CN114997975A - Abnormal enterprise identification method, device, equipment, medium and product - Google Patents
Abnormal enterprise identification method, device, equipment, medium and product Download PDFInfo
- Publication number
- CN114997975A CN114997975A CN202210420447.9A CN202210420447A CN114997975A CN 114997975 A CN114997975 A CN 114997975A CN 202210420447 A CN202210420447 A CN 202210420447A CN 114997975 A CN114997975 A CN 114997975A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- identified
- target
- abnormal
- sample
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000010801 machine learning Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 10
- 230000007306 turnover Effects 0.000 claims description 7
- 230000009849 deactivation Effects 0.000 claims description 6
- 230000002547 anomalous effect Effects 0.000 claims 1
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention relates to the technical field of intelligent finance, in particular to an abnormal enterprise identification method, device, equipment, medium and product. The method comprises the following steps: acquiring the business information of an enterprise to be identified and the financial information of the enterprise to be identified; inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, and obtaining an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the technical scheme of the invention can effectively improve the identification capability of abnormal enterprises and facilitate supervision.
Description
Technical Field
The embodiment of the invention relates to the technical field of intelligent finance, in particular to an abnormal enterprise identification method, device, equipment, medium and product.
Background
In financial systems, risk prevention has been the most important issue. With the rapid development of economy, the incidence relations and transactions among enterprises are more and more, and the incidence relations and transactions among enterprises are more and more complex, so that the difficulty of risk identification is extremely high.
Abnormal enterprises may not only cause the risk of credit default, but also hide the risk of associated transactions, and therefore, an effective technical means for identifying abnormal enterprises is urgently needed.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment, a medium and a product for identifying abnormal enterprises, which are used for effectively improving the identification capability of the abnormal enterprises and facilitating supervision.
According to an aspect of the present invention, there is provided an abnormal enterprise identification method, including:
acquiring the business information of an enterprise to be identified and the financial information of the enterprise to be identified;
inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, and obtaining an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the sample enterprise business information, the sample enterprise financial information, and the sample enterprise identification information.
Further, the business information of the enterprise to be identified and the financial information of the enterprise to be identified are obtained, and the method comprises the following steps:
acquiring an enterprise entity in an original knowledge graph;
determining the enterprise entity in the original knowledge graph as an enterprise to be identified;
and acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified according to the original knowledge map.
Further, after inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into the target model for identifying the abnormal enterprise and obtaining an identification result, the method further comprises the following steps:
determining a label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified;
and updating the original knowledge graph according to the label corresponding to the enterprise to be identified to obtain a target knowledge graph.
Further, determining the label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified includes:
if the enterprise to be identified is an abnormal enterprise, the label corresponding to the enterprise to be identified is in a first color;
and if the enterprise to be identified is a normal enterprise, the label corresponding to the enterprise to be identified is in a second color.
Further, updating the original knowledge graph according to the label corresponding to the enterprise to be identified to obtain a target knowledge graph, including:
and replacing the color of the abnormal enterprise in the original knowledge graph with a first color, and replacing the color of the normal enterprise in the original knowledge graph with a second color to obtain a target knowledge graph.
Further, iteratively training the machine learning model through the target sample set includes:
acquiring a target sample set;
establishing a machine learning model;
inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result;
training parameters of the machine learning model according to an objective function formed by the prediction result and the identification information of the sample enterprise;
and returning to execute the operation of inputting the business information of the sample enterprises and the financial information of the sample enterprises in the target sample set into the machine learning model to obtain a prediction result until the target model is obtained.
Further, obtaining a target sample set includes:
acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes;
determining a target index according to the first source data and the second source data;
and generating a target sample set according to the target indexes and the abnormal enterprise set.
Further, determining a target index according to the first source data and the second source data includes:
acquiring the similarity of data corresponding to the same index in the first source data and the second source data;
and determining the index with the similarity smaller than the similarity threshold value as a target index.
Further, if the sample enterprise is a normal enterprise, the identification information of the sample enterprise is the first identification, and if the sample enterprise is an abnormal enterprise, the identification information of the sample enterprise is the second identification.
Further, the business information includes: enterprise registration time.
Further, the business information further includes: the business registers capital and/or business properties.
Further, the financial information includes: at least one of an enterprise inflow amount, an enterprise outflow amount, an enterprise account balance, an account opening date, an account first transaction date, an account deactivation date, an account deregistration date, a transaction counter party name, a number of times funds flow through the account, a number of times funds flow through the self-associated entity, a transaction currency, a number of times the enterprise appears on a blacklist, a loan number, a loan amount, and a loan maximum amount usage rate.
Further, the financial information further includes: at least one of profit margin, equity rate, liquidity ratio, turnover rate of accounts receivable, net equity profit margin, business profit growth rate, and total equity growth rate.
According to another aspect of the present invention, there is provided an abnormal-enterprise identifying apparatus including:
the acquisition module is used for acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified;
the identification module is used for inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, so as to obtain an identification result, wherein the target model is obtained by a target sample set iteration machine learning model, and the target sample comprises: the sample enterprise business information, the sample enterprise financial information, and the sample enterprise identification information.
Further, the obtaining module is specifically configured to:
acquiring enterprise entities in an original knowledge graph;
determining the enterprise entity in the original knowledge graph as an enterprise to be identified;
and acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified according to the original knowledge map.
Further, the method also comprises the following steps:
the determining module is used for determining the label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified;
and the updating module is used for updating the original knowledge graph according to the label corresponding to the enterprise to be identified to obtain a target knowledge graph.
Further, the determining module is specifically configured to:
if the enterprise to be identified is an abnormal enterprise, the label corresponding to the enterprise to be identified is in a first color;
and if the enterprise to be identified is a normal enterprise, the label corresponding to the enterprise to be identified is in a second color.
Further, the update module is specifically configured to:
and replacing the color of the abnormal enterprise in the original knowledge graph with a first color, and replacing the color of the normal enterprise in the original knowledge graph with a second color to obtain the target knowledge graph.
Further, the identification module is specifically configured to:
acquiring a target sample set;
establishing a machine learning model;
inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result;
training parameters of the machine learning model according to an objective function formed by the prediction result and the identification information of the sample enterprise;
and returning to execute the operation of inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result until the target model is obtained.
Further, the identification module is specifically configured to:
acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes;
determining a target index according to the first source data and the second source data;
and generating a target sample set according to the target indexes and the abnormal enterprise set.
Further, the identification module is specifically configured to:
acquiring the similarity of data corresponding to the same index in the first source data and the second source data;
and determining the index with the similarity smaller than the similarity threshold value as a target index.
Further, if the sample enterprise is a normal enterprise, the identification information of the sample enterprise is a first identification, and if the sample enterprise is an abnormal enterprise, the identification information of the sample enterprise is a second identification.
Further, the business information includes: enterprise registration time.
Further, the business information further includes: the business registers capital and/or business properties.
Further, the financial information includes: at least one of an enterprise inflow amount, an enterprise outflow amount, an enterprise account balance, an account opening date, an account first transaction date, an account deactivation date, an account deregistration date, a transaction counter party name, a number of times funds flow through the account, a number of times funds flow through the self-associated entity, a transaction currency, a number of times the enterprise appears on a blacklist, a loan number, a loan amount, and a loan maximum amount usage rate.
Further, the financial information further includes: at least one of profit margin, equity rate, liquidity ratio, turnover rate of accounts receivable, net equity profit margin, business profit growth rate, and total equity growth rate.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the abnormal business identification method of any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the abnormal business identification method according to any one of the embodiments of the present invention when the computer instructions are executed.
According to another aspect of the present invention, there is provided a computer program product, which when executed by a processor, implements the abnormal business identification method according to any one of the embodiments of the present invention.
The embodiment of the invention obtains the business information of the enterprise to be identified and the financial information of the enterprise to be identified; inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, and obtaining an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the identification information of the business information of the sample enterprise, the financial information of the sample enterprise and the identification information of the sample enterprise can effectively improve the identification capability of the abnormal enterprise, and is convenient to supervise.
It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flow chart of a method for identifying abnormal businesses in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an abnormal enterprise recognition apparatus in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device in the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations 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 technical scheme related by the application can be used for acquiring, storing and/or processing the data, and the data can meet the relevant regulations of national laws and regulations.
Example one
Fig. 1 is a flowchart of an abnormal enterprise identification method according to an embodiment of the present invention, where the present embodiment is applicable to the case of abnormal enterprise identification, and the method may be executed by an abnormal enterprise identification device according to an embodiment of the present invention, where the abnormal enterprise identification device may be implemented in a software and/or hardware manner, as shown in fig. 1, the method specifically includes the following steps:
and S110, acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified.
The business information of the enterprise to be identified may include: registering time of the enterprise to be identified; the business information of the enterprise to be identified may further include: the business to be identified registers capital and/or the nature of the business to be identified.
Wherein the financial information of the enterprise to be identified may include: the method comprises the steps of at least one of inflow amount of an enterprise to be identified, outflow amount of the enterprise to be identified, account balance of the enterprise to be identified, account opening date corresponding to the enterprise to be identified, first transaction date of an account corresponding to the enterprise to be identified, account stopping date corresponding to the enterprise to be identified, name of a party to be transacted corresponding to the enterprise to be identified, number of times of fund flow through the account corresponding to the enterprise to be identified, number of times of fund flow through self-associated entities corresponding to the enterprise to be identified, transaction currency corresponding to the enterprise to be identified, number of times of occurrence of the enterprise to be identified on a blacklist, loan number of times of the enterprise to be identified, credit limit loan of the enterprise to be identified and maximum credit limit utilization rate of the loan of the enterprise to be identified. The financial information of the enterprise to be identified may further include: the profit margin of the enterprise to be identified, the asset liability margin of the enterprise to be identified, the liquidity ratio of the enterprise to be identified, the turnover rate of the debt to be charged of the enterprise to be identified, the net asset profitability of the enterprise to be identified, the operating profit growth rate of the enterprise to be identified, and the total asset growth rate of the enterprise to be identified.
Specifically, the manner of acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified may be: acquiring enterprise entities in an original knowledge graph; determining the enterprise entity in the original knowledge graph as an enterprise to be identified; and acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified according to the original knowledge map. For example, the enterprise entity a in the original knowledge graph is obtained, the enterprise entity a in the original knowledge graph is determined as the enterprise to be identified, and the registration time of the enterprise to be identified, the registration capital of the enterprise to be identified, the property of the enterprise to be identified, the inflow amount of the enterprise to be identified, the outflow amount of the enterprise to be identified, the account balance of the enterprise to be identified, the account opening date corresponding to the enterprise to be identified, the first transaction date of the account corresponding to the enterprise to be identified, the deactivation date of the account corresponding to the enterprise to be identified, the cancellation date of the account corresponding to the enterprise to be identified, the name of the counter party to the transaction corresponding to the enterprise to be identified, the number of times of the fund flow through the account corresponding to the enterprise to be identified, the number of the fund flow through the associated entity, the transaction currency corresponding to the enterprise to be identified, the number of times of the enterprise to be identified appearing on the blacklist, the enterprise to be identified, The method comprises the steps of determining the loan times of the enterprise to be identified, the loan amount of the enterprise to be identified, the loan maximum amount usage rate of the enterprise to be identified, the profit rate of the enterprise to be identified, the property liability rate of the enterprise to be identified, the flow rate of the enterprise to be identified, the accounts receivable turnover rate of the enterprise to be identified, the net property profitability rate of the enterprise to be identified, the business profit growth rate of the enterprise to be identified and the total property growth rate of the enterprise to be identified.
Optionally, the acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified includes:
acquiring enterprise entities in an original knowledge graph;
determining the enterprise entities in the original knowledge graph as enterprises to be identified;
and acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified according to the original knowledge map.
The knowledge graph is a series of various graphs for displaying the relationship between the knowledge development process and the structure.
The knowledge map applied in the financial supervision field can fully play the role of a map database, and is more beneficial to monitoring the abnormal credit fund in various service scenes. Common entities of financial knowledge-maps include: companies, individuals, products, securities, and the like. The original knowledge graph in the embodiment of the invention is only the guarantee relationship, the group relationship, the share right relationship and the fund penetrating relationship between the connected enterprises and between the individuals. The attributes displayed by the enterprises as the entities in the original knowledge graph are only basic enterprise information such as social uniform numbers and names of the enterprises, and various risk attributes of the enterprises as the entities in the original knowledge graph are not identified, and the risk enterprises are not displayed in the knowledge graph, so that the monitoring function of the knowledge graph is not fully exerted.
The method for acquiring the enterprise entity in the original knowledge graph can be as follows: sequentially acquiring each enterprise entity in the original knowledge graph according to a certain smoothness; the manner of obtaining the enterprise entity in the original knowledge graph may also be: and when the user clicks a certain enterprise entity in the original knowledge graph, acquiring the enterprise entity clicked by the user. The embodiment of the invention does not limit the way of acquiring the enterprise entity in the original knowledge graph.
Specifically, the manner of acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified according to the original knowledge graph may be as follows: and acquiring a target database corresponding to the original knowledge map, and screening the business information of the enterprise to be identified and the financial information of the enterprise to be identified from the target database according to the identification information of the enterprise to be identified.
S120, inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model for abnormal enterprise identification to obtain an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the sample enterprise business information, the sample enterprise financial information, and the sample enterprise identification information.
The target sample set may be obtained in a manner of: acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes; determining a target index according to the first source data and the second source data; and generating a target sample set according to the target indexes and the abnormal enterprise set. The target sample set may be obtained by: acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes; determining a target index according to the first source data and the second source data; and generating a target sample set according to the target index, the abnormal enterprise set and the normal enterprise set. The target sample set may be obtained by: acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data including: data corresponding to at least two indexes; acquiring the similarity of data corresponding to the same index in the first source data and the second source data; determining the index with the similarity smaller than the similarity threshold as a target index; and generating a target sample set according to the target indexes and the abnormal enterprise set. The target sample set may be obtained by: acquiring an abnormal enterprise set, wherein the abnormal enterprise set comprises: the source data corresponding to a plurality of abnormal enterprises is derived through a sample of a part of index labels derived after business investigation, for example, the registration time of most of the abnormal enterprises is not more than one year or shorter, so that the registration time of the enterprises is considered to be an effective variable for distinguishing the abnormal enterprises from the normal enterprises, and the variable of the number of days or years from the current date of the enterprise registration date derived according to the original variable 'enterprise registration date'; and further obtaining a plurality of derived indexes, and screening a target sample set from the source data corresponding to the abnormal enterprises according to the derived indexes.
Specifically, the business information of the enterprise to be identified and the financial information of the enterprise to be identified are input into the target model to identify the abnormal enterprise, and the identification result may be obtained in the following manner: acquiring a target sample set; establishing a machine learning model; inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result; training parameters of the machine learning model according to an objective function formed by the prediction result and the identification information of the sample enterprise; and returning to execute the operation of inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result until the target model is obtained.
In a specific example, table 1 is a sample of a part of index tags derived after business research, where the "application purpose" list indicates the purpose that the derived index of the corresponding row is derived by processing, that is, the derived index is derived by processing to consider the aspects and business scenarios, as shown in table 1:
TABLE 1
As shown in table 1, enterprise samples are screened from the abnormal enterprise set and the normal enterprise set according to the derived indexes and the statistical indexes in the table, and a target sample set is constructed. After the machine learning model is trained on the basis of the target sample set to obtain a target model, the derived indexes and the source data corresponding to the statistical indexes of the enterprise to be identified are obtained according to the derived indexes and the statistical indexes in the table, and the source data corresponding to the derived indexes and the statistical indexes are input into the target model to identify the abnormal enterprise.
Optionally, after inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into the target model to identify the abnormal enterprise and obtain an identification result, the method further includes:
determining a label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified;
and updating the original knowledge graph according to the label corresponding to the enterprise to be identified to obtain a target knowledge graph.
The method for determining the tag corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified may be: if the enterprise to be identified is an abnormal enterprise, the label corresponding to the enterprise to be identified is in a first color; and if the enterprise to be identified is a normal enterprise, the label corresponding to the enterprise to be identified is in a second color. The first color is different from the second color, and the mode of determining the label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified may further be: if the enterprise to be identified is an abnormal enterprise, the label corresponding to the enterprise to be identified is a first label; and if the enterprise to be identified is a normal enterprise, the label corresponding to the enterprise to be identified is a second label, and the first label is different from the second label.
Updating the original knowledge graph according to the label corresponding to the enterprise to be identified, wherein the mode of obtaining the target knowledge graph can be as follows: adding a corresponding label to an enterprise entity to be identified in an original knowledge graph to obtain a target knowledge graph, wherein for example, if the enterprise to be identified is an abnormal enterprise, a first label is added to the enterprise entity to be identified in the original knowledge graph; and if the enterprise to be identified is a normal enterprise, adding a second label aiming at the enterprise entity to be identified in the original knowledge graph. Or, if the enterprise to be identified is an abnormal enterprise, replacing the entity of the enterprise to be identified in the original knowledge graph with a first color; and if the enterprise to be identified is a normal enterprise, replacing the enterprise entity to be identified in the original knowledge graph with a second color.
Specifically, in the embodiment of the present invention, various types of risk information attributes are added to the enterprise entity on the original knowledge graph, so as to specially identify the enterprise entity in the target knowledge graph, for example, a special color is added to the enterprise entity, so as to distinguish different risk entities from the enterprise entity without a special identifier, which is more convenient for supervision, for example, monitoring the flow of credit funds into an enterprise entity with a special identifier.
Optionally, determining the tag corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified includes:
if the enterprise to be identified is an abnormal enterprise, the label corresponding to the enterprise to be identified is in a first color;
and if the enterprise to be identified is a normal enterprise, the label corresponding to the enterprise to be identified is in a second color.
The first color may be red or yellow, and the second color may be the same as or different from the color of the business entity in the original knowledge graph, for example, the second color may be set to green.
Optionally, updating the original knowledge graph according to the tag corresponding to the enterprise to be identified to obtain a target knowledge graph, including:
and replacing the color of the abnormal enterprise in the original knowledge graph with a first color, and replacing the color of the normal enterprise in the original knowledge graph with a second color to obtain the target knowledge graph.
In a specific example, the color of the enterprise entity in the original knowledge graph is black, and if the enterprise entity to be identified is an abnormal enterprise, the color of the enterprise entity to be identified in the original knowledge graph is replaced from black to red; and if the enterprise to be identified is a normal enterprise, replacing the color of the entity of the enterprise to be identified in the original knowledge graph from black to green.
In a specific example, the color of the enterprise entity in the original knowledge graph is black, and if the enterprise entity to be identified is an abnormal enterprise, the color of the enterprise entity to be identified in the original knowledge graph is replaced from black to red; and if the enterprise to be identified is a normal enterprise, keeping the color of the entity of the enterprise to be identified in the original knowledge graph unchanged.
Optionally, the iteratively training the machine learning model through the target sample set includes:
acquiring a target sample set;
establishing a machine learning model;
inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result;
training parameters of the machine learning model according to an objective function formed by the prediction result and the identification information of the sample enterprise;
and returning to execute the operation of inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result until the target model is obtained.
Wherein the enterprise identification information may be: the enterprise is a normal enterprise or may be an abnormal enterprise, which is not limited in this embodiment of the present invention.
The method for obtaining the target sample set may be as follows: acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes; determining a target index according to the first source data and the second source data; and generating a target sample set according to the target indexes and the abnormal enterprise set. The way of obtaining the target sample set may also be: through a sample of a part of index tags derived after business investigation, for example, the registration time of most abnormal enterprises does not exceed one year or less, so that the registration time of the enterprises is considered as a variable for effectively distinguishing the abnormal enterprises from the normal enterprises, and a variable of the number of days or years from the current date of the enterprise registration date can be derived according to an original variable 'enterprise registration date'; and further obtaining a plurality of derived indexes, and screening a target sample set from the source data corresponding to the abnormal enterprises according to the derived indexes and the statistical indexes.
In a specific example, the original knowledge map is used for displaying a fund link relationship between enterprises, typical credit funds flow back to the enterprises, credit funds flow into the enterprises of the real estate industry, credit funds flow into the enterprises of the financing companies based on the original knowledge map, derivative indexes of the enterprises are determined according to the statistical indexes of the enterprises, a target sample set is established according to the statistical indexes and the derivative indexes of the enterprises, and a target model is obtained by training a machine learning model through the target sample set. The specific method comprises the following steps: the derived indices and statistical indices of the individual dimensions are taken as the in-modulus variables according to, for example, logistic regression algorithms, xgboost algorithms. And predicting whether the enterprise is an enterprise with abnormal fund flow. Such as: the method comprises the steps of enabling credit funds to flow back enterprises, enabling credit funds to flow into enterprises of real estate industries and enabling credit funds to flow into enterprises of financing companies, labeling prediction results, enabling the labels to be used as abnormal enterprises, and enabling the enterprise entities to be labeled through labeling special colors in an original knowledge map.
When the data volume is extremely large, relevant characteristics under a certain service scene can be known through expert experience or relevant data, the derived indexes in the table 1 are the characteristic indexes, clustering or typicality correlation analysis is carried out after the indexes are defined, special samples are found out, the abnormal enterprises are preliminarily judged, whether the abnormal enterprises are real abnormal enterprises with risks or not is further judged through screening, and the condition for establishing the supervised machine learning model is formed until the real abnormal samples are found and accumulated.
Optionally, obtaining a target sample set includes:
acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal set of businesses includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes;
determining a target index according to the first source data and the second source data;
and generating a target sample set according to the target indexes and the abnormal enterprise set.
Specifically, the method for determining the target index according to the first source data and the second source data may be: acquiring the similarity of data corresponding to the same index in the first source data and the second source data; and determining the index with the similarity smaller than the similarity threshold value as a target index.
Specifically, the manner of generating the target sample set according to the target index and the abnormal enterprise set may be: and screening enterprise samples from the abnormal enterprise set according to the target indexes, and generating a target sample set according to the screened enterprise samples.
The embodiment of the invention designs the enterprise tag statistical indexes under different types of supervision service scenes, enriches enterprise characteristics from multiple dimensions, excavates the related behaviors of enterprise capital links, and enriches the multi-dimensional attributes of entities in a knowledge graph so as to meet further supervision requirements.
Optionally, determining a target index according to the first source data and the second source data includes:
acquiring the similarity of data corresponding to the same index in the first source data and the second source data;
and determining the index with the similarity smaller than the similarity threshold value as a target index.
The similarity threshold may be set by a system or a user, which is not limited in this embodiment of the present invention.
Optionally, if the sample enterprise is a normal enterprise, the identification information of the sample enterprise is the first identification, and if the sample enterprise is an abnormal enterprise, the identification information of the sample enterprise is the second identification.
Wherein the first and second identifiers are different.
Optionally, the business information includes: enterprise registration time.
Optionally, the business information further includes: the business registers capital and/or business properties.
Optionally, the financial information includes: at least one of an enterprise inflow amount, an enterprise outflow amount, an enterprise account balance, an account opening date, an account first transaction date, an account deactivation date, an account deregistration date, a transaction counter party name, a number of times funds flow through the account, a number of times funds flow through the self-associated entity, a transaction currency, a number of times the enterprise appears on a blacklist, a loan number, a loan amount, and a loan maximum amount usage rate.
The enterprise inflow amount can be weekly inflow amount in last half of the year, or 15 days inflow amount in last half of the year; the enterprise outflow amount can be weekly outflow amount in the last half year or 15 days outflow amount in the last half year. The financial information may further include: the ratio of inflow amount to outflow amount in each week in the last half year, the ratio of inflow amount to outflow amount in each 15 days in the last half year, the maximum ratio of inflow amount to outflow amount in each week in the last half year, the minimum ratio of inflow amount to outflow amount in each week in the last half year, the average ratio of inflow amount to outflow amount in each week in the last half year, the standard deviation of inflow amount to outflow amount in each week in the last half year, the maximum ratio of uniflow deposit per week in the last half year, the uniflow ratio of uniflow deposit per week in the last half year, the maximum ratio of uniflow deposit per week in the last half year, the minimum ratio of inflow amount to outflow amount per 15 days in the last half year, the average ratio of inflow amount to outflow amount per 15 days in the last half year, Standard deviation of the ratio of inflow amount to outflow amount every 15 days in the last half year, the ratio of the maximum value of the single-flow income amount every 15 days in the last half year, the ratio of the minimum value of the single-flow income amount every 15 days in the last half year, the ratio of the maximum value of the single-flow outflow amount every 15 days in the last half year, the ratio of the minimum value of the single-flow income amount every 15 days in the last half year, the ratio of the maximum value of the single-flow income amount every 15 days in the last half year and the like.
Wherein the financial information may further include: the ratio of the specific outflow amount to the account balance is the maximum value in the last half year, the ratio of the specific outflow amount to the account balance is the minimum value in the last half year, and the ratio of the specific outflow amount to the account balance is the average value in the last half year.
Wherein the financial information may further include: the distance between the transaction date and the account opening date for the first time, the distance between the account stop date/the account cancellation date and the account opening date, the amount of money per week flowing into the account after the transaction occurs for the first time, the amount of money per week flowing out of the account after the transaction occurs for the first time, the amount of money per week flowing into the account after the transaction occurs for the first time until the stop date or the cancellation date, the amount of money per week flowing out of the account after the transaction occurs for the first time until the stop date or the cancellation date, and the like.
If the name of the counterparty has keywords such as "tax" and/or "property", the enterprise is determined to be an abnormal enterprise.
Wherein the transaction currency may be: the currency may be related to the last month transaction, the currency may be related to the last 3 months transaction, the currency may be related to the last 6 months transaction, or the currency may be related to the last year transaction, which is not limited in this embodiment of the present invention.
The number of times that the enterprise appears on the blacklist may be: the average value of the times of blacklisting an enterprise in the month in the last year, the times of occurrence of the enterprise on the blacklist can be as follows: the maximum number of times of blacklisting an enterprise in the month in the last year, the number of times of occurrence of the enterprise on the blacklist may be: the minimum value of the blacklist times of the enterprise in the month in the last year can be as follows: and the standard deviation of blacklisting times of the enterprises in the month in the last year.
Wherein, the amount of the fund flow through the self-associated entity may be: funds flow through the account number before reflowing the own account.
Optionally, the financial information further includes: at least one of profit margin, equity rate, liquidity ratio, turnover rate of accounts receivable, net equity profit margin, business profit growth rate, and total equity growth rate.
According to the technical scheme of the embodiment, the business information of the enterprise to be identified and the financial information of the enterprise to be identified are obtained; inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, and obtaining an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the identification information of the business information of the sample enterprise, the financial information of the sample enterprise and the identification information of the sample enterprise can effectively improve the identification capability of the abnormal enterprise, and is convenient to supervise.
Example two
Fig. 2 is a schematic structural diagram of an abnormal enterprise identification apparatus according to an embodiment of the present invention. The embodiment may be applicable to the case of abnormal enterprise identification, the apparatus may be implemented in a software and/or hardware manner, and the apparatus may be integrated in any device that provides an abnormal enterprise identification function, as shown in fig. 2, where the abnormal enterprise identification apparatus specifically includes: an acquisition module 210 and an identification module 220.
The obtaining module 210 is configured to obtain business information of an enterprise to be identified and financial information of the enterprise to be identified;
the identification module 220 is configured to input the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model for performing abnormal enterprise identification, so as to obtain an identification result, where the target model is obtained by iterating a machine learning model through a target sample set, and the target sample includes: the sample enterprise business information, the sample enterprise financial information, and the sample enterprise identification information.
Optionally, the obtaining module is specifically configured to:
acquiring enterprise entities in an original knowledge graph;
determining the enterprise entity in the original knowledge graph as an enterprise to be identified;
and acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified according to the original knowledge map.
Optionally, the method further includes:
the determining module is used for determining the label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified;
and the updating module is used for updating the original knowledge graph according to the label corresponding to the enterprise to be identified to obtain a target knowledge graph.
Optionally, the determining module is specifically configured to:
if the enterprise to be identified is an abnormal enterprise, the label corresponding to the enterprise to be identified is in a first color;
and if the enterprise to be identified is a normal enterprise, the label corresponding to the enterprise to be identified is in a second color.
Optionally, the update module is specifically configured to:
and replacing the color of the abnormal enterprise in the original knowledge graph with a first color, and replacing the color of the normal enterprise in the original knowledge graph with a second color to obtain the target knowledge graph.
Optionally, the identification module is specifically configured to:
acquiring a target sample set;
establishing a machine learning model;
inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result;
training parameters of the machine learning model according to an objective function formed by the prediction result and the identification information of the sample enterprise;
and returning to execute the operation of inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result until the target model is obtained.
Optionally, the identification module is specifically configured to:
acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes;
determining a target index according to the first source data and the second source data;
and generating a target sample set according to the target indexes and the abnormal enterprise set.
Optionally, the identification module is specifically configured to:
acquiring the similarity of data corresponding to the same index in the first source data and the second source data;
and determining the index with the similarity smaller than the similarity threshold value as a target index.
Optionally, if the sample enterprise is a normal enterprise, the identification information of the sample enterprise is the first identification, and if the sample enterprise is an abnormal enterprise, the identification information of the sample enterprise is the second identification.
Optionally, the business information includes: enterprise registration time.
Optionally, the business information further includes: the business registers capital and/or business properties.
Optionally, the financial information includes: at least one of an enterprise inflow amount, an enterprise outflow amount, an enterprise account balance, an account opening date, an account first transaction date, an account deactivation date, an account deregistration date, a transaction counter party name, a number of times funds flow through the account, a number of times funds flow through the self-associated entity, a transaction currency, a number of times the enterprise appears on a blacklist, a loan number, a loan amount, and a loan maximum amount usage rate.
Optionally, the financial information further includes: at least one of profit margin, equity rate, liquidity ratio, turnover rate of accounts receivable, net equity profit margin, business profit growth rate, and total equity growth rate.
The product can execute the method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
According to the technical scheme of the embodiment, the business information of the enterprise to be identified and the financial information of the enterprise to be identified are obtained; inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, and obtaining an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the identification information of the business information of the sample enterprise, the financial information of the sample enterprise and the identification information of the sample enterprise can effectively improve the identification capability of the abnormal enterprise, and is convenient to supervise.
EXAMPLE III
FIG. 3 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM)12, a Random Access Memory (RAM)13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. Processor 11 performs the various methods and processes described above, such as the abnormal business identification method:
acquiring the business information of an enterprise to be identified and the financial information of the enterprise to be identified;
inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, and obtaining an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the sample enterprise business information, the sample enterprise financial information, and the sample enterprise identification information.
In some embodiments, the abnormal business identification method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above-described abnormal business identification method may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the abnormal business identification method in any other suitable manner (e.g., by way of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the abnormal enterprise identification method according to any embodiment of the present invention is implemented.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (17)
1. An abnormal enterprise identification method is characterized by comprising the following steps:
acquiring the business information of an enterprise to be identified and the financial information of the enterprise to be identified;
inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, and obtaining an identification result, wherein the target model is obtained by iteratively training a machine learning model through a target sample set, and the target sample comprises: the sample enterprise business information, the sample enterprise financial information, and the sample enterprise identification information.
2. The method of claim 1, wherein obtaining business information of a business to be identified and financial information of the business to be identified comprises:
acquiring enterprise entities in an original knowledge graph;
determining the enterprise entities in the original knowledge graph as enterprises to be identified;
and acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified according to the original knowledge map.
3. The method of claim 2, wherein after inputting the business information of the to-be-identified enterprise and the financial information of the to-be-identified enterprise into the target model for abnormal enterprise identification, and obtaining the identification result, the method further comprises:
determining a label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified;
and updating the original knowledge graph according to the label corresponding to the enterprise to be identified to obtain a target knowledge graph.
4. The method according to claim 3, wherein determining the label corresponding to the enterprise to be identified according to the identification result corresponding to the enterprise to be identified comprises:
if the enterprise to be identified is an abnormal enterprise, the label corresponding to the enterprise to be identified is in a first color;
and if the enterprise to be identified is a normal enterprise, the label corresponding to the enterprise to be identified is in a second color.
5. The method of claim 4, wherein updating the original knowledge graph according to the label corresponding to the enterprise to be identified to obtain a target knowledge graph comprises:
and replacing the color of the abnormal enterprise in the original knowledge graph with a first color, and replacing the color of the normal enterprise in the original knowledge graph with a second color to obtain the target knowledge graph.
6. The method of claim 1, wherein iteratively training a machine learning model through a set of target samples comprises:
acquiring a target sample set;
establishing a machine learning model;
inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result;
training parameters of the machine learning model according to an objective function formed by the prediction result and the identification information of the sample enterprise;
and returning to execute the operation of inputting the industrial and commercial information of the sample enterprises in the target sample set and the financial information of the sample enterprises into the machine learning model to obtain a prediction result until the target model is obtained.
7. The method of claim 6, wherein obtaining a target sample set comprises:
acquiring an abnormal enterprise set and a normal enterprise set, wherein the abnormal enterprise set comprises: first source data corresponding to the abnormal enterprise, wherein the first source data comprises: data corresponding to at least two indexes; the normal business set includes: second source data corresponding to a normal enterprise, the second source data comprising: data corresponding to at least two indexes;
determining a target index according to the first source data and the second source data;
and generating a target sample set according to the target indexes and the abnormal enterprise set.
8. The method of claim 7, wherein determining a target metric from the first source data and the second source data comprises:
acquiring the similarity of data corresponding to the same index in the first source data and the second source data;
and determining the index with the similarity smaller than the similarity threshold value as a target index.
9. The method of claim 6, wherein the identification information of the sample enterprise is the first identification if the sample enterprise is a normal enterprise, and the second identification if the sample enterprise is an abnormal enterprise.
10. The method of any one of claims 1-9, wherein the business information comprises: enterprise registration time.
11. The method of any one of claims 1-9, wherein the business information further comprises: the business registers capital and/or business properties.
12. The method according to any of claims 1-9, wherein the financial information comprises: at least one of an enterprise inflow amount, an enterprise outflow amount, an enterprise account balance, an account opening date, an account first transaction date, an account deactivation date, an account deregistration date, a transaction counter party name, a number of times funds flow through the account, a number of times funds flow through the self-associated entity, a transaction currency, a number of times the enterprise appears on a blacklist, a loan number, a loan amount, and a loan maximum amount usage rate.
13. The method according to any one of claims 1-9, wherein the financial information further comprises: at least one of a profit margin, a rate of liabilities, a liquidity ratio, a rate of turnover of debts due, a net asset profit margin, an operational profit margin and a total asset margin.
14. An abnormal business identification apparatus, comprising:
the acquisition module is used for acquiring the business information of the enterprise to be identified and the financial information of the enterprise to be identified;
the identification module is used for inputting the business information of the enterprise to be identified and the financial information of the enterprise to be identified into a target model to identify the abnormal enterprise, so as to obtain an identification result, wherein the target model is obtained by a target sample set iteration machine learning model, and the target sample comprises: the sample enterprise business information, the sample enterprise financial information, and the sample enterprise identification information.
15. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of anomalous business identification as claimed in any one of claims 1-13.
16. A computer-readable storage medium storing computer instructions for causing a processor to implement the abnormal business identification method of any one of claims 1-13 when executed.
17. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the abnormal business identification method according to any one of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210420447.9A CN114997975A (en) | 2022-04-20 | 2022-04-20 | Abnormal enterprise identification method, device, equipment, medium and product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210420447.9A CN114997975A (en) | 2022-04-20 | 2022-04-20 | Abnormal enterprise identification method, device, equipment, medium and product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114997975A true CN114997975A (en) | 2022-09-02 |
Family
ID=83024732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210420447.9A Pending CN114997975A (en) | 2022-04-20 | 2022-04-20 | Abnormal enterprise identification method, device, equipment, medium and product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114997975A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117172632A (en) * | 2023-10-30 | 2023-12-05 | 湖南财信数字科技有限公司 | Enterprise abnormal behavior detection method, device, equipment and storage medium |
| CN117893102A (en) * | 2024-03-15 | 2024-04-16 | 平潭综合实验区智慧岛投资发展有限公司 | Enterprise management system based on block chain |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
| CN111783829A (en) * | 2020-05-29 | 2020-10-16 | 广发证券股份有限公司 | Financial anomaly detection method and device based on multi-label learning |
-
2022
- 2022-04-20 CN CN202210420447.9A patent/CN114997975A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
| CN111783829A (en) * | 2020-05-29 | 2020-10-16 | 广发证券股份有限公司 | Financial anomaly detection method and device based on multi-label learning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117172632A (en) * | 2023-10-30 | 2023-12-05 | 湖南财信数字科技有限公司 | Enterprise abnormal behavior detection method, device, equipment and storage medium |
| CN117172632B (en) * | 2023-10-30 | 2024-01-19 | 湖南财信数字科技有限公司 | Enterprise abnormal behavior detection method, device, equipment and storage medium |
| CN117893102A (en) * | 2024-03-15 | 2024-04-16 | 平潭综合实验区智慧岛投资发展有限公司 | Enterprise management system based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240211967A1 (en) | Adaptive transaction processing system | |
| JP7017149B2 (en) | Information processing equipment, information processing method and information processing program using deep learning | |
| CN114997975A (en) | Abnormal enterprise identification method, device, equipment, medium and product | |
| Siekelova et al. | Prediction financial stability of Romanian production companies through Altman Z-score | |
| Wong et al. | Financial accounting fraud detection using business intelligence | |
| Liu et al. | Anticipating financial distress of high‐tech startups in the European Union: A machine learning approach for imbalanced samples | |
| Drabiková et al. | Decision trees-a powerful tool in mathematical and economic modeling | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN115526700A (en) | Risk prediction method and device and electronic equipment | |
| CN114781937A (en) | Method and device for pre-paid card enterprise risk early warning and storage medium | |
| Bi et al. | Risk assessment of operator’s big data Internet of Things credit financial management based on machine learning | |
| CN114092230A (en) | Data processing method and device, electronic equipment and computer readable medium | |
| CN113506173A (en) | Credit risk assessment method and related equipment thereof | |
| CN115795345A (en) | Information processing method, device, equipment and storage medium | |
| CN113450208A (en) | Loan risk change early warning and model training method and device | |
| CN113256351A (en) | User service demand identification method and device and computer readable storage medium | |
| CN113240513A (en) | Method for determining user credit line and related device | |
| Yu | [Retracted] Big Data Analytics and Discrete Choice Model for Enterprise Credit Risk Early Warning Algorithm | |
| CN112434083A (en) | Event processing method and device based on big data | |
| Yazdani | Developing a model for validation and prediction of bank customer credit using information technology (case study of Dey Bank) | |
| Priyadarshi et al. | A comprehensive review on insider trading detection using artificial intelligence | |
| CN116245629A (en) | Recognition method, device and model training method for cashing behavior of bank staff | |
| CN115526697A (en) | Bond issuer default risk identification method, device, equipment, medium and product | |
| Pangaribuan et al. | Profitability, Liquidity, and Solvency's Impact on Company Value: The Quality Audit's Moderating Role | |
| Karthik | Dr Somanchi Hari Krishna |
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 |