CN113034019A - Enterprise risk prediction method and device, computer equipment and readable storage medium - Google Patents
Enterprise risk prediction method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN113034019A CN113034019A CN202110352520.9A CN202110352520A CN113034019A CN 113034019 A CN113034019 A CN 113034019A CN 202110352520 A CN202110352520 A CN 202110352520A CN 113034019 A CN113034019 A CN 113034019A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- information
- risk
- early warning
- enterprise risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 230000008859 change Effects 0.000 claims abstract description 105
- 238000012549 training Methods 0.000 claims abstract description 28
- 230000007246 mechanism Effects 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000008520 organization Effects 0.000 claims description 10
- 230000004075 alteration Effects 0.000 claims 2
- 238000012544 monitoring process Methods 0.000 abstract description 16
- 238000007689 inspection Methods 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000013058 risk prediction model Methods 0.000 description 11
- 230000006399 behavior Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000010354 integration Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and provides an enterprise risk prediction method, an enterprise risk prediction device, computer equipment and a readable storage medium, wherein the method comprises the following steps: acquiring registered item change information and basic information of an enterprise to be supervised from a market supervision mechanism; extracting change characteristics from the registration item change information, and extracting service characteristics from the basic information; and inputting the change characteristics and the service characteristics into an enterprise risk early warning model, outputting a violation risk prediction result by the enterprise risk early warning model, and training the enterprise risk early warning model by taking historical registration item change information, basic information and historical violation information of the enterprise as samples. This scheme is favorable to reducing work load, improves the efficiency of risk inspection, has unified risk prediction's judgement standard, can avoid subjective factor, can supervise the full aspect information of enterprise, avoids single, the one-sidedness of supervision, and the accuracy of risk monitoring can be improved in enterprise's risk early warning model's use.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an enterprise risk prediction method, an enterprise risk prediction device, computer equipment and a readable storage medium.
Background
Traditional risk check systems, such as complaint reporting and joint supervision, can only perform law enforcement checks on a single aspect of ecology, safety and the like of enterprises or legal persons in mass feedback or regular checks, and law enforcement checks often occur after violation behaviors occur, so that certain hysteresis exists, that is, advanced prediction on enterprise risk points cannot be achieved, and supervision has one-sidedness and monitoring accuracy is affected due to the fact that information cannot be shared among systems; the conventional risk inspection system performs inspection in a rule matching mode based on an expert experience model, and has the defects of large data volume, large workload of manually integrating data, analyzing and summarizing, obtaining results and the like, heavy manual screening task, low efficiency, incapability of comprehensively screening information, large subjective factors of the expert experience model and incapability of uniformly judging standards, so that the inspection accuracy is influenced.
Disclosure of Invention
The embodiment of the invention provides an enterprise risk prediction method, which aims to solve the technical problems of hysteresis, low accuracy and low efficiency in risk supervision in the prior art. The method comprises the following steps:
acquiring registered item change information and basic information of an enterprise to be supervised from a market supervision mechanism;
extracting change characteristics from the registration item change information, and extracting service characteristics from the basic information;
and inputting the change characteristics and the service characteristics into an enterprise risk early warning model, and outputting a prediction result of violation risks by the enterprise risk early warning model, wherein the enterprise risk early warning model is obtained by training a sample of historical registration item change information, basic information and historical violation information of an enterprise.
In one embodiment, extracting change characteristics from the registration issue change information includes:
the change frequency of each registered item is extracted.
In one embodiment, extracting the change frequency for each registration entry comprises:
the change frequency of each registered item in a plurality of different time periods is extracted.
In one embodiment, extracting the service features from the basic information comprises:
and extracting enterprise attribute information, type information, credit information and registration information from the basic information.
In one embodiment, the prediction results include attribute information, risk level, of the enterprise at risk of the violation.
In one embodiment, further comprising:
the enterprise risk early warning model is obtained through XGboost algorithm training.
In one embodiment, further comprising:
and sending the prediction result to a corresponding supervision organization according to the registration address and the enterprise type of the enterprise with the violation risk in the prediction result.
In one embodiment, the enterprise risk prediction method is implemented based on a Spring group micro-service framework.
In one embodiment, further comprising:
and receiving processing information and corresponding supervision information of the enterprise to be supervised according to the prediction result fed back by a supervision mechanism, and adding the processing information and the corresponding supervision information into the sample to update the enterprise risk early warning model in an iterative manner.
The embodiment of the invention also provides an enterprise risk prediction device, which is used for solving the technical problems of lag, low accuracy and low efficiency in risk supervision in the prior art. The device includes:
the information acquisition module is used for acquiring registered item change information and basic information of the enterprise to be supervised from a market supervision mechanism;
the characteristic extraction module is used for extracting change characteristics from the registration item change information and extracting service characteristics from the basic information;
and the risk prediction module is used for inputting the change characteristics and the business characteristics into an enterprise risk early warning model, and the enterprise risk early warning model outputs a prediction result of violation risks, wherein the enterprise risk early warning model is obtained by training by taking historical registration item change information, basic information and historical violation information of an enterprise as samples.
In one embodiment, the feature extraction module: the method comprises the following steps:
a first feature extraction unit for extracting a change frequency for each registered item.
In one embodiment, the first feature extraction unit is specifically configured to extract a change frequency of each registration item in a plurality of different time periods.
In one embodiment, the feature extraction module includes:
and the second characteristic extraction unit is used for extracting the enterprise attribute information, the enterprise type information, the credit information and the registration information from the basic information.
In one embodiment, the prediction results include attribute information, risk level, of the enterprise at risk of the violation.
In one embodiment, further comprising:
and the training module is used for obtaining the enterprise risk early warning model through XGboost algorithm training.
In one embodiment, further comprising:
and the sending module is used for sending the prediction result to a corresponding supervision organization according to the registration address and the enterprise type of the enterprise with the violation risk in the prediction result.
In one embodiment, the enterprise risk prediction device is implemented based on a Spring group micro-service framework.
In one embodiment, further comprising:
and the model updating module is used for receiving processing information and corresponding supervision information of the enterprise to be supervised according to the prediction result fed back by the supervision mechanism, and adding the processing information and the corresponding supervision information into the sample to update the enterprise risk early warning model in an iterative manner.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the arbitrary enterprise risk prediction method when executing the computer program so as to solve the technical problems of hysteresis, low accuracy and low efficiency in risk supervision in the prior art.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing any enterprise risk prediction method is stored in the computer-readable storage medium, so as to solve technical problems of hysteresis, low accuracy, and low efficiency in risk supervision in the prior art.
In the embodiment of the invention, the change information and the basic information of the registered items of the enterprise to be supervised are obtained from a market supervision mechanism, the change characteristics are extracted from the change information of the registered items, the business characteristics are extracted from the basic information, and finally the change characteristics and the business characteristics are input into an enterprise risk early warning model, so that the enterprise risk early warning model can output the prediction result of the violation risk, and the enterprise risk prediction is complete. Compared with the prior art, the risk prediction can be realized by inputting the change characteristics in the change information of the registered items and the service characteristics in the basic information into the enterprise risk early warning model, so that the risk can be predicted in real time, the hysteresis of risk supervision is avoided, the effectiveness of risk supervision and prevention and control is improved, manual operations such as manual data integration, analysis summary, conclusion drawing and the like can be avoided, the workload is reduced, and the efficiency of risk inspection is improved; meanwhile, the enterprise risk early warning model is obtained by training a large amount of comprehensive data based on historical registration item change information, basic information, historical violation information and the like of the enterprise, the judgment standard of risk prediction is unified, subjective factors can be avoided, all-round information of the enterprise can be supervised, the supervision is prevented from being single and unilateral, and the accuracy of risk monitoring can be improved by using the enterprise risk early warning model.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a flowchart of an enterprise risk prediction method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a training process of an enterprise risk early warning model according to an embodiment of the present invention;
FIG. 3 is a flowchart of risk prediction using an enterprise risk early warning model according to an embodiment of the present invention;
FIG. 4 is a block diagram of a computer device according to an embodiment of the present invention;
fig. 5 is a block diagram illustrating an enterprise risk prediction apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In an embodiment of the present invention, an enterprise risk prediction method is provided, as shown in fig. 1, the method includes:
step 102: acquiring registered item change information and basic information of an enterprise to be supervised from a market supervision mechanism;
step 104: extracting change characteristics from the registration item change information, and extracting service characteristics from the basic information;
step 106: and inputting the change characteristics and the service characteristics into an enterprise risk early warning model, and outputting a prediction result of violation risks by the enterprise risk early warning model, wherein the enterprise risk early warning model is obtained by training a sample of historical registration item change information, basic information and historical violation information of an enterprise.
As can be seen from the flow shown in fig. 1, in the embodiment of the present invention, it is proposed to obtain the change information and the basic information of the registered items of the enterprise to be supervised from the market regulatory agency, further extract the change characteristics from the change information of the registered items, extract the business characteristics from the basic information, and finally input the change characteristics and the business characteristics into the enterprise risk early warning model, so that the enterprise risk early warning model can output the prediction result of the violation risk, thereby completing enterprise risk prediction. Compared with the prior art, the risk prediction can be realized by inputting the change characteristics in the change information of the registered items and the service characteristics in the basic information into the enterprise risk early warning model, so that the risk can be predicted in real time, the hysteresis of risk supervision is avoided, the effectiveness of risk supervision and prevention and control is improved, manual operations such as manual data integration, analysis summary, conclusion drawing and the like can be avoided, the workload is reduced, and the efficiency of risk inspection is improved; meanwhile, the enterprise risk early warning model is obtained by training a large amount of comprehensive data based on historical registration item change information, basic information, historical violation information and the like of the enterprise, the judgment standard of risk prediction is unified, subjective factors can be avoided, all-round information of the enterprise can be supervised, the supervision is prevented from being single and unilateral, and the accuracy of risk monitoring can be improved by using the enterprise risk early warning model.
In specific implementation, in order to realize that the enterprise risk prediction method can predict based on big data resources, improve data integration capability and further improve prediction accuracy, in this embodiment, the enterprise risk prediction method is implemented based on a Spring bound micro-service framework,
specifically, since the conventional relational database MySQL, the NoSQL-type database Redis, and the like have a characteristic of supporting data access, after the enterprise risk prediction method is implemented based on a Spring closed microservice framework, the information can be read and acquired from databases of market monitoring organizations such as industry and business, market supervision and management departments, and the like through network devices (e.g., terminals, servers), and the like, regardless of historical registration item change information, basic information, and historical violation information required for training the enterprise risk early warning model, or the registration item change information and the basic information input by the enterprise risk early warning model during risk prediction, and manual data acquisition is not required.
In specific implementation, in order to implement the enterprise risk prediction method, a training process of the enterprise risk early warning model is shown in fig. 2, and includes the following steps:
data reading and processing: historical registered item change information, basic information and historical violation information of the enterprise are obtained from market monitoring organizations such as industrial and commercial departments, market monitoring management departments and the like as sample data.
Specifically, in the past, only a single aspect of an enterprise is checked, for example, an ecological department only checks the problem of the enterprise in the ecological aspect, and a business department only checks business information of the enterprise, and when the enterprise has a problem, the enterprise often has a problem in multiple dimensions, and then a larger accident is caused. The traditional inspection can not integrate the data and the risk points, the application provides that the data are acquired and integrated from various market monitoring and warning mechanisms as samples, for example, the market monitoring and warning mechanisms can comprise a national platform, the Internet, a third-party platform, business departments, places, established and under-construction provincial risk monitoring and warning systems and the like, so that more comprehensive and comprehensive mass data can be acquired, the comprehensive integration of the data is realized, the problems appearing in the past and the existing risk points are comprehensively considered by combining with the credit information of enterprises, the accuracy of the warning information is greatly improved, and the trained enterprise risk prediction model is more accurate.
Specifically, on the basis of knowledge bases for monitoring laws and regulations, risk characteristics and the like, data which can reflect and reflect violation risks in all aspects can be integrated and obtained, for example, a mature big data analysis means is used for carrying out risk prediction around data related to key fields, key enterprises, key products and specific behaviors.
Specifically, the basic information may include various items of information registered by the enterprise at the market regulatory agency, such as company name, legal representative name, registered capital, address, company type, business scope, business term, credit information, etc., the registered item change information may include change items, change contents, change time, etc., and the violation information may include various violations of the enterprise, violation information, such as abnormal operation, penalty records, violation records, etc.
Characteristic engineering: in order to reflect the association between enterprise information change and enterprise violation, dig out potential relationships among various risk factors, deeply research an importance degree adjustment coefficient system of change items on enterprise operation influence, establish a frequent change registration risk identification model, propose extraction of change characteristics of change information of registration items, and extraction of business characteristics of basic information.
Specifically, in order to further highlight the association between the change of the registered item and the violation risk and further improve the accuracy of the violation risk prediction, in the present embodiment, the process of extracting the change feature for the change information of the registered item may be extracting the change frequency of each registered item, that is, extracting the frequent change of each registered item, and for example, the cross-section processing may be performed on the running data of the change information of the registered item in the basic information of the enterprise so as to count the change frequency of each registered item.
Specifically, in order to further highlight the relationship between the difference in change frequency and the violation risk, in the present embodiment, it is proposed to extract the change frequency of each registered item in a plurality of different time periods, that is, to count the change frequency of each registered item in a dimension of a plurality of different time periods. For example, the different time slots take 7 days, 14 days, 30 days, 60 days and 90 days as examples, the total number of changes of each registered item in 7 days, 14 days, 30 days, 60 days and 90 days is counted respectively, namely the frequent change of each registered item is counted in the dimension of 5 time slots, the changed registered items take 32 as examples, and 160 change features can be counted in the dimension of 5 time slots.
In a specific implementation, the registration items of the basic information may further include type information and registration information, for example, the type information may include an enterprise type, an industry type, an organization category, a national economy type, and the like, and the registration information may include information such as registered capital, registered address, and the like. In the process of extracting the change feature, the change frequency of the changed registration items may be counted in the dimension of the type information, for example, taking 24 enterprise types, 19 industry types, 5 organization types, and 24 national economy types as an example, on the basis of 5 time period dimensions, the dimension of the category feature of 72 kinds of "One-Hot Encoding" (total) is added for 4 enterprise types, 19 industry types, 5 organization types, and 24 national economy types to count the change frequency of the 32 registration items, and then the registration capital dimension is added to count 233 change features in total.
Specifically, the extracting of the business features from the basic information is to extract enterprise attribute information, type information, credit information, and registration information, where the enterprise attribute information includes basic information of an enterprise, such as a company name, a legal representative name, and the like, the type information includes properties, industries, and fields of the enterprise, such as an enterprise type, an industry type, an organization type, and a national economy type, and the registration information includes registration-related information, such as registration capital, a registration address, and the like.
Dividing the data set: the sample data is divided into a training set and a test set, for example, 568,698 pieces of full-scale sample data after the duplication removal is possessed, wherein each piece of data is section data of a certain enterprise on a certain day. In the 50 ten thousand pieces of data, 62,328 enterprises have abnormal and illegal behaviors in 365 days in the future, the data percentage is about 0.109, and then the sample data can be obtained according to the following ratio of 8: 2 into a training set and a test set, wherein the data of the test set is finally used to evaluate the model effect, and the data of the training set can be subjected to 5-fold cross validation (5-fold cross validation) to obtain the optimal model parameters.
Selecting a model: the enterprise risk prediction model can be obtained by training a machine learning component by sample data, and in order to make the model interpretable highly and effective, some complex models need to be thrown, such as a nonlinear SVM (support vector machine), Deep Neural Network (Deep Neural Network), and the like. The method selects Naive Bayesian (Naive Bayes), Logistic Regression (Logistic Regression), Random Forest, XGboost algorithm and the like for trial. After the prediction success rate, the recall rate and the AUC (area Under the customer) of the model are evaluated, the model learned by the XGboost algorithm is selected as the enterprise risk prediction model.
In the process of training the enterprise risk prediction model through the XGboost algorithm, a model which enables the AUC to be the maximum is searched by utilizing GridSearchCV (grid search), and the model is selected as the enterprise risk prediction model learned by the XGboost algorithm.
When the enterprise risk prediction model is implemented specifically, continuous optimization can be performed through continuous data parameter adjustment during use.
In specific implementation, the enterprise risk prediction model does not apply uniform conditions to all fields for study and judgment, but different fields have different conditions and algorithms, namely different enterprise risk prediction models are set based on the model training method according to information such as characteristics of enterprises in different fields, and then the enterprise risk prediction model is specialized.
In specific implementation, after the enterprise risk prediction model is obtained, violation risk prediction can be dynamically performed in real time by using the enterprise risk prediction model, the prediction process is similar to that of a training enterprise risk early warning model as shown in fig. 3, and a data acquisition process is also needed, namely, registered item change information and basic information of enterprises to be supervised in different industries at different development stages are acquired from market supervision organizations such as industrial and commercial departments, market supervision departments and the like, and the market supervision organizations can comprise national platforms, the internet, third party platforms, business departments, places, and established and under-built provincial risk monitoring and early warning systems and the like.
Further, change feature extraction is performed on the registered item change information, business feature extraction is performed on the basic information, for example, change frequency of each registered item is extracted, change frequency of each registered item in a plurality of different time periods is further extracted, and business attribute information, type information, credit information, and registration information are extracted for the basic information.
Finally, the change characteristics and the business characteristics are input into an enterprise risk early warning model, the enterprise risk early warning model outputs a prediction result of violation risk, and the violation risk prediction can be a possibility or a probability of violation risk occurring in a future period of time (for example, within a future year, within a half year, and the like).
For example, the prediction result may include content such as attribute information and risk level of an enterprise having the violation risk, that is, which enterprise has the violation risk of what level is output, specifically, the enterprise risk early warning model may divide different risk levels according to the magnitude of the risk probability, for example, an enterprise having a risk probability of more than 90% may be divided into high risks, an enterprise having a risk probability of less than 90% may be divided into low risks, and then a risk list is output, and the risk list may be output according to the risk levels, so as to monitor the risk in a targeted manner.
Specifically, after the enterprise risk early warning model outputs the prediction result, the prediction result can be sent to a corresponding supervision organization according to the registered address and the enterprise type of the enterprise with the violation risk in the prediction result so as to carry out risk supervision, for example, the prediction result is sent to the business, the market supervision department and the like of the location of the enterprise according to the registered address and the enterprise type, the prediction result flows back to a local risk monitoring and early warning data center in a more valuable data form so as to respectively process the enterprises of each risk level, the early warning can be removed from the low-risk enterprise, a key supervision enterprise list is established for the high-risk enterprise, and then the risk monitoring and early warning data center carries out contact or non-contact illegal behavior monitoring by utilizing the advanced technologies such as big data, cloud computing, internet of things, artificial intelligence and the like so as to continuously supervise the high-risk enterprise, the method is prevented in advance, and is beneficial to filling up the capacity shortages of traditional supervision.
In specific implementation, in order to further improve the prediction accuracy of the enterprise risk early warning model, in this embodiment, it is further proposed to update and optimize the enterprise risk early warning model based on the supervision information, the processing information, and the like of the prediction result, for example, the processing information and the corresponding supervision information of the enterprise to be supervised according to the prediction result, which are fed back by a supervision authority, are received, and the processing information and the corresponding supervision information are added to the sample to update the enterprise risk early warning model in an iterative manner. For example, after continuous supervision is performed on a high-risk enterprise, risk consultation is performed, the enterprise which is regarded as low-risk after supervision is subjected to treatment such as early warning removal and the like, and specific processing information and supervision result information are fed back to a supervision system which operates the enterprise risk prediction method, so that the supervision system adds the processing information and corresponding supervision information into the sample to update the enterprise risk early warning model in an iterative manner, and the enterprise risk early warning model is updated in an iterative manner in time.
During specific implementation, the enterprise risk early warning model comprehensively utilizes various supervision big data resources, integrates risk data of all aspects on the basis of knowledge bases for supervision laws, regulations, risk characteristics and the like, combines enterprise credit information, establishes a model based on XGboost, and performs operations such as classification, aggregation, association, comparison and the like on data, applies a mature big data analysis means, and performs accurate early warning on behaviors such as violation or abnormal operation and the like in a future period by surrounding information such as key fields, key enterprises, key products, specific behaviors and the like, so that the workload of manually identifying risks is greatly saved, the risk data of all aspects are integrated, the judgment standard of risk probability is unified, and continuous optimization can be performed through continuous data parameter adjustment.
In this embodiment, a computer device is provided, as shown in fig. 4, and includes a memory 402, a processor 404, and a computer program stored on the memory and executable on the processor, and the processor implements any of the above-mentioned enterprise risk prediction methods when executing the computer program.
In particular, the computer device may be a computer terminal, a server or a similar computing device.
In this embodiment, a computer-readable storage medium is provided, which stores a computer program for executing any of the above-described enterprise risk prediction methods.
In particular, computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable storage medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
Based on the same inventive concept, the embodiment of the present invention further provides an enterprise risk prediction apparatus, as described in the following embodiments. Because the principle of solving the problems of the enterprise risk prediction device is similar to that of the enterprise risk prediction method, the implementation of the enterprise risk prediction device can refer to the implementation of the enterprise risk prediction method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram of an enterprise risk prediction apparatus according to an embodiment of the present invention, and as shown in fig. 5, the apparatus includes:
the information acquisition module 502 is used for acquiring registered item change information and basic information of the enterprise to be supervised from a market supervision mechanism;
a feature extraction module 504, configured to extract change features from the registration item change information, and extract service features from the basic information;
and a risk prediction module 506, configured to input the change characteristic and the business characteristic into an enterprise risk early warning model, where the enterprise risk early warning model outputs a prediction result of violation risk, and the enterprise risk early warning model is obtained by training using historical registration item change information, basic information, and historical violation information of an enterprise as samples.
In one embodiment, the feature extraction module: the method comprises the following steps:
a first feature extraction unit for extracting a change frequency for each registered item.
In one embodiment, the first feature extraction unit is specifically configured to extract a change frequency of each registration item in a plurality of different time periods.
In one embodiment, the feature extraction module includes:
and the second characteristic extraction unit is used for extracting the enterprise attribute information, the enterprise type information, the credit information and the registration information from the basic information.
In one embodiment, the prediction results include attribute information, risk level, of the enterprise at risk of the violation.
In one embodiment, further comprising:
and the training module is used for obtaining the enterprise risk early warning model through XGboost algorithm training.
In one embodiment, further comprising:
and the sending module is used for sending the prediction result to a corresponding supervision organization according to the registration address and the enterprise type of the enterprise with the violation risk in the prediction result.
In one embodiment, the enterprise risk prediction device is implemented based on a Spring group micro-service framework.
In one embodiment, further comprising:
and the model updating module is used for receiving processing information and corresponding supervision information of the enterprise to be supervised according to the prediction result fed back by the supervision mechanism, and adding the processing information and the corresponding supervision information into the sample to update the enterprise risk early warning model in an iterative manner.
The embodiment of the invention realizes the following technical effects: according to the enterprise risk early warning method, registered item change information and basic information of an enterprise to be supervised are obtained from a market supervision mechanism, change characteristics are extracted from the registered item change information, business characteristics are extracted from the basic information, and finally the change characteristics and the business characteristics are input into an enterprise risk early warning model, so that the enterprise risk early warning model can output a prediction result of violation risks, and enterprise risk prediction is completed. Compared with the prior art, the risk prediction can be realized by inputting the change characteristics in the change information of the registered items and the service characteristics in the basic information into the enterprise risk early warning model, so that the risk can be predicted in real time, the hysteresis of risk supervision is avoided, the effectiveness of risk supervision and prevention and control is improved, manual operations such as manual data integration, analysis summary, conclusion drawing and the like can be avoided, the workload is reduced, and the efficiency of risk inspection is improved; meanwhile, the enterprise risk early warning model is obtained by training a large amount of comprehensive data based on historical registration item change information, basic information, historical violation information and the like of the enterprise, the judgment standard of risk prediction is unified, subjective factors can be avoided, all-round information of the enterprise can be supervised, the supervision is prevented from being single and unilateral, and the accuracy of risk monitoring can be improved by using the enterprise risk early warning model.
Although the present invention provides method steps as described in the examples or flowcharts, more or fewer steps may be included based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, apparatus (system) or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "upper", "lower", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are intended to be inclusive and mean, for example, that they may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention is not limited to any single aspect, nor is it limited to any single embodiment, nor is it limited to any combination and/or permutation of these aspects and/or embodiments. Moreover, each aspect and/or embodiment of the present invention may be utilized alone or in combination with one or more other aspects and/or embodiments thereof.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (20)
1. An enterprise risk prediction method, comprising:
acquiring registered item change information and basic information of an enterprise to be supervised from a market supervision mechanism;
extracting change characteristics from the registration item change information, and extracting service characteristics from the basic information;
and inputting the change characteristics and the service characteristics into an enterprise risk early warning model, and outputting a prediction result of violation risks by the enterprise risk early warning model, wherein the enterprise risk early warning model is obtained by training a sample of historical registration item change information, basic information and historical violation information of an enterprise.
2. The enterprise risk prediction method of claim 1, wherein extracting alteration features from the enrollment transaction alteration information comprises:
the change frequency of each registered item is extracted.
3. The method of enterprise risk prediction of claim 2, wherein extracting the frequency of change for each enrollment transaction comprises:
the change frequency of each registered item in a plurality of different time periods is extracted.
4. The enterprise risk prediction method of claim 1, wherein extracting business features from the base information comprises:
and extracting enterprise attribute information, type information, credit information and registration information from the basic information.
5. The enterprise risk prediction method of any one of claims 1-4, wherein the prediction result comprises attribute information of the enterprise at risk of the violation, a risk level.
6. The enterprise risk prediction method of any one of claims 1-4, further comprising:
the enterprise risk early warning model is obtained through XGboost algorithm training.
7. The enterprise risk prediction method of any one of claims 1-4, further comprising:
and sending the prediction result to a corresponding supervision organization according to the registration address and the enterprise type of the enterprise with the violation risk in the prediction result.
8. The enterprise risk prediction method of any one of claims 1-4, wherein the enterprise risk prediction method is implemented based on a Spring group micro-service framework.
9. The enterprise risk prediction method of any one of claims 1-4, further comprising:
and receiving processing information and corresponding supervision information of the enterprise to be supervised according to the prediction result fed back by a supervision mechanism, and adding the processing information and the corresponding supervision information into the sample to update the enterprise risk early warning model in an iterative manner.
10. An enterprise risk prediction device, comprising:
the information acquisition module is used for acquiring registered item change information and basic information of the enterprise to be supervised from a market supervision mechanism;
the characteristic extraction module is used for extracting change characteristics from the registration item change information and extracting service characteristics from the basic information;
and the risk prediction module is used for inputting the change characteristics and the business characteristics into an enterprise risk early warning model, and the enterprise risk early warning model outputs a prediction result of violation risks, wherein the enterprise risk early warning model is obtained by training by taking historical registration item change information, basic information and historical violation information of an enterprise as samples.
11. The enterprise risk prediction device of claim 10, wherein the feature extraction module: the method comprises the following steps:
a first feature extraction unit for extracting a change frequency for each registered item.
12. The risk prediction apparatus for an enterprise according to claim 11, wherein the first feature extraction means is specifically configured to extract a change frequency of each registered item in a plurality of different time periods.
13. The enterprise risk prediction device of claim 10, wherein the feature extraction module comprises:
and the second characteristic extraction unit is used for extracting the enterprise attribute information, the enterprise type information, the credit information and the registration information from the basic information.
14. The enterprise risk prediction device of any one of claims 10-13, wherein the prediction result comprises attribute information, a risk level, of the enterprise at risk of the violation.
15. The enterprise risk prediction device of any one of claims 10-13, further comprising:
and the training module is used for obtaining the enterprise risk early warning model through XGboost algorithm training.
16. The enterprise risk prediction device of any one of claims 10-13, further comprising:
and the sending module is used for sending the prediction result to a corresponding supervision organization according to the registration address and the enterprise type of the enterprise with the violation risk in the prediction result.
17. The enterprise risk prediction device of any of claims 10-13, wherein the enterprise risk prediction device is implemented based on a Spring bound microservice framework.
18. The enterprise risk prediction device of any one of claims 10-13, further comprising:
and the model updating module is used for receiving processing information and corresponding supervision information of the enterprise to be supervised according to the prediction result fed back by the supervision mechanism, and adding the processing information and the corresponding supervision information into the sample to update the enterprise risk early warning model in an iterative manner.
19. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the enterprise risk prediction method of any of claims 1-9 when executing the computer program.
20. A computer-readable storage medium storing a computer program for executing the enterprise risk prediction method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110352520.9A CN113034019A (en) | 2021-03-31 | 2021-03-31 | Enterprise risk prediction method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110352520.9A CN113034019A (en) | 2021-03-31 | 2021-03-31 | Enterprise risk prediction method and device, computer equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113034019A true CN113034019A (en) | 2021-06-25 |
Family
ID=76453536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110352520.9A Pending CN113034019A (en) | 2021-03-31 | 2021-03-31 | Enterprise risk prediction method and device, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034019A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091902A (en) * | 2021-11-22 | 2022-02-25 | 支付宝(杭州)信息技术有限公司 | Risk prediction model training method and device, and risk prediction method and device |
| CN115759760A (en) * | 2022-12-23 | 2023-03-07 | 企知道网络技术有限公司 | Enterprise risk early warning method and electronic equipment |
| CN116205496A (en) * | 2023-04-04 | 2023-06-02 | 广东远景信息科技有限公司 | Compliance risk management and control method, system, electronic equipment and storage medium |
| CN116720787A (en) * | 2023-08-04 | 2023-09-08 | 深圳中科闻歌科技有限公司 | XGBoost model-based new change abnormal enterprise detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921456A (en) * | 2018-08-21 | 2018-11-30 | 深圳市人民政府金融发展服务办公室 | Methods of risk assessment, device and computer readable storage medium |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN109858761A (en) * | 2018-12-29 | 2019-06-07 | 重庆誉存大数据科技有限公司 | Business risk predictor method and device |
| CN110033159A (en) * | 2019-02-27 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Risk Identification Method, device and equipment |
| CN111383101A (en) * | 2020-03-25 | 2020-07-07 | 深圳前海微众银行股份有限公司 | Post-loan risk monitoring method, device, equipment and computer-readable storage medium |
| CN112465393A (en) * | 2020-12-09 | 2021-03-09 | 南威软件股份有限公司 | Enterprise risk early warning method based on correlation analysis FP-Tree algorithm |
-
2021
- 2021-03-31 CN CN202110352520.9A patent/CN113034019A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921456A (en) * | 2018-08-21 | 2018-11-30 | 深圳市人民政府金融发展服务办公室 | Methods of risk assessment, device and computer readable storage medium |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN109858761A (en) * | 2018-12-29 | 2019-06-07 | 重庆誉存大数据科技有限公司 | Business risk predictor method and device |
| CN110033159A (en) * | 2019-02-27 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Risk Identification Method, device and equipment |
| CN111383101A (en) * | 2020-03-25 | 2020-07-07 | 深圳前海微众银行股份有限公司 | Post-loan risk monitoring method, device, equipment and computer-readable storage medium |
| CN112465393A (en) * | 2020-12-09 | 2021-03-09 | 南威软件股份有限公司 | Enterprise risk early warning method based on correlation analysis FP-Tree algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 刘军: "基于scikit-learn的机器学习算法与实践", 南京：东南大学出版社, pages: 61 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091902A (en) * | 2021-11-22 | 2022-02-25 | 支付宝(杭州)信息技术有限公司 | Risk prediction model training method and device, and risk prediction method and device |
| CN115759760A (en) * | 2022-12-23 | 2023-03-07 | 企知道网络技术有限公司 | Enterprise risk early warning method and electronic equipment |
| CN116205496A (en) * | 2023-04-04 | 2023-06-02 | 广东远景信息科技有限公司 | Compliance risk management and control method, system, electronic equipment and storage medium |
| CN116205496B (en) * | 2023-04-04 | 2023-08-15 | 广东远景信息科技有限公司 | Compliance risk management and control method, system, electronic equipment and storage medium |
| CN116720787A (en) * | 2023-08-04 | 2023-09-08 | 深圳中科闻歌科技有限公司 | XGBoost model-based new change abnormal enterprise detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113034019A (en) | Enterprise risk prediction method and device, computer equipment and readable storage medium | |
| Vajgel et al. | Development of intelligent robotic process automation: A utility case study in Brazil | |
| CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
| CN111738549A (en) | Food safety risk assessment method, device, equipment and storage medium | |
| Sarno et al. | Business process anomaly detection using ontology-based process modelling and multi-level class association rule learning | |
| CN111047122A (en) | Enterprise data maturity evaluation method and device and computer equipment | |
| CN111310803B (en) | Environment data processing method and device | |
| CN112989332B (en) | Abnormal user behavior detection method and device | |
| CN112232833A (en) | Lost member customer group data prediction method, model training method and model training device | |
| CN112419030A (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN114638498A (en) | ESG evaluation method, ESG evaluation system, electronic equipment and storage equipment | |
| CN113095647B (en) | Vehicle inspection system | |
| CN113283673A (en) | Model performance attenuation evaluation method, model training method and device | |
| CN117521060A (en) | System security risk management method, device, equipment and storage medium | |
| CN117422312A (en) | Assessment method, medium and device for enterprise management risk | |
| LUZHANSKA | SIMULATION AND OPTIMIZATION OF FREIGHT CUSTOMS COMPLEXESBASED ON QUEUEING SYSTEMS | |
| US11227288B1 (en) | Systems and methods for integration of disparate data feeds for unified data monitoring | |
| CN110909966B (en) | Efficiency evaluation method and efficiency evaluation system | |
| CN116227920A (en) | Enterprise risk assessment method and device, electronic equipment and storage medium | |
| CN116227862A (en) | Efficient budget project based full-flow supervision method and system | |
| CN115619539A (en) | Pre-loan risk evaluation method and device | |
| CN112651433B (en) | Abnormal behavior analysis method for privileged account | |
| CN113127465A (en) | Data fusion method and system | |
| CN113221556A (en) | Method, device and equipment for identifying potential safety hazard | |
| Prasad et al. | Predictive maintenance in forging industry |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |