CN111612610A - Risk early warning method and system, electronic equipment and storage medium - Google Patents
Risk early warning method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111612610A CN111612610A CN202010462218.4A CN202010462218A CN111612610A CN 111612610 A CN111612610 A CN 111612610A CN 202010462218 A CN202010462218 A CN 202010462218A CN 111612610 A CN111612610 A CN 111612610A
- Authority
- CN
- China
- Prior art keywords
- early warning
- enterprise
- classifier
- preset
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims description 55
- 238000012545 processing Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000012935 Averaging Methods 0.000 claims description 4
- 230000009193 crawling Effects 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 238000013145 classification model Methods 0.000 abstract description 5
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000035515 penetration Effects 0.000 description 25
- 230000008859 change Effects 0.000 description 10
- 230000007115 recruitment Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Library & Information Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Emergency Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to data analysis, and provides a risk early warning method, which comprises the following steps: acquiring enterprise information of a target enterprise in a preset time period, wherein the enterprise information comprises a business label of the target enterprise; matching an index value corresponding to the target enterprise from a preset label list according to the service label, wherein the index value is a numerical value related to the service type representing the target enterprise; and inputting the index value into a pre-trained early warning classifier to generate an early warning grade aiming at the target enterprise. The invention also provides a risk early warning system, an electronic device and a storage medium. The invention forms a classification model of customized type financial risk service early warning.
Description
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a risk early warning method and system, an electronic device, and a storage medium.
Background
With the development of modern financial economy and internet technology, various financial products and financial modes emerge endlessly, and a user stands at the perspective of a supervision department to see problems, and enterprises run financial risk services, if the problems occur and then supervise, the fact already causes damage to the society and the property of people, and the problems are difficult to recover.
In order to avoid risks, a financial institution usually contacts field inspection or non-field inspection to track users handling financial services, searches long-time related data, performs risk early warning by means of a computer, and has a single channel for acquiring user data, so that the early warning timeliness is poor, and short-period similar financial risk early warning of enterprises is always a key point and a difficult problem to be solved urgently in the industry.
Disclosure of Invention
In view of the foregoing problems, an object of the present invention is to provide a risk pre-warning method, an electronic device, and a storage medium for customizing a classification model of a generic financial risk service pre-warning.
According to an aspect of the present invention, there is provided a risk early warning method, including:
acquiring enterprise information of a target enterprise in a preset time period, wherein the enterprise information comprises a business label of the target enterprise;
matching an index value corresponding to the target enterprise from a preset label list according to the service label, wherein the index value is a numerical value related to the service type representing the target enterprise;
and inputting the index value into a pre-trained early warning classifier to generate an early warning grade aiming at the target enterprise.
In an embodiment, the method for matching the index value corresponding to the target enterprise from a preset tag list according to the service tag includes:
acquiring the service type mapped by the service label;
and matching the index value corresponding to the service type in a preset index database according to the service type.
In one embodiment, the training method of the early warning classifier comprises the following steps:
taking a plurality of indexes of enterprises with known early warning levels and a plurality of corresponding index values as a plurality of samples to form a training set;
averaging the weight distribution of each sample;
inputting a plurality of index values of a plurality of samples in a training set into an early warning classifier to obtain a classification error rate of first training, wherein the classification error rate is the ratio of the number of error-divided samples to the total number of samples;
obtaining the pre-warning classifier coefficient according to the classification error rate through the following formula
Wherein e ismRepresenting the classification error rate, and m representing the training times;
updating weight distribution of next training sample according to early warning classifier coefficient
Wherein, wm+1,iIs the weight, Z, of the ith sample of the m +1 trainingmTo normalize the factor, yiEarly warning grade, x, corresponding to ith sample of mth trainingiIndex matrix for ith sample of mth training, Gm(xi) For sample x of weak classifieriThe output early warning level;
training the early warning classifier and updating the weight distribution repeatedly until the sample classification is completely correct to obtain the final early warning classifier
Wherein M is the training times for achieving complete correct classification, G (x) is a strong classifier obtained after iterative training, Gm(x) The weak classifier of the mth training.
In one embodiment, after the step of inputting the index value into a pre-trained early warning classifier, the method further comprises:
and (4) adopting continuous attention monitoring in different periods for enterprises with different early warning levels, wherein the higher the early warning level is, the longer the period is.
In one embodiment, the construction method of the early warning classifier comprises the following steps:
obtaining the association degree between different enterprises through the preset weight combination;
sequentially matching the association degrees with a preset threshold value set, and regulating enterprises with the association degrees in a corresponding preset threshold value interval into a cluster;
and constructing an early warning classifier for each cluster according to a preset rule.
Preferably, the step of obtaining the association degrees between different enterprises through weight combination includes: and combining weights through preset parameters of the enterprises, wherein the preset parameters comprise the composition forms of the enterprises, the assets of the enterprises and the wealth ranks of enterprise relatives, and the larger the value of the preset parameters is, the larger the weights are.
In one embodiment, the method for acquiring the enterprise information of the target enterprise within the preset time period includes one or more of the following methods:
acquiring enterprise information from a preset webpage by adopting a webpage information crawling method; or
Acquiring enterprise information by adopting an intelligent outbound mode; or
And acquiring enterprise information from a preset enterprise database.
According to a second aspect of the present invention, there is provided a risk early warning system comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring enterprise information of a target enterprise in a preset time period, and the enterprise information comprises a business label of the target enterprise;
the processing module is used for matching an index value corresponding to the target enterprise from a preset label list according to the service label acquired by the acquisition module, wherein the index value is a numerical value related to the service type representing the target enterprise;
and the execution module is used for inputting the index values matched with the processing module into a pre-trained early warning classifier so as to generate an early warning grade aiming at the target enterprise.
According to a third aspect of the present invention, an electronic device is provided, which includes a memory and a processor, wherein the memory stores a risk pre-warning program, and the risk pre-warning program implements the steps of the risk pre-warning method when executed by the processor.
According to a fourth aspect of the present invention, a computer-readable storage medium is provided, which includes a risk pre-warning program, and when the risk pre-warning program is executed by a processor, the risk pre-warning program implements the steps of the risk pre-warning method.
The risk early warning method and system, the electronic device and the computer readable storage medium form a classification model of customized financial risk service early warning of thousands of businesses through data acquisition and industry-by-industry modeling of different industries on different types of model analysis of financial risk services, can capture violation behaviors caused by basic level data change and rapid expansion of risk exposure, can timely discover and confirm the operation behaviors of financial services of enterprises, greatly reduce the daily work labor input of a supervision organization and improve the supervision efficiency.
Drawings
FIG. 1 is a flow chart of a risk early warning method of the present invention;
FIG. 2 is a block diagram of a risk early warning system according to the present invention;
FIG. 3 is a schematic diagram of an application environment of the risk pre-warning method according to the preferred embodiment of the invention.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a risk early warning method according to the present invention, and as shown in fig. 1, the risk early warning method includes:
step S1, acquiring enterprise information of a target enterprise in a preset time period, wherein the enterprise information comprises a business label of the target enterprise;
step S2, matching index values corresponding to the target enterprise from a preset label list according to the service labels, wherein the indexes comprise liquidity risk indexes such as loan overdue amount, loan overdue time, loan overdue times and irrecoverable times, and the like, and include recruitment information number, recruitment post number, recruitment information number change, recruitment post number change, income rate change and the like, and further comprise relevance, whether the index values are located in a blacklist, several blacklists and the like, and the index values are values related to service types representing the target enterprise;
and step S3, inputting the index value into a pre-trained early warning classifier to generate an early warning grade aiming at the target enterprise.
In step S1, the method for acquiring the business information of the target business within the preset time period includes one or more of the following methods:
acquiring enterprise information from a preset webpage by adopting a webpage information crawling method; or
The enterprise information is obtained by adopting an intelligent outbound mode, for example, whether the enterprise can still be called, whether the service is normally carried out, whether the service can be brought up in time and the like are confirmed through a customer service telephone; or
The enterprise information is obtained from the preset enterprise database, for example, judicial data such as error-intensive business change, recent negative public opinion quantity change, litigation case quantity and the like, financial and newspaper data change, evaluation indexes, prospects and the like are obtained from the enterprise database.
In step S1, the obtained enterprise information further includes articles, documents, and the like, and the step of extracting the service tags from the articles and documents includes:
setting keywords of a service, and storing the keywords into a keyword library, wherein the keywords are words related to the service, for example, in the 7+ 4-class financial service, the keywords may include financing, products, loan and the like;
extracting key words of each service in the enterprise information;
when the enterprise information includes keywords of multiple services, according to the probability that one service includes one service corresponding to the enterprise by taking the ratio of the number of the keywords in the enterprise information to the total number of the keywords in all the services including the enterprise information as the service label corresponding to the enterprise, the service corresponding to the highest probability can be selected as the service label corresponding to the enterprise, and the probability of all the services corresponding to the keywords in the enterprise information can be combined into a service matrix corresponding to the enterprise to be used as the service label.
Preferably, in step S1, the reason why the preset time period is not greater than three months and a short period (not greater than three months) is used as the time window is that, according to the multiple times of the investigation experience of the risk of the financial transaction, the enterprise engaged in the financial transaction may absorb a large amount of public deposits and sell financial products which are not in compliance within three months before the "overdue", "thunderstorm" or "running", and a sudden violation behavior within a short period is easily formed, so the range of the time window is determined to have an important meaning for the risk early warning of the enterprise.
In step S2, the method for matching the index value corresponding to the target enterprise from the preset tag list according to the service tag includes:
obtaining the service type mapped by the service label, where the service type is set according to an industry attribute of an industry to which the service belongs, for example, the similar financial service may include: P2P business type, loan business type, financing business type, etc.;
matching index values corresponding to the service types in a preset index database according to the service types, preferably setting different indexes aiming at different service types, for example, indexes aiming at the P2P service types comprise liquidity risk indexes such as loan overdue amount, loan overdue time, loan overdue times, non-cashable times and the like; the indexes aiming at the financing service type comprise the number of recruitment information pieces, the number of recruitment positions, the change of the number of the recruitment information pieces, the change of the number of the recruitment positions, the change of the yield and the like. In addition, when the service label is a service matrix, a new index value is formed by combining the probability in the service matrix as a weight value and the index value, and an index matrix is formed.
In step S3, the training method of the early warning classifier includes:
taking a plurality of indexes of enterprises with known early warning levels and a plurality of corresponding index values as a plurality of samples to form a training set;
averaging the weight distribution of each sample;
inputting a plurality of index values of a plurality of samples in a training set into an early warning classifier to obtain a classification error rate of first training, wherein the classification error rate is the ratio of the number of error-divided samples to the total number of samples;
obtaining the pre-warning classifier coefficient according to the classification error rate through the following formula
Wherein e ismRepresenting the classification error rate, and m representing the training times;
updating weight distribution of next training sample according to early warning classifier coefficient
Wherein, wm+1,iIs the weight, Z, of the ith sample of the m +1 trainingmTo normalize the factor, yiEarly warning grade, x, corresponding to ith sample of mth trainingiIndex matrix for ith sample of mth training, Gm(xi) For sample x of weak classifieriThe output early warning level;
training the early warning classifier and updating the weight distribution repeatedly until the sample classification is completely correct to obtain the final early warning classifier
Wherein M is the training times for achieving complete correct classification, G (x) is a strong classifier obtained after iterative training, Gm(x) The weak classifier of the mth training.
In one embodiment, the construction method of the warning classifier of step S3 includes:
obtaining the association degree between different enterprises through the preset weight combination;
sequentially matching the association degrees with a preset threshold value set, and regulating enterprises with the association degrees in a corresponding preset threshold value interval into a cluster;
and constructing an early warning classifier for each cluster according to a preset rule.
Preferably, the step of obtaining the association degrees between different enterprises through the preset weight combination includes: the weight combination is carried out through preset parameters of an enterprise, the preset parameters comprise the composition form of the enterprise, the assets of the enterprise and the wealth ranking of enterprise associators, the larger the value of the preset parameters is, the larger the weight is, for example, when the enterprise is a stock making enterprise, the weight combination is carried out according to the level of stock holding and the strengths of the stock holding person and the associator (director, investor and the like), the more the level of stock holding is, the larger the weight is, the stronger the stock holding person and the associator are, the larger the weight is, and the strengths of the stock holding person and the associator are judged according to the wealth ranking.
In addition, preferably, the step of obtaining the association degrees between different enterprises through the preset weight combination may further include: setting the weight according to the investment mode of the enterprise, for example, the investment mode of the enterprise comprises investment, stock control and job control, the larger the investment amount is, the larger the weight is, the more stock control is, the larger the weight is, the more important the job control is, the larger the weight is, and the association degree among enterprises with hundred percent stock control is 1.
In one embodiment, the step S3 is followed by:
and (4) adopting continuous attention monitoring in different periods for enterprises with different early warning levels, wherein the higher the early warning level is, the longer the period is.
Preferably, the step of monitoring the enterprises with different early warning levels by continuous attention in different periods further includes screening the enterprises by using the number of penetration layers and the degree of association, the number of penetration layers of the enterprise with a high early warning level is greater than that of the enterprise with a low early warning level, and the number of other enterprises which are continuously associated with the enterprise with a high early warning level is greater than that of other enterprises which are continuously associated with the enterprise with a low early warning level, for example, the right of stock penetration means that when investment a is investment B and C, investment B is D, investment C is E, and investment D is E, then the right of stock penetration is respectively generated for D by a → B → D and a → C → E → D, and the right of stock penetration is generated for D by adding corresponding weights, namely adding the right of stock penetration of a to D. Then a has two penetrating layers for D, two and three. If the maximum penetration layer number can be set in the query process, all path conditions in all the maximum penetration layer numbers can be returned, and for example, an enterprise with the highest similar financial early warning level is indirectly associated to ten layers of penetration, and an enterprise with the association degree greater than 0 is taken as an analysis object, the classification condition is calculated periodically, and the ascending or descending of the early warning level is synchronously updated and recorded. And for enterprises with lower early warning levels, only direct correlation is concerned, and enterprises with the correlation degree larger than 0.9 are taken as analysis objects.
In one embodiment, a specialized blacklist library is constructed by matching and searching public data, government data, etc., and is a collection of public blacklist data, such as financial domain blacklist data, which can contain different types of blacklists such as illegal funding, fraud, etc. Whether the index database is located in the blacklist library or/and the number of the indexes located in the blacklist library can be used as the index of the index database.
In a preferred embodiment, in the process of training the early warning classifier, one or more parameters of the relevance, whether the business is in a blacklist, whether other businesses with the relevance exceeding a set value are in the blacklist and whether other businesses with the relevance exceeding the set value are in the blacklist and the number of penetration layers are taken as parameters for training the early warning classifier in the form of branches.
Fig. 2 is a block diagram of the risk early warning system according to the present invention, and as shown in fig. 2, the risk early warning system includes:
an obtaining module 21, configured to obtain enterprise information of a target enterprise in a preset time period, where the enterprise information includes a service tag of the target enterprise;
the processing module 22 is configured to match an index value corresponding to the target enterprise from a preset tag list according to the service tag acquired by the acquisition module, where the index value is a numerical value related to a service type that characterizes the target enterprise;
and the execution module 23 is configured to input the index value matched with the processing module into a pre-trained early warning classifier, so as to generate an early warning level for the target enterprise.
In one embodiment, the obtaining module 21 includes:
the first acquisition unit acquires enterprise information from a preset webpage by adopting a webpage information crawling method;
the second acquisition unit acquires enterprise information in an intelligent outbound mode;
the third acquisition unit is used for acquiring enterprise information from a preset enterprise database;
the keyword library is used for setting keywords of the service and storing the keywords into the keyword library, wherein the keywords are words related to the service;
the keyword extraction unit is used for extracting keywords of each service in the enterprise information;
and the service label obtaining unit is used for selecting the service corresponding to the highest probability as the service label corresponding to the enterprise according to the probability that the number of the keywords in the enterprise information contained in one service and the total number of the keywords in all the service contained enterprise information are taken as the service corresponding to the enterprise when the enterprise information comprises the keywords of a plurality of services, and also can form a service matrix corresponding to the enterprise by using the probabilities of all the services corresponding to the keywords in the enterprise information as the service label.
Preferably, the above-mentioned acquisition module 21 may include one or more of a first acquisition unit, a second acquisition unit and a third acquisition unit.
In one embodiment, the processing module 22 includes:
the mapping unit is used for acquiring the service type mapped by the service label;
and the index value obtaining unit is used for matching the index value corresponding to the service type in a preset index database according to the service type, and when the service label is a service matrix, combining the probability in the service matrix as a weight with the index value to form a new index value so as to form an index matrix.
In an embodiment, the executing module 23 includes an early warning classification model constructing sub-module and a training sub-module, and the training sub-module includes:
the training set constructing unit is used for forming a training set by taking a plurality of indexes of enterprises with known early warning levels and a plurality of corresponding index values as a plurality of samples;
a weight distribution unit averaging weight distribution of each sample;
the classification error obtaining unit is used for inputting a plurality of index values of a plurality of samples in the training set into the early warning classifier to obtain a classification error rate of first training, wherein the classification error rate is the ratio of the number of error-divided samples to the total number of samples;
an early warning classifier coefficient obtaining unit for obtaining the early warning classifier coefficient according to the classification error rate by the following formula
Wherein, amTo warn of classifier coefficients, emRepresenting the classification error rate, and m representing the training times;
a weight updating unit for updating the weight distribution of the next training sample according to the pre-warning classifier coefficient
Wherein, wm+1,iIs the weight, Z, of the ith sample of the m +1 trainingmTo normalize the factor, yiEarly warning grade, x, corresponding to ith sample of mth trainingiIs an index matrix of the ith sample, Gm(xi) For sample x of weak classifieriThe output early warning level;
an early warning classifier obtaining unit for obtaining a final early warning classifier by repeatedly and iteratively training the early warning classifier and updating the weight distribution until the sample classification is completely correct
Wherein M is the training times for achieving complete correct classification, G (x) is a strong classifier obtained after iterative training, Gm(x) The weak classifier of the mth training.
In one embodiment, the early warning classification model construction sub-module includes:
the association degree obtaining unit is used for obtaining association degrees among different enterprises through weight combination;
the grouping unit is used for sequentially matching the association degrees with a preset threshold value set and regulating enterprises with the association degrees in a corresponding preset threshold value interval into a cluster;
and the early warning classifier building unit is used for building an early warning classifier for each cluster according to a preset rule.
In one embodiment, the risk early warning system further includes a monitoring module 24, which employs continuous attention monitoring for different periods for enterprises with different early warning levels, wherein the higher the early warning level is, the longer the period is.
Preferably, the monitoring module 24 includes:
a setting unit for setting the maximum penetration layer number among different enterprises;
the path capturing unit captures all paths in all the maximum penetration layers of each enterprise according to the maximum penetration layers set by the setting unit and the sequence from high to low of the early warning level;
the penetration layer number determining unit is used for determining the penetration layer number and the corresponding penetration path of each enterprise according to the rule that the early warning level reduces the penetration layer number and also reduces the penetration path;
and the monitoring unit sets the number of the penetration layers to be continuously monitored according to the early warning level, the higher the early warning level is, the more the number of the penetration layers to be continuously monitored is, and other enterprises on the penetration path of the number of the penetration layers set by the monitoring unit corresponding to the penetration layer number determining unit are continuously monitored.
Further, preferably, the monitoring module 24 may further combine with the association degree obtaining unit to monitor the enterprise and other enterprises associated therewith, for example, the higher the warning level is, the number of penetration layers is continuously monitored, and the lower the association degree of continuous monitoring is.
In addition, the number of penetration layers and the correlation degree in the above embodiments may also be used as an index in the index database.
The risk early warning method provided by the invention can be applied to the electronic device 1. Fig. 3 is a schematic diagram of an application environment of the risk early warning method according to the preferred embodiment of the present invention.
In the present embodiment, the electronic device 1 may be a terminal client having an arithmetic function, such as a server, a mobile phone, a tablet computer, a portable computer, and a desktop computer.
The memory 11 includes at least one type of readable storage medium. The at least one type of readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory, and the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic apparatus 1, such as a hard disk of the electronic apparatus 1. In other embodiments, the readable storage medium may also be an external memory of the electronic device 1, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1.
In the present embodiment, the readable storage medium of the memory 11 is generally used for storing the risk pre-warning program 10 and the like installed in the electronic device 1. The memory 11 may also be used to temporarily store data that has been output or is to be output.
Processor 12, which in some embodiments may be a Central Processing Unit (CPU), microprocessor or other data Processing chip, is configured to execute program codes stored in memory 11 or process data, such as executing risk warning program 10.
The network interface 13 may optionally comprise a standard wired interface, a wireless interface (e.g. WI-FI interface), typically used for establishing a communication connection between the electronic apparatus 1 and other electronic clients.
The communication bus 14 is used to enable connection communication between these components.
Fig. 3 only shows the electronic device 1 with components 11-14, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may alternatively be implemented.
Optionally, the electronic device 1 may further include a user interface, the user interface may include an input unit such as a Keyboard (Keyboard), a voice input device such as a microphone (microphone) or other client with a voice recognition function, a voice output device such as a sound box, a headset, and the like, and optionally the user interface may further include a standard wired interface, a wireless interface.
Optionally, the electronic device 1 may further comprise a display, which may also be referred to as a display screen or a display unit.
In some embodiments, the display device may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch device, or the like. The display is used for displaying information processed in the electronic apparatus 1 and for displaying a visualized user interface.
Optionally, the electronic device 1 further comprises a touch sensor. The area provided by the touch sensor for the user to perform touch operation is called a touch area. Further, the touch sensor described herein may be a resistive touch sensor, a capacitive touch sensor, or the like. The touch sensor may include not only a contact type touch sensor but also a proximity type touch sensor. Further, the touch sensor may be a single sensor, or may be a plurality of sensors arranged in an array, for example.
Optionally, the electronic device 1 may further include logic gates, sensors, audio circuits, and the like, which are not described herein.
In the apparatus embodiment shown in fig. 3, a memory 11, which is a kind of computer storage medium, may include therein an operating system and a risk early warning program 10; the processor 12, when executing the risk pre-warning program 10 stored in the memory 11, implements the following steps:
acquiring enterprise information of a target enterprise in a preset time period, wherein the enterprise information comprises a business label of the target enterprise;
matching an index value corresponding to the target enterprise from a preset label list according to the service label, wherein the index value is a numerical value related to the service type representing the target enterprise;
and inputting the index value into a pre-trained early warning classifier to generate an early warning grade aiming at the target enterprise.
In other embodiments, the risk pre-warning program 10 may be further divided into one or more modules, and the one or more modules are stored in the memory 11 and executed by the processor 12 to implement the present invention. The modules referred to herein are referred to as a series of computer program instruction segments capable of performing specified functions. The risk pre-warning program 10 may be divided into modules of a risk pre-warning system.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a risk early warning program, and when executed by a processor, the risk early warning program implements the following steps:
acquiring enterprise information of a target enterprise in a preset time period, wherein the enterprise information comprises a business label of the target enterprise;
matching an index value corresponding to the target enterprise from a preset label list according to the service label, wherein the index value is a numerical value related to the service type representing the target enterprise;
and inputting the index value into a pre-trained early warning classifier to generate an early warning grade aiming at the target enterprise.
The embodiments of the computer-readable storage medium of the present invention are substantially the same as the embodiments of the risk pre-warning method, the risk pre-warning system, and the risk pre-warning electronic device, and are not repeated herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal client (e.g., a mobile phone, a computer, a server, or a network client) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A risk early warning method is characterized by comprising the following steps:
acquiring enterprise information of a target enterprise in a preset time period, wherein the enterprise information comprises a business label of the target enterprise;
matching an index value corresponding to the target enterprise from a preset label list according to the service label, wherein the index value is a numerical value related to the service type representing the target enterprise;
and inputting the index value into a pre-trained early warning classifier to generate an early warning grade aiming at the target enterprise.
2. The risk early warning method according to claim 1, wherein the method for matching the index value corresponding to the target enterprise from a preset tag list according to the service tag comprises:
acquiring the service type mapped by the service label;
and matching the index value corresponding to the service type in a preset index database according to the service type.
3. The risk pre-warning method according to claim 1, wherein the training method of the pre-warning classifier comprises:
taking a plurality of indexes of enterprises with known early warning levels and a plurality of corresponding index values as a plurality of samples to form a training set;
averaging the weight distribution of each sample;
inputting a plurality of index values of a plurality of samples in a training set into an early warning classifier to obtain a classification error rate of first training, wherein the classification error rate is the ratio of the number of error-divided samples to the total number of samples;
obtaining the pre-warning classifier coefficient according to the classification error rate through the following formula
Wherein e ismRepresenting classification error rate, m represents training timesCounting;
updating weight distribution of next training sample according to early warning classifier coefficient
Wherein, wm+1,iIs the weight, Z, of the ith sample of the m +1 trainingmTo normalize the factor, yiEarly warning grade, x, corresponding to ith sample of mth trainingiIndex matrix for ith sample of mth training, Gm(xi) For sample x of weak classifieriThe output early warning level;
training the early warning classifier and updating the weight distribution repeatedly until the sample classification is completely correct to obtain the final early warning classifier
Wherein M is the training times for achieving complete correct classification, G (x) is a strong classifier obtained after iterative training, Gm(x) The weak classifier of the mth training.
4. The risk pre-warning method according to claim 1, further comprising, after the step of inputting the indicator value into a pre-trained pre-warning classifier:
and continuously monitoring enterprises with different early warning levels in different periods, wherein the higher the early warning level is, the longer the monitoring period is.
5. The risk pre-warning method according to claim 1, wherein the pre-warning classifier is constructed by the method comprising the following steps:
obtaining the association degree between different enterprises through the preset weight combination;
sequentially matching the association degrees with a preset threshold value set, and regulating enterprises with the association degrees in a corresponding preset threshold value interval into a cluster;
and constructing an early warning classifier for each cluster according to a preset rule.
6. The risk early warning method according to claim 5, wherein the step of obtaining the association degrees between different enterprises through the preset weight combination comprises:
and combining weights through preset parameters of the enterprises, wherein the preset parameters comprise the composition forms of the enterprises, the assets of the enterprises and the wealth ranks of enterprise relatives, and the larger the value of the preset parameters is, the larger the weights are.
7. The risk pre-warning method according to claim 1, wherein the method for acquiring the enterprise information of the target enterprise within the preset time period comprises one or more of the following methods:
acquiring enterprise information from a preset webpage by adopting a webpage information crawling method; or,
acquiring enterprise information by adopting an intelligent outbound mode; or,
and acquiring enterprise information from a preset enterprise database.
8. A risk pre-warning system, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring enterprise information of a target enterprise in a preset time period, and the enterprise information comprises a business label of the target enterprise;
the processing module is used for matching an index value corresponding to the target enterprise from a preset label list according to the service label acquired by the acquisition module, wherein the index value is a numerical value related to the service type representing the target enterprise;
and the execution module is used for inputting the index values matched with the processing module into a pre-trained early warning classifier so as to generate an early warning grade aiming at the target enterprise.
9. An electronic device comprising a memory and a processor, the memory having stored therein a risk early warning program, the risk early warning program when executed by the processor implementing the steps of the risk early warning method according to any one of claims 1 to 7.
10. A computer-readable storage medium, comprising a risk pre-warning program which, when executed by a processor, performs the steps of the risk pre-warning method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010462218.4A CN111612610A (en) | 2020-05-27 | 2020-05-27 | Risk early warning method and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010462218.4A CN111612610A (en) | 2020-05-27 | 2020-05-27 | Risk early warning method and system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111612610A true CN111612610A (en) | 2020-09-01 |
Family
ID=72196161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010462218.4A Pending CN111612610A (en) | 2020-05-27 | 2020-05-27 | Risk early warning method and system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612610A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488569A (en) * | 2020-12-11 | 2021-03-12 | 绿瘦健康产业集团有限公司 | Risk early warning method and device and storage medium |
| CN113487183A (en) * | 2021-07-07 | 2021-10-08 | 苏州达家迎信息技术有限公司 | Method, device and storage medium for determining service resources in vertical service scene |
| CN113538020A (en) * | 2021-07-05 | 2021-10-22 | 深圳索信达数据技术有限公司 | Method and device for acquiring guest group feature association degree, storage medium and electronic device |
| CN114596011A (en) * | 2022-05-09 | 2022-06-07 | 未来地图(深圳)智能科技有限公司 | Enterprise data processing method based on artificial intelligence and related device |
| CN114647555A (en) * | 2022-05-13 | 2022-06-21 | 太平金融科技服务（上海）有限公司 | Data early warning method, device, equipment and medium based on multi-service system |
| CN114742430A (en) * | 2022-04-21 | 2022-07-12 | 平安科技（深圳）有限公司 | User retention early warning visualization method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110270647A1 (en) * | 2010-04-30 | 2011-11-03 | International Business Machines Corporation | Method and system for estimating risk in the financial metrics of a business case |
| WO2018090657A1 (en) * | 2016-11-18 | 2018-05-24 | 同济大学 | Bp_adaboost model-based method and system for predicting credit card user default |
| CN109583682A (en) * | 2018-10-11 | 2019-04-05 | 平安科技（深圳）有限公司 | Recognition methods, device and the computer equipment of business finance fraud risk |
| 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 |
| CN109829628A (en) * | 2019-01-07 | 2019-05-31 | 平安科技（深圳）有限公司 | Method for prewarning risk, device and computer equipment based on big data |
-
2020
- 2020-05-27 CN CN202010462218.4A patent/CN111612610A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110270647A1 (en) * | 2010-04-30 | 2011-11-03 | International Business Machines Corporation | Method and system for estimating risk in the financial metrics of a business case |
| WO2018090657A1 (en) * | 2016-11-18 | 2018-05-24 | 同济大学 | Bp_adaboost model-based method and system for predicting credit card user default |
| CN109583682A (en) * | 2018-10-11 | 2019-04-05 | 平安科技（深圳）有限公司 | Recognition methods, device and the computer equipment of business finance fraud risk |
| CN109829628A (en) * | 2019-01-07 | 2019-05-31 | 平安科技（深圳）有限公司 | Method for prewarning risk, device and computer equipment based on big data |
| 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 |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488569A (en) * | 2020-12-11 | 2021-03-12 | 绿瘦健康产业集团有限公司 | Risk early warning method and device and storage medium |
| CN113538020A (en) * | 2021-07-05 | 2021-10-22 | 深圳索信达数据技术有限公司 | Method and device for acquiring guest group feature association degree, storage medium and electronic device |
| CN113538020B (en) * | 2021-07-05 | 2024-03-26 | 深圳索信达数据技术有限公司 | Method and device for acquiring association degree of group of people features, storage medium and electronic device |
| CN113487183A (en) * | 2021-07-07 | 2021-10-08 | 苏州达家迎信息技术有限公司 | Method, device and storage medium for determining service resources in vertical service scene |
| CN113487183B (en) * | 2021-07-07 | 2024-01-16 | 苏州达家迎信息技术有限公司 | Method, device and storage medium for determining service resources in vertical service scene |
| CN114742430A (en) * | 2022-04-21 | 2022-07-12 | 平安科技（深圳）有限公司 | User retention early warning visualization method, device, equipment and storage medium |
| CN114742430B (en) * | 2022-04-21 | 2024-07-26 | 平安科技（深圳）有限公司 | User retention early warning visualization method, device, equipment and storage medium |
| CN114596011A (en) * | 2022-05-09 | 2022-06-07 | 未来地图(深圳)智能科技有限公司 | Enterprise data processing method based on artificial intelligence and related device |
| CN114596011B (en) * | 2022-05-09 | 2022-08-02 | 未来地图(深圳)智能科技有限公司 | Enterprise data processing method based on artificial intelligence and related device |
| CN114647555A (en) * | 2022-05-13 | 2022-06-21 | 太平金融科技服务（上海）有限公司 | Data early warning method, device, equipment and medium based on multi-service system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109325165B (en) | Network public opinion analysis method, device and storage medium | |
| CN109145216B (en) | Network public opinion monitoring method, device and storage medium | |
| CN109145215B (en) | Network public opinion analysis method, device and storage medium | |
| CN111612610A (en) | Risk early warning method and system, electronic equipment and storage medium | |
| CN109271512B (en) | Emotion analysis method, device and storage medium for public opinion comment information | |
| CN107818344A (en) | The method and system that user behavior is classified and predicted | |
| CN111552870A (en) | Object recommendation method, electronic device and storage medium | |
| CN112148843B (en) | Text processing method and device, terminal equipment and storage medium | |
| US11609959B2 (en) | System and methods for generating an enhanced output of relevant content to facilitate content analysis | |
| CN112818218B (en) | Information recommendation method, device, terminal equipment and computer readable storage medium | |
| CN111538931A (en) | Big data-based public opinion monitoring method and device, computer equipment and medium | |
| US20130282727A1 (en) | Unexpectedness determination system, unexpectedness determination method and program | |
| CN108647281B (en) | Webpage access risk detection and prompting method and device and computer equipment | |
| Ghankutkar et al. | Modelling machine learning for analysing crime news | |
| Gopal et al. | Machine learning based classification of online news data for disaster management | |
| CN110532229B (en) | Evidence file retrieval method, device, computer equipment and storage medium | |
| CN115062200A (en) | User behavior mining method and system based on artificial intelligence | |
| CN116610853A (en) | Search recommendation method, search recommendation system, computer device, and storage medium | |
| CN112182390B (en) | Mail pushing method, device, computer equipment and storage medium | |
| CN113505117A (en) | Data quality evaluation method, device, equipment and medium based on data indexes | |
| CN109491970B (en) | Bad picture detection method and device for cloud storage and storage medium | |
| CN116523622A (en) | Object risk prediction method and device, electronic equipment and storage medium | |
| CN114693409A (en) | Product matching method, device, computer equipment, storage medium and program product | |
| CN114491277A (en) | Knowledge tag endowing and applying method based on data cleaning | |
| CN113961811A (en) | Conversational recommendation method, device, equipment and medium based on event map |
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 |