation corresponding to the preliminary product information; and displaying the reason for generation and the preliminary product information in association.

[0183] The device shown in Figure 7 can execute the methods of the embodiments shown in Figures 2-4 and 6. For parts not described in detail in this embodiment, please refer to the relevant descriptions of the embodiments shown in Figures 2-4 and 6. The execution process and technical effects of this technical solution are described in the embodiments shown in Figures 2-4 and 6, and will not be repeated here.

[0184] In one possible design, the structure of the product information generation device shown in Figure 7 can be implemented as an electronic device, which can be a controller, personal computer, server, or other various devices. As shown in Figure 8, the electronic device may include a first processor 21 and a first memory 22. The first memory 22 is configured to store a program for the corresponding electronic device to execute the product information generation method provided in the embodiments shown in Figures 2-4 and 6, and the first processor 21 is configured to execute the program stored in the first memory 22.

[0185] The program includes one or more computer instructions, wherein when executed by the first processor 21, the one or more computer instructions can perform the following steps: obtaining a request to generate product information, the request including at least: a category description corresponding to the product information and at least one knowledge item description; determining, based on the category description and at least one knowledge item description in the request, a product category and conceptual attributes under each knowledge item of the product category that are compatible with the request; performing product segmentation analysis based on the product category and conceptual attributes to obtain preliminary product information, the preliminary product information including at least: recommended products corresponding to the request and a user profile corresponding to the recommended products; and generating product information corresponding to the request based on the preliminary product information, the product information including at least: product description information and product promotion copy.

[0186] Furthermore, the first processor 21 is also configured to perform all or part of the steps in the embodiments shown in Figures 2-4 and 6 above.

[0187] The structure of the electronic device may also include a first communication interface 23, which is configured to communicate between the electronic device and other devices or communication networks.

[0188] In addition, this disclosure provides a computer storage medium configured to store computer software instructions used by an electronic device, which includes programs for executing the product information generation method in the embodiments shown in Figures 2-4 and 6 above.

[0189] Furthermore, this disclosure provides a computer program product, including: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause one or more processors to perform the steps in the product information generation method in the method embodiments shown in Figures 2-4 and 6 above.

[0190] Figure 9 is a schematic diagram of a product information generation device provided in an embodiment of this disclosure; referring to Figure 9, this embodiment provides a product information generation device, which is configured to execute the product information generation method shown in Figure 5 above. Specifically, the product information generation device may include:

[0191] The second display module 31 is configured to display an interactive interface for generating product information, including a request interaction interface.

[0192] The second processing module 32 is configured to respond to the user's interactive operation input through the request interaction interface to obtain a request to generate product information. The request to generate product information includes at least: a category description corresponding to the product information and at least one knowledge item description.

[0193] The second display module 31 is configured to display product categories adapted to product information and conceptual attributes under each knowledge item of the product category. The product categories and conceptual attributes are determined by analyzing and processing the category description and at least one knowledge item description in the generation request.

[0194] The second display module 31 is configured to display preliminary product information corresponding to the generation request. The preliminary product information is obtained through product category and conceptual attribute analysis. The preliminary product information includes at least: recommended products corresponding to the generation request and the user profile corresponding to the recommended products.

[0195] The second display module 31 is configured to display product information corresponding to the generation request. The product information is determined based on the analysis and processing of preliminary product information. The product information includes at least: product description information and product promotion copy.

[0196] The apparatus shown in Figure 9 can perform the method of the embodiments shown in Figures 5-6. For parts not described in detail in this embodiment, please refer to the relevant descriptions of the embodiments shown in Figures 5-6. The execution process and technical effects of this technical solution are described in the embodiments shown in Figures 5-6, and will not be repeated here.

[0197] In one possible design, the structure of the product information generation device shown in Figure 9 can be implemented as an electronic device, which can be a controller, personal computer, server, or other various devices. As shown in Figure 10, the electronic device may include a second processor 41 and a second memory 42. The second memory 42 is configured to store a program for the corresponding electronic device to execute the product information generation method provided in the embodiments shown in Figures 5-6, and the second processor 41 is configured to execute the program stored in the second memory 42.

[0198] The program includes one or more computer instructions, wherein when executed by the second processor 41, the one or more computer instructions can perform the following steps: displaying an interactive interface for generating product information, the interactive interface including a request interaction interface; responding to the user's interactive operation input through the request interaction interface, obtaining a request to generate product information, the generation request including at least: a category description corresponding to the product information and at least one knowledge item description; displaying a product category adapted to the product information and conceptual attributes under each knowledge item of the product category, the product category and conceptual attributes being 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, the preliminary product information being obtained based on product category and conceptual attributes through product segmentation analysis; wherein the preliminary product information includes at least: a recommended product corresponding to the generation request and a user profile corresponding to the recommended product; displaying product information corresponding to the generation request, the product information being determined based on the preliminary product information through analysis and processing, wherein the product information includes at least: product description information and product promotion copy.

[0199] Furthermore, the second processor 41 is also configured to perform all or part of the steps in the embodiments shown in Figures 5-6 above.

[0200] The structure of the electronic device may also include a second communication interface 43, which is configured to communicate with other devices or communication networks.

[0201] In addition, this disclosure provides a computer storage medium configured to store computer software instructions used by an electronic device, which includes a program for executing the product information generation method in the embodiments shown in Figures 5-6 above.

[0202] Furthermore, this disclosure provides a computer program product, including: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause one or more processors to perform the steps in the product information generation method in the method embodiments shown in Figures 5-6 above.

[0203] 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, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0204] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0205] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of a necessary general-purpose hardware platform, or by a combination of hardware and software. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a computer product. This disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0206] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable device, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0207] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams. These computer program instructions may also be loaded onto a computer or other programmable device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable device, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent memory in a computer-readable medium, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0208] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0209] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit them. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure. Industrial applicability

[0210] The product information generation method, apparatus, device, and computer program product provided in this embodiment obtain a product information generation request, and based on the category description and at least one knowledge item description in the generation request, determine the product category and the conceptual attributes under each knowledge item of the product category that are compatible with the generation request; then, based on the product category and the conceptual attributes, perform product segmentation analysis to obtain preliminary product information, and generate product information corresponding to the generation request based on the preliminary product information. This can efficiently and automatically realize the product information generation operation, which can not only reduce the human and material resources required for product information generation, but also greatly improve the quality and efficiency of product information generation, thereby effectively ensuring the practicality of the method.

Claims

1. A method for generating product information, comprising: A request to generate product information, wherein the request includes at least: 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, determine the product category that matches the generation request and the conceptual attributes under each knowledge item of the product category; Based on the product category and the conceptual attributes, a product circle analysis is performed to obtain preliminary product information. The preliminary product information includes at least: recommended products corresponding to the generation request and the user profile corresponding to the recommended products. Based on the preliminary product information, product information corresponding to the generation request is generated. The product information includes at least: product description information and product promotion copy.

2. The method according to claim 1, wherein, Based on the category description and at least one knowledge item description in the generation request, determine the product category that matches the generation request, and the conceptual attributes under each knowledge item of the product category, including: Obtain 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; Based on the preset knowledge base, the category description and at least one knowledge item description in the generation request are adapted to obtain the product category and the conceptual attributes of each knowledge item under the product category that are adapted to the generation request.

3. The method according to claim 2, wherein, 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 product category adapted to the generation request, and the conceptual attributes under each knowledge item of the product category, including: Based on the category description and at least one knowledge item description in the generated request, determine the associated category of the product information and at least one associated knowledge item under the associated category; Based on the preset knowledge base, the associated categories and at least one associated knowledge item are matched to obtain the product category that matches the generation request, and the conceptual attributes of each knowledge item under the product category.

4. The method according to claim 3, wherein, Based on the category description and at least one knowledge item description in the generation request, determine the associated category of the product information and at least one associated knowledge item under the associated category, including: Based on the category description and at least one knowledge item description in the generated request, determine the description category corresponding to the product information and at least one description knowledge item under the description category; The description category is determined as the 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, wherein, Based on the category description and at least one knowledge item description in the generation request, determine the associated category of the product information and at least one associated knowledge item under the associated category, including: Based on the category description and at least one knowledge item description in the generated request, determine the description category corresponding to the product information and at least one description knowledge item under the description category; Determine the approximate categories corresponding to the described categories, and the approximate knowledge items corresponding to the described knowledge items; The descriptive category and the approximate category are determined as the associated category of the product information, and the at least one descriptive knowledge item and the approximate knowledge item are determined as at least one associated knowledge item under the associated category.

6. The method according to claim 2, wherein, Based on the category description and at least one knowledge item description in the generation request, determine the product category that matches the generation request, and the conceptual attributes under each knowledge item of the product category, including: A large language model is obtained for analyzing and processing the generated 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 generated request to obtain the product category that matches the generated request and the conceptual attributes of each knowledge item under the product category.

7. The method according to claim 6, wherein, Before obtaining a large language model for analyzing and processing the generated 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 product category or conceptual attribute under each knowledge item under the product category is obtained that is adapted to the generation request, a large language model for analyzing and processing the generation request is allowed. 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 and the conceptual attributes under each knowledge item of the product category that are adapted to the generation request, the acquisition of the large language model used to analyze and process the generation request is prohibited.

8. The method according to claim 7, wherein, The method further includes: Request additional attributes; Based on the attribute supplementation request, determine the supplementary concept attributes corresponding to the generation request; The supplementary conceptual attributes and the conceptual attributes determined using the large language model are used to determine the target conceptual attributes for each knowledge item under the product category.

9. The method according to any one of claims 1-8, wherein, Based on the product category and the conceptual attributes, a product segmentation analysis is performed to obtain preliminary product information, including: Obtain product-oriented parameters for implementing product-oriented analysis, wherein the product-oriented parameters include at least one of the following: sales-oriented parameters and innovation-oriented parameters; The product categories and the conceptual attributes are sorted to obtain the sorting information of the conceptual attributes; Based on the sorting information of the concept attributes and the circle product guidance parameters, the concept attributes of interest used to realize circle product analysis are determined from the concept attributes; Based on the associated product information corresponding to the aforementioned concept attributes, the preliminary product information is determined.

10. The method according to claim 9, wherein, Sort the product categories and the conceptual attributes to obtain the sorting information of the conceptual attributes, including: Obtain historical product data corresponding to the product category and the aforementioned conceptual attributes; Based on the historical data of the commodities, determine the growth rate of the total transaction volume of the commodities corresponding to the conceptual attributes; The product categories and conceptual attributes are sorted in reverse order based on the growth rate of the total transaction volume of the products to obtain the sorting information of the conceptual attributes.

11. The method according to claim 9, wherein, Based on the ranking information of the concept attributes and the circle-oriented parameters, the concept attributes of interest used to achieve circle-oriented analysis are determined from the concept attributes, including: Based on the circle-oriented parameters, determine the quantity information corresponding to the attention concept attributes; Based on the sorting information of the concept attributes, obtain the preceding concept attributes that satisfy the quantity information; The aforementioned front concept attributes are defined as the concept attributes of interest used to implement circle product analysis.

12. The method according to claim 9, wherein, Based on the associated product information corresponding to the aforementioned concept attributes, preliminary product information is determined, including: A large language model is obtained, wherein the large language model is obtained by training based on sample data; The large language model is used to diverge the associated product information corresponding to the interest concept attribute to obtain preliminary product information.

13. The method according to claim 12, wherein, The method further includes: In the process of using the large language model to diverge the associated product information corresponding to the concept attributes of interest, a reason for generation corresponding to the preliminary product information is generated. The reason for generation and the preliminary information of the product are displayed together.

14. A method for generating product information, comprising: Display an interactive interface for generating product information, the interactive interface including a request interaction interface; In response to an interactive operation input by a user through the request interaction interface, a request to generate product information is obtained, wherein the generation request includes at least: a category description corresponding to the product information and at least one knowledge item description; Displays product categories that match the product information, as well as the conceptual attributes of each knowledge item under the product category. The product categories and the conceptual attributes are determined by analyzing and processing the category description and at least one knowledge item description in the generation request. The system displays preliminary product information corresponding to the generation request. This preliminary product information is obtained through product segmentation analysis based on the product category and the conceptual attributes. The preliminary product information includes at least: recommended products corresponding to the generation request and a user profile of the recommended products. Display product information corresponding to the generated request. The product information is determined based on the analysis and processing of the preliminary product information. The product information includes at least: product description information and product promotional copy.

15. A device for generating product information, comprising: The first acquisition module is configured to acquire a generation request for product information, wherein the generation request includes at least: a category description corresponding to the product information and at least one knowledge item description; The first determining module is configured to determine, based on the category description and at least one knowledge item description in the generation request, a product category that matches the generation request and the conceptual attributes under each knowledge item of the product category. The first processing module is configured to perform product segmentation analysis based on the product category and the conceptual attributes to obtain preliminary product information. The preliminary product information includes at least: recommended products corresponding to the generation request and the user profile corresponding to the recommended products. The first processing module is configured to generate product information corresponding to the generation request based on the preliminary product information. The product information includes at least: product description information and product promotion copy.

16. A device for generating product information, comprising: The second display module is configured to display an interactive interface for generating product information, the interactive interface including a request interaction interface; The second processing module is configured to respond to the user's interactive operation input through the request interaction interface to obtain a request to generate product information. The request to generate 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 configured to display product categories adapted to the product information and conceptual attributes under each knowledge item of the product category. The product categories and conceptual attributes 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 configured to display preliminary product information corresponding to the generation request. The preliminary product information is obtained through product segmentation analysis based on the product category and the conceptual attributes. The preliminary product information includes at least: recommended products corresponding to the generation request and the user profile corresponding to the recommended products. The second display module is configured to display product information corresponding to the generation request. The product information is determined based on the analysis and processing of the preliminary product information, and includes at least: product description information and product promotional copy.

17. An electronic device comprising: A memory, a processor; wherein the memory is configured 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 configured to store a computer program that, when executed by a computer, implements the method of any one of claims 1-14.

19. A computer program product comprising: A computer program, when executed by a processor of an electronic device, causes the processor to perform the steps of the method of any one of claims 1-14.

Images