Enterprise information processing method and device based on large language model, equipment and storage medium

Abstract

The invention relates to the technical field of enterprise analysis, in particular to an enterprise information processing method and device based on a large language model, equipment and a storage medium, and the method comprises the steps: obtaining a target page group of a to-be-analyzed enterprise; performing data cleaning on a parent page and a child page of the same target page group to obtain a page source code group; performing classification processing on the page source code block through a first preset model to obtain a first classification source code block and a second classification source code block; constructing a basic product tree based on the first classification source code group through a second preset model; performing supplementary construction on the basic product tree based on the second classification source code group through a third preset model to obtain an enterprise product tree; and obtaining enterprise product information of the to-be-analyzed enterprise based on the enterprise product tree. The problem that enterprise product information is difficult to obtain can be solved, so that the blank of enterprise product library resources on the market is filled, and the beneficial effects of enabling enterprises, industries and industry analysis are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of enterprise product analysis, and in particular to an enterprise information processing method, apparatus, device and storage medium based on a large language model. Background Art

[0002] Industry research and industrial chain analysis conducted by financial and government-related institutions are of great significance in promoting economic development, guiding policy formulation, optimizing resource allocation, enhancing international competitiveness, and serving the real economy. The enterprise product library is crucial for industry research and industrial chain analysis. It is used to evaluate the diversity and coverage of enterprise products, provide researchers with comprehensive enterprise knowledge, and help researchers deeply analyze the potential and development prospects of enterprises, thereby providing more detailed enterprise information for government investment promotion.

[0003] It can be seen that the construction of an enterprise product library is crucial for industry research and industry chain analysis. Among them, building a product tree is one of the important means of analyzing enterprise information. By building a product tree, the hierarchical relationship and classification between different products in the industry can be clearly displayed, which helps to understand the product lines and product categories of the entire industry, so as to better grasp the market trends and competitive situation. However, there are difficulties in the process of building a product tree. From a macro perspective, the resistance comes from the following two aspects: 1. Information is not disclosed in a centralized manner: Whether it is a listed or unlisted company, there is a lack of a unified organization requiring them to disclose detailed product information, resulting in scattered data that is difficult to integrate.

[0004] 2. Diverse official website styles: The designs of corporate official websites vary greatly, making it difficult to extract all product information through unified crawler technology.

[0005] From a technical perspective, building an enterprise product library also faces many obstacles: 1. Limitations of general crawlers: Existing general crawlers are difficult to accurately extract product information directly from complex web page structures and require further analysis and processing based on the web page text level.

[0006] 2. Redundancy of web page text information: When extracting web page text, it often contains a large amount of content that is irrelevant to product information, such as navigation bars, footers, etc. These redundant information not only increases the difficulty of data processing, but may also interfere with the accurate extraction of information.

[0007] 3. Difficulty in locating product pages: In the process of crawling sub-pages step by step starting from the homepage of the company's official website, only a small part of the sub-pages contain the required valid product information. How to accurately locate the page containing valid product information is a tricky problem.

[0008] 4. Limitations of large language models: Although large language models make it possible to generate structured enterprise information, research has shown that some LLMs (Large Language Models) are sensitive to prompts and have the ability to output structured results, but their corresponding understanding and analysis capabilities are insufficient, making it difficult to obtain corresponding structured results simply through prompts.

[0009] Based on this, how to solve the problem of building a product tree corresponding to each enterprise to be analyzed, and finally summarize the enterprise product information, so as to solve the problem of difficulty in building an enterprise product library, fill the gap in enterprise product library resources on the market, and enable enterprise, industry and industry analysis, is a technical problem that needs to be solved urgently. Summary of the invention

[0010] In order to overcome the shortcomings of the prior art, the present application provides enterprise information processing methods, devices, equipment and storage media based on a large language model to solve the problem of difficulty in building an enterprise product library, fill the gap in enterprise product library resources on the market, and achieve the beneficial effect of enabling enterprise, industry and industry analysis.

[0011] The technical solution adopted by this application to solve its technical problem is: In a first aspect, the present application provides an enterprise information processing method based on a large language model, the method comprising: Obtain a target page group of the enterprise to be analyzed; one target page group includes a parent page and a child page; Performing data cleaning on the parent page and the child page of the same target page group to obtain a page source code group after data cleaning, wherein the page source code group includes page source codes corresponding to all parent pages and page source codes corresponding to all child pages; Inputting the page source code group into a first preset model, so as to classify the page source code group through the first preset model to obtain a first classification source code group and a second classification source code group, wherein the first classification source code group is a combination of all page source codes containing product category information, and the second classification source code group is a combination of all page source codes containing product detailed information; Inputting the first classification source code group into a second preset model, so as to construct a basic product tree based on the first classification source code group through the second preset model; Inputting the second classification source code group and the basic product tree into a third preset model, so as to supplement and construct the basic product tree based on the second classification source code group through the third preset model to obtain an enterprise product tree; The enterprise product information of the enterprise to be analyzed is obtained based on the enterprise product tree.

[0012] In a second aspect, the present application provides an enterprise information processing device based on a large language model, comprising: A target page group acquisition module is used to acquire a target page group of the enterprise to be analyzed; one target page group includes a parent page and a child page; A page cleaning and source code acquisition module, used to clean the parent page and the child page of the same target page group, and obtain a page source code group after data cleaning, wherein the page source code group includes page source codes corresponding to all parent pages and page source codes corresponding to all child pages; a page source code group classification module, used for inputting the page source code group into a first preset model, so as to classify the page source code group through the first preset model to obtain a first classification source code group and a second classification source code group, wherein the first classification source code group is a combination of all page source codes containing product category information, and the second classification source code group is a combination of all page source codes containing product detailed information; A basic product tree construction module, used for inputting the first classification source code group into a second preset model, so as to construct a basic product tree based on the first classification source code group through the second preset model; An enterprise product tree construction module, used for inputting the second classification source code group and the basic product tree into a third preset model, so as to supplement and construct the basic product tree based on the second classification source code group through the third preset model to obtain an enterprise product tree; The product information acquisition module is used to obtain the enterprise product information of the enterprise to be analyzed based on the enterprise product tree.

[0013] In a third aspect, the present application provides an electronic device, characterized in that it includes: one or more processors; one or more memories; and one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, and the one or more computer programs include instructions, which, when executed by the one or more processors, enable the electronic device to perform the above method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, characterized in that a program or instruction is stored in the storage medium, and when the program or instruction is executed, the above method is implemented.

[0015] This application crawls a target page on an enterprise's official website through crawler technology, and performs data cleaning on the crawled page to reduce data redundancy. The crawled page source code group is classified by the first preset model, so that the first classification source code group and the second classification source code group that are useful for generating enterprise product information can be retained, and other page source code groups that are not useful for generating enterprise product information can be eliminated, thereby improving the accuracy of subsequent enterprise product information extraction and reducing data redundancy. After the page source code group is classified, the first classification source code group is parsed by the second preset model to generate a basic product tree containing the enterprise's product classification, that is, to complete the division of the enterprise's product categories. Then, the basic product tree is constructed based on the product detailed information contained in the second classification source code group through the third preset model, and finally the enterprise product tree of the enterprise is formed. In this way, by first constructing the product classification and then filling in the product detailed information, it is possible to avoid the product detailed information being classified into other similar categories when the product tree is constructed, or the product detailed information and product category are divided into the same level, thereby improving the accuracy of the enterprise product tree construction. Finally, based on the enterprise product tree, the structured output of the enterprise product information can be completed, and then the enterprise product library can be quickly built based on the structured enterprise product information, filling the gap in enterprise product library resources on the market, and ultimately enabling enterprise, industry and sector analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of an enterprise information processing method based on a large language model provided in an embodiment of the present application; Figure 2 It is an example diagram of a web page of an enterprise to be analyzed for explaining the data cleaning step in the enterprise information processing method based on a large language model provided in an embodiment of the present application; Figure 3 It is an example diagram of a web page of an enterprise to be analyzed provided in an embodiment of the present application for explaining a data cleaning step when parallel sub-pages exist in an enterprise information processing method based on a large language model; Figure 4 It is an output structured style diagram provided in an embodiment of the present application; Figure 5 It is a virtual structural diagram of an enterprise information processing device based on a large language model provided by the present application; Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The present application is further described below in conjunction with the accompanying drawings and embodiments.

[0018] The following will clearly and completely describe the concept, specific structure and technical effects of the present application in combination with the embodiments and drawings, so as to fully understand the purpose, characteristics and effects of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments of the present application, other embodiments obtained by technicians in this field without creative work are all within the scope of protection of the present application. In addition, all the connection / connection relationships involved in the patent do not simply refer to the direct connection of components, but refer to the formation of a better connection structure by adding or reducing connection accessories according to the specific implementation situation. The various technical features created in this application can be combined interactively without conflicting with each other.

[0019] Reference Figure 1 , Figure 1 It is a flow chart of the enterprise information processing method based on the large language model provided by the embodiment of the present application. In the embodiment of the present application, in order to retrieve information from the enterprise homepage, an internally developed web crawler is used to collect web pages. Taking into account the characteristics of the product page, the crawling depth is limited to 3, and each hyperlink leading to a new internal page is considered to represent a level of navigation. Because some enterprises have forums or external links, these forums or external links may have the possibility of infinite crawling. Specifically, the following steps are included, and each step is described in detail below: In step S1, a target page group of the enterprise to be analyzed is obtained.

[0020] Specifically, one of the target page groups includes a parent page and a child page. The target page group refers to the collection of all target pages under the official website of the enterprise to be analyzed, wherein one of the target page groups includes a parent page and a child page, and the target page refers to all parent pages and child pages. The association between parent pages and child pages is based on the nested hierarchy of HTML (HyperText Markup Language). For example, for the enterprise to be analyzed, it is assumed that there is a complete link of "official website page-product category page-product A page-product A1 page". Through this link, the product information page of "Product A1" can be reached based on the web page link relationship. Then, the link includes three target page groups, which are: Target page group 1: the parent page is the official website page, and the child page is the product category page; Target page group 2: the parent page is the product category page, and the child page is the product A page; Target page group 3: The parent page is product A page, and the child page is product A1 page.

[0021] Based on the above examples, it can be seen that the parent page and child page exist independently in each target page group. A child page in one target page group can be the parent page of another target page group, and vice versa. However, it is worth noting that target pages such as "official website page" that do not have corresponding parent pages in the nested level can only be used as parent pages in the target page group. Similarly, target pages such as "product A1 page" that do not have child pages that continue to link downward can only be used as child pages in the target page group.

[0022] It can be understood that when executing step S1, the corporate website of the enterprise to be analyzed is crawled, and when multiple target page groups are obtained, the jump relationship between each page and its corresponding next page is already known. The jump relationship is the link relationship between the parent page and the child page, and the link relationship between the parent page and the child page in all target page groups is saved to facilitate the subsequent construction of the following basic product tree and enterprise product tree.

[0023] More specifically, the embodiment of the present application provides an implementation method for obtaining a target page group, which specifically includes: The official website page of the enterprise to be analyzed is located, and the official website page is used as the parent page in the first target page group.

[0024] Specifically, the official website of the company to be analyzed is found, and the homepage of the official website of the company to be analyzed is used as the official website page. The official website page is then used as the parent page in the first target page group. Since there is no corresponding parent page for the official website page, the first target page group is the starting target page group of the entire process. In layman's terms, the official website page is used as the starting page for subsequent data cleaning and data analysis, so as to gradually clean and process other pages within the official website of the company to be analyzed along its links from the starting page.

[0025] Furthermore, the page corresponding to the page link containing the preset keyword in the official website page is used as a child page in the first target page group and a parent page in the new target page group.

[0026] Specifically, the official website page is usually designed with a navigation menu, which may include link keywords such as products, services, about us, news, and contact information. For obtaining the enterprise product information of the enterprise to be analyzed, pages under links such as "about us", "contact information", and "news" are not applicable, so at least one preset keyword is required to further determine the required target page. Among them, the preset keywords include but are not limited to words such as "products" and "solutions". Specifically, the keywords can be appropriately adjusted according to the enterprise type to be analyzed. For example, for service-oriented enterprises, the preset keywords can be adjusted to "services".

[0027] More specifically, a link containing a preset keyword is found in the determined official website page, and the page pointed to by the link containing the preset keyword will become a subpage of the first target page group, that is, a subpage of the official website page. The page pointed to by the link containing the preset keyword is usually a category page of all products of the enterprise to be analyzed, that is, a product category page.

[0028] More specifically, there are usually multiple links in a product category page, which are used to point to product pages of multiple categories of products. That is, the product category page has a corresponding parent page upward, which forms the first target page with the official website page, and there may be corresponding child pages downward that form a new target page group with the product category page. Therefore, the product category page can be first used as the parent page of the new target page group, and it can be determined in the following steps whether the new target page group is formed.

[0029] Furthermore, it is detected whether the parent page in the new target page group has a corresponding child page.

[0030] Specifically, it is determined whether there is a corresponding sub-page on the product category page to determine whether a new target page group is formed. Specifically, a link search is performed based on the parent page of the new target page group determined in the above steps, and it is determined whether the found link points to a valid sub-page by verifying the link target, etc. If there is at least one valid sub-page, that is, it is determined whether there is a corresponding sub-page on the parent page in the new target page group, and a new target page group can be formed.

[0031] Furthermore, when the parent page in the new target page group does not have a corresponding child page, the first target page group is used as the target page group of the enterprise to be analyzed.

[0032] Specifically, if the parent page in the new target page group does not have a corresponding child page, it means that the official website page does not have a corresponding product category page, and the product information may be displayed directly. In this case, a complete link such as "official website homepage-product page" has been formed, and only the first target page group is obtained.

[0033] Furthermore, when a corresponding child page exists for a parent page in a new target page group, the parent page in the new target page group and the detected child page are combined into a new target page group, and the child page in the new target page group is used as the parent page in the next new target page group, and it is detected whether the parent page in the next new target page group has a corresponding child page, until the parent page in the next new target page group does not have a corresponding child page, then the first target page group and all new target page groups are used as the target page groups of the enterprise to be analyzed.

[0034] Specifically, if the parent page in the new target page group has a corresponding child page, the new target page group composition is determined, and then the next new target page group is constructed. The steps for constructing the next new target page group are the same as the above steps. First, the child page in the newly constructed target page group is used as the parent page of the next new target page group, and then a link search is performed based on the newly determined parent page. If there is a valid link, the newly determined parent page and the page pointed to by the newly found link can be used as the next new target page. Repeat this process until there is no corresponding child page for the parent page in the newly formed target page group, that is, the parent page is the bottom-level page in this new target page group. In this case, all the constructed target page groups including the first target page group are used as the target page groups of the enterprise to be analyzed.

[0035] For example, suppose that a product A under the first product category is crawled from the official website of an enterprise, and there is no next page to jump to after the page of product A, then the page of the product does not have a corresponding sub-page. However, if there is a next page to jump to for the page of another product B (for example, sub-product C of product B), the page of product B and the page of sub-product C will form a new target page group, and continue to detect whether there is a next page to jump to after the page of sub-product C. It can be seen that for the detection of parent pages and sub-pages, a parent page may correspond to multiple sub-pages (for example, if a company's products have multiple product categories, then the total product page will form a target page group with each product category page). Even if one of the sub-pages does not have a corresponding sub-page, it is still necessary to detect whether other sub-pages have corresponding sub-pages, so that all pages about products on the official website of the company can be completely crawled, which is convenient for the subsequent construction of the company's product tree.

[0036] In step S2, data cleaning is performed on the parent page and the child page of the same target page group to obtain a page source code group after data cleaning.

[0037] Specifically, based on the above step S1, at least one target page group can be obtained, each target page group includes a parent page and a corresponding child page. Since the method aims to obtain product information of the enterprise to be analyzed, each target page may contain links to the same resource or content. If these paths are not cleaned uniformly, redundancy and inconsistency in the data may occur, affecting subsequent data processing and analysis. By cleaning the data, the same paths of the parent page and the child page between the same target page group are removed, which can ensure data consistency and improve processing efficiency. Then, the page information of all target pages after data cleaning is obtained, wherein the page information includes the page source code of the target page and the file resources downloaded from the target page. The file resources can be product brochures, technical manuals, etc. of the product.

[0038] In one embodiment provided by the present application, the step of performing data cleaning on the parent page and the child page of the same target page group and obtaining the page source code group after data cleaning includes: Crawling the path data of the parent page and the path data of the child page of each target page group, and performing the path cleaning on the path data of the child page in the same target page group as the parent page according to the path data of each parent page; Specifically, all parent pages and all child pages constitute all target pages. The path data is obtained through the paths of all leaf nodes in the document object model tree (Dom Tree) corresponding to each target page. Since a target page may have multiple child pages, and the child pages of different target pages may be repeated, that is, the paths may be repeated. In order to reduce the repeated and redundant child pages, it is necessary to perform path cleaning. In one embodiment provided in the present application, the specific steps for performing path cleaning are as follows: The path data of all leaf nodes in the document object model tree corresponding to the parent page are crawled to obtain a first path set corresponding to the parent page.

[0039] Specifically, the Document Object Model Tree (Dom Tree) is a tree-like data structure, and a leaf node is a node without subsequent child nodes. The Document Object Model Tree includes a root node and possible intermediate nodes, as well as one or more leaf nodes. Starting from the root node, all nodes are arranged in a hierarchical manner of link relationships to obtain one or more link paths, where each path is "root node-intermediate node-leaf node" or "root node-leaf node".

[0040] More specifically, in this step, first find the document object model tree corresponding to the parent page in the target page group, take the page as the root node, and find the paths of all leaf nodes along the link relationship of its pages. Since there may be multiple link paths in the page, all the paths obtained in this step are defined as the first path set in this application. Generally speaking, one leaf node corresponds to one path.

[0041] Furthermore, the path data of all leaf nodes in the document object model tree corresponding to the sub-page are crawled to obtain a second path set corresponding to the sub-page.

[0042] Specifically, in the same manner as obtaining the first path set corresponding to the parent page, the child page in the same target page group as the parent page as the root node is used as the root node, and all leaf nodes in the corresponding document object model tree are crawled to obtain all link paths corresponding to the child page, which is defined as the second path set in this application.

[0043] Furthermore, invalid path data of sub-pages in each target page group is cleaned.

[0044] Specifically, the invalid path data is the same path data between the first path set and the second path set in the same target page group, and the link parts that are the same as the parent page in the child page of each target page group are removed, so as to remove the pages that are pointed to by the links shared by the parent page and the child page in the child page, and obtain the page source code of all parent pages and all child pages after the cleaning is completed. For example, both the parent page and the child page may have a link to the "About Us" page, but this page is not the page required for subsequent acquisition of product information. In the process of data cleaning, the link path of this page will be cleaned as an invalid path.

[0045] More specifically, all target page groups obtained in the above steps perform the above path cleaning between the parent page and the child page, until the child pages in all target page groups are cleaned, and then the page source code corresponding to each target page is obtained.

[0046] In the above embodiment, a data cleaning method is proposed that first determines all target page groups and then performs path cleaning on the sub-pages in each target page group. In another embodiment provided in the present application, it is also possible to first determine a target page group and then clean the invalid path part in the sub-pages of the target page group. The cleaned sub-page is used as the parent page of the next target page group, and the sub-page corresponding to the next target page group is found at the same time. The above cleaning process is repeated until the sub-page that is finally cleaned has no corresponding sub-page, and the data cleaning is terminated to achieve the effect of performing data cleaning on the parent page and the sub-page of the same target page group.

[0047] For example, refer to Figure 2 , Figure 2 is an example diagram of a web page of an enterprise to be analyzed for explaining the data cleaning step in the enterprise information processing method based on a large language model provided in an embodiment of the present application. Figure 2 In the example shown, the target page groups are the "Tapered Roller" page and the "Roller Series" page, where the "Roller Series" page is the parent page, and the "Tapered Roller" page is the child page corresponding to the "Roller Series" page. In this case, the part of the second path set corresponding to the "Roller Series" page that needs to be retained is the content selected in the box in the above figure.

[0048] More specifically, in the embodiments provided in the present application, there may be a situation where a parent page has multiple corresponding child pages, for example, a product category page has multiple product pages. In this case, each product page will be a child page of the product category page, forming multiple target page groups corresponding to the number of child pages. The product category is used as the parent page of each product page, that is, considering the parallel situation of multiple child pages contained in a parent page of a first path set, the cleaning steps are only repeated between the parent page and the child page, thereby avoiding incorrect cleaning and improving the reliability of data cleaning.

[0049] For example, refer to Figure 3 , Figure 3 This is an example diagram of a web page of an enterprise to be analyzed provided by an embodiment of the present application for explaining the data cleaning step when there are parallel sub-pages in the enterprise information processing method based on a large language model. It can be seen that there are three types of products under the "chip mounting" category in the figure, and the current "chip mounting" page is used as the parent page. The page pointed to by the link corresponding to each type of product map will be used as the sub-page corresponding to the current "chip mounting" page. Since there are three groups, that is, there are three sub-pages respectively, forming three target page groups. In response to this situation, the sub-pages in each target page group respectively perform the cleaning step based on the repeated path part with the parent page "chip mounting".

[0050] Furthermore, after completing the path cleaning step, the label cleaning step in data cleaning is entered, including: Obtaining the page source codes of all the parent pages and all the child pages after path cleaning to obtain a plurality of initial page source codes, performing the tag cleaning on all the initial page source codes to obtain a plurality of cleaned page source codes; The page source code group is determined according to all the cleaned page source codes.

[0051] Specifically, after completing the path cleaning, the page source codes of all target pages (all parent pages and all child pages) are obtained. Since the obtained page source codes may contain a large number of tags that are useless for extracting product-related information and need further cleaning, all the page source codes obtained at this time are defined as the initial page source codes, and then the redundant tags in each initial page source code are removed, and finally multiple cleaned page source codes are obtained. The collection of multiple cleaned page source codes is the page source code group. Among them, the redundant tags are preset by relevant personnel, and the cleaned page source code refers to the initial page source code after tag cleaning.

[0052] In an embodiment provided by the present application, the following steps can be used to perform tag cleaning on all the initial page source codes to obtain multiple cleaned page source codes, specifically including: Tag detection is performed on each of the initial page source codes to determine non-structural tags contained in each of the initial page source codes.

[0053] Specifically, in this step, each initial page source code is analyzed to identify and mark all non-structural tags therein (i.e., the step of performing tag detection on each initial page source code is performed). Non-structural tags are tags that do not convey structural information (e.g. ， , <script>等）。

[0054] 进一步地，剔除每一所述初始页面源码中不传递结构信息的非结构标签，得到中间页面源码。

[0055] 具体地，在识别并标记出每一初始页面源码中所有的非结构标签后，将所有的非结构标签从对应的初始页面源码中移除，并将完成本步骤的初始页面源码作为中间页面源码。其中，中间页面源码包含预设保留的结构标签（例如、、），结构标签为传递结构信息的标签，即可以传递有意义的结构信息的标签。移除非结构标签可以简化文档的结构，这是因为非结构标签通常用于提供额外的功能或样式信息，而不是承载内容本身，通过移除非结构标签，可以将注意力集中在主要内容上，同时减少了模型需要解析的标签数量。

[0056] 进一步地，检测所述中间页面源码中是否包含预设公共标签，以剔除所述中间页面源码中的预设公共标签后，得到所述清洗页面源码。

[0057] 具体地，预设公共标签为每一目标页面中共同存在的标签，包括但不限于页脚标签<footer>和版权信息标签<copyright>等，在检测中间页面源码中是否包含预设公共标签的步骤中，具体需要检测何种公共标签由相关人员根据实际情况进行预设。通常情况下，预设公共标签应当在步骤S2所执行的数据清洗中被去除，但实际情况中仍可能存在清洗的遗漏导致其仍可能存在于任一中间页面源码中，因此在本步骤中对每一中间页面源码执行进一步检测，标识并剔除其中所有的预设公共标签，直至确定所有中间页面源码中不存在预设公共标签后，即可将完成本步骤清洗的中间页面源码作为完成数据清洗的清洗页面源码。

[0058] 在步骤S3中，将所述页面源码组输入至第一预设模型，以通过所述第一预设模型对所述页面源码组进行分类处理，得到第一分类源码组和第二分类源码组。

[0059] 具体地，第一分类源码组为所有包含产品类别信息的页面源码的组合，所述第二分类源码组为所有包含产品详细信息的页面源码的组合。页面源码组中包括多种类别的网页对应的页面源码，一般而言，一个企业的网站包含了广泛信息，包括但不限于企业介绍、新闻资讯、产品信息、企业荣誉等，然而实际操作中，难以做到仅基于给定页面的易于访问的属性确定给定页面是否包含产品信息，例如页面URL（Uniform Resource Locator，统一资源定位符）、标题和类似的元数据等。因此在本步骤中，基于每一设定分类的定义，得到包含产品类别信息的页面源码（即第一分类源码组）与包含产品详细信息的页面源码（即第二分类源码组）。

[0060] 其中，可以采用相关提示词输入至第一预设模型的方式定义上述设定分类，举例而言，相关提示词可以是：产品类别页面说明：此页面仅列出了产品、服务或解决方案的名称；产品详细信息页面说明：此页面包含有关特定产品、服务或解决方案的详细信息，并对其进行了深入的描述。

[0061] 基于上述关键词，有助于第一预设模型理解对于"产品类别页面”和"产品详细信息页面”的定义，从而根据对应页面的页面内容进行分类。其中，所有"产品类别页面”的页面源码为第一分类源码组，所有"产品详细信息页面”的页面源码为第二分类源码组。

[0062] 更具体地，由于页面源码组中对应的页面不一定仅存在"产品类别页面”和"产品详细信息页面”，还可能存在一些其他的无关页面，因此可以在上述提示词加入对于无关页面的分类筛选，举例而言，可以加入：其他解释：本页面主要包含新闻、公司简介、职位招聘、客户介绍、联系信息或投标书等内容，与产品、服务或解决方案没有直接关系。

[0063] 具体地，基于对"其他解释”的定义，可以通过第一预设模型筛选出"其他解释”页面，所有的"其他解释”页面对应的页面源码可以组成第三分类页面源码，第三分类页面源码会从页面源码组中进行剔除，从而进一步去除产品无关内容，减少模型需要处理的无关信息，提高模型处理的效率和准确性。

[0064] 更具体地，为了确保第一预设模型理解其需要基于输入的页面源码组得到的输出内容，可以在相关提示词的开头加入诸如"您必须仔细考虑以下类别及其相应的解释，以确定本网页属于哪个类别”的系统提示词。此外，为了对所需的输出格式的规范化，可以在相关提示词后加入诸如"注意：您只需要返回类别的名称，并且您只能响应上面提供的一个类别。输出：上面三种类别中的一种”的引导。

[0065] 在上述对于页面源码的分类完成后，得到第一类别源码组和第二类别源码组并进入基本产品树的构建步骤。

[0066] 在步骤S4中，将所述第一分类源码组输入至第二预设模型，以通过所述第二预设模型基于所述第一分类源码组构建得到基本产品树。

[0067] 具体地，第一分类源码组中涉及的产品信息通常不包括确切的产品，而只包括更广泛的产品类别，因此本阶段构建的基本产品树仅包括产品类别信息，而产品类别信息中可以具备一定的类别层次，举例而言，较大的类别中包括类别1"处理器芯片”和类别2"产品解决方案”，类别2中包括类别21"分布式存储系统”和类别22"数据库设备”。在本申请提供的一个实施例中，可以由第一预设模型结合下述步骤输出基本产品树，具体包括：获取第一预设提示信息。

[0068] 具体地，第一预设提示信息包括基本产品树框架。其中，基本产品树框架包括多个产品分类节点，一个所述产品分类节点对应一个第一节点层级。产品分类节点是指基本产品树框架上未填充的节点，第一节点层级是指每一产品分类节点在基本产品树框架中的垂直层级，举例而言，假设产品树包括根节点（产品树的起点）和多个枝节点，那么越靠近根节点的枝节点的层级越高，而越远离根节点的枝节点的层级越低。

[0069] 更具体地，第一预设提示信息还包括第一引导信息，其有助于第二预设模型理解其职责，以便于正确处理输入的第一分类源码组，得到所需的输出结果，在本申请提供的一个实施例中，其可以为"您的职责是解析半结构化文本，并构造一个树状结构。术语"产品”被定义为被个人使用和消费、满足某种需求或欲望的任何东西。这包括有形的商品和无形的服务”。随即，对于需要构建的"树状结构”进行示例性提示，具体包括："下面是一个示例，由<example>和< / example>标记，以指示示例的开始和结束。

[0070] <example>基本产品树框架< / example>”。其中，采用特定的<example>和< / example>标记以避免第二预设模型混淆输入的第一分类源码组和示例的基本产品树框架。

[0071] 进一步地，将所述第一分类源码组和所述第一预设提示信息输入至所述第二预设模型，以通过所述第二预设模型基于所述第一引导信息提取所述第一分类源码组中的产品分类信息。

[0072] 具体地，第二预设模型基于上述步骤获取的第一引导信息提取第一分类源码组中所有与产品关联的信息，由于上述已解释第一分类源码组为对应产品类别的页面的页面源码，即此时可以提取得到关于产品分类的产品分类信息。举例而言，产品分类信息可以是"产品解决方案”"关于我们”等。

[0073] 进一步地，通过所述第二预设模型基于所述第一分类源码组中每一页面源码对应的页面的链路关系，确定待构建的所述基本产品树的第一页面层级。

[0074] 具体地，第二预设模型会根据第一分类源码组中每一页面源码对应页面的链路关系确定每一页面的层级关系（即第一页面层级），其链路关系保留在每一目标页面组中，即同一目标页面组中的父页面与子页面之间的关联关系。举例而言，假设存在"产品类别页面－产品A页面”与"产品A页面－产品A1页面”两个目标页面组，基于这两个目标页面组得到的层级为"产品类别页面－产品A页面－产品A1页面”。

[0075] 进一步地，通过所述第二预设模型基于所述第一节点层级和所述第一页面层级，将所述产品分类信息插入所述基本产品树框架，得到所述基本产品树。

[0076] 具体地，基于上述步骤获取的第一节点层级和第一页面层级，可以确定多个产品分类信息中每一产品分类信息在基本产品树框架中应当插入的位置，随即逐一对应插入产品分类信息，以得到基本产品树。

[0077] 更具体地，通过上述步骤得到的基本产品树中，尽管在提示中强调了 "产品 ”的定义，但就实际情况而言，第二预设模型可能无法准确识别和提取完全与产品相关的信息，即可能存在诸如"关于我们”"组织架构”这类与产品信息无关联的分类，因此需要将这部分无关联的分类进行剔除，在本申请实施例中，进一步提出了通过指示第二预设模型（或其它大语言模型）筛查并删除与产品无关的内容，以进一步优化基本产品树，完善其树形结构。

[0078] 其中，指示模型筛查并删除与产品无关的内容所采用指示词可以是："您是一个高级数据清理工具，任务是从提供的树形结构中删除与 "产品 ”无关的内容。"产品” 一词被定义为个人使用和消费的、满足某种需求或愿望的任何物品，包括有形商品和无形服务。您必须严格评估树形结构中的每个节点，以确定其是否与 "产品 ”有关。”可以看出，在这一指示词中，进一步强调了"产品”的定义，并指示模型删除上述步骤得到的基本产品树中与"产品”无关的节点。

[0079] 在步骤S5中，将所述第二分类源码组和所述基本产品树输入至第三预设模型，以通过所述第三预设模型基于所述第二分类源码组对所述基本产品树进行补充构建，得到企业产品树。

[0080] 具体地，通过上述步骤已经构建得到了具备清洗产品层级结构的基本产品树，但基本产品树中缺少关于每一产品分类下的产品详细信息，这部分信息需要从第二分类源码组中获取，获取得到的产品详细信息插入基本产品树中的对应节点，即可得到企业产品树。其中，产品详细信息包括但不限于产品名称、产品型号、产品规格等，第三预设模型与上述第一预设模型和第二预设模型类似，可以是大语言模型。

[0081] 在本申请提供的一个实施例中，将所述第二分类源码组和所述基本产品树输入至第三预设模型，以通过所述第三预设模型基于所述第二分类源码组对所述基本产品树进行补充构建，得到企业产品树的步骤包括：获取第二预设提示信息。

[0082] 具体地，第二预设提示信息包括企业产品树框架和第二引导信息，企业产品树框架可以是独立预设的树形结构框架，也可以沿用上述步骤中提供的基本产品树框架；第二引导信息与上述第一引导信息类似，其有助于第三预设模型理解其职责，以便于正确处理输入的第二分类源码组，得到所需的输出结果。

[0083] 进一步地，将所述基本产品树和所述第二预设提示信息输入至所述第三预设模型，以通过所述第三预设模型将所述基本产品树插入所述企业产品树框架中，得到待补充构建的中间产品树。

[0084] 具体地，将第二预设提示信息与上述步骤得到的基本产品树一并输入至第三预设模型中，第三预设模型会基于企业产品树框架，适配地将基本产品树插入其中，得到中间产品树。得到的中间产品树包括已填充的产品分类节点和待填充的产品信息节点。

[0085] 进一步地，将所述第二分类源码组输入至所述第三预设模型，以通过所述第三预设模型基于所述第二分类源码组中每一页面源码对应的页面的链路关系确定所述中间产品树的第二页面层级，并依据所述第二引导信息提取所述第二分类源码组中的所有产品信息。

[0086] 具体地，将第二分类源码组输入至第三预设模型中，第三预设模型第一方面会根据第二分类源码组中每一页面源码对应页面的链路关系确定第二页面层级，第二页面层级用于与上述第一页面层级区分，表示第二分类源码组中所有页面的层级关系；第二方面会依据第二引导信息提取第二分类源码组中所有所需的产品信息，所需的产品信息根据相关人员进行自定义。

[0087] 进一步地，通过所述第三预设模型基于所述第二节点层级和所述第二页面层级，将所有所述产品信息插入所述中间产品树，以得到所述企业产品树。

[0088] 具体地，基于第二节点层级和第二页面层级，可以确定每一产品信息应当插入中间产品树中哪一待填充的产品信息节点，随即将得到的所有产品信息逐一插入至对应的产品信息节点，最终形成待分析企业的企业产品树。

[0089] 示例性的，假设得到的基本产品树中包括产品类别节点"数据库设备”，而一个产品信息"y”基于其对应的节点层级确定其属于"数据库设备”下的产品信息，即可将"y”插入产品类别节点"数据库设备”下的产品信息节点。其中，产品信息包括但不限于产品名称、对应的产品型号、产品规格等，具体需要的产品详细信息可以根据实际需求而设定。

[0090] 在步骤S6中，基于所述企业产品树得到所述待分析企业的企业产品信息。

[0091] 具体地，基于上述步骤得到具备产品分类、产品名称及产品详细信息的企业产品树，这些内容的对应关系在企业产品树中以树形结构体现，随即，可以通过分析企业产品树中树形结构的每一分支，形成结构化的企业产品信息并输出结果。

[0092] 示例性的，参照图4，图4是本申请实施例提供的输出结构化样式图，每一个产品会对应有一个产品名称、产品分类信息、型号和规格的输出。

[0093] 进一步地，在得到待分析企业对应的企业产品信息中，可能存在部分信息内容的空缺，这部分空缺可能在上述清洗过程中被洗去，具体地，企业产品信息采用结构化的输出结果展示，而结构化由输入至预设大语言模型的结构化提示词调整得到，但实际情况中，可能存在从页面源码组中无法得到某些产品对应的产品详细信息的情况，从而产生结构化输出的企业产品信息中存在一个或多个产品对应的产品信息不完整的情况，为了完善企业产品信息的内容，提高本方法的可用性。示例性的，存在产品信息存在结构空缺可以参照图4中"无”的部分。

[0094] 基于此，本申请还提出在得到所述待分析企业对应的企业产品信息的步骤之后，还包括以下步骤：对所述企业产品信息进行完整性检测，以从所述企业产品信息中筛选出空缺产品信息。

[0095] 具体地，在得到企业产品信息的结构化输出（以下简称为结构化输出）后，对结构化输出进行完整性检测，完整性检测的过程中扫描并确认每一产品涉及的产品信息是否包含所有需求的产品信息，若否。则确定对应的产品的所有产品信息为空缺产品信息，所缺少的需求的产品信息为空缺信息项。在本申请实施例中，统一将结构化输出中的空缺信息项用同一关键词表示，例如图4中的"无”，随即进行关键词筛选，即可定位企业产品信息中的所有空缺产品信息，并确定每一空缺产品信息对应的空缺信息项。

[0096] 进一步地，获取所述空缺产品信息对应的页面信息中的文件资源。

[0097] 具体地，文件资源包含至少一个页面资源信息。在本步骤中，根据空缺产品信息对应的产品，到与该产品相对应的页面信息中进行检索，得到页面信息中包括的所有页面资源信息。此外，结合上述对于步骤S2的阐述可知，在完成步骤S2涉及的数据清洗之后，对每一目标页面的文件资源进行保存，若存在空缺产品信息则可进行调用。

[0098] 进一步地，检测所述文件资源信息是否存在与所述空缺信息项对应的页面资源信息；进一步地，若存在所述空缺信息项对应的页面资源信息，则将所述页面资源信息补充至所述空缺信息项并更新所述企业产品信息。

[0099] 具体地，在对应页面信息中得到的所有页面资源信息后，需要进一步检测得到的所有页面资源信息中是否存在可填补空缺信息项的页面资源信息。举例而言，若产品A涉及的产品信息为空缺产品信息，其空缺信息项为"产品规格”，获取的页面资源信息包括资源A、资源B和资源C，那么在此步骤中需要对这三个页面资源信息进行检测，以判断其中是否存在关于产品A的"产品规格”的信息。若否，则保留对应空缺信息项，否则，则基于对应的页面资源信息中关于产品A的"产品规格”所涉及的内容对该空缺信息项进行补充并更新。

[0100] 更具体地，对每一空缺信息项执行上述步骤后，得到最终的企业产品信息的结构化输出。而在本申请提出的一个实施例中，还可以将最终的结构化输出中的空缺产品信息设置为待补充产品信息，并获取与待补充产品信息对应页面信息的更新状态，若对应页面信息存在更新，则获取页面信息中新的文件资源信息，并返回检测所述文件资源信息是否存在与所述空缺信息项对应的页面资源信息的步骤，以持续优化完善待分析企业的企业产品信息。

[0101] 参照图5，图5是本申请提供的基于大语言模型的企业信息处理装置的虚拟结构示意图，本申请第二方面提供了基于大语言模型的企业信息处理装置，包括：目标页面组获取模块100，用于获取待分析企业的目标页面组；一个所述目标页面组包含一个父页面以及一个子页面；页面清洗及源码获取模块200，用于对同一所述目标页面组的所述父页面和所述子页面进行数据清洗，获取数据清洗后的页面源码组，所述页面源码组包括所有父页面对应的页面源码和所有子页面对应的页面源码；页面源码组分类模块300，用于将所述页面源码组输入至第一预设模型，以通过所述第一预设模型对所述页面源码组进行分类处理，得到第一分类源码组和第二分类源码组，所述第一分类源码组为所有包含产品类别信息的页面源码的组合，所述第二分类源码组为所有包含产品详细信息的页面源码的组合；基本产品树构建模块400，用于将所述第一分类源码组输入至第二预设模型，以通过所述第二预设模型基于所述第一分类源码组构建得到基本产品树；企业产品树构建模块500，用于将所述第二分类源码组和所述基本产品树输入至第三预设模型，以通过所述第三预设模型基于所述第二分类源码组对所述基本产品树进行补充构建，得到企业产品树；产品信息获取模块600，用于基于所述企业产品树得到所述待分析企业的企业产品信息。

[0102] 本申请实施例所述的基于大语言模型的企业信息处理装置可执行上述实施例所提供的基于大语言模型的企业信息处理方法，所述基于大语言模型的企业信息处理装置具备上述实施例所述基于大语言模型的企业信息处理方法相应的功能步骤以及有益效果，具体请参阅上述基于大语言模型的企业信息处理方法的实施例，本申请实施例在此不再赘述。

[0103] 本申请实施例还提供了一种电子设备，请参照图6，图6是本申请实施例提供的电子设备的结构示意图，该电子设备可以包括处理器和存储器，其中处理器和存储器可以通过总线或者其他方式连接。处理器可以为中央处理器（CentralProcessing Unit，CPU）。处理器还可以为其他通用处理器、数字信号处理器（DigitalSignal Processor，DSP）、专用集成电路（Application Specific Integrated Circuit，ASIC）、现场可编程门阵列（Field-Programmable Gate Array，FPGA）或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等芯片，或者上述各类芯片的组合。存储器作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态计算机可执行程序以及模块，如本申请实施例中的基于大语言模型的企业信息处理方法对应的程序指令 / 模块。处理器通过运行存储在存储器中的非暂态软件程序、指令以及模块，从而执行处理器的各种功能应用以及数据处理，即实现上述方法实施例中的基于大语言模型的企业信息处理方法。

[0104] 存储器可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储处理器所创建的数据等。此外，存储器可以包括高速随机存取存储器，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。所述一个或者多个模块存储在所述存储器中，当被所述处理器执行时，执行如上述方法实施例中的基于大语言模型的企业信息处理方法。上述电子设备具体细节可以对应上述方法实施例中对应的相关描述和效果进行理解，此处不再赘述。本领域技术人员可以理解，实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述存储介质可为只读存储记忆体（Read-Only Memory，ROM）、随机存储记忆体（Random AccessMemory，RAM）、快闪存储器（FlashMemory）、硬盘（Hard Disk Drive，缩写：HDD）或固态硬盘（Solid-State Drive，SSD)等；所述存储介质还可以包括上述种类的存储器的组合。

[0105] 在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。

[0106] 类似地，应当理解，为了精简本公开并帮助理解各个发明方面中的一个或多个，在上面对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该公开的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如权利要求书所反映的那样，发明方面在于少于前面公开的单个实施例的所有特征。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。

[0107] 应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。< / script>

Claims

1. An enterprise information processing method based on a large language model, characterized in that: The method comprises: Obtain a target page group of the enterprise to be analyzed; one target page group includes a parent page and a child page; Performing data cleaning on the parent page and the child page of the same target page group to obtain a page source code group after data cleaning, wherein the page source code group includes page source codes corresponding to all parent pages and page source codes corresponding to all child pages; Inputting the page source code group into a first preset model, so as to classify the page source code group through the first preset model to obtain a first classification source code group and a second classification source code group, wherein the first classification source code group is a combination of all page source codes containing product category information, and the second classification source code group is a combination of all page source codes containing product detailed information; Inputting the first classification source code group into a second preset model, so as to construct a basic product tree based on the first classification source code group through the second preset model; Inputting the second classification source code group and the basic product tree into a third preset model, so as to supplement and construct the basic product tree based on the second classification source code group through the third preset model to obtain an enterprise product tree; The enterprise product information of the enterprise to be analyzed is obtained based on the enterprise product tree.

2. The enterprise information processing method based on a large language model according to claim 1, characterized in that: The step of obtaining the target page group of the enterprise to be analyzed includes: Locate the official website page of the enterprise to be analyzed, and use the official website page as the parent page in the first target page group; The page corresponding to the page link containing the preset keyword on the official website page is used as a child page in the first target page group and a parent page in the new target page group; Check whether the parent page in the new target page group has a corresponding child page; When the parent page in the new target page group does not have a corresponding child page, the first target page group is used as the target page group of the enterprise to be analyzed; When there is a corresponding child page for the parent page in the new target page group, the parent page in the new target page group and the detected child page are combined into a new target page group, and the child page in the new target page group is used as the parent page in the next new target page group, and it is detected whether there is a corresponding child page for the parent page in the next new target page group, until there is no corresponding child page for the parent page in the next new target page group, then the first target page group and all new target page groups are used as the target page groups of the enterprise to be analyzed.

3. The enterprise information processing method based on a large language model according to claim 1, characterized in that: The data cleaning includes path cleaning and label cleaning. The step of performing data cleaning on the parent page and the child page of the same target page group and obtaining the page source code group after data cleaning includes: Crawling the path data of the parent page and the path data of the child page of each target page group, and performing the path cleaning on the path data of the child page in the same target page group as the parent page according to the path data of each parent page; Obtaining the page source codes of all the parent pages and all the child pages after path cleaning to obtain multiple initial page source codes; Performing the tag cleaning on all the initial page source codes to obtain a plurality of cleaned page source codes; The page source code group is determined according to all the cleaned page source codes.

4. The enterprise information processing method based on a large language model according to claim 3 is characterized in that: The performing the path cleaning on the path data of the child pages in the same target page group as the parent page according to the path data of each parent page includes: Crawling the path data of all leaf nodes in the document object model tree corresponding to the parent page to obtain a first path set corresponding to the parent page; Crawling the path data of all leaf nodes in the document object model tree corresponding to the subpage to obtain a second path set corresponding to the subpage; Invalid path data of sub-pages in each target page group are cleaned, wherein the invalid path data is the same path data between the first path set and the second path set in the same target page group.

5. The enterprise information processing method based on a large language model according to claim 3 is characterized in that: The step of performing tag cleaning on all the initial page source codes to obtain a plurality of cleaned page source codes comprises: Perform tag detection on each of the initial page source codes to determine non-structural tags contained in each of the initial page source codes; the non-structural tags are tags that do not transmit structural information; Eliminate non-structural tags that do not convey structural information in each of the initial page source codes to obtain an intermediate page source code; It is detected whether the intermediate page source code contains a preset public tag, so as to obtain the cleaned page source code after removing the preset public tag in the intermediate page source code.

6. The enterprise information processing method based on a large language model according to claim 1, characterized in that: The step of inputting the first classification source code group into a second preset model to construct a basic product tree based on the first classification source code group through the second preset model includes: Acquire first preset prompt information, the first preset prompt information including a basic product tree framework and first guide information, the basic product tree framework including a plurality of product classification nodes, one of the product classification nodes corresponding to one first node level; Inputting the first classification source code group and the first preset prompt information into the second preset model, so as to extract product classification information in the first classification source code group based on the first guide information through the second preset model; Determine the first page level of the basic product tree to be constructed based on the link relationship of the pages corresponding to each page source code in the first classification source code group through the second preset model; The product classification information is inserted into the basic product tree framework based on the first node level and the first page level through the second preset model to obtain the basic product tree.

7. The enterprise information processing method based on a large language model according to claim 1, characterized in that: The step of inputting the second classification source code group and the basic product tree into a third preset model to supplement and construct the basic product tree based on the second classification source code group through the third preset model to obtain the enterprise product tree includes: Acquire second preset prompt information, where the second preset prompt information includes an enterprise product tree framework and second guide information, where the enterprise product tree framework includes a plurality of product information nodes, and one product information node corresponds to one second node level; Inputting the basic product tree and the second preset prompt information into the third preset model, so as to insert the basic product tree into the enterprise product tree framework through the third preset model to obtain an intermediate product tree to be supplemented and constructed; Input the second classification source code group into the third preset model, so as to determine the second page level of the intermediate product tree based on the link relationship of the page corresponding to each page source code in the second classification source code group through the third preset model, and extract all product information in the second classification source code group according to the second guide information; All the product information is inserted into the intermediate product tree based on the second node level and the second page level through the third preset model to obtain the enterprise product tree.

8. An enterprise information processing device based on a large language model, characterized in that: include: A target page group acquisition module is used to acquire the target page group of the enterprise to be analyzed; One of the target page groups includes a parent page and a child page; A page cleaning and source code acquisition module, used to clean the parent page and the child page of the same target page group, and obtain a page source code group after data cleaning, wherein the page source code group includes page source codes corresponding to all parent pages and page source codes corresponding to all child pages; a page source code group classification module, used for inputting the page source code group into a first preset model, so as to classify the page source code group through the first preset model to obtain a first classification source code group and a second classification source code group, wherein the first classification source code group is a combination of all page source codes containing product category information, and the second classification source code group is a combination of all page source codes containing product detailed information; A basic product tree construction module, used for inputting the first classification source code group into a second preset model, so as to construct a basic product tree based on the first classification source code group through the second preset model; An enterprise product tree construction module, used for inputting the second classification source code group and the basic product tree into a third preset model, so as to supplement and construct the basic product tree based on the second classification source code group through the third preset model to obtain an enterprise product tree; The product information acquisition module is used to obtain the enterprise product information of the enterprise to be analyzed based on the enterprise product tree.

9. An electronic device, characterized in that: include: one or more processors; one or more memories; and one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, and the one or more computer programs include instructions, which, when executed by the one or more processors, cause the electronic device to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program or an instruction, and when the program or the instruction is executed, the method according to any one of claims 1 to 7 is implemented.

Images