CN110472660A - Abnormal deviation data examination method, device, computer equipment and storage medium - Google Patents
Abnormal deviation data examination method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110472660A CN110472660A CN201910613360.1A CN201910613360A CN110472660A CN 110472660 A CN110472660 A CN 110472660A CN 201910613360 A CN201910613360 A CN 201910613360A CN 110472660 A CN110472660 A CN 110472660A
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- account information
- model
- account
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
This application involves data analysis field, in particular to a kind of abnormal deviation data examination method, device, computer equipment and storage medium.The described method includes: receiving the detection request that first terminal is sent, account information and the corresponding financial data of account information are carried in detection request；It identifies the corresponding Account Type of account information, according to mapping relations preset between Account Type and detection project, obtains the corresponding detection project of account information；The corresponding Data Detection model of detection project is obtained, Data Detection model is model obtain according to financial data sample training, for identifying abnormal data from the financial data of input；By in financial data input data detection model, the abnormal data in financial data is identified by Data Detection model；Abnormal data is sent to first terminal.Data congestion in interaction can effectively be avoided using this method, improve the data-handling capacity of server.
Description
Technical field
This application involves computer technology application fields, more particularly to a kind of abnormal deviation data examination method, device, calculating
Machine equipment and storage medium.
Background technique
With the development of the social economy, bank and other financial mechanism by offer a loan to enterprise etc. between modes and enterprise into
Row cooperation, carrying out detection by the financial data to account will be seen that the operation situation of relevant enterprise, so as to effectively
Forecasting risk.
It traditionally, is usually to establish multiple detection nodes for the detection of abnormal data in financial data, server is by wealth
Business data are classified according to detection project, are assigned to multiple flow nodes and are detected respectively, then by server by the inspection of each node
Result is surveyed to be summarized, analyzed；However, traditional detection method is needed when server detects a large amount of financial datas
The data interaction with multiple nodes is established, data congestion is be easy to cause, influences the data-handling capacity of server.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of abnormal number that can be improved testing result accuracy
According to detection method, device, computer equipment and storage medium.
A kind of abnormal deviation data examination method, which comprises
The detection request that first terminal is sent is received, carries account information and the account information in the detection request
Corresponding financial data；
It identifies the corresponding Account Type of the account information, is closed according to mapping preset between Account Type and detection project
System, obtains the corresponding detection project of the account information；
The corresponding Data Detection model of the detection project is obtained, the Data Detection model is according to financial data sample
Model that training obtains, for identifying abnormal data from the financial data of input；
The financial data is inputted in the Data Detection model, the wealth is identified by the Data Detection model
Abnormal data in data of being engaged in；
The abnormal data is sent to the first terminal.
It is described in one of the embodiments, to obtain the corresponding Data Detection model of the detection project, comprising:
Trained decision-tree model is obtained, the corresponding detection project of the account information is inputted into the decision-tree model
In, obtain the corresponding characterization factor of the account information, wherein the decision-tree model is the sample training according to detection project
The model of the corresponding characterization factor of detection project obtain, that input is obtained according to decision tree logic；
Trained initial model is obtained, the initial detecting mould is adjusted according to the corresponding characterization factor of the account information
Type obtains Data Detection model.
The detection for receiving first terminal transmission is requested in one of the embodiments, is carried in the detection request
There are account information and the corresponding financial data of the account information, comprising:
The detection request that first terminal is sent is received, carries account information in the detection request；
Detect whether to have obtained the authorization of the corresponding account of the account information；
When having obtained the authorization of the corresponding account of the account information, the corresponding data storage of the account information is inquired
Address, and the corresponding financial data of the account information is obtained from the storage address.
In one of the embodiments, the authorization for detecting whether to have obtained the corresponding account of the account information it
Afterwards, further includes:
When not obtaining the authorization of the corresponding account of the account information, crawled according to the account information from predeterminated position
Finance media data corresponding with the account information, and financial data is extracted from the financial media data.
The exception identified by the Data Detection model in the financial data in one of the embodiments,
After data, further includes:
When in the abnormal data including degree of safety parameter, generates early warning and remind；
Early warning prompting is sent to the second terminal, and obtains the second terminal and is returned according to early warning prompting
The sustained release strategy returned；
The sustained release strategy is sent to the first terminal.
The exception identified by the Data Detection model in the financial data in one of the embodiments,
After data, further includes:
The financial data and the abnormal data are sent to second terminal, and the correction for receiving the second terminal refers to
It enables；
Preset mapping relations between the Account Type and detection project are corrected according to correction instruction.
A kind of anomaly data detection device, described device include:
Starting module is detected, for receiving the detection request of first terminal transmission, carries account in the detection request
Information and the corresponding financial data of the account information；
Detection project obtains module, for identification the corresponding Account Type of the account information, according to Account Type and inspection
Preset mapping relations between survey project obtain the corresponding detection project of the account information；
Model obtains module, for obtaining the corresponding Data Detection model of the detection project, the Data Detection model
It is model obtained according to financial data sample training, for identifying abnormal data from the financial data of input；
Model checking module is examined for inputting the financial data in the Data Detection model by the data
It surveys model and identifies the abnormal data in the financial data；
Data return module, for the abnormal data to be sent to the first terminal.
The model obtains module in one of the embodiments, comprising:
Trained decision-tree model is obtained, the corresponding detection project of the account information is inputted into the decision-tree model
In, obtain the corresponding characterization factor of the account information, wherein the decision-tree model is the sample training according to detection project
The model of the corresponding characterization factor of detection project obtain, that input is obtained according to decision tree logic；
Trained initial model is obtained, the initial detecting mould is adjusted according to the corresponding characterization factor of the account information
Type obtains Data Detection model.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes any of the above-described the method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of method described in any of the above embodiments is realized when row.
Above-mentioned abnormal deviation data examination method, device, computer equipment and storage medium, first terminal are needed to a certain account
Financial data when carrying out abnormality detection, the financial data of account information to be detected and account information is sent to server,
Server goes out several Data Detection models, the detection of each Data Detection model according to the financial data sample training being collected into
Project is not identical, when server needs the financial data to an account to carry out abnormality detection, directly acquires detection project, and
Corresponding model is called to be detected.In the above method, server can directly pass through Data Detection model, realize to finance
Effective detection of all data can effectively be kept away without obtaining the testing result of each node from multiple detection nodes in data
The data congestion in mutually is exempted from, the data-handling capacity of server is improved.
Detailed description of the invention
Fig. 1 is the application scenario diagram of abnormal deviation data examination method in one embodiment；
Fig. 2 is the flow diagram of abnormal deviation data examination method in one embodiment；
Fig. 3 is the flow diagram of step S202 in one embodiment；
Fig. 4 is the structural block diagram of anomaly data detection device in one embodiment；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Abnormal deviation data examination method provided by the embodiments of the present application can be applied in application environment as shown in Figure 1.Its
In, first terminal 102 is communicated with server 104 by network by network.When first terminal 102 is needed to a certain account
When being detected, the account information for needing to detect account and financial data are sent to server 104, server 104 starts different
Regular data detecting step obtains abnormal data and is back to first terminal 102.Second terminal 106 is then the management terminal of server,
The mistake that the testing result of server 104 can be inspected by random samples, and occurred in the detection of remediation server 104.Wherein, first terminal
102 and second terminal 106 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and just
Take formula wearable device, server 104 can with the server cluster of the either multiple servers compositions of independent server come
It realizes.
In one embodiment, as shown in Fig. 2, providing a kind of abnormal deviation data examination method, it is applied to Fig. 1 in this way
In server 104 for be illustrated, comprising the following steps:
S202 receives the detection request that first terminal is sent, carries account information and account information pair in detection request
The financial data answered.
Wherein, first terminal is can to lift the terminal of detection request to server by network connection with server；One
Under a scene, server can be to multiple financial companies and provide the business provider of anomaly data detection business, and each finance
Enterprise, can be using internal apparatus such as computer as first when needing to carry out abnormality detection the financial data of respective user
Terminal initiates detection request to server.
Detection request is detected to the financial data of an enterprise-level account, to obtain asking for abnormal data therein
It asks.Server can provide an interface to first terminal, after first terminal installs this interface, receive user's input by this interface
Information generate detection request.Optionally, the username and password etc. obtained when user can be by signing an agreement with server
Mode of proof logs in this interface, the corresponding account information of financial data to be detected is inputted on interface, and upload to be detected
Financial data, first terminal by the information inputted in interface generate detection request, be sent to server.Account information is corresponding
Main body may include enterprise or individual；When the corresponding main body of account information be enterprise, can by the full name of enterprise, number of registration or
Person address etc. is used as account information；It, can be by personal name, contact method, body when the corresponding main body of account information is individual
Part card number is equal to be used as account information.
Financial data is to reflect an enterprise financial and management state data whithin a period of time, such as can be enterprise
Year or the enterprise collected of quarterly financial statements or first terminal in the market occupancy volume of section time, sales volume or melt
Provide the data such as situation；It is also possible to the expenditure and income data of the personal savings account within the past period.
Specifically, when first terminal needs to detect the financial data of a certain account, detection request is generated, this detection request
In include the account information that can identify account identity and the financial data for reflecting this account financial situation whithin a period of time,
First terminal will test request and be sent to server, after server receives detection request, start following anomaly data detections
Step.
S204, the corresponding Account Type of identification account information, according to mapping preset between Account Type and detection project
Relationship obtains the corresponding detection project of account information.
Account Type is the type obtained after classifying to the corresponding account of account information, can be according to enterprise-level account
Industry, scope of the enterprise, enterprise nature etc. classify because of the usually corresponding account of reconciliation family information；And Account Type and detection
The mapping relations of project are rule of thumb or historical data analysis is set；For example, management terminal can first be set according to industry
The project that the account of each industry needs to detect is set, and each industry and detection project are stored to the setting position of server,
After server obtains the detection request that first terminal is sent, the corresponding industry of this account first can be judged according to account information, then
The detection project of the industry is inquired from setting position.
Detection project is the project detected to the corresponding financial data of account information；The corresponding wealth of each Account Type
Business data are different from, and server needs basis when the financial data of the account to types such as the same industry, scales detects
Different Account Types select corresponding detection project, just can accurately find abnormal data present in it；Therefore it needs to be arranged
Preset mapping relations between Account Type and detection project enable the server to identify the corresponding detection of each financial data
Mesh.If such as Account Type is investment concerns, is needed to scale of investment, earning rate, the risk mitigation period etc. in financial data
Project is as detection project；If Account Type is production class enterprise, can be by the production and sales situation of account monthly, product list
The projects such as valence and market occupancy volume are as detection project.
S206, obtains the corresponding Data Detection model of detection project, and Data Detection model is instructed according to financial data sample
Model getting, for identifying abnormal data from the financial data of input.
Wherein, Data Detection model is server end after having collected the corresponding history financial data of each detection project, is led to
The trained model obtained with machine learning training of big data is crossed, the rule that training obtains in Data Detection model, Neng Goushi are passed through
Abnormal data present in the financial data that Chu do not input；For example, when server gets and should detect to this financial data
Detection project include the projects such as scale of investment, earning rate, risk mitigation period, then Data Detection mould corresponding with detection project
Type, then should be classified for these detection projects to financial data, the operation such as anomalous identification.
Specifically, there are corresponding relationship between detection project and Data Detection model, server can train common detection
The corresponding Data Detection model of project can select suitable number after server gets detection project according to detection project
According to detection model.
S208 is identified in financial data input data detection model in financial data by Data Detection model
Abnormal data.
Abnormal data, which is in financial data, includes, reflects the data of the promise breaking of this account or overdue risk, financial data
In include multiple data item, the function of Data Detection model is the corresponding meaning of each data item in detection financial data, and is examined
Whether include the abnormal data that reflects this account risk, if comprising coming out disorder data recognition if surveying wherein.
Abnormal data is sent to first terminal by S210.
After server identifies the abnormal data in financial data by Data Detection model, these abnormal datas are returned
Back to first terminal, as the feedback of first terminal detection request, this time anomaly data detection process terminates, and first terminal can be with
Abnormal data is further analyzed in conjunction with the risk management situation of itself according to the abnormal data that server returns.
Optionally, for server after obtaining abnormal data, available preset report template adds to abnormal results
Report template is to generate examining report.Preset report template is the template for generating examining report, wherein should include account
The display form of data type and data that the examining report of financial data should include, the content of template can terminal demand
Situation carries out corresponding adjustment, and server can connect a template library, demand or terminal type (such as business automatically according to terminal
The types such as terminal, account terminal) selection template library in template.Examining report is the detection of above-mentioned abnormal deviation data examination method
As a result a kind of display form will generate in the testing result filling report template of financial data.
Above-mentioned abnormal deviation data examination method, when first terminal needs the financial data to a certain account to carry out abnormality detection,
The financial data of account information to be detected and account information is sent to server, server is according to the financial data being collected into
Sample training goes out several Data Detection models, and the detection project of each Data Detection model is not identical, in server needs pair
When the financial data of one account carries out abnormality detection, detection project is directly acquired, and corresponding model is called to be detected i.e.
It can.In the above method, server can directly pass through Data Detection model, realize effective inspection to all data in financial data
It surveys, without obtaining the testing result of each node from multiple detection nodes, can effectively avoid the data congestion in interaction, improve
The data-handling capacity of server.
In one embodiment, the corresponding Data Detection model of acquisition detection project in above-mentioned steps S206, can wrap
It includes: obtaining trained decision-tree model, by the corresponding detection project input decision-tree model of account information, obtain account letter
Cease corresponding characterization factor, wherein decision-tree model be obtained according to the sample training of detection project, according to decision tree logic
Obtain the model of the corresponding characterization factor of detection project of input；Trained initial model is obtained, it is corresponding according to account information
Characterization factor adjust initial detecting model, obtain Data Detection model.
Wherein, decision-tree model is with the tree structure of binary tree or multiway tree management detection project and Data Detection model
In characterization factor between associated model, be server end to the detection project sample in the history financial data analysis being collected into
After this is analyzed, the relationship between multiple detection projects and characterization factor is embodied by the bifurcated of decision tree, and feature because
Sub then setting is obtained to training on the corresponding decision node of bifurcated.For example, including investment rule to the detection project of an account
The working method of mould, decision-tree model is answered are as follows: and Boot Model, whether the registration information for detecting this account is accurate, if inaccurate,
Exit this time detection operation；If accurate, continue to test the scale of investment of account, for example, scale of investment may include 10,000,000,000 with
It is upper, between 5,000,000,000 to 10,000,000,000, between 1,000,000,000 to 5,000,000,000 and 1,000,000,000 hereinafter, can be arranged corresponding feature for each scale
The factor, the relationship between the root node and leaf node of decision tree can be more abundant by big data training.
Initial model is a kind of universal model of the corresponding Data Detection model of all detection projects, and server end is in training
When Data Detection model, the factor of wherein model corresponding with detection project is set as initial value or is emptied, obtains one
General initial model, server only needs to obtain the corresponding characterization factor of each detection project, by what is set in initial model
Initial value or the factor emptied replace with characterization factor, that is, produce corresponding Data Detection model.
Specifically, when corresponding relationship of the server between processing detection project and Data Detection model, certainly using one
Plan tree-model is come the relationship established between detection project and the characterization factor of model；The inspection that server is obtained by decision-tree model
The corresponding characterization factor of survey project, and corresponding factor initial value in initial model is replaced with characterization factor, by initial model tune
It is whole to be and the matched Data Detection model of this anomaly data detection.
In above-described embodiment, server only establishes a general initial model, realizes by adjusting the factor in model
Aimed detection is carried out to different detection projects, and saved by decision-tree model the corresponding feature of a variety of detection projects because
Son accurately can obtain characterization factor according to detection project, obtain the corresponding Data Detection model of detection project.
In one embodiment, Fig. 3, the step S202 in above-mentioned abnormal deviation data examination method are referred to: receiving first eventually
The detection request that end is sent, detects in request and carries account information and the corresponding financial data of account information, may include:
S2022 receives the detection request that first terminal is sent, carries account information in detection request.
Specifically, in above-mentioned step S202, for first terminal when sending detection request to server, need to only provide can
It identifies that this need to detect the account information of account, and needs the financial data detected that can obtain in the following manner.
S2024 detects whether the authorization for having obtained account information corresponding account.
Specifically, after server receives the detection request for carrying account information, account information is therefrom extracted, this account is detected
Whether information corresponding account in family allows server access internal data, i.e. whether detection book server has obtained account information pair
The authorization for the account answered；The account of authorization can be the account that cooperation agreement is signed with the server side of representative, and server can lead to
Cross whether inquiry account is cooperation account to detect whether to obtain its authorization.
S2026, when having obtained the authorization of account information corresponding account, inquiry account information corresponding data storage ground
Location, and the corresponding financial data of account information is obtained from address data memory.
It, can be from the data of account storing data if server inquires the authorization for having obtained account information corresponding account
The financial data that this detection needs is obtained in storage address, wherein address data memory can be the website of account side, inside
The address of database, cloud disk etc..It is corresponding with its address data memory that management terminal can establish a account information authorized
Address administration table, and this address management table is stored in management terminal or server, after server obtains account information,
Whether inquire in address administration table includes this account information, if so, then prove to have obtained the authorization of the corresponding account of account information,
The corresponding address data memory of account information is obtained from address administration table again.
In above-described embodiment, for the account authorized, server can be drawn from the address data memory of account automatically
Financial data is taken, since financial data derives from account side, server can pull accurate non-public number inside cooperation account
According to the accuracy of anomaly data detection is also higher.
In one embodiment, continuing with referring to Fig. 3, above-mentioned, step S2024 detects whether that having obtained account information corresponds to
Account authorization after, can also include:
S2028, when not obtaining the authorization of the corresponding account of account information, according to account information from predeterminated position crawl with
The corresponding financial media data of account information, and financial data is extracted from financial media data.
Wherein, predeterminated position is the positions such as the higher website of data accuracy, the database for being screened out, can be gold
The official website for melting finance and economics perhaps stock is also possible to the company official website of account or webpage or industry that industry inner evaluation is high
Shared data bank etc..
Financial media data is the number of the medias formats such as article relevant to the financial data of account, video, voice
According to, such as the article that changes of share price of enterprise, relevant video report of the relevant article of volume, enterprise etc. is occupied in market；And root
According to the different-format of financial media data, server can be extracted from financial media data using different contents extraction modes
The financial data of needs is detected out；For example, server can pass through semantics recognition skill if financial media data is text formatting
Art extracts in text and key content, recombinates out financial data；If financial media data is video or audio format, clothes
Audio-frequency unit can be converted into text formatting using speech recognition technology by business device, then be extracted by semantics recognition technology.Wherein,
Semantics recognition technology, which can be, identifies text by NLP (Natural Language Processing natural language processing) technology
Wen Yi in this.
It specifically, can be corresponding from phase according to account information if server does not obtain the authorization of the corresponding account of account information
It is relevant that the corresponding financial data of this account information in a period of time is crawled on the predeterminated positions such as the official Internet page of pass or database
Financial media data, it is contemplated that the authenticity of Webpage material, can emphasis refer to several official websites, server is from financial media number
According to middle extraction financial data, detecting step of the above-mentioned step S204 into S208 is continued to execute.
In above-described embodiment, for the account of unauthorized, the correlation for this account that server can be crawled from predeterminated position
Financial media data enriches analysis data, and the testing result of financial data is made to have more timeliness.
In one embodiment, being known in the step S208 in above-mentioned abnormal deviation data examination method by Data Detection model
It Chu can also not include: to generate early warning when including degree of safety parameter in abnormal data after the abnormal data in financial data
It reminds；Early warning prompting is sent to second terminal, and obtains second terminal and reminds the sustained release strategy returned according to early warning；It will sustained release
Strategy is sent to first terminal.
The application scenarios of abnormal deviation data examination method in referring to Figure 1, second terminal 106 are management terminal, can be right
The detection operation of server is adjusted, and the Data Detection result of management server；Second terminal 106 can be, but not limited to
Various personal computers, laptop, smart phone, tablet computer and portable wearable device.
Wherein, degree of safety parameter be in abnormal data may the representative side to first terminal and the cooperation between account cause
The parameter of influence can be adjusted according to type of cooperation；Such as when type of cooperation be loan intermediate item, then can choose inspection
Parameter relevant to the upper annual earnings data of account, share price change conditions of marketing enterprises etc. in result are surveyed to join as degree of safety
Number；Then preset value is the value for limiting the change conditions of numerical value of degree of safety parameter, and format is consistent with the numerical value of degree of safety parameter,
The preset value of the upper annual earnings data of such as account can be set to the mean value not less than similar size enterprise in industry；For
The enterprise of different industries and scale, identical case or volatility are to its influence degree difference, therefore preset value can be with
It is adjusted according to scope of the enterprise and industrial nature.
Early warning, which is reminded, to be can be for reminding the account of this detection of management terminal there may be the information of Cooperation Risk
The software interactive data of server and management terminal can also use the forms such as mail or wechat message.
Sustained release strategy is then that second terminal reminds early warning the solution made, and management terminal can be according to the row of account
Industry and property, the strategy of reflection and suggestion that the risk current to account or potential risk are made；For example, if the receipts of account last year
Benefit then suggests that first terminal is reduced to the investment of account or amount of the loan etc. lower than the mean value of similar size enterprise in industry
Deng.
Specifically, the testing result obtained for anomaly data detection, server can be according to the representative sides of first terminal
Cooperation between account corresponding with account information to carry out automatic Evaluation to the degree of safety parameter in testing result, for existing
The cooperation account of risk carries out risk prompting, and second terminal simultaneously reminds the representative side for first terminal to send sustained release plan according to risk
Slightly.
In above-described embodiment, in conjunction with actual collaboration scenario, risk judgment is carried out to the testing result of anomaly data detection,
And risk mitigation suggestion is provided for first terminal to high risk account.
In one embodiment, being known in the step S208 in above-mentioned abnormal deviation data examination method by Data Detection model
It Chu not be after the abnormal data in financial data, further includes: financial data and abnormal data are sent to second terminal, and receive the
The correction of two terminals instructs；Preset mapping relations between Account Type and detection project are corrected according to correcting to instruct.
Wherein, correcting instruction is that there are mistakes in second terminal discovery testing result, is proposed to the account stored in server
The instruction that preset mapping relations are corrected between family type and detection project；It can be what second terminal was sent to server
Preset mapping relations between the Account Type and detection project of update, after server receives, Account Type and inspection with update
Preset mapping relations replace locally stored mapping relations between survey project.
Specifically, it after server completes anomaly data detection every time, result can be will test is sent to second terminal and be deposited
Storage, second terminal can carry out secondary detection to financial data, and whether the detection operation to judge server is accurate, if inaccurate
Really, then preset mapping relations between the Account Type and detection project stored in server can be adjusted.Optionally,
After two terminals obtain the testing result that server is sent, it can classify according to industry, enterprise nature etc. to testing result, then
Testing result in each classification is inspected by random samples, the efficiency of secondary detection is improved.
In above-described embodiment, second terminal carries out secondary detection to financial data, and timely correction server is in abnormal data
Mistake in detection operation.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of anomaly data detection device, comprising: detection starting module
100, detection project obtains module 200, model obtains module 300, model checking module 400 and data return module 500,
In:
Starting module 100 is detected, for receiving the detection request of first terminal transmission, carries account letter in detection request
Cease financial data corresponding with account information.
Detection project obtains module 200, for identification the corresponding Account Type of account information, according to Account Type and detection
Preset mapping relations between project obtain the corresponding detection project of account information.
Model obtains module 300, and for obtaining the corresponding Data Detection model of detection project, Data Detection model is basis
Model that financial data sample training obtains, for identifying abnormal data from the financial data of input.
Model checking module 400, for being identified by Data Detection model by financial data input data detection model
Abnormal data in financial data out.
Data return module 500, for abnormal data to be sent to first terminal.
In one embodiment, the model in above-mentioned anomaly data detection device obtains module 300, may include:
Decision tree analysis unit, it is for obtaining trained decision-tree model, the corresponding detection project of account information is defeated
Enter in decision-tree model, obtain the corresponding characterization factor of account information, wherein decision-tree model is the sample according to detection project
The model of the corresponding characterization factor of detection project that training obtains, that input is obtained according to decision tree logic.
Data Detection model generation unit, for obtaining trained initial model, according to the corresponding feature of account information
The factor adjusts initial detecting model, obtains Data Detection model.
In one embodiment, the detection starting module 100 in above-mentioned anomaly data detection device may include:
Request reception unit carries account information in detection request for receiving the detection request of first terminal transmission.
Detection unit is authorized, for detecting whether having obtained the authorization of the corresponding account of account information.
Authorisation process unit, for inquiring account information pair when having obtained the authorization of the corresponding account of account information
The address data memory answered, and the corresponding financial data of account information is obtained from storage address.
In one embodiment, the detection starting module 100 stated in anomaly data detection device can also include:
Unauthorized processing unit, for when not obtaining the authorization of the corresponding account of account information, according to account information from
Predeterminated position crawls financial media data corresponding with account information, and extracts financial data from financial media data.
In one embodiment, above-mentioned anomaly data detection device can also include:
Warning module is reminded for when in abnormal data including degree of safety parameter, generating early warning.
Sustained release strategy obtains module, for early warning prompting to be sent to second terminal, and obtains second terminal according to early warning
Remind the sustained release strategy returned.
It is sustained tactful sending module, is sent to first terminal for strategy will to be sustained.
In one embodiment, above-mentioned anomaly data detection device can also include:
Command reception module is corrected, for financial data and abnormal data to be sent to second terminal, and receives second eventually
The correction at end instructs.
Module is corrected, corrects preset mapping relations between Account Type and detection project for instructing according to correction.
Specific about anomaly data detection device limits the limit that may refer to above for abnormal deviation data examination method
Fixed, details are not described herein.Modules in above-mentioned anomaly data detection device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 5.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing anomaly data detection data.The network interface of the computer equipment is used for and external terminal
It is communicated by network connection.To realize a kind of abnormal deviation data examination method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, which performs the steps of when executing computer program receives the detection request that first terminal is sent, inspection
It surveys in request and carries account information and the corresponding financial data of account information；Identify the corresponding Account Type of account information, root
According to mapping relations preset between Account Type and detection project, the corresponding detection project of account information is obtained；Obtain detection
The corresponding Data Detection model of mesh, Data Detection model be obtained according to financial data sample training, for the wealth from input
The model of abnormal data is identified in business data；By in financial data input data detection model, known by Data Detection model
It Chu not abnormal data in financial data；Abnormal data is sent to first terminal.
In one embodiment, processor executes the corresponding Data Detection of acquisition detection project realized when computer program
Model, comprising: obtain trained decision-tree model, by the corresponding detection project input decision-tree model of account information, obtain
To the corresponding characterization factor of account information, wherein decision-tree model be obtained according to the sample training of detection project, according to certainly
Plan tree logic obtains the model of the corresponding characterization factor of detection project of input；Trained initial model is obtained, according to account
The corresponding characterization factor of information adjusts initial detecting model, obtains Data Detection model.
In one embodiment, the detection that processor executes that the reception first terminal realized when computer program is sent is asked
It asks, carries account information and the corresponding financial data of account information in detection request, comprising: receive the inspection that first terminal is sent
Request is surveyed, carries account information in detection request；Detect whether to have obtained the authorization of the corresponding account of account information；When having obtained
When obtaining the authorization of the corresponding account of account information, the corresponding address data memory of inquiry account information, and obtained from storage address
The corresponding financial data of account information.
In one embodiment, processor executes the account information that detects whether to have obtained realized when computer program and corresponds to
Account authorization after, further includes: when not obtaining the authorization of the corresponding account of account information, according to account information from default
Position crawls financial media data corresponding with account information, and extracts financial data from financial media data.
In one embodiment, that realizes when processor execution computer program identifies finance by Data Detection model
After abnormal data in data, further includes: when in abnormal data including degree of safety parameter, generate early warning and remind；By early warning
Prompting is sent to second terminal, and obtains second terminal and remind the sustained release strategy returned according to early warning；Sustained release strategy is sent to
First terminal.
In one embodiment, that realizes when processor execution computer program identifies finance by Data Detection model
After abnormal data in data, further includes: financial data and abnormal data are sent to second terminal, and receive second terminal
Correction instruction；Preset mapping relations between Account Type and detection project are corrected according to correcting to instruct.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor receives the detection request that first terminal is sent, and carries in detection request
Account information and the corresponding financial data of account information；The corresponding Account Type of account information is identified, according to Account Type and inspection
Preset mapping relations between survey project obtain the corresponding detection project of account information；Obtain the corresponding data inspection of detection project
Survey model, Data Detection model be obtained according to financial data sample training, for being identified from the financial data of input
The model of abnormal data；By in financial data input data detection model, identified in financial data by Data Detection model
Abnormal data；Abnormal data is sent to first terminal.
In one embodiment, the corresponding data inspection of the acquisition detection project realized when computer program is executed by processor
Survey model, comprising: trained decision-tree model is obtained, the corresponding detection project of account information is inputted in decision-tree model,
Obtain the corresponding characterization factor of account information, wherein decision-tree model be obtained according to the sample training of detection project, according to
Decision tree logic obtains the model of the corresponding characterization factor of detection project of input；Trained initial model is obtained, according to account
Information corresponding characterization factor in family adjusts initial detecting model, obtains Data Detection model.
In one embodiment, the detection that the reception first terminal realized when computer program is executed by processor is sent is asked
It asks, carries account information and the corresponding financial data of account information in detection request, comprising: receive the inspection that first terminal is sent
Request is surveyed, carries account information in detection request；Detect whether to have obtained the authorization of the corresponding account of account information；When having obtained
When obtaining the authorization of the corresponding account of account information, the corresponding address data memory of inquiry account information, and obtained from storage address
The corresponding financial data of account information.
In one embodiment, detecting whether of realizing when computer program is executed by processor has obtained account information pair
After the authorization for the account answered, further includes: when not obtaining the authorization of the corresponding account of account information, according to account information from pre-
If position crawls financial media data corresponding with account information, and extracts financial data from financial media data.
In one embodiment, that realizes when computer program is executed by processor identifies wealth by Data Detection model
After abnormal data in data of being engaged in, further includes: when in abnormal data including degree of safety parameter, generate early warning and remind；It will be pre-
Alert remind is sent to second terminal, and obtains second terminal and remind the sustained release strategy returned according to early warning；Sustained release strategy is sent
To first terminal.
In one embodiment, that realizes when computer program is executed by processor identifies wealth by Data Detection model
After abnormal data in data of being engaged in, further includes: financial data and abnormal data are sent to second terminal, and receive second eventually
The correction at end instructs；Preset mapping relations between Account Type and detection project are corrected according to correcting to instruct.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of abnormal deviation data examination method, which comprises
The detection request that first terminal is sent is received, account information is carried in the detection request and the account information is corresponding
Financial data；
Identify the corresponding Account Type of the account information, according to mapping relations preset between Account Type and detection project,
Obtain the corresponding detection project of the account information；
The corresponding Data Detection model of the detection project is obtained, the Data Detection model is according to financial data sample training
Model obtaining, for identifying abnormal data from the financial data of input；
The financial data is inputted in the Data Detection model, the financial number is identified by the Data Detection model
Abnormal data in；
The abnormal data is sent to the first terminal.
2. the method according to claim 1, wherein described obtain the corresponding Data Detection mould of the detection project
Type, comprising:
Trained decision-tree model is obtained, the corresponding detection project of the account information is inputted in the decision-tree model,
Obtain the corresponding characterization factor of the account information, wherein the decision-tree model is obtained according to the sample training of detection project
The model of the corresponding characterization factor of detection project arrive, that input is obtained according to decision tree logic；
Trained initial model is obtained, the initial detecting model is adjusted according to the corresponding characterization factor of the account information,
Obtain Data Detection model.
3. the method according to claim 1, wherein the detection request for receiving first terminal and sending, described
Account information and the corresponding financial data of the account information are carried in detection request, comprising:
The detection request that first terminal is sent is received, carries account information in the detection request；
Detect whether to have obtained the authorization of the corresponding account of the account information；
When having obtained the authorization of the corresponding account of the account information, the account information corresponding data storage ground is inquired
Location, and the corresponding financial data of the account information is obtained from the storage address.
4. according to the method described in claim 3, it is characterized in that, it is described detect whether to have obtained the account information it is corresponding
After the authorization of account, further includes:
When not obtaining the authorization of the corresponding account of the account information, crawled according to the account information from predeterminated position and institute
The corresponding financial media data of account information is stated, and extracts financial data from the financial media data.
5. the method according to claim 1, which is characterized in that described to pass through the Data Detection model
After identifying the abnormal data in the financial data, further includes:
When in the abnormal data including degree of safety parameter, generates early warning and remind；
Early warning prompting is sent to the second terminal, and obtains the second terminal and return is reminded according to the early warning
Sustained release strategy；
The sustained release strategy is sent to the first terminal.
6. the method according to claim 1, which is characterized in that described to pass through the Data Detection model
After identifying the abnormal data in the financial data, further includes:
The financial data and the abnormal data are sent to second terminal, and receive the correction instruction of the second terminal；
Preset mapping relations between the Account Type and detection project are corrected according to correction instruction.
7. a kind of anomaly data detection device, which is characterized in that described device includes:
Starting module is detected, for receiving the detection request of first terminal transmission, carries account information in the detection request
Financial data corresponding with the account information；
Detection project obtains module, for identification the corresponding Account Type of the account information, according to Account Type and detection
Preset mapping relations between mesh obtain the corresponding detection project of the account information；
Model obtains module, and for obtaining the corresponding Data Detection model of the detection project, the Data Detection model is root
Model being obtained according to financial data sample training, for identifying abnormal data from the financial data of input；
Model checking module passes through the Data Detection mould for inputting the financial data in the Data Detection model
Type identifies the abnormal data in the financial data；
Data return module, for the abnormal data to be sent to the first terminal.
8. device according to claim 7, which is characterized in that the model obtains module, comprising:
Trained decision-tree model is obtained, the corresponding detection project of the account information is inputted in the decision-tree model,
Obtain the corresponding characterization factor of the account information, wherein the decision-tree model is obtained according to the sample training of detection project
The model of the corresponding characterization factor of detection project arrive, that input is obtained according to decision tree logic；
Trained initial model is obtained, the initial detecting model is adjusted according to the corresponding characterization factor of the account information,
Obtain Data Detection model.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910613360.1A CN110472660A (en) | 2019-07-09 | 2019-07-09 | Abnormal deviation data examination method, device, computer equipment and storage medium |
| PCT/CN2020/086956 WO2021004132A1 (en) | 2019-07-09 | 2020-04-26 | Abnormal data detection method, apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910613360.1A CN110472660A (en) | 2019-07-09 | 2019-07-09 | Abnormal deviation data examination method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110472660A true CN110472660A (en) | 2019-11-19 |
Family
ID=68507195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910613360.1A Pending CN110472660A (en) | 2019-07-09 | 2019-07-09 | Abnormal deviation data examination method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110472660A (en) |
| WO (1) | WO2021004132A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369177A (en) * | 2020-03-30 | 2020-07-03 | 深圳市云智融科技有限公司 | Financial data analysis method and device and computer readable storage medium |
| CN111612040A (en) * | 2020-04-24 | 2020-09-01 | 平安直通咨询有限公司上海分公司 | Financial data anomaly detection method based on isolated forest algorithm and related device |
| CN111882415A (en) * | 2020-07-24 | 2020-11-03 | 未鲲(上海)科技服务有限公司 | Training method and related device of quality detection model |
| CN112016600A (en) * | 2020-08-14 | 2020-12-01 | 中国石油大学(北京) | Pipeline abnormity identification method, device and system |
| WO2021004132A1 (en) * | 2019-07-09 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Abnormal data detection method, apparatus, computer device, and storage medium |
| CN112559487A (en) * | 2020-12-03 | 2021-03-26 | 黎红 | Financial data analysis early warning method and device, computer equipment and storage medium |
| CN113569910A (en) * | 2021-06-25 | 2021-10-29 | 石化盈科信息技术有限责任公司 | Account type identification method and device, computer equipment and storage medium |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112953904B (en) * | 2021-01-27 | 2022-11-18 | 北京达佳互联信息技术有限公司 | Abnormality detection method, abnormality detection device, server, and storage medium |
| CN112818235B (en) * | 2021-02-03 | 2023-07-21 | 招联消费金融有限公司 | Method and device for identifying illegal user based on association characteristics and computer equipment |
| CN113328908B (en) * | 2021-05-10 | 2022-07-26 | 广东电网有限责任公司广州供电局 | Abnormal data detection method and device, computer equipment and storage medium |
| CN113344621B (en) * | 2021-05-31 | 2023-08-04 | 北京百度网讯科技有限公司 | Determination method and device for abnormal account and electronic equipment |
| CN113435517B (en) * | 2021-06-29 | 2023-06-02 | 平安科技（深圳）有限公司 | Abnormal data point output method, device, computer equipment and storage medium |
| CN113489773B (en) * | 2021-06-30 | 2022-11-04 | 未鲲(上海)科技服务有限公司 | Data access method, device, equipment and medium |
| CN113554093B (en) * | 2021-07-23 | 2024-02-13 | ***股份有限公司 | Prediction model training and account value prediction method, device, equipment and medium |
| CN114118949B (en) * | 2021-11-09 | 2023-06-27 | 北京市燃气集团有限责任公司 | Information processing system and method for bill |
| CN117114911B (en) * | 2023-10-25 | 2024-01-30 | 北京中企导航技术服务有限公司 | Automatic statistical settlement method and system for financial statement |
| CN117473048B (en) * | 2023-12-28 | 2024-03-01 | 长春职业技术学院 | Financial abnormal data monitoring and analyzing system and method based on data mining |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006252259A (en) * | 2005-03-11 | 2006-09-21 | Ntt Data Corp | Data analysis apparatus and method |
| JP2009164714A (en) * | 2007-12-28 | 2009-07-23 | Duaxes Corp | Bot detector |
| CA2704864A1 (en) * | 2010-06-07 | 2010-08-16 | S. Bhinder Mundip | Method and system for controlling access to a monetary valued account |
| US20110055072A1 (en) * | 2009-08-31 | 2011-03-03 | Bank Of America Corporation | Event processing for detection of suspicious financial activity |
| CN104426859A (en) * | 2013-08-26 | 2015-03-18 | 深圳市腾讯计算机***有限公司 | Request authorization method and apparatus, and server |
| CN108198063A (en) * | 2018-01-20 | 2018-06-22 | 菏泽学院 | A kind of financial management system |
| CN108629675A (en) * | 2018-04-27 | 2018-10-09 | 信阳师范学院 | A kind of Multiple trees financial alert method |
| CN109376995A (en) * | 2018-09-18 | 2019-02-22 | 平安科技（深圳）有限公司 | Financial data methods of marking, device, computer equipment and storage medium |
| CN109635992A (en) * | 2018-10-22 | 2019-04-16 | 成都万江港利科技股份有限公司 | A kind of internet of things equipment operating analysis diagnosis algorithm based on big data |
| CN109858734A (en) * | 2018-12-14 | 2019-06-07 | 宋晓飞 | A kind of financial risk early warning management system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140172748A1 (en) * | 2012-12-19 | 2014-06-19 | Chicago Mercantile Exchange Inc. | Liquidity Margin |
| CN110472660A (en) * | 2019-07-09 | 2019-11-19 | 深圳壹账通智能科技有限公司 | Abnormal deviation data examination method, device, computer equipment and storage medium |
-
2019
- 2019-07-09 CN CN201910613360.1A patent/CN110472660A/en active Pending
-
2020
- 2020-04-26 WO PCT/CN2020/086956 patent/WO2021004132A1/en active Application Filing
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006252259A (en) * | 2005-03-11 | 2006-09-21 | Ntt Data Corp | Data analysis apparatus and method |
| JP2009164714A (en) * | 2007-12-28 | 2009-07-23 | Duaxes Corp | Bot detector |
| US20110055072A1 (en) * | 2009-08-31 | 2011-03-03 | Bank Of America Corporation | Event processing for detection of suspicious financial activity |
| CA2704864A1 (en) * | 2010-06-07 | 2010-08-16 | S. Bhinder Mundip | Method and system for controlling access to a monetary valued account |
| CN104426859A (en) * | 2013-08-26 | 2015-03-18 | 深圳市腾讯计算机***有限公司 | Request authorization method and apparatus, and server |
| CN108198063A (en) * | 2018-01-20 | 2018-06-22 | 菏泽学院 | A kind of financial management system |
| CN108629675A (en) * | 2018-04-27 | 2018-10-09 | 信阳师范学院 | A kind of Multiple trees financial alert method |
| CN109376995A (en) * | 2018-09-18 | 2019-02-22 | 平安科技（深圳）有限公司 | Financial data methods of marking, device, computer equipment and storage medium |
| CN109635992A (en) * | 2018-10-22 | 2019-04-16 | 成都万江港利科技股份有限公司 | A kind of internet of things equipment operating analysis diagnosis algorithm based on big data |
| CN109858734A (en) * | 2018-12-14 | 2019-06-07 | 宋晓飞 | A kind of financial risk early warning management system |
Non-Patent Citations (2)
| Title |
|---|
| SHU-CHUN LI ET AL.: "Discovery of Abnormal Financial Behavior in a Dynamic Finance Environment with Hierarchical Self-Organizing Mapping", 《 THE 2ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND DATA MINING》, pages 450 - 455 * |
| 林翠珑等: "大数据环境下医院财务管理的探析", 《中国卫生经济》, vol. 37, no. 12, pages 100 - 101 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021004132A1 (en) * | 2019-07-09 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Abnormal data detection method, apparatus, computer device, and storage medium |
| CN111369177A (en) * | 2020-03-30 | 2020-07-03 | 深圳市云智融科技有限公司 | Financial data analysis method and device and computer readable storage medium |
| CN111612040A (en) * | 2020-04-24 | 2020-09-01 | 平安直通咨询有限公司上海分公司 | Financial data anomaly detection method based on isolated forest algorithm and related device |
| CN111612040B (en) * | 2020-04-24 | 2024-04-30 | 平安直通咨询有限公司上海分公司 | Financial data anomaly detection method and related device based on isolated forest algorithm |
| CN111882415A (en) * | 2020-07-24 | 2020-11-03 | 未鲲(上海)科技服务有限公司 | Training method and related device of quality detection model |
| CN112016600A (en) * | 2020-08-14 | 2020-12-01 | 中国石油大学(北京) | Pipeline abnormity identification method, device and system |
| CN112559487A (en) * | 2020-12-03 | 2021-03-26 | 黎红 | Financial data analysis early warning method and device, computer equipment and storage medium |
| CN113569910A (en) * | 2021-06-25 | 2021-10-29 | 石化盈科信息技术有限责任公司 | Account type identification method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021004132A1 (en) | 2021-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110472660A (en) | Abnormal deviation data examination method, device, computer equipment and storage medium | |
| Campbell et al. | Macroeconomic drivers of bond and equity risks | |
| CN109992601B (en) | To-do information pushing method and device and computer equipment | |
| US11494180B2 (en) | Systems and methods for providing predictive quality analysis | |
| US11367008B2 (en) | Artificial intelligence techniques for improving efficiency | |
| CN114971879B (en) | Information processing system and information processing method | |
| US9508100B2 (en) | Methods and apparatus for on-line analysis of financial accounting data | |
| CN110609954A (en) | Data acquisition method and device, computer equipment and storage medium | |
| KR20210058229A (en) | Method and server for providing loan service based on inventory and sales analysys | |
| US20230092559A1 (en) | Systems and methods for unstructured data processing | |
| US10740772B2 (en) | Systems and methods for forecasting based upon time series data | |
| Keathley-Herring | An approach to quantify the factors that affect performance measurement system implementation | |
| CN111967999A (en) | Investigation processing method, device, computer equipment and storage medium | |
| JP7371690B2 (en) | Analysis system, device, control method, and program | |
| CN115587898B (en) | Financial data secure sharing method and system based on cloud service | |
| US20220327635A1 (en) | Methods and systems for efficient delivery of accounting and corporate planning services | |
| KR20130135810A (en) | System and a method for trading stocks automatically based on opinion mining, and a storage medium storing a program thereof | |
| Perico Ortiz | Measuring Economic Policy Uncertainty in Colombia: a News Based Approach | |
| CN113298575A (en) | Method, system, equipment and storage medium for trademark value batch evaluation | |
| CN113724064B (en) | Parameter determination method and device based on artificial intelligence and electronic equipment | |
| Santos | The impact of big data and data analytics in external auditing procedures | |
| CN116050366A (en) | Original document management method and system | |
| CN117035956A (en) | Merchant risk inspection method, operation terminal, wind control terminal and storage medium | |
| CN116166912A (en) | Information processing method, information processing device, storage medium and electronic equipment | |
| CN116861087A (en) | Customer intelligent recommendation method, system, equipment and medium based on large language model |
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 |