Method and system for searching risk enterprise ethnic group based on knowledge graph

Abstract

The invention discloses a method and system for searching a risk enterprise group based on a knowledge graph, and the method comprises the steps: obtaining the related information of an enterprise industrial chain graph, carrying out the layering of hierarchical labels, selecting the related elements of the labels of the enterprise industrial chain graph according to the basic information of the enterprise industrial chain, forming an enterprise industrial chain key element knowledge base, and carrying out the searching of the risk enterprise group. Performing label keyword extraction and matching, generating an enterprise portrait and enterprise data report information, constructing an enterprise industry chain knowledge graph, performing enterprise risk evaluation according to the enterprise industry chain knowledge graph, and then performing enterprise investment attraction management strategy processing; according to the method, the business feature tag of the enterprise can be formed, and after the business feature tag is accurately matched with the industrial chain graph, the enterprise industrial chain knowledge graph is constructed, and the risk of the enterprise ethnic group is evaluated and analyzed in multiple dimensions, so that the risk evaluation of the enterprise ethnic group is more accurate, efficient and comprehensive compared with a traditional method, and the risk evaluation efficiency of the enterprise ethnic group is improved. And an enterprise investment attraction management strategy is given.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for finding risk enterprise clusters based on a knowledge graph. Background Art

[0002] The industrial chain is a series of links involved in the whole process from product production to consumption, covering multiple links, including raw material procurement, production, processing, sales, etc. These links are based on certain technical and economic connections, and form a chain-like relationship based on specific logical relationships and time-space layout relationships. The concept of the industrial chain includes four dimensions: value chain, enterprise chain, supply and demand chain, and space chain. These four dimensions form an industrial chain in the process of mutual docking and equilibrium.

[0003] However, the existing natural language processing technology, feature extraction, forming the business feature labels of enterprises, and matching them with the industrial chain map lacks the construction and application of the enterprise industrial chain knowledge map, especially the risk assessment and analysis of enterprise groups, which is still at the stage of manual research and judgment. It is not only inefficient but also generally inaccurate, and it is difficult to provide data support and analysis basis for subsequent enterprise policy formulation and enterprise decision-making. For this reason, we propose a method and system for finding risk enterprise groups based on knowledge graphs. Summary of the invention

[0004] In view of the above problems existing in the existing enterprise risk data processing and analysis, the present invention is proposed.

[0005] Therefore, one of the objects of the present invention is to provide a method and system for finding risky enterprise clusters based on knowledge graphs, which extracts features through big data processing technology to form business feature labels for enterprises. After precise matching with the industrial chain graph, it can construct a knowledge graph for the enterprise industrial chain and conduct multi-dimensional risk assessment and analysis of enterprise clusters, and provide enterprise investment management strategies.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In one aspect, the present invention provides a method for finding a risk enterprise group based on a knowledge graph, comprising:

[0008] Obtain information related to the enterprise industry chain map and stratify the hierarchical labels as the basic information of the enterprise industry chain;

[0009] According to the basic information of the enterprise industrial chain and after selecting the elements associated with the enterprise industrial chain map label, mark the key elements of the enterprise industrial chain map and supplement the marked key element information associated with the enterprise to form a knowledge base of the key elements of the enterprise industrial chain;

[0010] Responding to the enterprise industrial chain key element knowledge base and according to the enterprise's named entity recognition method, extracting and matching label keywords in the enterprise industrial chain map to form enterprise industrial chain group matching result information;

[0011] According to the enterprise industrial chain group matching result information, the enterprise industrial chain risk assessment model is constructed, and the enterprise portrait and the enterprise data report information are generated; wherein the enterprise industrial chain risk assessment model is constructed specifically according to the enterprise industrial chain group matching result information to conduct a multi-dimensional evaluation of the enterprise industrial chain, and the multi-dimensional evaluation is evaluated from the scale index, development index, innovation index, money absorption index, risk index, and efficiency index, that is, a qualitative and quantitative analysis of the enterprise industrial chain risk assessment is conducted, that is, the enterprise exposure flow amplitude, scale index, development index, innovation index, money absorption index, risk index, and efficiency index are normalized and then comprehensively calculated to generate the enterprise's dynamic risk coefficient δ k , by analyzing the dynamic risk coefficient δ of enterprises in the industrial chain k After the value is calculated, the enterprises in the industrial chain map are divided according to the dynamic risk coefficient δ k The values ​​are sorted from large to small and a risk list of enterprises in the industrial chain map is generated. The dynamic risk coefficient of the enterprise δ k The calculation of is as follows:

[0012]

[0013] In the formula, g k is the exposure flow amplitude of enterprise k, is the scale dimension index value, is the development dimension index value, is the innovation dimension index value, is the gold-attracting dimension index value, is the risk dimension index value, is the efficiency dimension index value; a k , b k 、c k ,d k 、e k 、f k are the proportional coefficients of the scale dimension index, development dimension index, innovation dimension index, capital attraction dimension index, risk dimension index, and efficiency dimension index, respectively, and a k , b k 、c k ,d k 、e k 、f k are both greater than 0, and the proportional coefficient a k , b k 、c k ,d k 、e k 、fk The specific value of is set according to the importance of the corresponding dimension index in the enterprise industrial chain map, and ln represents the symbol of the natural logarithm function;

[0014] In response to the enterprise portrait and the enterprise data report information, the enterprise industrial chain relevance evaluation is performed, and at the same time, the enterprise industrial chain knowledge map is constructed and the enterprise risk evaluation is performed according to the enterprise industrial chain knowledge map, and then the enterprise investment management strategy is processed, wherein the enterprise portrait is specifically constructed through enterprise data integration and fusion, and the enterprise micro-portrait is formed to form an enterprise digital archive, and the enterprise risk value is evaluated and modeled according to the enterprise digital archive. Specifically, the enterprise micro-portrait is constructed by establishing a reliability function of the enterprise portrait, and the calculation is as follows:

[0015]

[0016] Among them, Q n (f) Micro-profile of the enterprise n The reliability function of C(n,i) is the factorial, which is the reliability function of the enterprise from the i-th micro-profile to the enterprise n The factorial of microscopic images, Q i (f) is the reliability function of the i-th enterprise micro-profile, Q 0 (f) is the average reliability function of the enterprise micro-portrait.

[0017] As a preferred solution of the present invention, it obtains information related to the enterprise industrial chain map, specifically based on industrial data resources and industrial chain models, and forms a hierarchical structure of the enterprise industrial chain knowledge map according to industry reports, industrial research institutions and expert discussions. The hierarchical structure of the industrial chain knowledge map includes upstream, midstream, downstream and subdivided level labels, and also includes analyzing the industrial chains of marked enterprises in the region, combining the chain investment promotion method to provide strategy information for supplementing, strengthening and extending the specified industrial chain.

[0018] As a preferred solution of the present invention, wherein: the enterprise industrial chain knowledge graph is constructed and enterprise risk assessment is performed based on the enterprise industrial chain knowledge graph, wherein the enterprise industrial chain knowledge graph includes an industry encyclopedia overview and local status analysis;

[0019] The industry encyclopedia overview includes industry graphs, industry maps, industry insights and industry evaluations;

[0020] The local status analysis includes industry analysis, spatial distribution analysis and evolution analysis.

[0021] As a preferred solution of the present invention, the industrial map is to display the industrial structure division of the current enterprise industrial chain and the number of operating enterprises corresponding to the subdivided industries;

[0022] The industrial map shows the spatial distribution and agglomeration information of enterprises associated with the industrial chain in the form of a heat map;

[0023] The industry insight is to analyze and display the current status of the industry from the perspective of the number of existing enterprises in the industry and the regional distribution of enterprises for a single enterprise industry chain, and to provide data and information support for regional industry investment promotion and industry direction selection;

[0024] The industrial evaluation is to conduct qualitative and quantitative analysis of the enterprise industrial chain risk assessment by constructing an enterprise industrial chain risk assessment model;

[0025] The industrial analysis combines the industrial development insights and the analysis of the local industrial status, and matches the development suggestion information of each industry in the local marked industrial chain through the algorithm model of strengthening, supplementing and extending the chain. The industrial analysis is expressed in the following forms: relationship diagram and tree diagram; the relationship diagram is a bubble diagram;

[0026] The spatial distribution analysis is to display the spatial agglomeration information of the marked industrial enterprises in the region in the form of a map, which is used to measure whether the development of the industry in the region is balanced, and to reflect the degree of concentration and specialization of the industry in the region;

[0027] The evolution analysis is to visually display the overall scale of the region's marked industries through the dimensions of the number of marked industry enterprises and the registered capital of marked industry enterprises, and is used to measure the overall development level of the region's marked industries.

[0028] As a preferred solution of the present invention, the scale index, development index, innovation index, money-absorbing index, risk index, and efficiency index are visualized in the form of a radar chart and compared with the average level of the enterprise's associated industrial chain. At the same time, the enterprise's scale index, development index, innovation index, money-absorbing index, risk index, and efficiency index are integrated into the enterprise's comprehensive index, and a ranking and overall overview are made in the enterprise's industrial chain based on the enterprise's comprehensive index.

[0029] As a preferred solution of the present invention, the data report information includes three dimensions: basic information, business management information, and social credit information.

[0030] As a preferred solution of the present invention, while generating enterprise portraits, it also includes generating enterprise strict selection portraits. Specifically, through industrial chain investment promotion, theme enterprise recommendation, enterprise search, park enterprise search and investment promotion headlines, high-quality enterprises that meet the strict selection standards are found and matched to generate enterprise strict selection portraits.

[0031] As a preferred solution of the present invention, the industrial chain investment promotion is to locate the target enterprise group to form an enterprise group according to the selected different industrial chain links and the preset screening conditions; wherein the screening conditions include: industry screening, city screening, registered capital, enterprise age, label, innovation index, credit rating, comprehensive strategy, innovation advantage, capital advantage, credit advantage, keyword search, and similar enterprise recommendation;

[0032] The theme recommendation is to recommend enterprises based on various enterprise lists and generate enterprise diagnosis reports;

[0033] The enterprise search is based on keyword query of enterprise information in various dimensions, combined with various screening conditions, to locate the target enterprise group;

[0034] The park enterprise search is based on the park's leading industry positioning, screening parks and resident enterprises related to the target industrial chain across the country, exploring target parks and intended enterprises through various means, and supporting value assessment of enterprises and selecting them as investment targets;

[0035] The investment headlines are various types of financing, bidding, exhibition and patent information released on the Internet, and relevant enterprise information of the industrial chain involved is extracted.

[0036] As a preferred solution of the present invention, the enterprise risk assessment is based on the enterprise's investment records, intellectual property rights, operating conditions, compliance and legality, and related group information, to conduct a panoramic scan of the enterprise, and evaluate the investment intention, value level and risk level of the enterprise through the scanning results, providing data reference for investment target screening and investment management strategy processing.

[0037] In another aspect, the present invention provides a system for searching for risk enterprise groups based on a knowledge graph, comprising:

[0038] The industrial chain information acquisition module is used to obtain information related to the enterprise industrial chain map and stratify the hierarchical labels as the basic information of the enterprise industrial chain;

[0039] The industrial chain map element marking module is used to mark the key elements of the enterprise industrial chain map according to the basic information of the enterprise industrial chain and select the elements associated with the enterprise industrial chain map label, and then supplement the marked key element information associated with the enterprise to form a knowledge base of the key elements of the enterprise industrial chain;

[0040] The industrial chain graph recognition and matching module is used to respond to the enterprise industrial chain key element knowledge base and extract and match the label keywords in the enterprise industrial chain graph according to the enterprise's named entity recognition method to form the enterprise industrial chain group matching result information;

[0041] The enterprise portrait generation module is used to build an enterprise industry chain risk assessment model based on the enterprise industry chain group matching result information, and generate enterprise portraits and enterprise data report information;

[0042] The enterprise management module is used to respond to the enterprise portrait and the enterprise's data report information, conduct an enterprise industry chain relevance evaluation, construct an enterprise industry chain knowledge graph and conduct an enterprise risk evaluation based on the enterprise industry chain knowledge graph, and then process the enterprise investment management strategy.

[0043] Compared with the prior art, the present invention has the following beneficial effects: the present invention extracts features through big data processing and knowledge graph construction technology to form the business feature labels of the enterprises, and after accurate matching with the industrial chain graph, completes the construction of the enterprise industrial chain knowledge graph and the multi-dimensional risk assessment and analysis of enterprise groups. By establishing enterprise portraits and constructing enterprise micro-portraits based on reliability, the unified analysis of enterprise portraits is further scientifically refined, which is more conducive to the qualitative and quantitative analysis of the risks, importance and influence of each enterprise in the enterprise industrial chain, and is conducive to the formation of intelligent and efficient management strategies. At the same time, it is more reasonable and accurate, making the risk assessment of enterprise groups more accurate, efficient and comprehensive than traditional methods, and providing enterprise investment management strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0045] Figure 1 This is a flow chart of the method for finding risk enterprise groups based on the knowledge graph of the present invention;

[0046] Figure 2 It is a schematic diagram of the module structure of a system for searching for risk enterprise groups based on a knowledge graph in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of an index of the knowledge graph of the industrial chain of integrated circuit enterprises in an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of marking key element information of an enterprise industry tag in an embodiment of the present invention;

[0049] Figure 5 A schematic diagram of an interface display of evolution analysis in an embodiment of the present invention;

[0050] Numbers in the figure: 100, industrial chain information acquisition module; 101, industrial chain map element marking module; 102, industrial chain map identification and matching module; 103, enterprise portrait generation module; 104, enterprise management module. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0052] Reference Figure 1-Figure 5 , is an embodiment of the present invention, which provides a method for finding risk enterprise groups based on knowledge graph, such as Figure 1 The method flow of finding risk enterprise groups based on knowledge graph is as follows:

[0053] Obtain information related to the enterprise's industrial chain map and stratify the hierarchical labels as the basic information of the enterprise's industrial chain; that is, form a complete industrial chain knowledge map hierarchical structure based on industry reports, case studies of industrial research institutions and expert discussions, including upstream, midstream and downstream as well as subdivided hierarchical labels, which is the basis of the industrial chain;

[0054] According to the basic information of the enterprise industrial chain and after selecting the enterprise industrial chain map label associated elements, mark the key elements of the enterprise industrial chain map and supplement the marked key element information associated with the enterprise to form the enterprise industrial chain key element knowledge base, that is, based on the industrial chain map label associated elements, as well as the leading enterprise name, enterprise profile, business scope, patents, software copyrights, national standard industry, standards, recruitment job descriptions, product services, national standards and other corpora to supplement the marked key elements to form the enterprise industrial chain key element knowledge base;

[0055] Responding to the enterprise industrial chain key element knowledge base and according to the enterprise's named entity recognition method, extracting and matching label keywords in the enterprise industrial chain map to form enterprise industrial chain group matching result information;

[0056] According to the enterprise industrial chain group matching result information, the enterprise industrial chain risk assessment model is constructed, and the enterprise portrait and the enterprise data report information are generated; wherein the enterprise industrial chain risk assessment model is constructed specifically according to the enterprise industrial chain group matching result information to conduct a multi-dimensional evaluation of the enterprise industrial chain, and the multi-dimensional evaluation is evaluated from the scale index, development index, innovation index, money absorption index, risk index, and efficiency index, that is, a qualitative and quantitative analysis of the enterprise industrial chain risk assessment is conducted, that is, the enterprise exposure flow amplitude, scale index, development index, innovation index, money absorption index, risk index, and efficiency index are normalized and then comprehensively calculated to generate the enterprise's dynamic risk coefficient δ k , by analyzing the dynamic risk coefficient δ of enterprises in the industrial chain k After the value is calculated, the enterprises in the industrial chain map are divided according to the dynamic risk coefficient δ k The values ​​are sorted from large to small and a risk list of enterprises in the industrial chain map is generated. The dynamic risk coefficient of the enterprise δ k The calculation of is as follows:

[0057]

[0058] In the formula, g k is the exposure flow amplitude of enterprise k, is the scale dimension index value, is the development dimension index value, is the innovation dimension index value, is the gold-attracting dimension index value, is the risk dimension index value, is the efficiency dimension index value; a k , b k 、c k ,d k 、e k 、f k are the proportional coefficients of the scale dimension index, development dimension index, innovation dimension index, capital attraction dimension index, risk dimension index, and efficiency dimension index, respectively, and a k , b k 、c k ,d k 、e k 、f k are both greater than 0, and the proportional coefficient a k , b k 、c k ,d k 、e k 、f k The specific value of is set according to the importance of the corresponding dimension index in the enterprise industrial chain map, and ln represents the symbol of the natural logarithm function;

[0059] In response to the enterprise portrait and the enterprise data report information, the enterprise industrial chain relevance evaluation is performed, and at the same time, the enterprise industrial chain knowledge map is constructed and the enterprise risk evaluation is performed according to the enterprise industrial chain knowledge map, and then the enterprise investment management strategy is processed, wherein the enterprise portrait is specifically constructed through enterprise data integration and fusion, and the enterprise micro-portrait is formed to form an enterprise digital archive, and the enterprise risk value is evaluated and modeled according to the enterprise digital archive. Specifically, the enterprise micro-portrait is constructed by establishing a reliability function of the enterprise portrait, and the calculation is as follows:

[0060]

[0061] Among them, Q n (f) Micro-profile of the enterprise n The reliability function of C(n,i) is the factorial, which is the reliability function of the enterprise from the i-th micro-profile to the enterprise n The factorial of microscopic images, Q i (f) is the reliability function of the i-th enterprise micro-profile, Q 0 (f) is the average reliability function of the enterprise micro-portrait.

[0062] Based on the above, by establishing the enterprise portrait and constructing the enterprise micro-portrait according to reliability, the unified analysis of the enterprise portrait is further refined scientifically, which is more conducive to the qualitative and quantitative analysis of the risks, importance and influence of each enterprise in the enterprise industrial chain, and is conducive to the formation of intelligent and efficient management strategies, which are more reasonable and accurate.

[0063] In this embodiment, the enterprise industrial chain relevance evaluation includes: weighting and scoring the industrial label matching of enterprises with industrial chain labels in terms of enterprise name, enterprise introduction, business scope, standards, patents, products and services, industry information, etc., to obtain the industrial chain relevance score. According to the industrial chain relevance score, a list of enterprises with a high degree of matching with the industry can be obtained.

[0064] Specifically, this embodiment obtains information related to the enterprise industrial chain map, which is specifically based on industrial data resources and industrial chain models, and forms a hierarchical structure of the enterprise industrial chain knowledge map according to industry reports, industrial research institutions and expert discussions. The hierarchical structure of the industrial chain knowledge map includes upstream, midstream, downstream and subdivided level labels, and also includes analyzing the industrial chains of marked enterprises in the region, combining the chain investment promotion method to provide strategy information for supplementing, strengthening and extending the specified industrial chain.

[0065] Specifically, this embodiment constructs an enterprise industrial chain knowledge graph and performs enterprise risk assessment based on the enterprise industrial chain knowledge graph, wherein the enterprise industrial chain knowledge graph includes an industry encyclopedia overview and local status analysis;

[0066] The industry encyclopedia overview includes industry maps, industry insights and industry evaluations;

[0067] Local status analysis includes industry analysis, spatial distribution analysis and evolution analysis.

[0068] Specifically, in this embodiment, the industrial map is to display the industrial structure division of the current enterprise industrial chain and the number of operating enterprises corresponding to the subdivided industries;

[0069] The industrial map uses a heat map to display the spatial distribution and agglomeration information of enterprises related to the industrial chain;

[0070] Industry insights analyze and display the current status of a single enterprise industry chain from the number of existing enterprises in the industry and the regional distribution of enterprises, and provide data and information support for regional industrial investment promotion and industrial direction selection;

[0071] Industry evaluation is to conduct qualitative and quantitative analysis of enterprise industry chain risk assessment by building an enterprise industry chain risk assessment model;

[0072] Industry analysis combines industry development insights with analysis of the current status of local industries, and matches development suggestions for each industry in the local marked industry chain through algorithm models of strengthening, supplementing, and extending the chain. The presentation forms of industry analysis are: relationship diagram and tree diagram;

[0073] Spatial distribution analysis is to display the spatial agglomeration information of the marked industrial enterprises in the region in the form of a map, which is used to measure whether the development of the industry in the region is balanced, and to reflect the degree of concentration and specialization of the industry in the region;

[0074] like Figure 5 As shown, the evolution analysis uses the number of enterprises in the marked industries and the registered capital of the marked industries to display the overall scale of the marked industries in the region in an intuitive way, which is used to measure the overall development level of the marked industries in the region. It has the following functions: Industry screening: Display the detailed industrial division under the industrial chain. Click the text of the upper-level industry to switch the directory of the lower-level industry. Multiple selections can be made, and cross-industry selections can be made. A maximum of 20 indicators can be selected. Indicator switching: Users can switch between existing and newly established indicators. Time range: The overall scale development trend from 2000 to the most recent year can be viewed at most.

[0075] Preferably, this embodiment constructs an enterprise industrial chain risk assessment model, and specifically conducts a multi-dimensional evaluation of the enterprise industrial chain based on the enterprise industrial chain group matching result information. The multi-dimensional evaluation is to evaluate from the scale index, development index, innovation index, money absorption index, risk index, and efficiency index, that is, to conduct qualitative and quantitative analysis of the enterprise industrial chain risk assessment; wherein the scale index, development index, innovation index, money absorption index, risk index, and efficiency index are visualized in the form of a radar chart, and compared with the average level of the enterprise's related industrial chain. At the same time, the scale index, development index, innovation index, money absorption index, risk index, and efficiency index of the enterprise are integrated into the comprehensive index of the enterprise, and a ranking and overall overview are made in the enterprise industrial chain based on the comprehensive index of the enterprise. The overall overview also shows the total number of operating enterprises in the current industrial chain and the total registered capital of the operating enterprises. The specific dimensions are explained as follows:

[0076] 1. Industry scale: Displays the average scale of the industry chain and each industry subcategory in the previous year, and divides the colors according to the year-on-year growth rate.

[0077] 2. Industrial Development: Displays the development trend of the number of enterprises in the industrial chain and the registered capital of enterprises in the past ten years, showing the year, number of enterprises, and total registered capital.

[0078] 3. Industry risk: Display the average number of administrative penalties, credit events, lawsuits, guarantee events and mortgage events per household in the previous year to assess the risk status of the industry chain.

[0079] 4. Innovation capability: The innovation capability of the industry chain is assessed through the average number of intellectual property events per household, such as patent authorization, software copyright registration, and trademark registration in the previous year.

[0080] 5. Industry efficiency: displays the average listing period of enterprises in the industry chain and the average listing period of enterprises nationwide, and shows the ranking of industry efficiency in the entire industry chain.

[0081] 6. Ability to attract capital: Evaluate the attractiveness of the industrial chain to capital through the PE / VC investment amount, listed company investment amount and overseas investment amount in the previous year.

[0082] Specifically, in this embodiment, the enterprise portrait is specifically constructed by integrating and merging enterprise data to form a micro-profile of the enterprise, form an enterprise digital archive, and evaluate and model the enterprise risk value;

[0083] The data report information includes three dimensions: basic information, business management information, and social credit information.

[0084] It should be emphasized in this embodiment that, while generating enterprise portraits, it also includes generating enterprise carefully selected portraits. Specifically, through industrial chain investment promotion, theme enterprise recommendation, enterprise search, park enterprise search and investment promotion headlines, we search and match high-quality enterprises that meet the carefully selected standards to generate enterprise carefully selected portraits.

[0085] Based on the above, it can be seen that the method of finding risky enterprise groups based on the knowledge graph in this embodiment, when generating enterprise portraits and enterprise data report information, completing the enterprise industrial chain correlation evaluation to construct the enterprise industrial chain knowledge graph and conduct enterprise risk evaluation, constructs the enterprise industrial chain knowledge graph and conducts multi-dimensional risk assessment and analysis of enterprise groups, makes the risk assessment of enterprise groups more accurate, efficient and comprehensive compared to traditional methods, and can also provide data support and analysis basis for subsequent enterprise policy formulation and enterprise decision-making.

[0086] In this embodiment, the industrial chain investment promotion is to locate the target enterprise group to form an enterprise group according to the selected different industrial chain links and the preset screening conditions; the screening conditions include: industry screening, city screening, registered capital, enterprise age, label, innovation index, credit rating, comprehensive strategy, innovation advantage, capital advantage, credit advantage, keyword search, and similar enterprise recommendation;

[0087] Theme recommendation is to recommend enterprises based on various enterprise lists and generate enterprise diagnosis reports;

[0088] Enterprise search is based on keyword query of enterprise information in various dimensions, combined with various screening conditions, to locate the target enterprise group;

[0089] The park enterprise search is based on the park's leading industry positioning, screening parks and resident enterprises related to the target industrial chain across the country, exploring target parks and intended enterprises through various means, and supporting the value assessment of enterprises and selecting them as investment targets;

[0090] China Merchants Headlines extracts information about various types of financing, bidding, exhibitions and patents published on the Internet, and relevant corporate information on the industrial chain involved.

[0091] In addition, the enterprise risk assessment in this embodiment is based on the enterprise's investment record, intellectual property rights, operating conditions, compliance and legality, and related group information, and conducts a panoramic scan of the enterprise. The investment intention, value level and risk level of the enterprise are evaluated through the scanning results, providing data reference for the screening of investment targets and the processing of investment management strategies.

[0092] like Figure 2 As shown, this embodiment is also based on the above-mentioned method for finding venture enterprise groups based on knowledge graphs, and provides a system for finding venture enterprise groups based on knowledge graphs, including:

[0093] The industrial chain information acquisition module 100 is used to obtain information related to the enterprise industrial chain map and to perform layering of hierarchical labels as basic information of the enterprise industrial chain;

[0094] The industrial chain map element marking module 101 is used to mark the key elements of the enterprise industrial chain map and supplement the key element information of the enterprise's associated marking according to the basic information of the enterprise industrial chain and after selecting the enterprise industrial chain map tag associated elements, to form a knowledge base of the key elements of the enterprise industrial chain;

[0095] The industrial chain graph recognition and matching module 102 is used to respond to the enterprise industrial chain key element knowledge base and extract and match the label keywords in the enterprise industrial chain graph according to the enterprise's named entity recognition method to form the enterprise industrial chain group matching result information;

[0096] The enterprise portrait generation module 103 is used to construct an enterprise industrial chain risk assessment model based on the enterprise industrial chain group matching result information, and generate enterprise portraits and enterprise data report information;

[0097] The enterprise management module 104 is used to respond to the enterprise portrait and the enterprise data report information, conduct the enterprise industry chain relevance evaluation, build the enterprise industry chain knowledge map and conduct enterprise risk evaluation based on the enterprise industry chain knowledge map, and then process the enterprise investment management strategy.

[0098] In summary, the present invention can extract valuable data from massive amounts of enterprise information by utilizing big data technology, including but not limited to enterprise registration information, recruitment information, patent information, trademark information, etc. These data provide a comprehensive view for the enterprise, which helps to deeply understand the enterprise's operating conditions and market performance.

[0099] By building a knowledge graph, various information and relationships of enterprises can be displayed in a graphical way, thereby revealing the connections between enterprises and the structure of the industrial chain. The knowledge graph not only includes direct connections between enterprises, but also covers multi-dimensional relationships such as products and industries.

[0100] Through natural language processing technology, key features can be extracted from enterprise data and the enterprise's operating feature labels can be formed. These labels help to quickly identify the core capabilities and market positioning of the enterprise.

[0101] By matching the business characteristic labels of enterprises with the industrial chain map, we can accurately identify the position and role of enterprises in the industrial chain. This helps to analyze the dependencies between enterprises and potential cooperation opportunities.

[0102] Based on the above technologies and methods, a knowledge graph of the enterprise industrial chain can be constructed, which can comprehensively display the complex relationships between enterprises and the structure of the industrial chain.

[0103] By using the knowledge graph of the industrial chain, we can conduct risk assessment and analysis on enterprise groups and identify potential risk points and vulnerable links. This helps enterprises formulate risk management strategies and improve their risk response capabilities.

[0104] Based on the results of the industry chain knowledge map and enterprise risk assessment, the construction of the enterprise industry chain knowledge map and the multi-dimensional risk assessment and analysis of enterprise groups can provide enterprises with customized investment management strategies. These strategies include the selection of target markets, the screening of partners, the optimization of investment channels, etc., to improve investment efficiency and success rate.

[0105] Through the process processing and system configuration of this embodiment, enterprises can not only better understand their own position in the industrial chain, but also identify and evaluate potential business opportunities and risks, so as to formulate more effective investment promotion and management strategies.

[0106] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0107] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0108] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0109] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0111] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0112] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0113] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for finding risk enterprise groups based on knowledge graph, characterized by: include: Obtain information related to the enterprise industry chain map and stratify the hierarchical labels as the basic information of the enterprise industry chain; According to the basic information of the enterprise industrial chain and after selecting the elements associated with the enterprise industrial chain map label, mark the key elements of the enterprise industrial chain map and supplement the marked key element information associated with the enterprise to form a knowledge base of the key elements of the enterprise industrial chain; Responding to the enterprise industrial chain key element knowledge base and according to the enterprise's named entity recognition method, extracting and matching label keywords in the enterprise industrial chain map to form enterprise industrial chain group matching result information; According to the matching result information of enterprise industrial chain groups, a risk assessment model for the enterprise industrial chain is constructed, and enterprise portraits and data report information of the enterprise are generated; The enterprise industrial chain risk assessment model is constructed to conduct a multi-dimensional evaluation of the enterprise industrial chain according to the enterprise industrial chain group matching result information. The multi-dimensional evaluation is evaluated from the scale index, development index, innovation index, money absorption index, risk index, and efficiency index, that is, to conduct qualitative and quantitative analysis of the enterprise industrial chain risk assessment, that is, to perform a comprehensive calculation after normalizing the enterprise exposure flow amplitude, scale index, development index, innovation index, money absorption index, risk index, and efficiency index to generate the enterprise's dynamic risk coefficient δ k , by analyzing the dynamic risk coefficient δ of enterprises in the industrial chain k After the value is calculated, the enterprises in the industrial chain map are divided according to the dynamic risk coefficient δ k The values ​​are sorted from large to small and a risk list of enterprises in the industrial chain map is generated. The dynamic risk coefficient of the enterprise δ k The calculation of is as follows: In the formula, g k is the exposure flow amplitude of enterprise k, is the scale dimension index value, is the development dimension index value, is the innovation dimension index value, is the gold-attracting dimension index value, is the risk dimension index value, is the efficiency dimension index value; a k 、b k 、c k d k 、e k 、f k are the proportional coefficients of the scale dimension index, development dimension index, innovation dimension index, capital attraction dimension index, risk dimension index, and efficiency dimension index, respectively, and a k 、b k 、c k d k 、e k 、f k are both greater than 0, and the proportional coefficient a k 、b k 、c k d k 、e k 、f k The specific value of is set according to the importance of the corresponding dimension index in the enterprise industrial chain map, and ln represents the symbol of the natural logarithm function; In response to the enterprise portrait and the enterprise data report information, the enterprise industrial chain relevance evaluation is performed, and at the same time, the enterprise industrial chain knowledge map is constructed and the enterprise risk evaluation is performed according to the enterprise industrial chain knowledge map, and then the enterprise investment management strategy is processed, wherein the enterprise portrait is specifically constructed through enterprise data integration and fusion, and the enterprise micro-portrait is formed to form an enterprise digital archive, and the enterprise risk value is evaluated and modeled according to the enterprise digital archive. Specifically, the enterprise micro-portrait is constructed by establishing a reliability function of the enterprise portrait, and the calculation is as follows: Among them, Q n (f) is the reliability function of enterprise micro-profile n, C(n,i) represents the factorial, which is the factorial of the i-th micro-profile to the n-th micro-profile of the enterprise, Q i (f) is the reliability function of the i-th enterprise micro-portrait, and Q0(f) is the average reliability function of the enterprise micro-portraits.

2. A method for finding venture enterprise groups based on knowledge graph as claimed in claim 1, characterized in that: Obtain information related to the enterprise industrial chain map, specifically based on industrial data resources and industrial chain models, and form a hierarchical structure of the enterprise industrial chain knowledge map according to industry reports, industrial research institutions and expert discussions. The hierarchical structure of the industrial chain knowledge map includes upstream, midstream, downstream and subdivided level labels, and also includes analysis of the industrial chains of marked enterprises in the region, combined with the chain investment promotion method to provide strategy information for supplementing, strengthening and extending the designated industrial chain.

3. The method for finding venture enterprise groups based on knowledge graph according to claim 1, characterized in that: The enterprise industrial chain knowledge graph is constructed and enterprise risk assessment is performed based on the enterprise industrial chain knowledge graph, wherein the enterprise industrial chain knowledge graph includes an industry encyclopedia overview and local status analysis; The industry encyclopedia overview includes industry graphs, industry maps, industry insights and industry evaluations; The local status analysis includes industry analysis, spatial distribution analysis and evolution analysis.

4. A method for finding risk enterprise groups based on knowledge graph as claimed in claim 3, characterized in that: The industrial map is to show the industrial structure division of the current enterprise industrial chain and the number of operating enterprises corresponding to the subdivided industries; The industrial map is a heat map showing the spatial distribution and agglomeration information of enterprises associated with the industrial chain; The industry insight is to analyze and display the current status of the industry from the perspective of the number of existing enterprises in the industry and the regional distribution of enterprises for a single enterprise industry chain, and to provide data and information support for regional industry investment promotion and industry direction selection; The industrial evaluation is to conduct qualitative and quantitative analysis of the enterprise industrial chain risk assessment by constructing an enterprise industrial chain risk assessment model; The industrial analysis combines industrial development insights with analysis of the current status of local industries, and matches the development suggestion information of various industries in the local marked industrial chain through the algorithm model of strengthening, supplementing and extending the chain. The industrial analysis is expressed in the following forms: relationship diagram and tree diagram; The spatial distribution analysis is to display the spatial agglomeration information of the marked industrial enterprises in the region in the form of a map, which is used to measure whether the development of the industry in the region is balanced, and to reflect the degree of concentration and specialization of the industry in the region; The evolution analysis is to visually display the overall scale of the region's marked industries through the dimensions of the number of marked industry enterprises and the registered capital of marked industry enterprises, and is used to measure the overall development level of the region's marked industries.

5. A method for finding venture enterprise groups based on knowledge graph as claimed in claim 4, characterized in that: The scale index, development index, innovation index, money-absorbing index, risk index, and efficiency index are visualized in the form of a radar chart and compared with the average level of the enterprise's associated industrial chain. At the same time, the enterprise's scale index, development index, innovation index, money-absorbing index, risk index, and efficiency index are integrated into the enterprise's comprehensive index, and a ranking and overall overview are made in the enterprise's industrial chain based on the enterprise's comprehensive index.

6. The method for finding venture enterprise groups based on knowledge graph according to claim 1, characterized in that: The data report information includes three dimensions: basic information, business management information, and social credit information.

7. The method for finding venture enterprise groups based on knowledge graph according to claim 1, characterized in that: While generating the enterprise portrait, it also includes generating the enterprise selection portrait. Specifically, through industrial chain investment promotion, theme enterprise recommendation, enterprise search, park enterprise search and investment promotion headlines, we find and match high-quality enterprises that meet the strict selection standards to generate the enterprise selection portrait.

8. The method for finding venture enterprise groups based on knowledge graph according to claim 7, characterized in that: The industrial chain investment promotion is to locate the target enterprise groups to form enterprise groups based on the selected different industrial chain links and the preset screening conditions; The screening conditions include: industry screening, city screening, registered capital, enterprise age, label, innovation index, credit rating, comprehensive strategy, innovation advantage, capital advantage, credit advantage, keyword search, and similar enterprise recommendation; The theme recommendation is to recommend enterprises based on various enterprise lists and generate enterprise diagnosis reports; The enterprise search is based on keyword query of enterprise information in various dimensions, combined with various screening conditions, to locate the target enterprise group; The park enterprise search is based on the dominant industry positioning of the park, screening parks and resident enterprises related to the target industrial chain across the country, exploring target parks and enterprises to be recruited, and supporting the value evaluation of enterprises and selecting them as investment targets; The investment headlines are various types of financing, bidding, exhibition and patent information released on the Internet, and relevant enterprise information of the industrial chain involved is extracted.

9. The method for finding venture enterprise groups based on knowledge graph according to claim 1, characterized in that: The enterprise risk assessment is based on a panoramic scan of the enterprise's investment records, intellectual property rights, operating conditions, compliance and legality, and related group information. The investment intention, value level and risk level of the enterprise are evaluated through the scanning results, providing data reference for the screening of investment targets and the processing of investment management strategies.

10. A system applied to the method for finding venture enterprise groups based on knowledge graph as claimed in claim 1, characterized in that: include: The industrial chain information acquisition module is used to obtain information related to the enterprise industrial chain map and stratify the hierarchical labels as the basic information of the enterprise industrial chain; The industrial chain map element marking module is used to mark the key elements of the enterprise industrial chain map and supplement the marked key element information associated with the enterprise according to the basic information of the enterprise industrial chain and after selecting the elements associated with the enterprise industrial chain map label, to form a knowledge base of the key elements of the enterprise industrial chain; The industrial chain graph recognition and matching module is used to respond to the enterprise industrial chain key element knowledge base and extract and match the label keywords in the enterprise industrial chain graph according to the enterprise's named entity recognition method to form the enterprise industrial chain group matching result information; The enterprise portrait generation module is used to build an enterprise industry chain risk assessment model based on the enterprise industry chain group matching result information, and generate enterprise portraits and enterprise data report information; The enterprise management module is used to respond to the enterprise portrait and the enterprise's data report information, conduct an enterprise industry chain relevance evaluation, construct an enterprise industry chain knowledge graph and conduct an enterprise risk evaluation based on the enterprise industry chain knowledge graph, and then process the enterprise investment management strategy.

Images