Enterprise score management method and system based on big data

Abstract

The invention relates to the technical field of big data analysis and mining, in particular to an enterprise score management method and system based on big data, and the method comprises the steps: obtaining a monitoring data set of an enterprise; substituting the monitoring data set of the enterprise into the scoring management model, generating a rectification suggestion scheme of the enterprise on each project and / or a scoring management scheme of the enterprise for different types of target terminals, and outputting the rectification suggestion scheme and the scoring management scheme; if the score management model outputs a rectification suggestion scheme of the enterprise on each project, after rectification time in the rectification suggestion scheme, re-executing the'obtaining the monitoring data set of the enterprise 'and the subsequent steps; and in response to analysis instructions of different types of target terminals, feeding back a plurality of groups of newly generated scoring management schemes to the various types of target terminals corresponding to the scoring management schemes. Accurate and real-time management insight is provided for enterprises, so that the management scheme is optimized, and the enterprise competitiveness is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis and mining, and in particular to the technical field of enterprise rating management, and in particular to a method and system for enterprise rating management based on big data. Background Art

[0002] In economic activities, a good corporate scoring system can reflect the corporate governance level and decision-making quality, which in turn affects the company's reputation and competitiveness. A company with a higher score usually means that it has a higher level of management and transparency, which can attract more investors and partners. This helps the company obtain more resources and opportunities and enhance its market competitiveness.

[0003] However, the scoring management methods in the prior art often have the problems of strong subjectivity and inability to update in real time, which in turn leads to the inability to timely and effectively evaluate the operating conditions, management quality and production efficiency of the enterprise, and the inability to timely discover problems and make adjustments.

[0004] Therefore, there is an urgent need to study a big data-based enterprise scoring management method and system that can provide enterprises with accurate and real-time management insights, thereby optimizing management plans and enhancing enterprise competitiveness. Summary of the invention

[0005] Based on this, the present invention proposes an enterprise scoring management method and system based on big data, which solves the problem that the scoring management methods in the prior art often have strong subjectivity in scoring and cannot be updated in real time, which in turn leads to the inability to timely and effectively evaluate the operating status, management quality and production efficiency of the enterprise, and the technical problem of being unable to discover problems and make adjustments in a timely manner.

[0006] According to a first aspect of the present invention, there is provided a method for enterprise rating management based on big data, the method comprising the following steps:

[0007] Acquire a monitoring data set of an enterprise, wherein the monitoring data set of the enterprise includes monitoring data of enterprise assets and monitoring data of enterprise credit;

[0008] Substituting the monitoring data set of the enterprise into the scoring management model, so as to analyze the monitoring data set of the enterprise, determine the scoring results of the enterprise on each preset project, and then generate and output the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals according to the scoring results of the enterprise on each preset project;

[0009] If the scoring management model outputs the enterprise's rectification suggestions for each project, then after the rectification time in the rectification suggestions, "obtaining the enterprise's monitoring data set" and subsequent steps are re-executed;

[0010] In response to analysis instructions of different types of target terminals, the newly generated multiple groups of scoring management solutions are fed back to the target terminals of each type corresponding to the scoring management solutions.

[0011] According to an embodiment of the present invention, obtaining a monitoring data set of an enterprise includes:

[0012] In response to the enterprise's score management instruction or rectification completion instruction, obtaining the enterprise's asset monitoring data, wherein the enterprise's asset monitoring data at least includes net asset data and working capital data;

[0013] Obtaining monitoring data on the credit of the enterprise;

[0014] Obtain monitoring data on the personal credit of each authorized employee in the enterprise, as well as enterprise-level data on each authorized employee;

[0015] The monitoring data of the enterprise's credit and the monitoring data of the personal credit of each authorized employee in the enterprise are used to form the monitoring data of the enterprise's credit;

[0016] The monitoring data set of the enterprise is composed of the monitoring data of the enterprise assets and the monitoring data of the enterprise credit;

[0017] Furthermore, the acquisition time of the monitoring data set of the enterprise is recorded.

[0018] According to an embodiment of the present invention, before substituting the monitoring data set of the enterprise into the scoring management model, the method further includes the following steps to train the scoring management model:

[0019] Using different enterprises as multiple training samples, obtaining multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets, wherein the training sample sets include asset monitoring data of the training samples and enterprise credit monitoring data;

[0020] According to the multiple training sample sets corresponding to each training sample, a scoring index and a scoring coefficient corresponding to each monitoring data in each training sample set are determined;

[0021] According to the scoring index and scoring coefficient corresponding to each type of monitoring data in each set of training samples, it is judged whether the monitoring data scoring training of each set of training samples is successful:

[0022] If the judgment is no, retraining the scoring management model;

[0023] If the judgment is yes, then according to the multiple training sample sets corresponding to each training sample, the selection time corresponding to each training sample set, and the scoring index and scoring coefficient corresponding to each type of monitoring data in each training sample set, the scoring results of the training samples corresponding to each training sample set on each preset item are obtained;

[0024] According to the scoring results of the training samples corresponding to each group of training sample sets on various preset items, it is judged whether the scoring results of each group of training sample sets are successfully trained:

[0025] If the judgment is no, retraining the scoring management model;

[0026] If the judgment is yes, then according to the scoring results of the training samples corresponding to each group of training sample sets on each preset item, the generation results corresponding to each group of training sample sets are generated, wherein the generation results include the rectification suggestions for the training samples corresponding to each group of training sample sets on each item, and / or the scoring management schemes of the training samples for different types of target terminals;

[0027] According to the generation results corresponding to each group of training sample sets, determine whether the solution generation training of each group of training sample sets is successful;

[0028] The training results of the training are generated according to the scheme of each group of training sample sets, and the training of the scoring management model is selectively determined to be successful.

[0029] According to an embodiment of the present invention, a preset enterprise history monitoring database is stored in the scoring management model, and the preset enterprise history monitoring database stores historical monitoring data sets of different enterprises at different times;

[0030] The method of using different enterprises as multiple training samples, obtaining multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets includes:

[0031] Randomly select multiple different companies and use different companies as multiple training samples;

[0032] Randomly select multiple moments, and randomly match multiple moments corresponding to each training sample based on multiple training samples;

[0033] According to the multiple moments corresponding to each training sample and the preset enterprise historical monitoring database, a monitoring data set corresponding to each selected moment of each training sample is obtained;

[0034] In order to obtain multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets.

[0035] According to an embodiment of the present invention, determining the scoring index and the scoring coefficient corresponding to each type of monitoring data in each set of training samples according to the multiple sets of training samples corresponding to each training sample includes:

[0036] Determine the score comparison table corresponding to each group of training sample sets according to the selection time corresponding to each group of training sample sets;

[0037] Determine the credit rating corresponding to the enterprise credit monitoring data in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise according to the enterprise credit monitoring data in each training sample set;

[0038] According to the credit rating corresponding to the credit monitoring data of the enterprise in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise, the credit rating of each training sample set is judged to determine whether the training is successful:

[0039] If the judgment is no, retraining the scoring management model;

[0040] If the judgment is yes, then according to the credit rating corresponding to the credit monitoring data of the enterprise in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise, determine the scoring index and scoring coefficient corresponding to the credit monitoring data of the enterprise in each training sample set, as well as the scoring index and scoring coefficient corresponding to the personal credit monitoring data of each authorized employee in the enterprise in each training sample set;

[0041] Furthermore, according to the enterprise asset monitoring data in each set of training sample sets, a scoring index and a scoring coefficient corresponding to the enterprise asset monitoring data in each set of training sample sets are determined;

[0042] In order to obtain the scoring index and scoring coefficient corresponding to each type of monitoring data in each set of training samples.

[0043] According to an embodiment of the present invention, the scoring results of the training samples corresponding to each training sample set on each preset item are obtained according to the multiple training sample sets corresponding to each training sample set, the selection time corresponding to each training sample set, and the scoring index and scoring coefficient corresponding to each monitoring data in each training sample set, including:

[0044] According to the selection time corresponding to each group of training sample sets, determine the scoring scheme of each preset project corresponding to each group of training sample sets, wherein the scoring scheme includes at least one type of monitoring data corresponding to the preset project, the proportion value corresponding to each type of monitoring data, the number of reward points corresponding to at least one type of monitoring data, and the reward conditions;

[0045] According to the multiple groups of training sample sets corresponding to each training sample, the scoring schemes of the preset items corresponding to each group of training sample sets, and the scoring index and scoring coefficient corresponding to each type of monitoring data in each group of training sample sets, the scoring results of the training samples corresponding to each group of training sample sets on the preset items are obtained.

[0046] According to an embodiment of the present invention, generating the generation result corresponding to each group of training sample sets according to the scoring results of the training samples corresponding to each group of training sample sets on various preset items includes:

[0047] Determine the comprehensive scoring result of the training samples corresponding to each group of training sample sets according to the scoring results of the training samples corresponding to each group of training sample sets on various preset items;

[0048] If the comprehensive scoring results of the training samples corresponding to the training sample set, or the scoring results of the training samples corresponding to the training sample set on each preset item meet the preset rectification requirements, then according to the multiple groups of training sample sets corresponding to each training sample and the scoring results of the training samples corresponding to the training sample set on each preset item, a rectification suggestion plan for the training samples corresponding to the training sample set on each item is generated;

[0049] and / or,

[0050] If the comprehensive scoring results of the training samples corresponding to the training sample set do not meet the preset rectification requirements, then based on the scoring results of the training samples corresponding to the training sample set on each preset item, a scoring management plan for the training samples for different types of target terminals is generated, and the scoring management plan includes at least the management difficulty level, risk level and failure rate of the training samples for the type of target terminals.

[0051] According to an embodiment of the present invention, generating a rectification suggestion plan for each item of the training sample corresponding to the training sample set according to the multiple groups of training sample sets corresponding to each training sample and the scoring results of the training sample corresponding to the training sample set on each preset item includes:

[0052] Determining at least one rectification direction of the training samples corresponding to the training sample set according to the scoring results of the training samples corresponding to the training sample set on various preset items;

[0053] Generate multiple groups of rectification reference solutions for the training samples corresponding to the training sample sets on various items according to the multiple groups of training sample sets corresponding to each training sample, the scoring results of the training samples corresponding to the training sample sets on various preset items, and at least one rectification direction of the training samples corresponding to the training sample sets;

[0054] Simulate each group of rectification reference plans to obtain simulation data of each group of rectification reference plans;

[0055] Determine the rectification simulation result of each group of rectification reference schemes according to the multiple groups of training sample sets corresponding to each training sample and the simulation data of each group of rectification reference schemes, wherein the rectification simulation result includes the rectification execution completion rate, the rectification time and the rectification optimization ratio;

[0056] Screening multiple groups of rectification reference plans according to the rectification simulation results of each group of rectification reference plans, and selecting a group of rectification reference plans as rectification recommendation plans for the training samples corresponding to the training sample set on the project;

[0057] In order to obtain the rectification suggestions for each item of the training samples corresponding to the training sample set.

[0058] According to an embodiment of the present invention, the monitoring data set of the enterprise is substituted into the scoring management model, so that the monitoring data set of the enterprise is analyzed, and the scoring results of the enterprise on each preset project are determined, and then according to the scoring results of the enterprise on each preset project, the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals are generated and output including:

[0059] Get the current rating comparison table;

[0060] Determine the scoring index and scoring coefficient corresponding to each monitoring data in the monitoring data set of the enterprise according to the current scoring comparison table and the monitoring data set of the enterprise;

[0061] According to the monitoring data set of the enterprise and the scoring index and the scoring coefficient corresponding to each type of monitoring data in the monitoring data set of the enterprise, obtaining the scoring results of the enterprise corresponding to the monitoring data set of the enterprise on various preset items;

[0062] According to the scoring results of the enterprise on each preset project corresponding to the monitoring data set of the enterprise, the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals are generated and output.

[0063] According to a second aspect of the present invention, there is provided an enterprise rating management system based on big data, the system comprising a data acquisition device, a rating management model and a control device, the data acquisition device interacts with different devices within the enterprise, the Internet and different types of target terminals to realize respective data collection for different devices within the enterprise, the Internet and different types of target terminals, the rating management model stores a preset enterprise history monitoring database and a preset enterprise history generation result database, the control device comprises a processor and a memory, the memory is suitable for storing multiple program codes, the program codes are suitable for being loaded and run by the processor to execute the enterprise rating management method based on big data described in any one of the technical solutions of the above-mentioned technical solutions of the enterprise rating management method based on big data.

[0064] It can be seen from the above technical solutions that the enterprise rating management method and system based on big data provided by the present invention have the following beneficial effects:

[0065] The enterprise scoring management method and system based on big data provided by the present invention substitutes the acquired monitoring data set of the enterprise into the scoring management model, so that the scoring results of the enterprise on each project are determined according to the analysis of the monitoring data set of the enterprise, and then the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals are generated and called out, so as to give professional rectification suggestion plans for each project of the enterprise, and then optimize the management plan of the enterprise. After the rectification period, the above technical plan is re-executed, so as to further optimize the management of the enterprise, and then improve the matching degree between the rectification plan and the enterprise, make the rectification plan more intelligent, and improve the precise management of the enterprise. It manages and responds to the analysis instructions of different types of target terminals, and feeds back the latest generated multiple groups of scoring management plans to the corresponding target terminals, so that the investors or partners corresponding to different types of target terminals can promptly know the latest scoring situation of the enterprise, thereby improving the investment capabilities of the investors or partners corresponding to different types of target terminals, and providing the enterprise with accurate and real-time management insights, so as to optimize the management plan and enhance the competitiveness of the enterprise, avoiding the problems in the scoring management methods in the prior art that the scoring is often highly subjective and cannot be updated in real time, which leads to the inability to timely and effectively evaluate the operating status, management quality and production efficiency of the enterprise, and the technical problem of being unable to discover problems and make adjustments in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the figures are used to represent similar components, among which:

[0067] Figure 1 This is a flowchart of the main steps of a big data-based enterprise scoring management method according to an embodiment of the present invention;

[0068] Figure 2 It is a flowchart of main steps of processing data by a scoring management model of an enterprise scoring management method based on big data according to an embodiment of the present invention;

[0069] Figure 3 It is a schematic diagram of the main structural block diagram of an enterprise scoring management system based on big data according to an embodiment of the present invention.

[0070] List of reference numerals:

[0071] 300: Enterprise scoring management system based on big data; 301: Control device; 3011: Processor; 3012: Memory; 3013: Program code; 302: Scoring management model; 3021: Enterprise history monitoring database; 3022: Enterprise history generation result database; 303: Data acquisition device. DETAILED DESCRIPTION

[0072] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0073] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.

[0074] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart of the main steps of a method for enterprise rating management based on big data according to an embodiment of the present invention. Figure 1 As shown, a big data-based enterprise rating management method in an embodiment of the present invention mainly includes the following steps S101 to S104.

[0075] Step S101: Acquire a monitoring data set of an enterprise, wherein the monitoring data set of the enterprise includes monitoring data of enterprise assets and monitoring data of enterprise credit;

[0076] Specifically, obtaining the monitoring data set of the enterprise includes:

[0077] In response to the enterprise's score management instruction or rectification completion instruction, obtaining the enterprise's asset monitoring data, wherein the enterprise's asset monitoring data at least includes net asset data and working capital data;

[0078] Obtaining monitoring data on the credit of the enterprise;

[0079] Obtain monitoring data on the personal credit of each authorized employee in the enterprise, as well as enterprise-level data on each authorized employee;

[0080] The monitoring data of the enterprise's credit and the monitoring data of the personal credit of each authorized employee in the enterprise are used to form the monitoring data of the enterprise's credit;

[0081] The monitoring data set of the enterprise is composed of the monitoring data of the enterprise assets and the monitoring data of the enterprise credit;

[0082] Furthermore, the acquisition time of the monitoring data set of the enterprise is recorded.

[0083] Step S102: Substituting the monitoring data set of the enterprise into the scoring management model, so as to analyze the monitoring data set of the enterprise, determine the scoring results of the enterprise on each preset project, and then generate and output the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals according to the scoring results of the enterprise on each preset project;

[0084] Furthermore, before substituting the monitoring data set of the enterprise into the scoring management model, the method further includes the following steps to train the scoring management model:

[0085] Using different enterprises as multiple training samples, obtaining multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets, wherein the training sample sets include asset monitoring data of the training samples and enterprise credit monitoring data;

[0086] According to the multiple training sample sets corresponding to each training sample, a scoring index and a scoring coefficient corresponding to each monitoring data in each training sample set are determined;

[0087] According to the scoring index and scoring coefficient corresponding to each type of monitoring data in each set of training samples, it is judged whether the monitoring data scoring training of each set of training samples is successful:

[0088] If the judgment is no, retraining the scoring management model;

[0089] If the judgment is yes, then according to the multiple training sample sets corresponding to each training sample, the selection time corresponding to each training sample set, and the scoring index and scoring coefficient corresponding to each type of monitoring data in each training sample set, the scoring results of the training samples corresponding to each training sample set on each preset item are obtained;

[0090] According to the scoring results of the training samples corresponding to each group of training sample sets on various preset items, it is judged whether the scoring results of each group of training sample sets are successfully trained:

[0091] If the judgment is no, retraining the scoring management model;

[0092] If the judgment is yes, then according to the scoring results of the training samples corresponding to each group of training sample sets on each preset item, the generation results corresponding to each group of training sample sets are generated, wherein the generation results include the rectification suggestions for the training samples corresponding to each group of training sample sets on each item, and / or the scoring management schemes of the training samples for different types of target terminals;

[0093] According to the generation results corresponding to each group of training sample sets, determine whether the solution generation training of each group of training sample sets is successful;

[0094] The training results of the training are generated according to the scheme of each group of training sample sets, and the training of the scoring management model is selectively determined to be successful.

[0095] Specifically, the scoring management model stores a preset enterprise history monitoring database, and the preset enterprise history monitoring database stores historical monitoring data sets of different enterprises at different times;

[0096] The method of using different enterprises as multiple training samples, obtaining multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets includes:

[0097] Randomly select multiple different companies and use different companies as multiple training samples;

[0098] Randomly select multiple moments, and randomly match multiple moments corresponding to each training sample based on multiple training samples;

[0099] According to the multiple moments corresponding to each training sample and the preset enterprise historical monitoring database, a monitoring data set corresponding to each selected moment of each training sample is obtained;

[0100] In order to obtain multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets.

[0101] Specifically, the step of determining the scoring index and the scoring coefficient corresponding to each monitoring data in each training sample set according to the multiple training sample sets corresponding to each training sample includes:

[0102] Determine the score comparison table corresponding to each group of training sample sets according to the selection time corresponding to each group of training sample sets;

[0103] Determine the credit rating corresponding to the enterprise credit monitoring data in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise according to the enterprise credit monitoring data in each training sample set;

[0104] According to the credit rating corresponding to the credit monitoring data of the enterprise in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise, the credit rating of each training sample set is judged to determine whether the training is successful:

[0105] If the judgment is no, retraining the scoring management model;

[0106] If the judgment is yes, then according to the credit rating corresponding to the credit monitoring data of the enterprise in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise, determine the scoring index and scoring coefficient corresponding to the credit monitoring data of the enterprise in each training sample set, as well as the scoring index and scoring coefficient corresponding to the personal credit monitoring data of each authorized employee in the enterprise in each training sample set;

[0107] Furthermore, according to the enterprise asset monitoring data in each set of training sample sets, a scoring index and a scoring coefficient corresponding to the enterprise asset monitoring data in each set of training sample sets are determined;

[0108] In order to obtain the scoring index and scoring coefficient corresponding to each type of monitoring data in each set of training samples.

[0109] Specifically, the preset enterprise historical monitoring database also stores the historical scoring index and scoring coefficient corresponding to each type of monitoring data in each historical monitoring data set, and the scoring results of the enterprise corresponding to each historical monitoring data set on each preset item;

[0110] The step of judging whether the monitoring data scoring training of each set of training samples is successful according to the scoring index and the scoring coefficient corresponding to each type of monitoring data in each set of training samples includes:

[0111] If the scoring index and scoring coefficient corresponding to each type of monitoring data in the training sample set are consistent with the historical scoring index and scoring coefficient corresponding to each type of monitoring data in the historical monitoring data set corresponding to the training sample set in the preset enterprise historical monitoring database, then the training result of the monitoring data scoring training of the training sample set is determined to be successful;

[0112] Otherwise, it is determined that the training result of the monitoring data scoring training of the training sample set is training failure.

[0113] Specifically, the scoring results of the training samples corresponding to each training sample set on each preset item are obtained according to the multiple training sample sets corresponding to each training sample set, the selection time corresponding to each training sample set, and the scoring index and scoring coefficient corresponding to each monitoring data in each training sample set, including:

[0114] According to the selection time corresponding to each group of training sample sets, determine the scoring scheme of each preset project corresponding to each group of training sample sets, wherein the scoring scheme includes at least one type of monitoring data corresponding to the preset project, the proportion value corresponding to each type of monitoring data, the number of reward points corresponding to at least one type of monitoring data, and the reward conditions;

[0115] According to the multiple groups of training sample sets corresponding to each training sample, the scoring schemes of the preset items corresponding to each group of training sample sets, and the scoring index and scoring coefficient corresponding to each type of monitoring data in each group of training sample sets, the scoring results of the training samples corresponding to each group of training sample sets on the preset items are obtained.

[0116] Specifically, judging whether the scoring results of each training sample set are successfully trained according to the scoring results of the training samples corresponding to each training sample set on various preset items includes:

[0117] If the scoring results of the training samples corresponding to the training sample set on the preset items are consistent with the scoring results of the enterprise in the historical monitoring data set corresponding to the training sample set in the preset enterprise historical monitoring database on the preset items, then the training result of the scoring result training of the training sample set is determined to be successful;

[0118] Otherwise, it is determined that the training result of the scoring result training of the training sample set is a training failure.

[0119] Specifically, generating the generated results corresponding to each group of training sample sets according to the scoring results of the training samples corresponding to each group of training sample sets on various preset items includes:

[0120] Determine the comprehensive scoring result of the training samples corresponding to each group of training sample sets according to the scoring results of the training samples corresponding to each group of training sample sets on various preset items;

[0121] If the comprehensive scoring results of the training samples corresponding to the training sample set, or the scoring results of the training samples corresponding to the training sample set on each preset item meet the preset rectification requirements, then according to the multiple groups of training sample sets corresponding to each training sample and the scoring results of the training samples corresponding to the training sample set on each preset item, a rectification suggestion plan for the training samples corresponding to the training sample set on each item is generated;

[0122] and / or,

[0123] If the comprehensive scoring results of the training samples corresponding to the training sample set do not meet the preset rectification requirements, then based on the scoring results of the training samples corresponding to the training sample set on each preset item, a scoring management plan for the training samples for different types of target terminals is generated, and the scoring management plan includes at least the management difficulty level, risk level and failure rate of the training samples for the type of target terminals.

[0124] Specifically, the scoring management model further stores a preset enterprise history generation result database, which stores the generation result corresponding to each historical monitoring data set, the rectification result corresponding to the rectification suggestion plan of the enterprise on each project in the generation result, and the scoring management plan of the enterprise for different types of target terminals in the generation result;

[0125] The determining, based on the generation result corresponding to each group of training sample sets, whether the solution generation training of each group of training sample sets is successful comprises:

[0126] When the generated result corresponding to the training sample set includes a suggested rectification plan for the training sample corresponding to the training sample set on the project and multiple groups of rectification reference plans for the training sample corresponding to the training sample set on various projects:

[0127] If the rectification simulation result corresponding to the rectification suggestion scheme of the training sample corresponding to the training sample set on the project is better than the rectification result corresponding to the rectification suggestion scheme of the enterprise on each project in the preset enterprise history generation result database, and the overlap rate of multiple groups of rectification reference schemes of the training sample corresponding to the training sample set on each project and the scoring management scheme of the enterprise for different types of target terminals reaches a preset overlap rate threshold, then the training result of the scheme generation training of the training sample set is determined to be training successful;

[0128] Otherwise, it is determined that the training result of the solution generation training of the training sample set is training failure;

[0129] or,

[0130] When the generated result corresponding to the training sample set only contains the rectification suggestion scheme for the training sample corresponding to the training sample set on the project, or multiple sets of rectification reference schemes for the training sample corresponding to the training sample set on various projects:

[0131] If the rectification simulation result corresponding to the rectification suggestion scheme on the project of the training sample corresponding to the training sample set is better than the rectification result corresponding to the rectification suggestion scheme of the enterprise on each project in the preset enterprise history generation result database, or the overlap rate of multiple groups of rectification reference schemes on each project of the training sample corresponding to the training sample set and the scoring management scheme of the enterprise for different types of target terminals reaches a preset overlap rate threshold, then the training result of the scheme generation training of the training sample set is determined to be training successful;

[0132] Otherwise, it is determined that the training result of the solution generation training for the training sample set is training failure.

[0133] Specifically, the preset overlap rate threshold may be 80% or 85%. The selection of the preset overlap rate threshold here is only an exemplary description. In actual testing, those skilled in the art may make a selection according to actual needs, which will not be elaborated here.

[0134] Specifically, generating a correction suggestion plan for each item of the training sample corresponding to the training sample set according to the multiple training sample sets corresponding to each training sample and the scoring results of the training sample corresponding to the training sample set on each preset item includes:

[0135] Determining at least one rectification direction of the training samples corresponding to the training sample set according to the scoring results of the training samples corresponding to the training sample set on various preset items;

[0136] Generate multiple groups of rectification reference solutions for the training samples corresponding to the training sample sets on various items according to the multiple groups of training sample sets corresponding to each training sample, the scoring results of the training samples corresponding to the training sample sets on various preset items, and at least one rectification direction of the training samples corresponding to the training sample sets;

[0137] Simulate each group of rectification reference plans to obtain simulation data of each group of rectification reference plans;

[0138] Determine the rectification simulation result of each group of rectification reference schemes according to the multiple groups of training sample sets corresponding to each training sample and the simulation data of each group of rectification reference schemes, wherein the rectification simulation result includes the rectification execution completion rate, the rectification time and the rectification optimization ratio;

[0139] Screening multiple groups of rectification reference plans according to the rectification simulation results of each group of rectification reference plans, and selecting a group of rectification reference plans as rectification recommendation plans for the training samples corresponding to the training sample set on the project;

[0140] In order to obtain the rectification suggestions for each item of the training samples corresponding to the training sample set.

[0141] Specifically, generating training results according to the scheme of each group of training sample sets and selectively determining whether the training of the scoring management model is successful includes:

[0142] Generate training results according to the scheme of each training sample set, and determine the training success rate of all training sample sets;

[0143] According to the generated results corresponding to each group of training sample sets, determine the rectification optimization rate and the score management compliance rate of all training sample sets;

[0144] If the training success rate of all training sample sets reaches a preset training success rate threshold, and the rectification optimization rate reaches a preset rectification optimization rate threshold, and the score management compliance rate reaches a preset score management compliance rate threshold, then the training result of the score management model training is determined to be successful;

[0145] Otherwise, it is determined that the training result of the rating management model training is training failure, and the rating management model is retrained.

[0146] In the above embodiment, multiple groups of rectification reference plans are generated by the scoring results of the training samples corresponding to the training sample set on each preset project, and then according to the simulation results of each group of rectification reference plans, one group of rectification reference plans is selected as the rectification suggestion plan for the training sample on the project, thereby realizing automatic screening of the rectification suggestion plan, and then obtaining the rectification suggestion plan that best suits the training sample set, thereby improving the accuracy and reliability of the scoring management model.

[0147] Specifically, the preset training success rate threshold may be 80%, the preset rectification and optimization rate threshold may be 85%, and the preset score management compliance rate threshold may be 85%. The selection of the preset training success rate threshold, the preset rectification and optimization rate threshold, and the preset score management compliance rate threshold here is only an exemplary description. In actual testing, those skilled in the art may make a selection according to actual needs, which will not be elaborated here.

[0148] In the above embodiment, in the model training, by obtaining multiple sets of training sample sets and the time of selection of each training sample, the scoring index and the scoring coefficient corresponding to each type of monitoring data in each set of training sample are determined according to the multiple sets of training sample sets of each training sample, and then it is judged whether the scoring training of the monitoring data of each set of training sample is successful, so as to realize the automatic judgment of the scoring training of the monitoring data of the scoring management model, avoid the waste of training resources, avoid the occurrence of overfitting and overfitting. If the judgment is successful, the scoring index and the scoring coefficient corresponding to each type of monitoring data in each set of training sample are determined according to the multiple sets of training sample sets and the time of selection of each training sample. And the scoring coefficient, get the scoring results of the training samples corresponding to each group of training sample sets on the preset items, and then judge whether the scoring results of each group of training sample sets are successfully trained. If the training is successful, generate corresponding rectification suggestions according to the scoring results of the training samples corresponding to each group of training sample sets on the preset items, judge whether the scheme generation training of each group of training sample sets is successful, and selectively judge whether the training of the scoring management model is successful based on the judgment result, so as to realize the scoring of monitoring data, scoring results and scheme generation of the scoring management model in sequence, and then improve the stability and convergence of the scoring management model.

[0149] Specifically, the monitoring data set of the enterprise is substituted into the scoring management model, so that the monitoring data set of the enterprise is analyzed to determine the scoring results of the enterprise on each preset project, and then according to the scoring results of the enterprise on each preset project, the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals are generated and output including:

[0150] Get the current rating comparison table;

[0151] Determine the scoring index and scoring coefficient corresponding to each monitoring data in the monitoring data set of the enterprise according to the current scoring comparison table and the monitoring data set of the enterprise;

[0152] According to the monitoring data set of the enterprise and the scoring index and the scoring coefficient corresponding to each type of monitoring data in the monitoring data set of the enterprise, obtaining the scoring results of the enterprise corresponding to the monitoring data set of the enterprise on various preset items;

[0153] According to the scoring results of the enterprise on each preset project corresponding to the monitoring data set of the enterprise, the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals are generated and output.

[0154] Specifically, determining the scoring index and the scoring coefficient corresponding to each monitoring data in the monitoring data set of the enterprise according to the current scoring comparison table and the monitoring data set of the enterprise includes:

[0155] Determining, based on the enterprise credit monitoring data in the enterprise monitoring data set, the credit rating corresponding to the enterprise credit monitoring data in the enterprise monitoring data set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise;

[0156] Determine the scoring index and scoring coefficient corresponding to the credit monitoring data of the enterprise in the monitoring data set of the enterprise, and the scoring index and scoring coefficient corresponding to the personal credit monitoring data of each authorized employee in the enterprise, according to the current scoring comparison table, the credit rating corresponding to the credit monitoring data of the enterprise in the monitoring data set of the enterprise, and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise;

[0157] Furthermore, according to the enterprise asset monitoring data in the monitoring data set of the enterprise and the current scoring comparison table, the scoring index and scoring coefficient corresponding to the enterprise asset monitoring data in the monitoring data set of the enterprise are determined;

[0158] To obtain the scoring index and scoring coefficient corresponding to each monitoring data in the monitoring data set of the enterprise.

[0159] Specifically, the method for generating the rectification suggestion plan for each project of the enterprise and the method for generating the scoring management plan for different types of target terminals of the enterprise can adopt a trained neural network model, or can be a trained machine learning model and a neural network model respectively. The selection of the generation method here is only an exemplary explanation. In actual testing, technical personnel in this field can make a selection according to actual needs. As long as it is possible to generate the rectification suggestion plan for each project of the enterprise and / or the scoring management plan for different types of target terminals according to the scoring results of the enterprise on each preset project corresponding to the monitoring data set of the enterprise, it will not be repeated here.

[0160] In the above embodiment, in the model processing, the scoring index and scoring coefficient corresponding to each monitoring data in the monitoring data set of the enterprise are determined by obtaining the current scoring comparison table and the enterprise monitoring data set, thereby improving the matching degree of the scoring index and the scoring coefficient with the monitoring data of the enterprise, thereby ensuring the accuracy of the scoring index and the scoring coefficient in evaluating the enterprise, and then obtaining the scoring results of the enterprise on each preset project, and based on the scoring results, generating and outputting the rectification suggestion plan for the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals, so as to obtain the scoring index and the scoring coefficient of each monitoring data of the enterprise through the current scoring comparison table and the enterprise monitoring data set, realize the automatic generation of the rectification suggestion plan and / or the scoring management plan, ensure that the enterprise optimizes and rectifys in time, and timely updates the scoring management plan of the enterprise for different types of target terminals, ensures that different types of target terminals can timely know the latest scoring management plan of the enterprise, thereby realizing timely rectification and scoring management of the enterprise, thereby providing accurate and real-time management insights for the enterprise, thereby optimizing the management plan and enhancing the competitiveness of the enterprise.

[0161] Step S103: if the scoring management model outputs the enterprise's rectification suggestions for each project, then after the rectification time in the rectification suggestions, "obtaining the enterprise's monitoring data set" and subsequent steps are re-executed;

[0162] Step S104: in response to analysis instructions of different types of target terminals, the newly generated multiple groups of scoring management solutions are fed back to the target terminals of each type corresponding to the scoring management solutions.

[0163] Based on the above steps S101 to S104, by substituting the acquired monitoring data set of the enterprise into the scoring management model, the scoring results of the enterprise on each project are determined according to the analysis of the monitoring data set of the enterprise, and then the rectification suggestion plan for the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals are generated and called out, so as to provide professional rectification suggestion plans for each project of the enterprise, thereby optimizing the management plan of the enterprise. After the rectification period, the above technical plan is re-executed to further optimize the management of the enterprise, thereby improving the matching degree between the rectification plan and the enterprise, making the rectification plan more intelligent, and improving the precise management of the enterprise. In response to analysis instructions from different types of target terminals, the latest generated multiple groups of scoring management plans are fed back to the corresponding target terminals, so that the investors or partners corresponding to the different types of target terminals can promptly know the latest scoring situation of the enterprise, thereby improving the investment capabilities of the investors or partners corresponding to the different types of target terminals, and providing the enterprise with accurate and real-time management insights, thereby optimizing management plans and enhancing the competitiveness of the enterprise, avoiding the problems in the scoring management methods in the prior art that the scoring is often highly subjective and cannot be updated in real time, which in turn leads to the inability to timely and effectively evaluate the operating status, management quality and production efficiency of the enterprise, and the technical problem of being unable to discover problems and make adjustments in a timely manner.

[0164] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0165] Furthermore, the present invention also provides an enterprise scoring management system based on big data.

[0166] See attached Figure 3 , Figure 3 1 is a main structural diagram of an enterprise rating management system based on big data according to an embodiment of the present invention. Figure 3As shown, an enterprise rating management system 300 based on big data in the embodiment of the present invention mainly includes a data collection device 303, a rating management model 302 and a control device 301. The data collection device 303 interacts with different devices, the Internet and different types of target terminals within the enterprise to realize the respective data collection of different devices, the Internet and different types of target terminals within the enterprise. The rating management model 302 stores a preset enterprise history monitoring database 3021 and a preset enterprise history generation result database 3022. The control device 301 includes a processor 3011 and a memory 3012. The memory 3012 can be configured to store a program code 3013 for executing the enterprise rating management method based on big data in the above method embodiment. The processor 3011 can be configured to execute the program code 3013 in the memory 3012, which includes but is not limited to the program code 3013 for executing the enterprise rating management method based on big data in the above method embodiment. For the convenience of explanation, only the part related to the embodiment of the present invention is shown. For the specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control device 301 can be a control device device formed by various electronic devices.

[0167] Specifically, the data acquisition device 303 can be various communication devices or data acquisition devices of different communication types. The selection of the data acquisition device 303 here is only an exemplary description. In actual testing, technical personnel in this field can make a selection according to actual needs, as long as information interaction can be achieved between the data acquisition device 303 and different devices within the enterprise, the Internet, and different types of target terminals. It will not be repeated here.

[0168] Specifically, the preset enterprise historical monitoring database 3021 stores historical monitoring data sets of different enterprises at different times;

[0169] The preset enterprise historical monitoring database 3021 also stores the historical scoring index and scoring coefficient corresponding to each monitoring data in each historical monitoring data set, as well as the scoring results of the enterprise corresponding to each historical monitoring data set on each preset item;

[0170] The preset enterprise historical generation result database 3022 stores the generation results corresponding to each historical monitoring data set, the rectification results corresponding to the rectification suggestions of the enterprise on each project in the generation results, and the scoring management plans of the enterprise for different types of target terminals in the generation results.

[0171] Specifically, the different types of target terminals can be various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Different types of target terminals can also represent various forms of mobile devices, such as mobile phones, tablet computers, personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0172] In one implementation, the description of the specific implementation functions may refer to steps S101 to S104.

[0173] The enterprise rating management system 300 based on big data is used to execute Figure 1 The embodiment of the enterprise rating management method based on big data shown in the figure has similar technical principles, technical problems solved and technical effects produced. Technical personnel in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the enterprise rating management system 300 based on big data can refer to the contents described in the embodiment of the enterprise rating management method based on big data, which will not be repeated here.

[0174] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor 3011, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electric carrier signal and telecommunication signal.

[0175] Furthermore, the enterprise rating management system 300 based on big data of the present invention also includes a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program code 3013 for executing the enterprise rating management method based on big data of the above-mentioned method embodiment, and the program code 3013 can be loaded and run by the processor 3011 to implement the above-mentioned enterprise rating management method based on big data. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0176] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor 3011 itself, or a part of the software, a part of the hardware, or a part of the combination of software and hardware in the processor 3011. Therefore, the number of each module in the figure is only schematic.

[0177] Those skilled in the art will appreciate that the modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.

[0178] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A big data-based enterprise rating management method, characterized in that: The method comprises the following steps: Acquire a monitoring data set of an enterprise, wherein the monitoring data set of the enterprise includes monitoring data of enterprise assets and monitoring data of enterprise credit; Substituting the monitoring data set of the enterprise into the scoring management model, so as to analyze the monitoring data set of the enterprise, determine the scoring results of the enterprise on each preset project, and then generate and output the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals according to the scoring results of the enterprise on each preset project; If the scoring management model outputs the enterprise's rectification suggestions for each project, then after the rectification time in the rectification suggestions, "obtain the enterprise's monitoring data set" and subsequent steps are re-executed; In response to analysis instructions of different types of target terminals, the newly generated multiple groups of scoring management solutions are fed back to the target terminals of each type corresponding to the scoring management solutions.

2. The enterprise scoring management method based on big data according to claim 1 is characterized in that: The obtaining of the monitoring data set of the enterprise includes: In response to the enterprise's score management instruction or rectification completion instruction, obtaining the enterprise's asset monitoring data, wherein the enterprise's asset monitoring data at least includes net asset data and working capital data; Obtaining monitoring data on the credit of the enterprise; Obtain monitoring data on the personal credit of each authorized employee in the enterprise, as well as enterprise-level data on each authorized employee; The monitoring data of the enterprise's credit and the monitoring data of the personal credit of each authorized employee in the enterprise are used to form the monitoring data of the enterprise's credit; The monitoring data set of the enterprise is composed of the monitoring data of the enterprise assets and the monitoring data of the enterprise credit; Furthermore, the acquisition time of the monitoring data set of the enterprise is recorded.

3. The enterprise scoring management method based on big data according to claim 2 is characterized in that: Before substituting the monitoring data set of the enterprise into the scoring management model, the method further includes the following steps of training the scoring management model: Using different enterprises as multiple training samples, obtaining multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets, wherein the training sample sets include asset monitoring data of the training samples and enterprise credit monitoring data; According to the multiple training sample sets corresponding to each training sample, a scoring index and a scoring coefficient corresponding to each monitoring data in each training sample set are determined; According to the scoring index and scoring coefficient corresponding to each type of monitoring data in each set of training samples, it is judged whether the monitoring data scoring training of each set of training samples is successful: If the judgment is no, retraining the scoring management model; If the judgment is yes, then according to the multiple training sample sets corresponding to each training sample, the selection time corresponding to each training sample set, and the scoring index and scoring coefficient corresponding to each type of monitoring data in each training sample set, the scoring results of the training samples corresponding to each training sample set on each preset item are obtained; According to the scoring results of the training samples corresponding to each group of training sample sets on various preset items, it is judged whether the scoring results of each group of training sample sets are successfully trained: If the judgment is no, retraining the scoring management model; If the judgment is yes, then generating a generation result corresponding to each group of training sample sets according to the scoring results of the training samples corresponding to each group of training sample sets on each preset item, wherein the generation result includes a rectification suggestion plan for the training samples corresponding to each group of training sample sets on each item, and / or a scoring management plan for the training samples for different types of target terminals; According to the generation results corresponding to each group of training sample sets, determine whether the solution generation training of each group of training sample sets is successful; The training results of the training are generated according to the scheme of each group of training sample sets, and the training of the scoring management model is selectively determined to be successful.

4. The enterprise scoring management method based on big data according to claim 3 is characterized in that: The scoring management model stores a preset enterprise historical monitoring database, and the preset enterprise historical monitoring database stores historical monitoring data sets of different enterprises at different times; The method of using different enterprises as multiple training samples, obtaining multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets includes: Randomly select multiple different companies and use different companies as multiple training samples; Randomly select multiple moments, and randomly match multiple moments corresponding to each training sample based on multiple training samples; According to the multiple moments corresponding to each training sample and the preset enterprise historical monitoring database, a monitoring data set corresponding to each selected moment of each training sample is obtained; In order to obtain multiple groups of training sample sets corresponding to each training sample and the selection time corresponding to each group of training sample sets.

5. The enterprise scoring management method based on big data according to claim 4 is characterized in that: Determining the scoring index and the scoring coefficient corresponding to each monitoring data in each training sample set according to the multiple training sample sets corresponding to each training sample includes: Determine the score comparison table corresponding to each group of training sample sets according to the selection time corresponding to each group of training sample sets; Determine the credit rating corresponding to the enterprise credit monitoring data in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise according to the enterprise credit monitoring data in each training sample set; According to the credit rating corresponding to the credit monitoring data of the enterprise in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise, the credit rating of each training sample set is judged to determine whether the training is successful: If the judgment is no, retraining the scoring management model; If the judgment is yes, then according to the credit rating corresponding to the credit monitoring data of the enterprise in each training sample set and the credit rating corresponding to the personal credit monitoring data of each authorized employee in the enterprise, determine the scoring index and scoring coefficient corresponding to the credit monitoring data of the enterprise in each training sample set, as well as the scoring index and scoring coefficient corresponding to the personal credit monitoring data of each authorized employee in the enterprise in each training sample set; Furthermore, according to the enterprise asset monitoring data in each set of training sample sets, a scoring index and a scoring coefficient corresponding to the enterprise asset monitoring data in each set of training sample sets are determined; In order to obtain the scoring index and scoring coefficient corresponding to each type of monitoring data in each set of training samples.

6. The enterprise rating management method based on big data according to claim 5 is characterized in that: The scoring results of the training samples corresponding to each training sample set on each preset item are obtained according to the multiple training sample sets corresponding to each training sample set, the selection time corresponding to each training sample set, and the scoring index and scoring coefficient corresponding to each monitoring data in each training sample set, including: According to the selection time corresponding to each group of training sample sets, determine the scoring scheme of each preset project corresponding to each group of training sample sets, wherein the scoring scheme includes at least one type of monitoring data corresponding to the preset project, the proportion value corresponding to each type of monitoring data, the number of reward points corresponding to at least one type of monitoring data, and the reward conditions; According to the multiple groups of training sample sets corresponding to each training sample, the scoring schemes of the preset items corresponding to each group of training sample sets, and the scoring index and scoring coefficient corresponding to each type of monitoring data in each group of training sample sets, the scoring results of the training samples corresponding to each group of training sample sets on the preset items are obtained.

7. The enterprise rating management method based on big data according to claim 6 is characterized in that: The step of generating the generated results corresponding to each set of training sample sets according to the scoring results of the training samples corresponding to each set of training sample sets on various preset items includes: Determine the comprehensive scoring result of the training samples corresponding to each group of training sample sets according to the scoring results of the training samples corresponding to each group of training sample sets on various preset items; If the comprehensive scoring results of the training samples corresponding to the training sample set, or the scoring results of the training samples corresponding to the training sample set on each preset item meet the preset rectification requirements, then according to the multiple groups of training sample sets corresponding to each training sample and the scoring results of the training samples corresponding to the training sample set on each preset item, a rectification suggestion plan for the training samples corresponding to the training sample set on each item is generated; and / or, If the comprehensive scoring results of the training samples corresponding to the training sample set do not meet the preset rectification requirements, then based on the scoring results of the training samples corresponding to the training sample set on each preset item, a scoring management plan for the training samples for different types of target terminals is generated, and the scoring management plan includes at least the management difficulty level, risk level and failure rate of the training samples for the type of target terminals.

8. The enterprise scoring management method based on big data according to claim 7 is characterized in that: Generating a correction suggestion plan for each item of the training sample corresponding to the training sample set according to the multiple training sample sets corresponding to each training sample and the scoring results of the training sample corresponding to the training sample set on each preset item includes: Determining at least one rectification direction of the training samples corresponding to the training sample set according to the scoring results of the training samples corresponding to the training sample set on various preset items; Generate multiple groups of rectification reference solutions for the training samples corresponding to the training sample sets on various items according to the multiple groups of training sample sets corresponding to each training sample, the scoring results of the training samples corresponding to the training sample sets on various preset items, and at least one rectification direction of the training samples corresponding to the training sample sets; Simulate each group of rectification reference plans to obtain simulation data of each group of rectification reference plans; Determine the rectification simulation result of each group of rectification reference schemes according to the multiple groups of training sample sets corresponding to each training sample and the simulation data of each group of rectification reference schemes, wherein the rectification simulation result includes the rectification execution completion rate, the rectification time and the rectification optimization ratio; Screening multiple groups of rectification reference plans according to the rectification simulation results of each group of rectification reference plans, and selecting a group of rectification reference plans as rectification recommendation plans for the training samples corresponding to the training sample set on the project; In order to obtain the rectification suggestions for each item of the training samples corresponding to the training sample set.

9. The enterprise scoring management method based on big data according to claim 8 is characterized in that: Substituting the monitoring data set of the enterprise into the scoring management model, analyzing the monitoring data set of the enterprise, determining the scoring results of the enterprise on each preset project, and then generating the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals according to the scoring results of the enterprise on each preset project and outputting the following: Get the current rating comparison table; Determine the scoring index and scoring coefficient corresponding to each monitoring data in the monitoring data set of the enterprise according to the current scoring comparison table and the monitoring data set of the enterprise; According to the monitoring data set of the enterprise and the scoring index and scoring coefficient corresponding to each type of monitoring data in the monitoring data set of the enterprise, obtaining the scoring results of the enterprise corresponding to the monitoring data set of the enterprise on various preset items; According to the scoring results of the enterprise on each preset project corresponding to the monitoring data set of the enterprise, the rectification suggestion plan of the enterprise on each project and / or the scoring management plan of the enterprise for different types of target terminals are generated and output.

10. An enterprise rating management system based on big data, characterized in that: The system includes a data acquisition device, a scoring management model and a control device. The data acquisition device interacts with different devices within the enterprise, the Internet and different types of target terminals to realize respective data collection for different devices within the enterprise, the Internet and different types of target terminals. The scoring management model stores a preset enterprise history monitoring database and a preset enterprise history generation result database. The control device includes a processor and a memory. The memory is suitable for storing multiple program codes. The program code is suitable for being loaded and run by the processor to execute a big data-based enterprise scoring management method as described in any one of claims 1 to 9.

Images