Method, system and device for evaluating and predicting enterprise growth based on model training

Abstract

The invention relates to the technical field of data processing, and provides an enterprise growth evaluation prediction method, system and device based on model training, and the method comprises the steps: building and storing an enterprise stability evaluation model, an enterprise research and development evaluation model and an enterprise innovation power evaluation model; obtaining target enterprise information; generating a stability score of the target enterprise according to the target enterprise information and an enterprise stability evaluation model; generating a research and development score of the target enterprise according to the target enterprise information and an enterprise research and development evaluation model; generating an innovation power score of the target enterprise according to the target enterprise information and an enterprise innovation power evaluation model; performing weight calculation on the stability score, the research and development score and the innovation power score to obtain a target weighted sum; and performing normalization processing on the target weighted sum to obtain a target enterprise growth score. According to the technical scheme, the growth of the enterprise can be accurately estimated in combination with the enterprise information.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for enterprise growth assessment and prediction based on model training. Background Art

[0002] Many companies will enter a relatively slow growth period after experiencing a short period of explosive growth. Many companies in the growth period have key technologies or resources but have not yet converted them into economic value, making them the focus of market investors.

[0003] At present, many platforms will collect various information of enterprises, especially some platforms can collect the innovative technologies of enterprises. For example, some platforms that combine new technology search and enterprise consulting will enter some enterprise information into the system during the enterprise application process. The enterprise's new technology and enterprise input information can reflect the enterprise's potential in scientific and technological innovation.

[0004] Based on the information uploaded by enterprises on the platform, many solutions for evaluating the growth potential of enterprises have appeared in the market. However, these solutions generally only establish portraits of the corresponding enterprises, and enterprise portraits are only used to present data of enterprises in different dimensions. When the number of data dimensions is too large, it is difficult to accurately evaluate the growth potential of enterprises in terms of technological growth through simple enterprise portraits. Summary of the invention

[0005] The purpose of this application is to provide a method, system and device for enterprise growth assessment and prediction based on model training, which can accurately predict the growth of an enterprise in combination with enterprise information.

[0006] The above application objectives of this application are achieved through the following technical solutions: In the first aspect, the enterprise growth assessment and prediction method based on model training provided in this application adopts the following technical solution.

[0007] A method for evaluating and predicting enterprise growth based on model training, the method comprising: Establish and store enterprise stability assessment models, enterprise R&D assessment models, and enterprise innovation assessment models; Obtaining target enterprise information, including upstream enterprise information, downstream enterprise information, target enterprise personnel information, financial information, R&D project information, and patent information; Generate a stability score for the target enterprise based on the target enterprise information and the enterprise stability assessment model; Generate a research and development score for the target enterprise based on the target enterprise information and the enterprise research and development evaluation model; Generate an innovation score for the target enterprise based on the target enterprise information and the enterprise innovation assessment model; Performing weight calculation on the stability score, R&D score, and innovation score to obtain a target weighted sum; The weighted sum of the targets is normalized to obtain the growth score of the target enterprise.

[0008] In a preferred solution, generating the stability score of the target enterprise based on the target enterprise information and the enterprise stability assessment model includes: Generating an upstream score for the upstream enterprise based on the upstream enterprise information; Generating a downstream score for the downstream enterprise based on the downstream enterprise information; Generating enterprise employee personnel scores based on the target enterprise personnel information; Performing weighted calculation on the upstream score, the downstream score and the personnel score to obtain a stable weighted sum; The stability score is obtained by normalizing the stability weighted sum.

[0009] In a preferred solution, generating a downstream score of a downstream enterprise based on the downstream enterprise information includes: Obtain basic scores for each downstream enterprise; Obtain transaction information of each downstream enterprise; Calculating the relevance score of the downstream enterprise based on the transaction information of the downstream enterprise; The downstream score is calculated based on the basic score of each downstream enterprise and the associated score of the downstream enterprise.

[0010] In a preferred solution, calculating the association score of the downstream enterprise based on the transaction information of the downstream enterprise includes: Calculate the transaction proportion of the downstream enterprise in the target enterprise based on the transaction information; The association score is calculated based on the transaction proportion of the downstream enterprise in the target enterprise.

[0011] In a preferred solution, generating enterprise employee personnel scores based on the target enterprise personnel information includes: The target enterprise generates a personnel evaluation model; Performing personnel scoring on enterprise personnel according to the personnel evaluation model; Generate enterprise employee personnel scores based on personnel scores as well as personnel entry information and personnel resignation information.

[0012] In a preferred solution, the target enterprise generates a personnel evaluation model including: the target enterprise sets a weighted score for the personnel's education, length of service and rank based on the position. In a preferred solution, generating a personnel score for an enterprise employee based on the personnel score and the personnel entry information and the personnel resignation information includes: Obtaining the enterprise entry score within a preset time based on the personnel entry information and personnel score; Obtaining the enterprise resignation score within a preset time based on the employee resignation information and employee score; The personnel score is generated by the ratio of the enterprise entry score and the enterprise resignation score.

[0013] In a preferred solution, generating the innovation score of the target enterprise based on the target enterprise information and the enterprise innovation assessment model includes: Generate an intellectual property score for the target enterprise based on patent information; Generating a project score of the target enterprise based on the R&D project information and financial information; The innovation score is generated based on the target enterprise's intellectual property score and the target enterprise's project score.

[0014] On the second aspect, the enterprise growth assessment and prediction system based on model training provided by this application adopts the following technical solution.

[0015] The enterprise growth evaluation and prediction system based on model training is characterized in that the system includes: Model storage module, used to establish and store enterprise stability assessment model, enterprise R&D assessment model and enterprise innovation assessment model; An information acquisition module is used to acquire target enterprise information, including upstream enterprise information, downstream enterprise information, enterprise personnel information, business information, financial information, R&D project information and patent information; Scoring module for: Generate a stability score for the target enterprise based on the target enterprise information and the enterprise stability assessment model; Generate a research and development score for the target enterprise based on the target enterprise information and the enterprise research and development evaluation model; and generating an innovation score for the target enterprise based on the target enterprise information and the enterprise innovation assessment model; The data calculation module is used to perform weight calculation on the stability score, R&D score, and innovation score to obtain a target weighted sum, and normalize the target weighted sum to obtain a target enterprise growth score.

[0016] On the third aspect, the enterprise growth assessment and prediction device based on model training provided in this application adopts the following technical solution.

[0017] A device for evaluating and predicting enterprise growth based on model training, the device comprising: one or more memories for storing instructions, and One or more processors are used to call and run the instructions from the memory to perform the method.

[0018] To sum up, this application includes the following beneficial technical effects: This application combines the upstream enterprise information, downstream enterprise information and enterprise personnel information of the target enterprise to score the stability of the target enterprise, and then combines its R&D score and innovation score to realize the evaluation and prediction of the enterprise's growth. For science and technology enterprises, it can intuitively express the enterprise stability and scientific and technological innovation capabilities that investors are concerned about, thereby providing strong support for the prediction of the enterprise's growth potential. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a topological diagram of the enterprise growth assessment prediction method in the embodiment of the present application.

[0020] Figure 2 It is a topological diagram for analyzing the stability of the target enterprise in the embodiment of the present application.

[0021] Figure 3 It is a topological diagram for generating downstream scores of downstream enterprises in the embodiment of the present application.

[0022] Figure 4 It is a topological diagram for generating personnel scores of employees of the target enterprise in the embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0025] Currently, many service companies will build service platforms based on the needs of the customers they serve. The customers served by the company upload their own information to the platform or the platform automatically obtains customer information directly through crawler technology, thereby integrating customer information into the platform. Service companies can screen customers in a targeted manner based on customer information on the platform. Especially for operating service companies, most of the customer data they can obtain can accurately represent their technological innovation capabilities, personnel turnover capabilities, project research and development and other information. This application plan aims to provide market investors with a model-trained enterprise growth assessment and prediction method based on customer information on the platform. The method can accurately predict the growth of service customers based on customer information on the service platform.

[0026] Reference Figure 1 The enterprise growth assessment and prediction method based on model training provided in this application specifically includes the following steps: Step S100: Establish and store an enterprise stability assessment model, an enterprise R&D assessment model, and an enterprise innovation assessment model; Step S200: Acquire target enterprise information, wherein the target enterprise information includes upstream enterprise information, downstream enterprise information, target enterprise personnel information, financial information, R&D project information, and patent information; Step S300: Generate a stability score of the target enterprise based on the target enterprise information and the enterprise stability evaluation model; generate a research and development score of the target enterprise based on the target enterprise information and the enterprise research and development evaluation model; generate an innovation score of the target enterprise based on the target enterprise information and the enterprise innovation evaluation model; Step S400: weight the stability score, R&D score, and innovation score to obtain a target weighted sum, and normalize the target weighted sum to obtain a target enterprise growth score.

[0027] Reference Figure 2 The enterprise stability assessment model analyzes the stability of the target enterprise based on the upstream enterprise information, downstream enterprise information, and target enterprise personnel information, specifically including: Generating an upstream score for the upstream enterprise based on the upstream enterprise information; Generating a downstream score for the downstream enterprise based on the downstream enterprise information; Generating enterprise employee personnel scores based on the target enterprise personnel information; Performing weighted calculation on the upstream score, the downstream score and the personnel score to obtain a stable weighted sum; The stability score is obtained by normalizing the stability weighted sum.

[0028] Among them, the upstream enterprise represents the supplier required by the target enterprise for product production. Generally, there are multiple upstream enterprises corresponding to one target enterprise. In the present application scheme, when generating the upstream score, the technological nature of the upstream enterprise is mainly evaluated. In a preferred example, the upstream score is set according to the high-tech enterprise score of the upstream enterprise, specifically: the high-tech enterprise score of each upstream enterprise when it is certified as a high-tech enterprise is used as the basic score of the upstream enterprise. If the upstream enterprise has no high-tech enterprise score, the basic score of the upstream enterprise is set to the lowest value of the high-tech enterprise score of all enterprises in the platform. When there is no upstream enterprise for the target enterprise, the basic score of the upstream enterprise takes the maximum value of 100. The upstream score takes the average of the basic scores of all upstream enterprises of the target enterprise.

[0029] Downstream enterprises refer to enterprises that use the target enterprise as a supplier. One target enterprise corresponds to one or more downstream enterprises. Figure 3 Generating downstream scores of downstream enterprises based on the downstream enterprise information includes: Obtain basic scores for each downstream enterprise; Obtain transaction information of each downstream enterprise; Calculating the relevance score of the downstream enterprise based on the transaction information of the downstream enterprise; The downstream score is calculated based on the basic score of each downstream enterprise and the associated score of the downstream enterprise.

[0030] The downstream enterprises are enterprises that have been entered into the platform or have not been entered into the platform. The basic score of the downstream enterprises is proportional to the output value of the downstream enterprises, that is, the output value Cx of the downstream enterprises is obtained by crawler technology, then the basic score Nx of the downstream enterprises is: Nj=Kx1*Cx, Kx1 represents the basic score constant of the xth downstream enterprise, and Cx represents the output value of the xth downstream enterprise. It should be noted that Kx1 has different values ​​according to the industry in which the downstream enterprise is located.

[0031] Calculating the association score of the downstream enterprise based on the transaction information of the downstream enterprise includes: calculating the transaction proportion of the downstream enterprise in the target enterprise based on the transaction information; and calculating the association score based on the transaction proportion of the downstream enterprise in the target enterprise.

[0032] Specifically, the transaction information of the downstream enterprise includes the product type and transaction amount Ji traded from the target enterprise to the downstream enterprise, where Ji represents the transaction amount of the i-th product. If the transaction information of the downstream enterprise contains n products in total, the association score Nx is: Nx=Kx2* ; Pi represents the sales volume of the product type of the i-th product in the target enterprise, T represents the total sales volume of the target enterprise, Kx2 represents the association score constant of the x-th downstream enterprise, and Kx2 has different values ​​depending on the industry corresponding to the product type.

[0033] After calculating the basic score and associated score of each downstream enterprise, the basic score and associated score of each downstream enterprise are multiplied together to obtain the calculation factor of the downstream enterprise. The downstream enterprise whose calculation factor is greater than the average calculation factor of the downstream enterprises of the target enterprise is taken as the selected enterprise, and the average calculation factor of the selected enterprise is taken as the downstream score.

[0034] Reference Figure 4 Generating a target enterprise employee personnel score based on the target enterprise personnel information includes: The target enterprise generates a personnel evaluation model; Performing personnel scoring on enterprise personnel according to the personnel evaluation model; Generate enterprise employee personnel scores based on personnel scores as well as personnel entry information and personnel resignation information.

[0035] The personnel evaluation model includes the weighted scores set by the target enterprise for the personnel's education, length of service and rank based on the position. After setting the score weights, the personnel scores of the enterprise personnel can be obtained after obtaining the personnel information of the target enterprise. The enterprise entry score within the preset time is obtained based on the personnel entry information and the personnel score; the enterprise resignation score within the preset time is obtained based on the personnel resignation information and the personnel score; the personnel score is generated by the enterprise entry score and the enterprise resignation score ratio. The enterprise entry score is the sum of the personnel scores of the incoming personnel, the enterprise resignation score is the sum of the personnel scores of the resigned personnel, and the personnel score is the ratio of the enterprise entry score to the enterprise resignation score.

[0036] The enterprise innovation assessment model obtains the innovation score of the target enterprise based on the target enterprise's patent information, R&D project information, financial information and intellectual property score, specifically including: generating the target enterprise's intellectual property score from patent information; generating the target enterprise's project score from R&D project information and financial information; generating the innovation score based on the target enterprise's intellectual property score and the target enterprise's project score.

[0037] Specifically, the innovation score C of the target enterprise is: C= ; Nz is the intellectual property score within the preset time period, Ny is the number of R&D projects within the preset time period, S is the R&D cost within the preset time period, and Ky is the cost constant; Score the project of the target enterprise.

[0038] Among them, intellectual property rights include Class I intellectual property rights and Class II intellectual property rights. Each type of intellectual property right is assigned a fixed score based on its legal status, for example, an authorized invention patent is 5 points, an invention patent application is 2 points, and an authorized utility model is 1 point. The intellectual property score is the sum of the fixed scores of Class I and Class II intellectual property rights of the target enterprise. The R&D expenses are obtained from the financial information.

[0039] The enterprise R&D evaluation model obtains the R&D score of the target enterprise based on the R&D project information and financial information, specifically including: selecting a preset time period, dividing the time period into several R&D scoring segments, and obtaining the number of projects and R&D expenditures in each R&D scoring segment, wherein the number of projects is obtained from the R&D project information, and the R&D expenditures are obtained from the financial information. In a preferred embodiment, the preset time period is the previous five years. For example, this year is year a, and the R&D scoring segments are year a-1, year a-2, year a-3, year a-4, and year a-5. After obtaining the number of projects and R&D expenditures, linear normalization is performed on the number of projects and R&D expenditures, respectively, and the slope after linear normalization is used as the growth rate of the number of projects and the growth rate of R&D expenditures. Then the R&D score Y of the target enterprise is: Y=Kl*fl+Kx3*fx; Kl is the project growth constant, Kx3 is the expenditure growth constant, fl is the project growth rate, and fx is the R&D expenditure growth rate.

[0040] By adopting the above-mentioned technical solution, this application combines the upstream enterprise information, downstream enterprise information and enterprise personnel information of the target enterprise to score the stability of the target enterprise, and then combines its R&D score and innovation score to realize the evaluation and prediction of the enterprise's growth. For science and technology enterprises, it can intuitively express the enterprise stability and scientific and technological innovation capabilities that investors are concerned about, thereby providing strong support for the prediction of the enterprise's growth potential.

[0041] In another preferred embodiment, the present application also provides an enterprise growth assessment and prediction system based on model training, the system comprising a model storage module, an information acquisition module, a scoring module and a data calculation module.

[0042] Model storage module, used to establish and store enterprise stability assessment model, enterprise R&D assessment model and enterprise innovation assessment model; An information acquisition module is used to acquire target enterprise information, including upstream enterprise information, downstream enterprise information, enterprise personnel information, business information, financial information, R&D project information and patent information; Scoring module for: Generate a stability score for the target enterprise based on the target enterprise information and the enterprise stability assessment model; Generate a research and development score for the target enterprise based on the target enterprise information and the enterprise research and development evaluation model; and generating an innovation score for the target enterprise based on the target enterprise information and the enterprise innovation assessment model; The data calculation module is used to perform weight calculation on the stability score, R&D score, and innovation score to obtain a target weighted sum, and normalize the target weighted sum to obtain a target enterprise growth score.

[0043] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0044] In the several embodiments provided in this application, it should be understood that the disclosed system modules can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0045] The modules described as separate components may or may not be physically separated, and the components described as functional modules may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple physical structures, especially the model storage module and the scoring module. The model storage module is only used to store the constructed stability evaluation model, enterprise R&D evaluation model and enterprise innovation evaluation model, which can be arranged in an integrated memory or distributed to the clients of each target enterprise. The scoring module is used to call the stability evaluation model, enterprise R&D evaluation model and enterprise innovation evaluation model and generate stability scores, R&D scores and innovation scores. Therefore, the scoring module can be configured in a central server or distributed to the clients of each target enterprise.

[0046] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0047] The present application also discloses a device for evaluating and predicting enterprise growth based on model training, which is mainly composed of one or more memories and one or more processors: The memory is used to store instructions; The processor is used to call and run instructions from the memory to execute the enterprise growth assessment and prediction method as described above.

[0048] It can be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories.

[0049] The nonvolatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0050] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus DRAM.

[0051] The processor mentioned in any of the above places may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the above acceptance method. The processor and the memory may be decoupled and respectively arranged on different physical devices, and connected by wire or wireless means to realize the respective functions of the processor and the memory, so as to support the chip of the device to realize various functions in the above embodiments. Alternatively, the processor and the memory may also be coupled on the same device.

[0052] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0053] In the technical solution of the present application, the heating device blocked by the front device can be identified by identifying the overlapping halo area, and the device temperature can be combined to determine whether the blocked heating device has a heating fault, thereby improving the accuracy of detecting the fault location of the power equipment.

Claims

1. Enterprise growth assessment and prediction method based on model training, It is characterized in that The method comprises: Establish and store enterprise stability assessment models, enterprise R&D assessment models, and enterprise innovation assessment models; Obtaining target enterprise information, including upstream enterprise information, downstream enterprise information, target enterprise personnel information, financial information, R&D project information, and patent information; Generate a stability score for the target enterprise based on the target enterprise information and the enterprise stability assessment model; Generate a research and development score for the target enterprise based on the target enterprise information and the enterprise research and development evaluation model; Generate an innovation score for the target enterprise based on the target enterprise information and the enterprise innovation assessment model; Performing weight calculation on the stability score, R&D score, and innovation score to obtain a target weighted sum; The weighted sum of the targets is normalized to obtain the growth score of the target enterprise.

2. The enterprise growth assessment and prediction method based on model training according to claim 1, It is characterized in that The stability score of the target enterprise is generated based on the target enterprise information and the enterprise stability assessment model, including: Generating an upstream score for the upstream enterprise based on the upstream enterprise information; Generating a downstream score for the downstream enterprise based on the downstream enterprise information; Generating enterprise employee personnel scores based on the target enterprise personnel information; Performing weighted calculation on the upstream score, the downstream score and the personnel score to obtain a stable weighted sum; The stability score is obtained by normalizing the stability weighted sum.

3. The enterprise growth assessment and prediction method based on model training according to claim 2, It is characterized in that Generating downstream scores of downstream enterprises based on the downstream enterprise information includes: Obtain basic scores for each downstream enterprise; Obtain transaction information of each downstream enterprise; Calculating the relevance score of the downstream enterprise based on the transaction information of the downstream enterprise; The downstream score is calculated based on the basic score of each downstream enterprise and the associated score of the downstream enterprise.

4. The enterprise growth assessment and prediction method based on model training according to claim 3, It is characterized in that Calculating the relevance score of the downstream enterprise based on the transaction information of the downstream enterprise includes: Calculate the transaction proportion of the downstream enterprise in the target enterprise based on the transaction information; The association score is calculated based on the transaction proportion of the downstream enterprise in the target enterprise.

5. The enterprise growth assessment and prediction method based on model training according to claim 2, It is characterized in that Generating enterprise employee personnel scores based on the target enterprise personnel information includes: The target enterprise generates a personnel evaluation model; Performing personnel scoring on enterprise personnel according to the personnel evaluation model; Generate enterprise employee personnel scores based on personnel scores as well as personnel entry information and personnel resignation information.

6. The enterprise growth assessment and prediction method based on model training according to claim 5, It is characterized in that The personnel evaluation model generated by the target enterprise includes: the target enterprise sets weighted scores for personnel's education, length of service and rank based on the position.

7. The enterprise growth assessment and prediction method based on model training according to claim 5, It is characterized in that Generating enterprise employee personnel scores based on personnel scores and personnel entry information and personnel resignation information includes: Obtaining the enterprise entry score within a preset time based on the personnel entry information and personnel score; Obtaining the enterprise resignation score within a preset time based on the employee resignation information and employee score; The personnel score is generated by the ratio of the enterprise entry score and the enterprise resignation score.

8. The enterprise growth assessment and prediction method based on model training according to claim 1, It is characterized in that Generating the innovation score of the target enterprise based on the target enterprise information and the enterprise innovation assessment model includes: Generate an intellectual property score for the target enterprise based on patent information; Generating a project score of the target enterprise based on the R&D project information and financial information; The innovation score is generated based on the target enterprise's intellectual property score and the target enterprise's project score.

9. Enterprise growth assessment and prediction system based on model training, It is characterized in that The system comprises: Model storage module, used to establish and store enterprise stability assessment model, enterprise R&D assessment model and enterprise innovation assessment model; An information acquisition module is used to acquire target enterprise information, including upstream enterprise information, downstream enterprise information, enterprise personnel information, business information, financial information, R&D project information and patent information; Scoring module for: Generate a stability score for the target enterprise based on the target enterprise information and the enterprise stability assessment model; Generate a research and development score for the target enterprise based on the target enterprise information and the enterprise research and development evaluation model; and generating an innovation score for the target enterprise based on the target enterprise information and the enterprise innovation assessment model; The data calculation module is used to perform weight calculation on the stability score, R&D score, and innovation score to obtain a target weighted sum, and normalize the target weighted sum to obtain a target enterprise growth score.

10. Enterprise growth assessment and prediction device based on model training, It is characterized in that The device comprises: one or more memories for storing instructions, and One or more processors, configured to call and execute the instructions from the memory to execute the method according to any one of claims 1 to 8.

Images