CN112907101A - Enterprise illegal funding behavior risk early warning method and system - Google Patents
Enterprise illegal funding behavior risk early warning method and system Download PDFInfo
- Publication number
- CN112907101A CN112907101A CN202110255566.9A CN202110255566A CN112907101A CN 112907101 A CN112907101 A CN 112907101A CN 202110255566 A CN202110255566 A CN 202110255566A CN 112907101 A CN112907101 A CN 112907101A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- early warning
- text information
- risk
- illegal
- 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 35
- 230000006399 behavior Effects 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000012795 verification Methods 0.000 claims abstract description 11
- 230000003542 behavioural effect Effects 0.000 claims abstract description 9
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008520 organization Effects 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
- G06Q10/0635—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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a risk early warning method and a system for illegal investment collection behaviors of enterprises, wherein the risk early warning method comprises the following steps: acquiring behavioral characteristics of an enterprise marked with an illegal collective resource label, wherein the behavioral characteristics comprise enterprise basic information, tax credit text information, internet comment text information, legal referee document information and intellectual property text information, so as to construct a text information base for mapping the enterprise, the illegal collective resource label and the behavioral characteristics; training a pre-constructed risk early warning model according to a text information base; constructing a multi-dimensional image of the enterprise to be identified according to the behavior characteristics of the enterprise to be identified; and obtaining a comprehensive risk value of the enterprise to be identified by adopting the trained risk early warning model according to the multi-dimensional image, and obtaining a risk early warning result of the enterprise to be identified according to a comparison result of the comprehensive risk value and a preset threshold value. After the obtained enterprise information is screened and quantified, model training and model verification are respectively carried out, and the enterprise information is trained after being weighted, so that the model accuracy is improved, and the accuracy of risk early warning is improved.
Description
Technical Field
The invention relates to the technical field of big data analysis methods, in particular to a risk early warning method and system for illegal fundraising behaviors of enterprises.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Illegal funding refers to the act of a unit or person raising funds to the public in a manner of issuing stocks, bonds, lottery tickets, investment fund securities, or other creditory documents, without being approved by the relevant departments in accordance with legal procedures, and committing to pay or give a return in money, in real life, or otherwise to the payers within a certain period of time. At present, illegal funding crimes comprise illegal public deposit crimes, funding fraud crimes, fraudulent stock issuing, bond crimes and unauthorized stock issuing, company and enterprise bond crimes, and the crime behaviors not only cause great loss and influence on victims, but also have great harm to the development of the whole society.
Firstly, the existing risk early warning method and device related to illegal funding mostly adopt fixed early warning models and parameters, and if specific models and characteristics are used, the real data relationship cannot be accurately acquired, so that the phenomenon of over-fitting or under-fitting occurs.
Secondly, in the illegal funding early warning method, the following problems exist in the acquisition and processing of enterprise data: the authenticity of the data is solved, and the authenticity of the data is solved due to the risk of counterfeiting through the enterprise basic information, product information, financial information and other operation data actively provided by the enterprise; moreover, the operation data of the enterprise is only depended on to have one-sidedness, and if the data is incomplete, the illegal funding risk is difficult to be fully evaluated from the global perspective; furthermore, if the multidimensional information of an enterprise is obtained from the internet and other channels, not all the information is related to illegal funding due to the complexity of the information in the internet, and all the data quality is also a problem facing the risk of illegal funding.
Finally, because illegal funding modes are various and high in concealment, common users are difficult to distinguish independently, when the users inquire related information of enterprises, the users often inquire the related information of the enterprises through channels such as official networks of the enterprises, comprehensive comparison among different enterprise data cannot be carried out, the filing progress of the enterprises in the internet is slow, the information disclosure has certain hysteresis, and potential illegal funding risks are difficult to find.
Disclosure of Invention
In order to solve the problems, the invention provides an early warning method and a system for the risk of illegal funding behaviors of enterprises, and the diversification of enterprise information sources and types ensures the comprehensiveness, integrity and authenticity of all public information of the enterprises; when the acquired enterprise information is used for training the risk early warning model, the accuracy of the model is improved through weighting of the enterprise information and optimization of the weight, and the accuracy of risk early warning is improved.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a risk early warning method for illegal fundraising behavior of an enterprise, including:
acquiring behavioral characteristics of an enterprise marked with an illegal collective resource label, wherein the behavioral characteristics comprise enterprise basic information, tax credit text information, internet comment text information, legal referee document information and intellectual property text information, so as to construct a text information base for mapping the enterprise, the illegal collective resource label and the behavioral characteristics;
training a pre-constructed risk early warning model according to a text information base;
constructing a multi-dimensional image of the enterprise to be identified according to the behavior characteristics of the enterprise to be identified;
and obtaining a comprehensive risk value of the enterprise to be identified by adopting the trained risk early warning model according to the multi-dimensional image, and obtaining a risk early warning result of the enterprise to be identified according to a comparison result of the comprehensive risk value and a preset threshold value.
In a second aspect, the present invention provides a risk early warning system for illegal fundamentation behavior of an enterprise, comprising:
the text information construction module is configured to acquire behavior characteristics of an enterprise marked with an illegal collective resource label, wherein the behavior characteristics comprise enterprise basic information, tax credit text information, internet comment text information, legal referee document information and intellectual property text information, so that a text information base for mapping the enterprise, the illegal collective resource label and the behavior characteristics is constructed;
the model training module is configured to train a pre-constructed risk early warning model according to the text information base;
the data processing module is configured to construct a multi-dimensional image of the enterprise to be identified according to the behavior characteristics of the enterprise to be identified;
and the risk early warning module is configured to obtain a comprehensive risk value of the enterprise to be identified by adopting the trained risk early warning model according to the multi-dimensional image, and obtain a risk early warning result of the enterprise to be identified according to a comparison result of the comprehensive risk value and a preset threshold value.
In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method of the first aspect is performed.
In a fourth aspect, the present invention provides a computer readable storage medium for storing computer instructions which, when executed by a processor, perform the method of the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
the invention has diversified data sources and data types, acquires all public information of enterprises and does not depend on data actively provided by the enterprises, ensures the comprehensiveness, integrity and authenticity of the data, can fully evaluate all related business data of the enterprises, realizes early warning of suspected illegal funding risks, and has higher detection efficiency.
The invention carries out cleaning, screening, quantification and other processing on enterprise multidimensional information acquired from channels such as the Internet and the like, filters non-relevant data and improves the data quality.
When the method is used for model training, a proper model is selected, an optimization algorithm such as a gradient descent algorithm is used for training, enterprise information weight parameters are optimized according to the verification on the model accuracy, the problem of over-fitting or under-fitting is solved, the model parameters are flexibly adjusted, whether illegal investment risk exists in an enterprise can be accurately and effectively predicted, and the risk early warning accuracy is improved.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a flowchart of a risk early warning method for illegal fundamentation behavior of an enterprise according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a risk early warning system for illegal fundamentation behavior of an enterprise according to embodiment 2 of the present invention.
The specific implementation mode is as follows:
the invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example 1
As shown in fig. 1, the embodiment provides a risk early warning method for illegal fundamentation behavior of an enterprise, including:
s1: acquiring enterprise behavior characteristics marked with illegal collective resource labels and enterprise behavior characteristics to be identified without the illegal collective resource labels; the behavior characteristics comprise basic enterprise information, tax credit text information, Internet comment text information, legal referee document information and intellectual property text information, so that a text information base for mapping enterprises, illegal collective labels and behavior characteristics is constructed;
s2: training a pre-constructed risk early warning model according to a text information base;
s3: constructing a multi-dimensional image of the enterprise to be identified according to the behavior characteristics of the enterprise to be identified;
s4: and obtaining a comprehensive risk value of the enterprise to be identified by adopting the trained risk early warning model according to the multi-dimensional image, and obtaining a risk early warning result of the enterprise to be identified according to a comparison result of the comprehensive risk value and a preset threshold value.
In step S1, in this embodiment, the crawler software is used to directly crawl all the behavior feature data of the enterprise from the web page, where the web page channels include news media, social media, third-party information disclosure platforms, third-party business databases, enterprise information platforms (such as sky-eye search), network loan product information platforms, tax platforms, and the like, and ensure authenticity and comprehensiveness of the data.
In step S1, the embodiment performs preprocessing operations such as data cleaning, screening, and quantization on the obtained enterprise behavior features, classifies text data in the enterprise behavior features by constructing a text classification model, and filters non-relevant text data.
In step S1, after preprocessing the acquired enterprise behavior features labeled with whether or not there is an illegal funding risk and the behavior features of the to-be-identified enterprise not labeled with whether or not there is an illegal funding risk, mapping the behavior features with the enterprise, and simultaneously associating the behavior features with the illegal funding risk labels labeled by the enterprise, to construct a text information base related to the illegal funding risk labels; preferably, an enterprise index is also generated at the same time for quick retrieval.
Preferably, the text information base marked with the illegal funding risk label is used for model training and model verification, and the behavior characteristics of the enterprise to be identified are used for risk early warning.
Preferably, in the text information base labeled with the illegal funding risk label, the ratio of data used for model training and model verification is 8: 2.
Preferably, if an individual index is missing, the missing item is replaced with the average of the indexes of other enterprises.
Preferably, the enterprise basic information includes: industry subclass code, risk industry, number of workers, number of partners, number of executives, organization form, registered capital, real-time payment capital, total investment, registered capital, enterprise change information, annual newspaper basic information;
the enterprise change information includes: enterprise information code change frequency;
the annual report basic information of the enterprise comprises: capital amount, operator number, employee number, public status, whether a website mark exists, whether an external investment enterprise mark exists, and operation status;
the tax credit text information comprises: tax type, tax item, tax counting basis, tax rate, deduction value and tax amount;
the internet comment text information includes: positive news public sentiment information and negative news public sentiment information;
the intellectual property text information comprises: number of registered trademarks, number of patents.
In step S2, an illegal funding risk early warning model of an enterprise is constructed, the model is trained by using a text information base for model training, the accuracy of the model is improved by adjusting the weight of the enterprise behavior characteristics in the text information base in the model, the model accuracy of the risk early warning model is verified by using the text information base for model verification, and whether the accuracy of the model reaches the standard is verified;
preferably, the verifying the model accuracy of the risk pre-warning model comprises: setting an expected value of model accuracy; if the accuracy of the model is greater than the expected value, applying the risk early warning model to risk early warning to judge whether the enterprise has illegal funding risk; if the model accuracy is less than the expected value, the training data and the selection of the model are readjusted.
Preferably, adjusting the weight of the enterprise behavior feature in the model comprises: and performing multiple iterations to obtain a set of optimized weight parameters by adopting an optimization mode of back propagation and gradient descent on the test data.
In step S4, a preset threshold may be determined according to the comprehensive risk value of the typical illegal fundamentation case, and when the comprehensive risk value is greater than the preset value, a prediction result is output as 1, which indicates that the to-be-identified enterprise has an illegal fundamentation risk; and when the comprehensive risk value is less than or equal to the preset value, outputting a prediction result of 0, and representing that the to-be-identified enterprise does not have illegal funding risk.
Example 2
As shown in fig. 2, the embodiment provides an early warning system for risk of illegal fundamentation behavior of an enterprise, including:
the text information construction module is configured to obtain enterprise behavior characteristics marked with illegal collective resource labels and enterprise behavior characteristics to be identified without marked illegal collective resource labels; the behavior characteristics comprise basic enterprise information, tax credit text information, Internet comment text information, legal referee document information and intellectual property text information, so that a text information base for mapping enterprises, illegal collective labels and behavior characteristics is constructed;
the model training module is configured to train a pre-constructed risk early warning model according to the text information base;
the data processing module is configured to construct a multi-dimensional image of the enterprise to be identified according to the behavior characteristics of the enterprise to be identified;
and the risk early warning module is configured to obtain a comprehensive risk value of the enterprise to be identified by adopting the trained risk early warning model according to the multi-dimensional image, and obtain a risk early warning result of the enterprise to be identified according to a comparison result of the comprehensive risk value and a preset threshold value.
In this embodiment, the text information constructing module 100 includes a data collecting module 101, a data sorting and screening module 102 and a data quantifying module 103;
the data collection module 101 is configured to obtain enterprise behavior characteristics labeled with an illegal funding label and enterprise behavior characteristics to be identified that are not labeled with an illegal funding label;
the data sorting and screening module 102 is used for cleaning and screening the acquired enterprise behavior characteristics, selecting appropriate enterprise indexes related to illegal funding prediction, and filtering non-related data;
the data quantization module 103 is configured to quantize the selected enterprise index; the quantified enterprise behavior characteristics marked whether the illegal funding risk exists or not are used for the model training module 200 and the model verification module 300, and the quantified enterprise behavior characteristics marked whether the illegal funding risk exists or not are used for the prediction module 400.
In this embodiment, the model training module 200 includes a model selection module 201 and a parameter adjustment module 202;
the model selection module 201 is configured to select a suitable risk early warning model, and input a constructed text information base in the model for training;
the parameter tuning module 202 obtains a set of optimized weight parameters through multiple iterations through an optimization approach using back propagation and gradient descent on the test data.
In this embodiment, after training is completed, the model verification module 300 is used for verification, and the model verification module 300 includes an accuracy module 301 for verifying whether the accuracy of the model reaches the standard;
in this embodiment, in the prediction module 400, if the prediction result is 0, it represents that there is no illegal funding risk for the enterprise to be identified; and if the prediction result is 1, the illegal funding risk exists in the enterprise to be identified.
It should be noted that the modules correspond to the steps described in embodiment 1, and the modules are the same as the corresponding steps in the implementation examples and application scenarios, but are not limited to the disclosure in embodiment 1. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In further embodiments, there is also provided:
an enterprise illegal funding behavior risk inquiry system comprises a server and a user terminal; the server is configured with the risk early warning system of embodiment 2, and the risk early warning system is adopted to obtain the risk early warning result of the enterprise to be identified according to the information query instruction of the user terminal.
The server is also provided with an enterprise text information index library, and an enterprise text information index library mapped with enterprises is constructed by crawling enterprise directories related to financial services in the whole country from an enterprise registration information platform to generate enterprise indexes;
the server receives an information query instruction of the user terminal, and extracts enterprise behavior characteristics related to the enterprise to be identified by using an enterprise index according to the enterprise to be identified in the information query instruction to construct a multi-dimensional image of the enterprise to be identified; and obtaining a risk early warning result of the enterprise to be identified by adopting a risk early warning model according to the multi-dimensional portrait.
The user terminal can inquire any enterprise in the server, and can retrieve the data of any enterprise according to the enterprise index, so that comprehensive comparison can be realized among a plurality of enterprises, and the method is convenient and fast and has high risk early warning accuracy.
In further embodiments, there is also provided:
an electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions when executed by the processor performing the method of embodiment 1. For brevity, no further description is provided herein.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the method described in embodiment 1.
The method in embodiment 1 may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here.
Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A risk early warning method for illegal fundraising behaviors of enterprises is characterized by comprising the following steps:
acquiring behavioral characteristics of an enterprise marked with an illegal collective resource label, wherein the behavioral characteristics comprise enterprise basic information, tax credit text information, internet comment text information, legal referee document information and intellectual property text information, so as to construct a text information base for mapping the enterprise, the illegal collective resource label and the behavioral characteristics;
training a pre-constructed risk early warning model according to a text information base;
constructing a multi-dimensional image of the enterprise to be identified according to the behavior characteristics of the enterprise to be identified;
and obtaining a comprehensive risk value of the enterprise to be identified by adopting the trained risk early warning model according to the multi-dimensional image, and obtaining a risk early warning result of the enterprise to be identified according to a comparison result of the comprehensive risk value and a preset threshold value.
2. The risk early warning method for the illegal fundamentation behavior of an enterprise according to claim 1, wherein the verifying the model accuracy during the training of the risk early warning model comprises: setting an expected value of the model accuracy, and finishing training of the risk early warning model if the model accuracy is greater than the expected value; and if the accuracy of the model is smaller than the expected value, carrying out weight adjustment on the behavior characteristics in the text information base.
3. The method as claimed in claim 2, wherein the adjusting of the weight of the behavior feature in the text information base includes: and (4) carrying out multiple iterations by adopting an optimization method of back propagation and gradient descent to obtain the optimal weight parameter.
4. The method as claimed in claim 1, wherein the pre-processing operations of data cleaning, screening and quantification are performed on the behavior characteristics of the enterprise, and non-relevant text information is filtered.
5. The method as claimed in claim, wherein the text information base is divided in proportion to obtain a training set for model training and a verification set for model verification.
6. The method for early warning the risk of illegal fundraising behaviors of enterprises as claimed in claim 1, wherein the missing values of the behavior characteristics of the enterprises are replaced by the average values of the same behavior characteristic information of other enterprises.
7. The risk early warning method for illegal fundamentation behavior of an enterprise according to claim 1, wherein the risk early warning result comprises: if the prediction result is 0, the enterprise to be identified has no illegal funding risk; and if the prediction result is 1, the illegal funding risk exists in the enterprise to be identified.
8. The system for early warning the risk of the illegal fundamentation behavior of an enterprise is characterized by comprising the following steps:
the text information construction module is configured to acquire behavior characteristics of an enterprise marked with an illegal collective resource label, wherein the behavior characteristics comprise enterprise basic information, tax credit text information, internet comment text information, legal referee document information and intellectual property text information, so that a text information base for mapping the enterprise, the illegal collective resource label and the behavior characteristics is constructed;
the model training module is configured to train a pre-constructed risk early warning model according to the text information base;
the data processing module is configured to construct a multi-dimensional image of the enterprise to be identified according to the behavior characteristics of the enterprise to be identified;
and the risk early warning module is configured to obtain a comprehensive risk value of the enterprise to be identified by adopting the trained risk early warning model according to the multi-dimensional image, and obtain a risk early warning result of the enterprise to be identified according to a comparison result of the comprehensive risk value and a preset threshold value.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions when executed by the processor performing the method of any of claims 1-7.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110255566.9A CN112907101A (en) | 2021-03-09 | 2021-03-09 | Enterprise illegal funding behavior risk early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110255566.9A CN112907101A (en) | 2021-03-09 | 2021-03-09 | Enterprise illegal funding behavior risk early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112907101A true CN112907101A (en) | 2021-06-04 |
Family
ID=76108281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110255566.9A Pending CN112907101A (en) | 2021-03-09 | 2021-03-09 | Enterprise illegal funding behavior risk early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907101A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109829631A (en) * | 2019-01-14 | 2019-05-31 | 北京中兴通网络科技股份有限公司 | A kind of business risk early warning analysis method and system based on memory network |
| 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 |
| CN110689438A (en) * | 2019-08-26 | 2020-01-14 | 深圳壹账通智能科技有限公司 | Enterprise financial risk scoring method and device, computer equipment and storage medium |
| CN110704572A (en) * | 2019-09-04 | 2020-01-17 | 北京航空航天大学 | Suspected illegal fundraising risk early warning method, device, equipment and storage medium |
| CN111914542A (en) * | 2020-05-21 | 2020-11-10 | 国家计算机网络与信息安全管理中心 | Suspected illegal investment market subject identification method, device, terminal and storage medium |
| WO2021000678A1 (en) * | 2019-07-04 | 2021-01-07 | 平安科技（深圳）有限公司 | Business credit review method, apparatus, and device, and computer-readable storage medium |
-
2021
- 2021-03-09 CN CN202110255566.9A patent/CN112907101A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109829631A (en) * | 2019-01-14 | 2019-05-31 | 北京中兴通网络科技股份有限公司 | A kind of business risk early warning analysis method and system based on memory network |
| 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 |
| WO2021000678A1 (en) * | 2019-07-04 | 2021-01-07 | 平安科技（深圳）有限公司 | Business credit review method, apparatus, and device, and computer-readable storage medium |
| CN110689438A (en) * | 2019-08-26 | 2020-01-14 | 深圳壹账通智能科技有限公司 | Enterprise financial risk scoring method and device, computer equipment and storage medium |
| CN110704572A (en) * | 2019-09-04 | 2020-01-17 | 北京航空航天大学 | Suspected illegal fundraising risk early warning method, device, equipment and storage medium |
| CN111914542A (en) * | 2020-05-21 | 2020-11-10 | 国家计算机网络与信息安全管理中心 | Suspected illegal investment market subject identification method, device, terminal and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 武玉伟: "《深度学习基础与应用》", 30 November 2020, 北京理工大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11568400B2 (en) | Anomaly and fraud detection with fake event detection using machine learning | |
| US7458508B1 (en) | System and method for identity-based fraud detection | |
| US7562814B1 (en) | System and method for identity-based fraud detection through graph anomaly detection | |
| US7686214B1 (en) | System and method for identity-based fraud detection using a plurality of historical identity records | |
| Spathis et al. | Detecting falsified financial statements: a comparative study using multicriteria analysis and multivariate statistical techniques | |
| US20060149674A1 (en) | System and method for identity-based fraud detection for transactions using a plurality of historical identity records | |
| Franceschetti et al. | Do bankrupt companies manipulate earnings more than the non-bankrupt ones? | |
| US20120158563A1 (en) | Multidimensional risk-based detection | |
| CN101194286A (en) | Risk based data assessment | |
| US20090248560A1 (en) | Assessment of risk associated with doing business with a party | |
| US20090248465A1 (en) | Assessment of risk associated with doing business with a party | |
| Alden et al. | Detection of financial statement fraud using evolutionary algorithms | |
| Carvalho et al. | Goodwill and mandatory disclosure compliance: A critical review of the literature | |
| US11308492B2 (en) | Anomaly and fraud detection with fake event detection using pixel intensity testing | |
| US20090248559A1 (en) | Assessment of risk associated with doing business with a party | |
| CN112182246A (en) | Method, system, medium, and application for creating an enterprise representation through big data analysis | |
| EP3761227A1 (en) | Anomaly and fraud detection with fake event detection using machine learning | |
| CN112308638A (en) | False invoice behavior detection method and device, electronic equipment and storage medium | |
| Fratzscher et al. | Foreign exchange intervention: A new database | |
| Ka et al. | Performance Analysis of KN earest Neighbor Classification Algorithms for Bank Loan Sectors | |
| CN112907101A (en) | Enterprise illegal funding behavior risk early warning method and system | |
| TWI713877B (en) | Regulatory compliance processing device for auditing | |
| CN115952186A (en) | Problem data and link tracing method and device thereof | |
| CN114708090A (en) | Bank payment business risk identification device based on big data | |
| CN114238280A (en) | Method and device for constructing financial sensitive information standard library and electronic equipment |
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 |
Application publication date: 20210604 |
|
| RJ01 | Rejection of invention patent application after publication |