Enterprise investigation method and device, equipment and storage medium

Abstract

The invention provides an enterprise investigation method and device, equipment and a storage medium, and relates to the technical field of information processing. The method comprises the following steps: acquiring investigation information of a target enterprise, wherein the investigation information comprises at least one of investigation background information, enterprise information and historical investigation information; determining an investigation keyword according to the investigation information; matching the investigation keyword with a preset investigation theme to obtain a target investigation theme for the target enterprise; matching the investigation keyword with an investigation question corresponding to the target investigation theme to obtain a target investigation question of the target enterprise corresponding to the target investigation theme; and calling the preset questionnaire template, and generating a questionnaire for the target enterprise by applying the AIGC technology based on the target investigation question, so that the investigation cost of the enterprise can be reduced, and the investigation efficiency of the enterprise can be improved.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an enterprise research method, device, equipment and storage medium. Background Art

[0002] Under the wave of digital economy, digital transformation and intelligent transformation of enterprises (hereinafter referred to as "digital transformation and intelligent transformation") has become an inevitable trend in line with the development of the times. However, the business of digital transformation and intelligent transformation of enterprises is complex, and the industry characteristics, production practices, and differentiation characteristics of various industries are obvious. In addition, many enterprises are not very clear about their own digital transformation and intelligent transformation layout, and do not understand the development of new technologies such as intelligent manufacturing, industrial Internet, and 5G. Therefore, conducting comprehensive and in-depth research on enterprises and providing targeted solutions have become an important means for enterprises to accelerate the promotion of digitalization and intelligence, a prerequisite for comprehensive upgrading of enterprises, and an entry point for developing innovative business of industrial Internet.

[0003] In related technologies, enterprise research is usually conducted manually by researchers, but there are often problems such as limited research topics, rigid content, and uneven levels of researchers, which leads to high costs and low efficiency of enterprise research. Summary of the invention

[0004] The present application provides an enterprise research method, device, equipment and storage medium to solve the technical problems of high cost and low efficiency of enterprise research.

[0005] In a first aspect, the present application provides an enterprise research method, comprising:

[0006] Obtaining research information of the target enterprise, the research information including at least one of research background information, enterprise information and historical research information;

[0007] Determine the research keywords based on the research information;

[0008] Match the research keywords with the preset research topics to obtain the target research topics for the target companies;

[0009] Match the research keywords with the research topics corresponding to the target research topics to obtain the target research topics corresponding to the target companies;

[0010] Call the preset survey questionnaire template, based on the target survey topic, and apply Artificial Intelligence General Content (AIGC) technology to generate a survey questionnaire for the target enterprise.

[0011] In a possible implementation, determining the research keywords according to the research information includes:

[0012] For the research background information, apply Natural Language Processing (NLP) technology to extract the first keyword contained in the research background information based on the vocabulary in the preset knowledge base;

[0013] For enterprise information, based on the knowledge base, extract the second keyword contained in the enterprise information;

[0014] For historical survey information, based on the knowledge base, extract the third keyword contained in the historical survey information;

[0015] Based on the information type included in the research information, a research keyword is determined according to at least one of the first keyword, the second keyword, and the third keyword.

[0016] In a possible implementation, based on the type of information included in the survey information, the survey keyword is determined according to at least one of the first keyword, the second keyword, and the third keyword, including:

[0017] Based on the information types included in the survey information, corresponding to any keyword X included in the first keyword, the second keyword, and the third keyword, determine a comprehensive interest index of the keyword X;

[0018] Based on the first set condition that the research keyword should satisfy, the research keyword is determined according to the comprehensive interest index of the target keyword, the first set condition being that the comprehensive interest index is greater than a first threshold, or the first set condition being that the keywords corresponding to N comprehensive interest indexes with larger comprehensive interest indexes;

[0019] The determination of the comprehensive interest index satisfies Interest(X)=β*pre_Interest(X)+δ*com_Interest(X)+ε*his_Interest(X), wherein Interest(X) represents the comprehensive interest index, pre_Interest(X) represents the interest index of keyword X in the research background information, com_Interest(X) represents the interest index of keyword X in enterprise information, his_Interest(X) represents the interest index of keyword X in historical research information, β is the comprehensive interest index factor of the keyword in the research background information, δ is the comprehensive interest index factor of the keyword in enterprise information, ε is the comprehensive interest index factor of the keyword in historical research information, and the comprehensive interest index factors are all taken according to the empirical method;

[0020] Where times represents the number of times keyword X appears in the research background information, SUM represents the number of times all keywords appear in the research background information, Total_times represents the number of times keyword X appears in all research background information, Total_SUM represents the number of times all keywords appear in the research content of all research tasks, ∝ is the interest index factor, and its value is determined according to the empirical method; the determination method of com_Interest(X) and his_Interest(X) refers to the determination method of pre_Interest(X).

[0021] In a possible implementation, the research keywords are matched with preset research topics to obtain target research topics for target enterprises, including:

[0022] Obtaining a first comprehensive interest index vector corresponding to all research keywords corresponding to the research information, wherein the first comprehensive interest index vector includes elements that are comprehensive interest indexes corresponding to the research keywords;

[0023] Calculate the matching degree of the first comprehensive interest index vector and the second comprehensive interest index vector corresponding to the preset research topic to obtain the first matching degree of the research information corresponding to different preset research topics;

[0024] Based on the second set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the first matching degree, and the second set condition is the preset research topic corresponding to the first matching degree greater than the first threshold, or the second set condition is the preset research topic corresponding to the larger M1 first matching degrees.

[0025] In a possible implementation, the research keywords are matched with the research topics corresponding to the target research topics to obtain the target research topics corresponding to the target research topics of the target enterprises, including:

[0026] Obtaining a first comprehensive interest index vector corresponding to all research keywords corresponding to the research information, wherein the elements included in the first comprehensive interest index vector are comprehensive interest indexes corresponding to each research keyword;

[0027] For any research topic corresponding to the target research topic, the first comprehensive interest index vector is matched with the keyword index vector corresponding to the research topic to obtain a second matching degree of the research information corresponding to different research topics. The method for determining the keyword index vector refers to the method for determining the first comprehensive interest index vector.

[0028] Based on the third set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the second matching degree, the third set condition is the research topic corresponding to the second matching degree greater than the second threshold, or the third set condition is the research topic corresponding to the larger M2 second matching degrees.

[0029] In a possible implementation, the research keywords are matched with the research titles corresponding to the target research topics to obtain the target research titles corresponding to the target research topics of the target enterprises, including:

[0030] Obtain the research topic corresponding to the target research topic;

[0031] The research topics are merged and duplicated to obtain processed research topics;

[0032] For any processed research topic, match the research topic with the research keywords to obtain the target research topic corresponding to the target enterprise.

[0033] In a possible implementation, after generating a survey questionnaire for a target enterprise, the survey questionnaire is output to obtain a survey result for the survey questionnaire;

[0034] Call the preset research report template to generate a research report for the target enterprise based on the research results. The research report is editable.

[0035] In a second aspect, the present application provides an enterprise research device, comprising:

[0036] An acquisition module, used to acquire research information of a target enterprise, the research information including at least one of research background information, enterprise information and historical research information;

[0037] The determination module is used to determine the research keywords based on the research information;

[0038] The first matching module is used to match the research keywords with the preset research topics to obtain the target research topics for the target enterprises;

[0039] The second matching module is used to match the research keywords with the research topics corresponding to the target research topics, and obtain the target research topics corresponding to the target research topics of the target enterprises;

[0040] The generation module is used to call the preset survey questionnaire template and generate a survey questionnaire for the target enterprise based on the target survey topic using AIGC technology.

[0041] In a possible implementation, the determination module is specifically used to: apply natural language processing (NLP) technology to the research background information, based on a vocabulary in a preset knowledge base, to extract the first keyword included in the research background information;

[0042] For enterprise information, based on the knowledge base, extract the second keyword contained in the enterprise information;

[0043] For historical survey information, based on the knowledge base, extract the third keyword contained in the historical survey information;

[0044] Based on the information type included in the research information, a research keyword is determined according to at least one of the first keyword, the second keyword, and the third keyword.

[0045] In a possible implementation, the determination module is used to: determine the comprehensive interest index of keyword X according to any keyword X included in the first keyword, the second keyword, and the third keyword based on the information type included in the survey information;

[0046] Based on the first set condition that the research keyword should satisfy, the research keyword is determined according to the comprehensive interest index of the target keyword, the first set condition being that the comprehensive interest index is greater than a first threshold, or the first set condition being that the keywords corresponding to N comprehensive interest indexes with larger comprehensive interest indexes;

[0047] The determination of the comprehensive interest index satisfies Interest(X)=β*pre_Interest(X)+δ*com_Interest(X)+ε*his_Interest(X), wherein Interest(X) represents the comprehensive interest index, pre_Interest(X) represents the interest index of keyword X in the research background information, com_Interest(X) represents the interest index of keyword X in enterprise information, his_Interest(X) represents the interest index of keyword X in historical research information, β is the comprehensive interest index factor of the keyword in the research background information, δ is the comprehensive interest index factor of the keyword in enterprise information, ε is the comprehensive interest index factor of the keyword in historical research information, and the comprehensive interest index factors are all taken according to the empirical method;

[0048] Where times represents the number of times keyword X appears in the research background information, SUM represents the number of times all keywords appear in the research background information, Total_times represents the number of times keyword X appears in all research background information, Total_SUM represents the number of times all keywords appear in the research content of all research tasks, ∝ is the interest index factor, and its value is determined according to the empirical method; the determination method of com_Interest(X) and his_Interest(X) refers to the determination method of pre_Interest(X).

[0049] In a possible implementation manner, the first matching module is specifically used to: obtain a first comprehensive interest index vector corresponding to all research keywords corresponding to the research information, wherein the elements included in the first comprehensive interest index vector are comprehensive interest indexes corresponding to each research keyword;

[0050] Calculate the matching degree of the first comprehensive interest index vector and the second comprehensive interest index vector corresponding to the preset research topic to obtain the first matching degree of the research information corresponding to different preset research topics;

[0051] Based on the second set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the first matching degree, and the second set condition is the preset research topic corresponding to the first matching degree greater than the first threshold, or the second set condition is the preset research topic corresponding to the larger M1 first matching degrees.

[0052] In a possible implementation manner, the second matching module is specifically used to: obtain a first comprehensive interest index vector corresponding to all research keywords corresponding to the research information, wherein the elements included in the first comprehensive interest index vector are comprehensive interest indexes corresponding to each research keyword;

[0053] For any research topic corresponding to the target research topic, the first comprehensive interest index vector is matched with the keyword index vector corresponding to the research topic to obtain a second matching degree of the research information corresponding to different research topics. The method for determining the keyword index vector refers to the method for determining the first comprehensive interest index vector.

[0054] Based on the third set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the second matching degree, the third set condition is the research topic corresponding to the second matching degree greater than the second threshold, or the third set condition is the research topic corresponding to the larger M2 second matching degrees.

[0055] In a possible implementation manner, the second matching module is further used to: obtain a research topic corresponding to the target research topic;

[0056] The research topics are merged and duplicated to obtain processed research topics;

[0057] For any processed research topic, match the research topic with the research keywords to obtain the target research topic corresponding to the target enterprise.

[0058] In a possible implementation manner, the generating module is specifically used to: after generating a survey questionnaire for the target enterprise, output the survey questionnaire to obtain a survey result for the survey questionnaire;

[0059] Call the preset research report template to generate a research report for the target enterprise based on the research results. The research report is editable.

[0060] In a third aspect, the present application provides an electronic device, including:

[0061] Memory for storing computer-executable instructions;

[0062] A processor is used to execute computer-executable instructions to implement any enterprise research method in the first aspect.

[0063] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed, they are used to implement any one of the enterprise research methods in the first aspect.

[0064] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed, is used to implement the enterprise research method of any one of the first aspects.

[0065] The enterprise research method, device, equipment and storage medium provided in this application obtain the research information of the target enterprise, and the research information includes at least one of the research background information, enterprise information and historical research information; determine the research keywords according to the research information; match the research keywords with the preset research topics to obtain the target research topics for the target enterprise; match the research keywords with the research topics corresponding to the target research topics to obtain the target research topics corresponding to the target research topics of the target enterprise; call the preset research questionnaire template, and generate the research questionnaire for the target enterprise based on the target research topic using AIGC technology. Compared with manual enterprise research, this application can reduce the cost of enterprise research and improve the efficiency of enterprise research by intelligently matching the target research topics and intelligently matching the target research topics, and automatically generating the research questionnaire for the target enterprise using AIGC technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0067] Figure 1 A schematic diagram of a system for enterprise research provided in an embodiment of the present application;

[0068] Figure 2 An example of building a knowledge base provided in one embodiment of the present application;

[0069] Figure 3 A flowchart of an enterprise research method provided in an embodiment of the present application;

[0070] Figure 4 A flowchart for determining research keywords based on research information provided in an embodiment of the present application;

[0071] Figure 5 A schematic diagram of a process for determining research keywords based on the types of research information provided in an embodiment of the present application;

[0072] Figure 6 A flowchart of matching research keywords with preset research topics to obtain target research topics for target enterprises provided in an embodiment of the present application;

[0073] Figure 7 A schematic diagram of the research process provided for the embodiment of the present application;

[0074] Figure 8 A timing diagram of an enterprise survey provided for an embodiment of the present application;

[0075] Fig. 9 A schematic diagram of the structure of an enterprise research device provided in one embodiment of the present application;

[0076] Fig.10 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0077] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0078] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0079] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0080] In related technologies, some problems arise because companies and researchers are not familiar with digital transformation and intelligent change, such as the inability to formulate targeted survey questionnaires, the high cost of manual editing of survey questionnaire questions, and manual typesetting and editing of survey questionnaire questions.

[0081] Based on the above, this application proposes an enterprise research method, device, equipment and storage medium, which integrates AIGC technology into this application in combination with industry knowledge, data and expert experience. It matches intelligent research topics and titles and automatically generates research questionnaires, replacing the original research questionnaire generation method with limited research topics, monotonous content and high manual writing costs. It improves enterprises' perception of digital transformation content, improves the efficiency and quality of research questionnaire generation and filling, reduces the cost of research questionnaire customization, and improves research efficiency and quality.

[0082] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0083] For example, a system provided in the embodiment of the present application can be divided into seven modules: enterprise information management, subject research, knowledge base, research personnel management, research report, artificial intelligence (AI) model library and research task management. For a specific structure diagram, see Figure 1 , Figure 1 A schematic diagram of a system for enterprise research provided in one embodiment of the present application.

[0084] Among them, the enterprise information management module is used to record and manage the enterprise's industry, region, business, revenue, key personnel and other information. Basic enterprise information can be obtained in batches through authoritative enterprise information management platforms such as Qichacha, Tianyancha, and historical research reports, using web crawlers and NLP and other technical methods. Supplementary explanation: The enterprise information obtained by this application is the updated enterprise information.

[0085] The researcher management module is used to record and manage the basic information of researchers, including their region, industry, company, business areas of expertise, roles, levels, etc.

[0086] Research task management is used to record and manage research tasks, including creating new tasks, assigning tasks, pushing tasks, and calculating tasks. When creating a new enterprise research, the administrator fills in information such as the research enterprise, research background, and time. The system automatically associates the enterprise information and historical research diagnosis results. The administrator then selects appropriate researchers to assign tasks based on the situation.

[0087] Theme surveys are used to record and manage research topics, including the generation and filling of research topics. When adding a new research topic, the system will first automatically associate the research background, company information, and historical research diagnosis results, then mine the keywords of this research, and automatically match the research topic and research title, and finally generate the research questionnaire. After the researcher fills in the research questionnaire, the system will call the preset report template to automatically generate the research report, which the researcher can then edit and supplement.

[0088] The research report is used to generate and manage research reports, including automatic report generation and editing. After the survey questionnaire is completed, the system automatically calls the preset report template to generate a research report, and the researcher can edit and optimize it based on the report.

[0089] The knowledge base is used to generate and manage research-related knowledge, including enterprise databases, research subject databases, research topic databases, etc. The knowledge base is based on historical research questionnaires, research reports, enterprise information, research personnel information, industry and expert knowledge and other structured and unstructured information. It uses knowledge graph technology to extract entities and establish relationships in knowledge content, and establishes relevant knowledge graphs through Neo4j graph databases, such as enterprise databases, research subject databases, etc. Knowledge base construction examples are as follows: Figure 2 , Figure 2 An example of building a knowledge base provided for an embodiment of the present application.

[0090] The AI ​​model library is used to manage various survey-related AI models, including keyword mining models, survey topic matching models, survey question matching models, etc.

[0091] It is understandable that before conducting an enterprise survey, the administrator needs to create a new enterprise survey task in the survey task management module, fill in the survey background information, time, surveyed person information, survey personnel requirements and other related survey information, the system automatically associates the enterprise information and historical survey diagnosis results from the enterprise information management according to the enterprise name, and the administrator selects the appropriate researcher from the information in the researcher management according to the situation and assigns the task in the survey task management. The selection is based on the researcher's business, region, and business field of expertise. In addition, the administrator only does the work of assigning tasks here.

[0092] Figure 3 The following is a flow chart of a method for conducting an enterprise survey provided in one embodiment of the present application. Figure 3 As shown in the figure, the enterprise research methods include:

[0093] S301. Obtain research information of a target enterprise, where the research information includes at least one of research background information, enterprise information, and historical research information.

[0094] It can be understood that after the manager selects the researcher, the corresponding researcher enters the research task management module, and the relevant research topic and related information will automatically appear on the front-end page.

[0095] After obtaining the research information of the target enterprise, that is, after the researcher accepts the research task, he needs to add a new research topic in the research task management by entering the new research topic into the input box, and then the system will automatically obtain relevant research information such as research background information, enterprise information and historical research information. In addition, after accepting the research task, the researcher may also communicate with the target enterprise to complete more detailed research background information.

[0096] S302. Determine research keywords based on the research information.

[0097] Based on the research background information, enterprise information, historical research information and other related research information, the research keywords are automatically mined and the comprehensive interest index of the research keywords is calculated. Through keyword mining, the key directions of the research can be automatically focused, reducing the manual sorting costs of researchers.

[0098] S303: Match the research keywords with the preset research topics to obtain target research topics for the target enterprises.

[0099] By automatically matching research keywords with preset research topics, the scope of research topics and their related questions can be quickly identified from a large number of preset research topic libraries, greatly reducing the cost of manual screening of research topics.

[0100] S304: Match the research keywords with the research topics corresponding to the target research themes to obtain target research topics corresponding to the target research themes of the target enterprises.

[0101] By automatically matching research keywords with research topics corresponding to the target research themes, we can further accurately screen topics and improve the relevance and efficiency of the research.

[0102] S305: Call a preset survey questionnaire template, and based on the target survey topic, apply AIGC technology to generate a survey questionnaire for the target enterprise.

[0103] Among them, through training models and learning from large amounts of data, AIGC technology can generate relevant content based on the conditions or guidance entered by the user, such as generating relevant survey questionnaires based on the target survey topics entered by the user.

[0104] The enterprise research method provided in this application obtains the research information of the target enterprise, and the research information includes at least one of the research background information, enterprise information and historical research information; determines the research keywords according to the research information; matches the research keywords with the preset research topics to obtain the target research topics for the target enterprise; matches the research keywords with the research topics corresponding to the target research topics to obtain the target research topics corresponding to the target research topics for the target enterprise; calls the preset research questionnaire template, and generates the research questionnaire for the target enterprise based on the target research topic using AIGC technology. Compared with manual enterprise research, this application can reduce the cost of enterprise research and improve the efficiency of enterprise research by intelligently matching the target research topics and intelligently matching the target research topics, and automatically generating the research questionnaire for the target enterprise using AIGC technology.

[0105] Based on the above embodiment, in one implementation, the specific process of determining the research keywords according to the research information in S302 is shown in Figure 4 , Figure 4 A flowchart for determining research keywords based on research information provided in an embodiment of the present application. Figure 4 As shown, including:

[0106] S401. Apply NLP technology to the research background information and extract the first keyword contained in the research background information based on the vocabulary in the preset knowledge base.

[0107] It can be understood that this application uses NLP technology to perform text mining on research background information, wherein the method used for text mining is keyword extraction. Keyword extraction is to automatically extract the most representative and important keywords or phrases from the text. In addition, the keyword extraction method is a prior art, and this application will not be repeated here and will not limit the specific technical means.

[0108] S402: extract the second keyword contained in the enterprise information based on the knowledge base.

[0109] S403: extracting the third keyword contained in the historical research information based on the knowledge base.

[0110] It should be noted that the techniques used to extract the first keyword, the second keyword and the third keyword are the same.

[0111] S404: Based on the information type included in the research information, determine the research keyword according to at least one of the first keyword, the second keyword, and the third keyword.

[0112] For example, the types of information included in the research information can be divided into three categories: research background information, enterprise information, and historical research information. If the research information is research background information, the research keyword is determined to be the first keyword, if the research information is enterprise information, the research keyword is determined to be the second keyword, and if the research information is historical research information, the research keyword is determined to be the third keyword.

[0113] Further, based on the types of research information included, determine the research keywords. Figure 5 , Figure 5 A flow chart of determining research keywords based on the types of research information provided by an embodiment of the present application. Figure 5 As shown, including:

[0114] Based on the type of information included in the survey information, the comprehensive interest index of keyword X is determined according to any keyword X included in the first keyword, the second keyword and the third keyword; based on the first set condition that the survey keyword should meet, the survey keyword is determined according to the comprehensive interest index of the target keyword, the first set condition is that the comprehensive interest index is greater than the first threshold, or the first set condition is the keywords corresponding to N comprehensive interest indexes with larger comprehensive interest indexes.

[0115] Among them, the determination of the comprehensive interest index satisfies Interest(X) = β*pre_Interest(X)+δ*com_Interest(X)+ε*his_Interest(X), where Interest(X) represents the comprehensive interest index, pre_Interest(X) represents the interest index of keyword X in the research background information, com_Interest(X) represents the interest index of keyword X in enterprise information, his_Interest(X) represents the interest index of keyword X in historical research information, β is the comprehensive interest index factor of the keyword in the research background information, δ is the comprehensive interest index factor of the keyword in enterprise information, ε is the comprehensive interest index factor of the keyword in historical research information, and the comprehensive interest index factor is determined according to the empirical method, and the general value range is (0,1). In addition, Interest(X) is a scalar.

[0116] Further, Among them, times represents the number of times keyword X appears in the research background information, SUM represents the number of times all keywords appear in the research background information, Total_times represents the number of times keyword X appears in all research background information, Total_SUM represents the number of times all keywords appear in the research content of all research tasks, ∝ is the interest index factor, and its value is determined according to the empirical method, and the general value range is (0,1); the determination method of com_Interest(X) and his_Interest(X) refers to the determination method of pre_Interest(X). Further, Where com_times is the number of times keyword X appears in the enterprise information text, com_SUM is the number of times all keywords appear in the enterprise information text, com_Total_times is the number of times keyword X appears in all enterprise information, com_Total_SUM is the number of times all keywords appear in all enterprise information, and ρ is the comprehensive interest index factor, whose value is determined according to the empirical method. In addition, his_Interest(X) is logically consistent with com_Interest(X), which will not be repeated here.

[0117] Supplementary explanation: This application sorts the keywords corresponding to the N comprehensive interest indexes whose comprehensive interest index is greater than the first threshold, or the first setting condition is that the comprehensive interest index is larger, according to the comprehensive interest index. The specific sorting method is not limited in this application. Further, the first threshold is determined based on the empirical method.

[0118] By determining research keywords based on the types of information contained in the research information, the accuracy of corporate research information can be improved.

[0119] Furthermore, it is necessary to match the research keywords obtained above with the preset research topics to obtain the target research topics for the target enterprise, that is, intelligent research topic matching. The intelligent research topic matching method is based on relevant research information such as enterprise research background information, historical research information, enterprise information, etc., to mine research keywords and their comprehensive interest index, and can quickly match target research topics that meet the requirements among a large number of research topics, thereby improving the matching degree and speed of topic screening, and reducing the cost of manual screening and the threshold for researchers to use. For specific operations of the intelligent research topic matching method, see Figure 6 , Figure 6 A flowchart of matching research keywords with preset research topics to obtain target research topics for target enterprises is provided in an embodiment of the present application. Figure 6 As shown, including:

[0120] Obtain a first comprehensive interest index vector corresponding to all research keywords corresponding to the research information, wherein the elements contained in the first comprehensive interest index vector are the comprehensive interest indexes corresponding to the research keywords; calculate the matching degree between the first comprehensive interest index vector and the second comprehensive interest index vector corresponding to the preset research topic, and obtain a first matching degree between the research information and different preset research topics.

[0121] It can be understood that the first comprehensive interest index vector is composed of the comprehensive interest indexes corresponding to all the research keywords corresponding to the research information and all the keywords consisting of the preset research topics, and the second comprehensive interest index vector corresponding to the preset research topic is composed of the comprehensive interest indexes corresponding to all the keywords consisting of the keywords of the preset research topic and all the keywords corresponding to the research information. Assuming that the first comprehensive interest index vector is D, D=(x 1 ,x 2 ,…,x i ,…,x n ), the second comprehensive interest index vector is S, S = (s 1 ,s 2 ,…,s i ,…,s n As an example, if all the research keywords corresponding to the research information and the corresponding first comprehensive interest index are human resources 0.5 and finance 0.6, and all the research keywords corresponding to the preset research topics and the corresponding second comprehensive interest index are finance 0.6 and freight 0.3, then the first comprehensive interest index vector D = (0.5, 0.6, 0), and the second comprehensive interest index vector S = (0, 0.6, 0.3).

[0122] Furthermore, the first comprehensive interest index vector D and the second comprehensive interest index vector S are used to perform a matching calculation. The matching calculation satisfies

[0123]

[0124] Wherein, D·S is the dot product of the first comprehensive interest index vector D and the second comprehensive interest index vector S, |D| is the modulus of the first comprehensive interest index vector D, and |S| is the modulus of the second comprehensive interest index vector S.

[0125] Based on the second set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the first matching degree, and the second set condition is the preset research topic corresponding to the first matching degree greater than the first threshold, or the second set condition is the preset research topic corresponding to the larger M1 first matching degrees.

[0126] The matching degree of the target research topic is a first matching degree greater than a first threshold or a larger M1 first matching degrees.

[0127] By matching research keywords with preset research topics, we can obtain the target research topic. We can quickly identify the research topic scope and related questions in a large number of research topic libraries, greatly reducing the cost of manual screening of research topics.

[0128] Further, on the basis of the above embodiments, the research keywords are matched with the research topics corresponding to the target research themes to obtain the target research topics for the target enterprises corresponding to the target research themes, including: obtaining a first comprehensive interest index vector corresponding to all the research keywords corresponding to the research information, the elements contained in the first comprehensive interest index vector are the comprehensive interest indexes corresponding to the research keywords; for any research topic corresponding to the target research theme, the first comprehensive interest index vector is matched with the keyword index vector corresponding to the research topic to obtain a second matching degree of the research information corresponding to different research topics, and the method for determining the keyword index vector refers to the method for determining the first comprehensive interest index vector; based on the third setting condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the second matching degree, the third setting condition being the research topic corresponding to the second matching degree greater than the second threshold, or the third setting condition being the research topic corresponding to the larger M2 second matching degrees.

[0129] It is understandable that it is necessary to obtain the research topics corresponding to the target research theme, merge and remove duplicate research topics to obtain processed research topics, and for any processed research topic, match the research topic with the research keywords to obtain the target research topic corresponding to the target enterprise's target research theme.

[0130] Optionally, matching the research topic with the research keyword means calculating the matching degree between the first comprehensive interest index vector and the keyword index vector corresponding to the research topic to obtain a second matching degree. Assuming that the keyword index vector corresponding to the research topic is Z, the second matching degree calculation satisfies

[0131]

[0132] Among them, the calculation method of the keyword index vector Z corresponding to the research topic is consistent with the first comprehensive interest index vector D, which will not be repeated here. Further, D·Z is the dot product of the first comprehensive interest index vector D and the keyword index vector Z corresponding to the research topic, |D| is the modulus of the first comprehensive interest index vector D, and |Z| is the modulus of the keyword index vector Z corresponding to the research topic.

[0133] After obtaining the second matching degree, it is necessary to determine whether the second matching degree of the target research topic for the target enterprise is greater than the second matching degree of the second threshold, or whether it is a larger M2 second matching degree. If the result of the judgment is yes, the research topic corresponding to the second matching degree is determined as the research topic of this time, wherein the second threshold is determined based on the empirical method and can be set according to specific needs.

[0134] By calculating the matching degree between the research keywords and the research topics corresponding to the target research theme, the scope of the research topics can be accurately defined, reducing the cost of manual screening of research topics and improving the efficiency of subsequent research.

[0135] For example, assuming that the surveyed enterprise is Enterprise A, the relevant survey information of Enterprise A can be found in Table 1.

[0136] Table 1

[0137]

[0138] As can be seen from Table 1, after obtaining the comprehensive interest index corresponding to the research keyword of Company A, the comprehensive interest index of the preset research topic is matched to obtain the target research topic. After obtaining the target research topic, the research keyword is matched with the research topic of the target research topic to obtain the target research topic. For relevant information on matching the research topic of the target research topic according to the research keyword of Company A, see Table 2, which is the relevant information of the matching topic of Company A provided in an embodiment of the present application.

[0139] Table 2

[0140]

[0141] Furthermore, after determining the target research topic, the researcher will automatically generate a research questionnaire based on a certain business logic using a preset research questionnaire template, thereby reducing the cost and time of manually combing and editing the research questionnaire.

[0142] After generating a survey questionnaire for the target enterprise, the survey questionnaire is output to obtain the survey results for the survey questionnaire; a preset survey report template is called to generate a survey report for the target enterprise based on the survey results, and the survey report is editable.

[0143] Based on the results of the survey questionnaire, the system automatically generates a survey report according to a certain business logic using a preset survey report template, thus reducing the cost of manual editing and adjustment of the survey report.

[0144] For example, the research flow diagram provided in the embodiment of the present application is shown in Figure 7 , Figure 7 This is a schematic diagram of the research process provided by the embodiment of this application. Figure 7 As shown, the present application first uses NLP technology to extract keywords of research background information, enterprise information, and historical research information, and calculates its comprehensive interest index, and determines the keywords corresponding to N comprehensive interest indexes that are greater than the first threshold or are larger as research keywords, matches the research keywords with preset research topics, and obtains the target research topics for the target enterprises, matches the research keywords with the research topics corresponding to the target research topics, and obtains the target research topics corresponding to the target research topics for the target enterprises, and then calls the preset research questionnaire template to generate a research questionnaire, fills in the questionnaire and calls the preset report to generate a research report, wherein the research report can be manually edited. For additional information, see the enterprise research timing diagram provided in the embodiment of the present application. Figure 8 , Figure 8 A timing diagram of an enterprise survey provided for an embodiment of the present application.

[0145] Fig. 9 This is a schematic diagram of the structure of an enterprise research device provided in an embodiment of the present application. Figure 4 As shown, the enterprise research device 900 includes:

[0146] An acquisition module 901 is used to acquire research information of a target enterprise, where the research information includes at least one of research background information, enterprise information, and historical research information;

[0147] A determination module 902 is used to determine research keywords based on the research information;

[0148] The first matching module 903 is used to match the research keywords with the preset research topics to obtain the target research topics for the target enterprises;

[0149] The second matching module 904 is used to match the research keywords with the research topics corresponding to the target research topics, and obtain the target research topics corresponding to the target research topics of the target enterprises;

[0150] The generation module 905 is used to call a preset survey questionnaire template and generate a survey questionnaire for a target enterprise based on the target survey topic by applying AIGC technology.

[0151] In a possible implementation manner, the determination module 902 is specifically used to: apply NLP technology to the research background information, based on a vocabulary in a preset knowledge base, to extract the first keyword included in the research background information;

[0152] For enterprise information, based on the knowledge base, extract the second keyword contained in the enterprise information;

[0153] For historical survey information, based on the knowledge base, extract the third keyword contained in the historical survey information;

[0154] Based on the information type included in the research information, a research keyword is determined according to at least one of the first keyword, the second keyword, and the third keyword.

[0155] In a possible implementation, the determination module 902 is used to: determine the comprehensive interest index of the keyword X according to any keyword X included in the first keyword, the second keyword, and the third keyword based on the information type included in the survey information;

[0156] Based on the first set condition that the research keyword should satisfy, the research keyword is determined according to the comprehensive interest index of the target keyword, the first set condition being that the comprehensive interest index is greater than a first threshold, or the first set condition being that the keywords corresponding to N comprehensive interest indexes with larger comprehensive interest indexes;

[0157] The determination of the comprehensive interest index satisfies Interest(X)=β*pre_Interest(X)+δ*com_Interest(X)+ε*his_Interest(X), wherein Interest(X) represents the comprehensive interest index, pre_Interest(X) represents the interest index of keyword X in the research background information, com_Interest(X) represents the interest index of keyword X in enterprise information, his_Interest(X) represents the interest index of keyword X in historical research information, β is the comprehensive interest index factor of the keyword in the research background information, δ is the comprehensive interest index factor of the keyword in enterprise information, ε is the comprehensive interest index factor of the keyword in historical research information, and the comprehensive interest index factors are all taken according to the empirical method;

[0158] Where times represents the number of times keyword X appears in the research background information, SUM represents the number of times all keywords appear in the research background information, Total_times represents the number of times keyword X appears in all research background information, Total_SUM represents the number of times all keywords appear in the research content of all research tasks, ∝ is the interest index factor, and its value is determined according to the empirical method; the determination method of com_Interest(X) and his_Interest(X) refers to the determination method of pre_Interest(X).

[0159] In a possible implementation manner, the first matching module 903 is specifically used to: obtain a first comprehensive interest index vector corresponding to all research keywords corresponding to the research information, where the elements included in the first comprehensive interest index vector are comprehensive interest indexes corresponding to each research keyword;

[0160] Calculate the matching degree of the first comprehensive interest index vector and the second comprehensive interest index vector corresponding to the preset research topic to obtain the first matching degree of the research information corresponding to different preset research topics;

[0161] Based on the second set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the first matching degree, and the second set condition is the preset research topic corresponding to the first matching degree greater than the first threshold, or the second set condition is the preset research topic corresponding to the larger M1 first matching degrees.

[0162] In a possible implementation manner, the second matching module 904 is specifically used to: obtain a first comprehensive interest index vector corresponding to all research keywords corresponding to the research information, where the elements included in the first comprehensive interest index vector are comprehensive interest indexes corresponding to each research keyword;

[0163] For any research topic corresponding to the target research topic, the first comprehensive interest index vector is matched with the keyword index vector corresponding to the research topic to obtain a second matching degree of the research information corresponding to different research topics. The method for determining the keyword index vector refers to the method for determining the first comprehensive interest index vector.

[0164] Based on the third set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the second matching degree, the third set condition is the research topic corresponding to the second matching degree greater than the second threshold, or the third set condition is the research topic corresponding to the larger M2 second matching degrees.

[0165] In a possible implementation manner, the second matching module 904 is further used to: obtain a research topic corresponding to the target research topic;

[0166] The research topics are merged and duplicated to obtain processed research topics;

[0167] For any processed research topic, match the research topic with the research keywords to obtain the target research topic corresponding to the target enterprise.

[0168] In a possible implementation, the generation module 905 is specifically used to: after generating a survey questionnaire for the target enterprise, output the survey questionnaire to obtain a survey result for the survey questionnaire;

[0169] Call the preset research report template to generate a research report for the target enterprise based on the research results. The research report is editable.

[0170] The enterprise research device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0171] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the processing module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0172] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more microprocessors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element to allocate program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0173] Fig.10 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Fig.10 As shown, the electronic device 1000 provided in the embodiment of the present application may include: a processor 1001 and a memory 1002, wherein:

[0174] Memory 1002, used for storing computer-executable instructions;

[0175] The processor 1001 is used to execute the computer execution instructions stored in the memory 1002 to implement the enterprise research method described in the above method embodiment.

[0176] It should be understood that the processor 1001 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor. The memory 1002 may include a high-speed random access memory (RAM), and may also include non-volatile storage NVM (non-volatile memory), such as at least one disk storage, and can also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disk, etc.

[0177] Optionally, the electronic device 1000 may further include a communication interface 1003. In a specific implementation, if the communication interface 1003, the memory 1002 and the processor 1001 are implemented independently, the communication interface 1003, the memory 1002 and the processor 1001 may be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0178] Optionally, in a specific implementation, if the communication interface 1003, the memory 1002 and the processor 1001 are integrated on a chip, the communication interface 1003, the memory 1002 and the processor 1001 can communicate through an internal interface.

[0179] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the enterprise research method described in any of the aforementioned embodiments.

[0180] It is understood that the computer readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special computer.

[0181] An exemplary computer-readable storage medium is coupled to a processor so that the processor can read information from the computer-readable storage medium and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be an integral part of the processor. The processor and the computer-readable storage medium can be located in an ASIC. Of course, the processor and the computer-readable storage medium can also exist in an electronic device as discrete components.

[0182] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a computer-readable storage medium, including a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application.

[0183] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements the enterprise research method described in any of the aforementioned embodiments.

[0184] It should be noted that, for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application. It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indications of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated in this article, the execution of these steps is not strictly restricted in sequence, and these steps can be performed in other sequences. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps. In the above embodiments, the description of each embodiment has its own emphasis, and the part that is not described in detail in a certain embodiment can refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0186] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for enterprise research, characterized in that: include Acquire research information of the target enterprise, wherein the research information includes at least one of research background information, enterprise information, and historical research information; Determine the research keywords based on the research information; Matching the research keywords with preset research topics to obtain target research topics for the target enterprise; Matching the research keywords with the research topics corresponding to the target research topics to obtain the target research topics corresponding to the target enterprises; The preset survey questionnaire template is called, and based on the target survey topic, the artificial intelligence general content AIGC technology is applied to generate a survey questionnaire for the target enterprise.

2. The enterprise research method according to claim 1, characterized in that: Determining the research keywords according to the research information includes: For the research background information, applying natural language text NLP technology, based on a vocabulary in a preset knowledge base, extracting the first keyword contained in the research background information; For the enterprise information, based on the knowledge base, extracting a second keyword contained in the enterprise information; With respect to the historical research information, based on the knowledge base, extracting a third keyword contained in the historical research information; Based on the information type included in the research information, the research keyword is determined according to at least one of the first keyword, the second keyword and the third keyword.

3. The enterprise research method according to claim 2, characterized in that: The determining the research keyword based on the type of information included in the research information and correspondingly according to at least one of the first keyword, the second keyword, and the third keyword includes: Based on the information types included in the survey information, correspondingly determining a comprehensive interest index of keyword X according to any keyword X included in the first keyword, the second keyword, and the third keyword; Based on a first setting condition that the research keyword should satisfy, the research keyword is determined according to the comprehensive interest index of the target keyword, wherein the first setting condition is that the comprehensive interest index is greater than a first threshold, or the first setting condition is keywords corresponding to N comprehensive interest indexes with larger comprehensive interest indexes; The determination of the comprehensive interest index satisfies Interest(X)=β*pre_Interest(X)+δ*com_Interest(X)+ε*his_Interest(X), wherein Interest(X) represents the comprehensive interest index, pre_Interest(X) represents the interest index of keyword X in the research background information, com_Interest(X) represents the interest index of keyword X in the enterprise information, his_Interest(X) represents the interest index of keyword X in the historical research information, β is the comprehensive interest index factor of the keyword in the research background information, δ is the comprehensive interest index factor of the keyword in the enterprise information, ε is the comprehensive interest index factor of the keyword in the historical research information, and the comprehensive interest index factors are all taken according to the empirical method; Wherein, times represents the number of times keyword X appears in the research background information, SUM represents the number of times all keywords appear in the research background information, Total_times represents the number of times keyword X appears in all research background information, Total_SUM represents the number of times all keywords appear in the research content of all research tasks, ∝ is the interest index factor, and its value is determined according to the empirical method; the determination method of com_Interest(X) and his_Interest(X) refers to the determination method of pre_Interest(X).

4. The enterprise research method according to claim 3, characterized in that: The research keywords are matched with preset research topics to obtain target research topics for the target enterprise, including: Obtaining a first comprehensive interest index vector corresponding to all the research keywords corresponding to the research information, wherein the elements included in the first comprehensive interest index vector are comprehensive interest indexes corresponding to the research keywords; Calculating the matching degree of the first comprehensive interest index vector and the second comprehensive interest index vector corresponding to the preset research topic to obtain a first matching degree of the research information corresponding to different preset research topics; Based on a second set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the first matching degree, the second set condition is a preset research topic corresponding to a first matching degree greater than a first threshold, or the second set condition is a preset research topic corresponding to a larger number of M1 first matching degrees.

5. The enterprise research method according to claim 3, characterized in that: Matching the research keywords with the research topics corresponding to the target research topics to obtain the target research topics of the target enterprises corresponding to the target research topics, including: Obtaining a first comprehensive interest index vector corresponding to all the research keywords corresponding to the research information, wherein the elements included in the first comprehensive interest index vector are comprehensive interest indexes corresponding to the research keywords; For any research topic corresponding to the target research topic, the first comprehensive interest index vector is matched with the keyword index vector corresponding to the research topic to obtain a second matching degree of the research information corresponding to different research topics. The method for determining the keyword index vector refers to the method for determining the first comprehensive interest index vector; Based on the third set condition that the target research topic should meet, the target research topic for the target enterprise is determined according to the second matching degree, the third set condition is the research topic corresponding to the second matching degree greater than the second threshold, or the third set condition is the research topic corresponding to the larger M2 second matching degrees.

6. The enterprise research method according to any one of claims 1 to 5, characterized in that: Matching the research keywords with the research topics corresponding to the target research topics to obtain the target research topics of the target enterprises corresponding to the target research topics, including: Obtaining a research topic corresponding to the target research topic; The research topics are combined and duplicated to obtain processed research topics; For any processed research topic, the research topic is matched with the research keyword to obtain a target research topic of the target enterprise corresponding to the target research theme.

7. The enterprise research method according to any one of claims 1 to 5, characterized in that: Also includes: After generating a survey questionnaire for the target enterprise, outputting the survey questionnaire to obtain a survey result for the survey questionnaire; A preset research report template is called to generate a research report for the target enterprise based on the research results, and the research report is editable.

8. An enterprise research device, characterized in that: include: An acquisition module, used to acquire research information of a target enterprise, wherein the research information includes at least one of research background information, enterprise information, and historical research information; A determination module, used to determine the research keywords according to the research information; A first matching module is used to match the research keyword with a preset research topic to obtain a target research topic for the target enterprise; The second matching module is used to match the research keyword with the research topic corresponding to the target research topic to obtain the target research topic corresponding to the target enterprise; The generation module is used to call a preset survey questionnaire template, and based on the target survey topic, apply AIGC technology to generate a survey questionnaire for the target enterprise.

9. An electronic device, characterized in that: include: Memory for storing computer-executable instructions; A processor, configured to execute the computer-executable instructions to implement the enterprise research method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the enterprise research method according to any one of claims 1 to 7.

Images