Industrial chain generation method and system based on big data

Abstract

The invention discloses an industrial chain generation method and system based on big data, and the method comprises the steps: designing a main structure of an industrial chain and a keyword table of each node, and determining the classification of the upstream, the middle and the downstream of the industrial chain, including a main node, a child node, a branch node, a name of each node and a keyword contained in the node; multi-dimensional industrial data such as industry and commerce data, bidding and tendering, public opinions, patents and software aboriginal information of enterprises are collected and acquired, and an enterprise basic database is established; primary screening of the uplink enterprises: screening the enterprises from the enterprise basic database according to the industrial chain node keywords, and incorporating the enterprises into an alternative uplink enterprise database; the enterprise upper chain evaluation index system is used for evaluating the matching degree between dimension information such as the business scope, the technical achievement, the public opinion information and the bidding and tendering of the enterprise and the industrial chain node; selecting each node benchmark enterprise on an industrial chain according to industrial research, and calculating each uplink index of each benchmark enterprise; calculating a vector distance between the primarily screened selected enterprise and the benchmarking enterprise; ranking the similarity calculation results in a descending order; according to the Pareto's law, the first 20% of enterprises are taken to be linked, and a complete industrial chain is constructed. The method comprises the following steps: collecting enterprise multi-dimensional data, constructing an industrial chain main body structure and each node keyword, screening to-be-linked enterprises according to keywords, establishing an uplink evaluation index system, calculating vector distances between the to-be-linked enterprises and benchmarking enterprises, and determining an uplink enterprise mode according to vector distance ranking to generate an industrial chain. The method is beneficial for improving the accuracy and efficiency of industrial chain generation, so that reference basis is provided for scientifically evaluating the industrial development level, making investment decisions of industrial development, making effective industrial policies and the like.

Description

Technical Field

[0001] This application relates to the technical fields of industrial chain and big data, and more specifically, to a method and system for generating an industrial chain based on big data. Background Art

[0002] The industrial chain is an important concept in industrial economics, which describes all relevant enterprises and activities in the whole process from raw material acquisition to the delivery of the final product to consumers. The industrial chain reflects the interdependence and connection within and between industries, and is an objectively formed chain-like correlation form based on certain technical and economic associations and according to specific logical and spatio-temporal layout relationships. In the context of globalization, the industrial chain usually crosses national boundaries, forming a complex global supply chain network. The security and stability of the industrial chain are crucial for national economic security. Especially in the face of emergencies such as natural disasters, economic crises or global pandemics, ensuring the continuity and resilience of the industrial chain becomes particularly important.

[0003] The design of the industrial chain is not only a technical challenge, but also support for understanding and decision-making of the industrial chain, which can help decision-makers, governors, product planners and researchers accurately grasp the business pattern and make wise decisions. Most traditional methods for generating industrial chains construct industrial chains by manually viewing information, label marking, etc., which have problems such as long cycle, large workload, insufficient accuracy, and incomplete data. There is a need to establish a method for efficiently and accurately constructing industrial chains. The present invention proposes an industrial chain generation method that combines top-down research results in the integrated circuit industry and bottom-up quantitative evaluation of enterprise characteristics. At the same time, the workload and time cycle can meet the requirements of batch processing of enterprises, and it has strong practical operability and is convenient for the research team and the data product development team to cooperate and complete together. Summary of the Invention

[0004] In view of this, the present invention provides a method and system for generating an industrial chain based on big data that at least solves the above-mentioned partial technical problems. The integrated circuit industrial chain is constructed by combining top-down and bottom-up methods. On the one hand, based on the experience of industry experts, the main structure of the industrial chain and the keyword list of each node are constructed starting from the top-level concept. On the other hand, enterprise information is extracted from open multi-source data, and enterprises that meet the industrial chain nodes are screened out through keywords, and then the similarity with benchmark enterprises is compared. According to the Pareto principle, the top 20% of the enterprises ranked by similarity are selected to be on the chain, and then a complete industrial chain is constructed.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] In the first aspect, an embodiment of the present invention provides a method for generating an industrial chain based on big data, and the method includes the following steps:

[0007] S1. Design the main structure of the industrial chain and the keyword list for each node, clarify the classification of the upstream, midstream, and downstream of the industrial chain, including main nodes, sub-nodes, branch nodes, as well as the names of each node and the keywords it contains;

[0008] S2. Collect and obtain multi-dimensional industrial data such as the business data, bidding, public opinion, patents, and software copyright information of enterprises, and establish an enterprise basic database;

[0009] S3. Conduct a preliminary screening of enterprises to be included in the chain. From the enterprise basic database, screen enterprises according to the keyword of the industrial chain node and include them in the alternative enterprise database to be included in the chain;

[0010] S4. Design an evaluation index system for enterprises to be included in the chain, which is used to evaluate the matching degree of information in dimensions such as the business scope, technological achievements, public opinion information, and bidding of enterprises with the industrial chain node;

[0011] S5. Select benchmark enterprises for each node on the industrial chain according to industrial research, and calculate various indexes for each benchmark enterprise to be included in the chain;

[0012] S6. Calculate the vector distance between the initially screened enterprises to be included in the chain and the benchmark enterprises;

[0013] S7. Sort the similarity calculation results in descending order;

[0014] S8. According to the Pareto law, select the top 20% of the enterprises to be included in the chain to build a complete industrial chain.

[0015] In the second aspect, the embodiment of the present invention also provides a system for generating an industrial chain based on big data, which applies the above-mentioned method for generating an industrial chain based on big data to generate an industrial chain. The system includes:

[0016] A data collection module, which is used to collect and obtain multi-dimensional data related to the generation of the industrial chain;

[0017] An index system construction module, which is used to construct a comprehensive evaluation index system for enterprises to be included in the chain, and each index forms a multi-dimensional vector representing the characteristics of the enterprise;

[0018] A calculation module, which is used to calculate each index in the comprehensive evaluation index system by using the collected data, and calculate the vector distance between the initially screened enterprises to be included in the chain and the benchmark enterprises, which is characterized by the Yu Xuan distance;

[0019] An evaluation result output module, which sorts the vector distances in descending order, and selects the top 20% of the enterprises to be included in the chain according to the Pareto rule, so as to obtain a complete industrial chain.

[0020] Compared with the prior art, the present invention has at least the following beneficial effects:

[0021] In view of the problems existing in the traditional industrial chain generation mode, such as long cycle, large workload, insufficient accuracy, and incomplete data, the present invention provides a method and system for generating an industrial chain based on big data. The present invention generates an industrial chain by collecting multi-dimensional data of enterprises, constructing the main structure of the industrial chain and keyword tags for each node, screening enterprises to be put on the chain according to keywords, establishing an evaluation index system for putting on the chain, calculating the vector distance between the enterprises to be put on the chain and benchmark enterprises, and determining the enterprises to be put on the chain according to the vector distance ranking, which helps to improve the accuracy and efficiency of industrial chain generation, so as to provide a reference basis for scientifically evaluating the industrial development level, making investment decisions for industrial development, formulating effective industrial policies, etc.

[0022] Other features and advantages of the present invention will be described in the following specification, and part of them will be obvious from the specification or understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structures specifically pointed out in the written specification and the drawings.

[0023] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention.

[0026] Figure 1 It is a schematic flow chart of a method for generating an industrial chain based on big data provided by an embodiment of the present invention.

[0027] Figure 2 It is a schematic diagram of an evaluation index system for enterprises to be put on the chain provided by an embodiment of the present invention. Detailed Embodiments

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. In addition, various serial numbers, etc. are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0029] Accordingly, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0030] Referring to Figure 1 as shown, the present invention provides a method for generating an industrial chain based on big data, which mainly includes the following steps:

[0031] S1. Design the main structure of the industrial chain, determine the keyword list for each node, and clarify the classification of the upstream, midstream, and downstream of the industrial chain, including main nodes, sub-nodes, branch nodes, as well as the names of each node and the keywords included;

[0032] S2. With the construction of the industrial chain as the goal, collect and obtain multi-dimensional industrial data such as the industrial and commercial data, bidding, public opinion, patents, and software copyrights of enterprises, and establish an enterprise basic database;

[0033] S3. Preliminary screening of enterprises to be on the chain, and select enterprises from the enterprise basic database according to the keyword of the industrial chain node, and include them in the alternative enterprise library to be on the chain;

[0034] S4. Design an evaluation index system for enterprises to be on the chain, which is used to evaluate the matching degree of information such as the business scope, technical achievements, public opinion information, and bidding of enterprises with the industrial chain nodes;

[0035] S5. Select benchmark enterprises for each node on the industrial chain according to the industrial research results, and calculate various on-chain indicators for each benchmark enterprise;

[0036] S6. Calculate the vector distance between the initially screened enterprises and the benchmark enterprises;

[0037] S7. Sort the similarity calculation results in descending order;

[0038] S8. According to the Pareto law, select the top 20% of the enterprises to be on the chain to build a complete industrial chain.

[0039] The following is a detailed description of each of the above steps:

[0040] In a specific embodiment, in the above step S1, by deeply researching the industry, conducting a full investigation of the industry, communicating and discussing with industry practitioners, industry associations, and market research institutions, deeply understanding the participants and node key information of each link of the industrial chain, the main structure of the industrial chain and the keyword list of each node are designed from the top level. Through the research and analysis of the industrial chain, the classification of the upstream, midstream, and downstream of the industrial chain is clarified, including main nodes, sub-nodes, branch nodes, as well as the names of each node and the relevant keywords included.

[0041] In a specific embodiment, in the above step S2, with the goal of building an industrial chain, information on industry-related market entities is collected. The information sources include public channels and specific sources, such as the official website of the State Intellectual Property Office, bidding websites, CNKI, iQiyicha, Tianyancha, investment and financing platform websites, as well as industry associations, market research institutions, third-party professional institutions, etc. Create an entity relationship diagram, define entities and relationships, and entity types include "company name", "legal representative", "business scope", "invention patent", "software copyright", "successful bid project", "new product", etc., and relationship types include "own", "belong to", "publish", etc. Convert the conceptual design into a specific database table structure, including fields, data types, and primary keys, select a database management system, and design the data storage structure, index, and partitioning strategy.

[0042] In a specific embodiment, in the above step S3, enterprises are screened from the basic database according to the industrial chain node rules, and the screening criteria include: first, the business status of the enterprise is normal, and the normal sign is that the business status continues and there are public opinion dynamics; second, the enterprise name, business scope, patent name, patent abstract, software title, software copyright abstract, winning bid information, and public opinion information contain industrial chain node keywords.

[0043] In a specific embodiment, in the above step S4, a probability evaluation index system for enterprises to be put on the chain is designed to evaluate the matching degree between the business scope, technological achievements, public opinion information, bidding behavior, etc. of the enterprise and the industrial chain nodes, which serves as the basis for the enterprise to be put on the industrial chain.

[0044] Design an enterprise on-chain evaluation index system as shown in the attached manual Figure 2 As shown, it includes 14 indicators in four categories: industrial and commercial information, intellectual property information, bidding information and public opinion information. Among them, the industrial and commercial information indicators include the number of clues of enterprise names, the number of clues of business scope, the frequency of enterprise names, and the frequency of business scope. The intellectual property information indicators include the number of clues of names, the number of clues of abstracts, the frequency of names, and the frequency of abstracts. The bidding information indicators include the number of clues of winning names, the number of winning projects in the field, and the total amount of winning projects in the field. The public opinion information indicators include the number of clues of new product names released, the number of clues of foreign cooperation, and the number of clues of foreign investment. The entropy weight method combined with the Delphi method is used to assign weights to the 14 indicators. First, linear regression is performed on the multidimensional data of more than 100 enterprises to calculate the weights of each indicator. Then, the Delphi method is used to correct the indicator weights to obtain the final weight data.

[0045] In a specific embodiment, in the above step S5, benchmark enterprises at various nodes of the industrial chain are selected according to the industrial research results, and various on-chain indicators of each benchmark enterprise are calculated.

[0046] In a specific embodiment, in the above step S6, the distance between the initially screened selected enterprises and the benchmark enterprises is calculated. In mathematics and computer science, different distance metrics are used to quantify the differences between two points in a multi-dimensional space: Cosine Similarity, Euclidean Distance, Chebyshev Distance, and Manhattan Distance are four commonly used distance metrics, each applicable to different scenarios. Euclidean Distance considers the direct distance of the shortest path between two points, Manhattan Distance considers the actual path length of moving along the coordinate axis directions, Chebyshev Distance focuses on the maximum difference between two points in each dimension, Cosine Similarity focuses on the similarity of vector directions rather than their magnitudes or specific positions. Cosine Similarity determines whether the directions of two vectors are similar by calculating the cosine value of the included angle between the two vectors. Since the present invention mainly studies the similarity in direction among different enterprises, Cosine Similarity is selected.

[0047] For two vectors A and B, Cosine Similarity = 1 - cos(A, B), where cos(A, B) is the cosine similarity, and the calculation formula is as follows:

[0048]

[0049] where: A·B is the dot product of vector A and vector B,

[0050] ||A|| is the Euclidean norm of vector A (i.e., the vector length),

[0051] ||B|| is the Euclidean norm of vector B.

[0052] In a specific embodiment, in the above step S7, the calculation results of the vector distances between the initially screened selected enterprises and the benchmark enterprises are sorted in descending order.

[0053] Finally, in the above step S8, according to the Pareto principle, the top 20% of the enterprises ranked by the calculation results of the vector distances are selected to go on the chain.

[0054] From the description of the above embodiments, those skilled in the art can learn that the present invention provides a big data-based industrial chain generation method and system for the problems existing in the traditional industrial chain generation mode, such as long cycle, large workload, insufficient accuracy, and incomplete data. In the method of the present invention, industrial chain generation is carried out through technologies such as multi-dimensional industrial data collection, construction of an enterprise on-chain probability evaluation index system, top-level design of the industrial entity structure, construction of an industrial chain node keyword table, initial screening of enterprises to be on the chain, selection of benchmark enterprises, and calculation of the vector distances between the enterprises to be on the chain and the benchmark enterprises. The method of the present invention has the following advantages:

[0055] ①The enterprise on-chain evaluation data is comprehensive, collecting multi-dimensional data such as the production and operation, bidding, technical achievements, and public opinion dynamics of the enterprise, and comprehensively evaluating the matching degree between the enterprise and the industrial chain nodes.

[0056] ②The top-level architecture is clear and accurate, fully absorbing the research results of the industry, and the main structure of the industrial chain and the positioning of node keywords are accurate.

[0057] ③The probability of an enterprise going on-chain can be quantitatively evaluated. An index system is constructed by using the entropy weight method combined with the Delphi method, the vector distance between the enterprise to be on-chain and the benchmark enterprise is calculated, and the similarity is used to determine the probability of the enterprise going on-chain.

[0058] ④The construction speed of the industrial chain is fast. The work such as the design of the node keyword table, data collection, selection of benchmark enterprises, and calculation of indicators and vectors is clearly decomposed, which is convenient for team division of labor and cooperation, and the work efficiency is high.

[0059] ⑤The industrial chain can be dynamically adjusted and optimized. The on-chain probability evaluation index system changes with the change of the industrial chain, including the index name and weight, so as to screen out the enterprises that meet the characteristics of the industrial chain nodes to go on-chain.

[0060] Furthermore, the present invention also provides a big data-based industrial chain generation system, which applies the big data-based industrial chain generation method in the above embodiment to construct an industrial chain. The system includes:

[0061] A data collection module for collecting and obtaining multi-dimensional data related to industrial chain generation;

[0062] An index system construction module for constructing an on-chain comprehensive evaluation index system, and each index forms a multi-dimensional vector representing the characteristics of the enterprise;

[0063] A calculation module for calculating each index in the comprehensive evaluation index system by using the collected data, and performing vector calculation on the initially screened shortlisted enterprises and the benchmark enterprises;

[0064] An evaluation result output module for sorting the remaining distance in descending order, and selecting the top 20% of the enterprises to go on-chain according to the Pareto principle, so as to obtain a complete industrial chain.

[0065] For the system provided by the embodiment of the present invention, its implementation principle and the technical effects produced are the same as those of the foregoing method embodiment. For the sake of brief description, for the parts not mentioned in the system embodiment, reference may be made to the corresponding content in the foregoing method embodiment, and details will not be repeated here.

[0066] In addition, the embodiment of the present invention also provides a storage medium, on which one or more programs readable by a computing device are stored. The one or more programs include instructions, and when the instructions are executed by the computing device, the computing device is caused to execute the big data-based industrial chain generation method in the above embodiment.

[0067] In the embodiments of the present invention, the storage medium may be, for example, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device, and any suitable combination of the above.

[0068] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method, a system, or a computer program product, etc. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] It should be noted that the word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention can be implemented by means of hardware including several different components and by means of a suitably programmed computer.

[0070] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other.

[0071] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method and system for generating an industrial chain based on big data, characterized in that: The method comprises the following steps: S1. Design the main structure of the industrial chain and the keyword table of each node, clarify the classification of the upstream, midstream and downstream of the industrial chain, including main nodes, sub-nodes, branch nodes, as well as the names of each node and the keywords contained; S2. Collect and obtain multi-dimensional industrial data such as business data, bidding, public opinion, patents, and software copyright information of enterprises, and establish a basic enterprise database; S3. Initial screening of on-chain enterprises: select enterprises from the enterprise basic database according to the keywords of the industrial chain nodes and include them in the candidate on-chain enterprise database; S4. Design of enterprise on-chain evaluation index system, which is used to evaluate the matching degree between enterprise’s business scope, technological achievements, public opinion information, bidding and other dimension information and industrial chain nodes; S5. Select benchmark enterprises at each node in the industrial chain based on industrial research and calculate various on-chain indicators for each benchmark enterprise; S6. Calculate the vector distance between the initial screening enterprises and the benchmark enterprises; S7, arranging the similarity calculation results in descending order; S8. According to Pareto's law, the top 20% of enterprises are put on the chain to build a complete industrial chain.

2. The method for generating an industrial chain based on big data according to claim 1, characterized in that: In step S4, the enterprise on-chain evaluation index system includes four categories and 14 indicators, namely, industrial and commercial information, intellectual property information, bidding information, and public opinion information. The industrial and commercial information includes the number of enterprise name clues, the number of business scope clues, enterprise name frequency, and business scope frequency indicators. The intellectual property information includes the number of intellectual property name clues, the number of intellectual property summary clues, intellectual property name frequency, and intellectual property summary frequency indicators. The bidding information includes the number of winning project name clues, the number of winning bids in the field, and the total amount of winning bids in the field. The public opinion information includes the number of new product name clues, the number of foreign cooperation name clues, and the number of foreign investment name clues.

3. The method for generating an industrial chain based on big data according to claim 1, characterized in that: In step S5, the selection of benchmark enterprises at industry chain nodes is based on industry research results, taking into account enterprise scale, social influence, market share, etc.

4. The method for generating an industrial chain based on big data according to claim 1, characterized in that: In step S6, the vector distance between the initially screened enterprises and the benchmark enterprises is measured using the Coxon distance.

5. The method for generating an industrial chain based on big data according to claim 1, characterized in that: In step S8, the top ranked enterprises follow the Pareto principle and the top 20% of the enterprises are put on the chain.

6. An industrial chain generation system based on big data, characterized in that: The method for generating an industrial chain based on big data according to any one of claims 1 to 6 is applied, and the system comprises: Data collection module, used to collect and obtain multi-dimensional data related to industrial chain generation; The indicator system construction module is used to build a comprehensive evaluation indicator system for the chain. Each indicator constitutes a multi-dimensional vector that represents the characteristics of the enterprise; A calculation module, used to calculate each indicator in the comprehensive evaluation indicator system using the collected data, and to perform vector calculation between the initial screening enterprises and the benchmark enterprises, using the Yuxuan distance as the measurement; The evaluation result output module arranges the co-distances in descending order, and selects the top 20% of the enterprises to be included in the chain according to the Pareto principle, thereby obtaining a complete industrial chain.

Images