CN107832429A - audit data processing method and system - Google Patents
audit data processing method and system Download PDFInfo
- Publication number
- CN107832429A CN107832429A CN201711124937.XA CN201711124937A CN107832429A CN 107832429 A CN107832429 A CN 107832429A CN 201711124937 A CN201711124937 A CN 201711124937A CN 107832429 A CN107832429 A CN 107832429A
- Authority
- CN
- China
- Prior art keywords
- audit
- data
- risk
- forecast model
- audit data
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Abstract
The present invention relates to a kind of audit data processing method and system, and methods described includes：Extracted from historical auditing database by the Audit data of the audit target, data cleansing is carried out to the Audit data, and carry out exploratory analysis and obtain data characteristics；The audit risk data are sampled and are divided into test set and training set, is closed according to the data characteristics in training set and establishes forecast model, and forecast model is trained to obtain risk forecast model using test set；Risk profile is carried out to the Audit data of the audit target of input using the risk forecast model, identifies the risk classifications of Audit data.Technical scheme can predict the risk classifications of Audit data exactly, realize and the possibility of all kinds of audit risks present in the audit target is predicted, the audit treatment effect to Audit data is improved, significant data support is provided for the expansion of audit work.
Description
Technical field
The present invention relates to data mining technology field, more particularly to a kind of audit data processing method and system.
Background technology
Information age brings new challenge and risk to audit work, and audit evidence is hidden in mass data, examines
Track increasingly complex is counted, in order to solve the seriously asymmetric problem of the information between auditor and unit under auditing, audit
Risk management introduces computer technology.
Audit data excavation is the general designation of application of the Data Mining knowledge in audit work, is auditing risk management
One of important branch of Import computer technology in work.It is often under cover valuable to auditing in the Audit data of magnanimity
Information, by data digging method and technology, these useful information are found and disclose, and audit work offer data support is
The direction of Audit data digger author effort always.Current Audit data is excavated based on statistical analysis and sign discovery,
Mainly there is following feature：I.e. using unit under auditing financial data as single analysis object；By the experience of modeling personnel
More with professional skill limitation, modeling efficiency is low, and in the difficult discovery mass data of the model established the problem of logic complexity.
Mainly based on noting abnormalities, analyzed more using the Audit data in different time points as independent individual.
Based on above feature, in excavation processing is carried out to Audit data, it is difficult to predict the wind of Audit data exactly
Dangerous type, so as to have impact on the audit treatment effeciency to Audit data.
The content of the invention
Based on this, it is necessary to the problem of for being difficult to detect the abnormal data in Audit data exactly, there is provided a kind of
Audit data processing method and system.
A kind of audit data processing method, comprises the following steps：
Extracted from historical auditing database by the Audit data of the audit target, it is clear to carry out data to the Audit data
Wash, and carry out exploratory analysis and obtain data characteristics；
The audit risk data are sampled and are divided into test set and training set, are existed according to the data characteristics
Training set, which closes, establishes forecast model, and forecast model is trained to obtain risk forecast model using test set；
Risk profile, identification audit number are carried out to the Audit data of the audit target of input using the risk forecast model
According to risk classifications.
A kind of audit data processing system, including：
Data acquisition module, for being extracted from historical auditing database by the Audit data of the audit target, examine described
Carry out data cleansing is counted, and carries out exploratory analysis and obtains data characteristics；
Data modeling module, test set and training set are divided into for being sampled to the audit risk data,
Closed according to the data characteristics in training set and establish forecast model, and forecast model is trained to obtain using test set
Risk forecast model；
Risk profile module, for entering sector-style to the Audit data of the audit target of input using the risk forecast model
Danger prediction, identify the risk classifications of Audit data.
Above-mentioned audit data processing method and system, by extracting, Audit data carries out data cleansing and exploratory analysis obtains
To data characteristics, then audit risk data are sampled with division and establishes forecast model and is trained to obtain risk profile mould
Type, recycle the risk forecast model to carry out risk profile to the Audit data of the audit target of input, identify Audit data
Risk classifications；The technical scheme can predict the risk classifications of Audit data exactly, realize to present in the audit target
The possibility of all kinds of audit risks is predicted, and improves the audit treatment effect to Audit data, is the expansion of audit work
Significant data support is provided.
A kind of computer equipment, including memory, processor and be stored on the memory and can be in the processing
The computer program run on device, such as above-mentioned audit data processing side is realized described in the computing device during computer program
Method.
Above computer equipment, by the computer program run on the processor, realize to by audit target institute
There is a possibility that all kinds of audit risks are predicted.
A kind of computer-readable storage medium, is stored thereon with computer program, is realized as above when the program is executed by processor
State audit data processing method.
Above computer storage medium, by the computer program of its storage, realize to each present in the audit target
The possibility of class audit risk is predicted.
Brief description of the drawings
Fig. 1 is the audit data processing method flow diagram of one embodiment；
Fig. 2 is the step S10 of one embodiment flow chart；
Fig. 3 is the step S20 of one embodiment flow chart；
Fig. 4 is the audit data processing system structure diagram of one embodiment；
Fig. 5 is the forecasting system structural representation of the audit data processing method based on the present invention；
Fig. 6 is the schematic diagram of the forecasting system modules of one embodiment.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The term " comprising " and " having " of the embodiment of the present invention and their any deformations, it is intended that cover non-exclusive
Comprising.Such as contain series of steps or the process, method, system, product or equipment of (module) unit are not limited to
The step of listing or unit, but alternatively also including the step of not listing or unit, or alternatively also include for these
The intrinsic other steps of process, method, product or equipment or unit.
Referenced herein " embodiment " is it is meant that the special characteristic, structure or the characteristic that describe can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiment.
Referenced herein " multiple " refer to two or more."and/or", the association for describing affiliated partner are closed
System, expression may have three kinds of relations, for example, A and/or B, can be represented：Individualism A, while A and B be present, individualism
These three situations of B.It is a kind of relation of "or" that character "/", which typicallys represent forward-backward correlation object,.
With reference to shown in figure 1, Fig. 1 is the audit data processing method flow diagram of one embodiment, is comprised the following steps：
S10, is extracted from historical auditing database by the Audit data of the audit target, and data are carried out to the Audit data
Cleaning, and carry out exploratory analysis and obtain data characteristics.
In above-mentioned steps, it is directed primarily to by the collection and processing of the historical auditing data of the audit target.Audited with one
Exemplified by unit, the financial rule that the unit is reacted by the audit issues that unit under auditing history occurs from side perfects degree
With the ability of financial staff, its historical development trend can reflect unit under auditing financial rule process of construction and each stage
Existing audit risk.Unit under auditing historical auditing risk data is analyzed, excavates its changing rule, so as to
The audit issues being likely to occur under the current financial rule of prediction unit under auditing.
In one embodiment, with reference to shown in figure 2, Fig. 2 is the step S10 of one embodiment flow chart, can be included
Following steps：
S101, extract by the Audit data of the audit target, can include as follows from historical auditing database：
(Extract-Transform-Load, describe to pass through data from source terminal and extract, change, being loaded onto using ETL
The process of destination) instrument extracts from historical auditing database by the Audit data of the audit target, the Audit data turned
It is changed to unified form to obtain by the historical auditing risk data of the audit target, by historical auditing risk data storage to analysis number
According in storehouse.
Specifically, ETL tool data pooling functions can be used, unit under auditing is extracted from historical auditing database and is examined
Result data is counted, unified form, unit under auditing historical auditing risk data is formed, stores in analytical database, the quilt
Unit historical auditing risk data of auditing includes audit issues description, problem discovery time, the frequency found.Historical auditing data
Storehouse corresponds to multiple systems, multiple data storage storehouses.Data structure is not quite identical between each thesaurus.ETL data merge work(
Can, the data pick-up of multiple thesaurus is come, unifies its structure, is aggregated into a unit under auditing historical auditing risk data
Table, and it is deposited into analytical database.
S102, data cleansing is carried out to the Audit data, may include steps of：
Investigation processing is carried out to the content that record is repeated in the Audit data, and delete processing is carried out to duplicate contents；
Exception in the Audit data is checked, abnormal number is determined according to historical auditing result database and business tine
According to；Abnormal data is modified according to the result of the investigation processing.
Specifically, the cleaning to Audit data includes investigation repetition, abnormality detection etc.；Repeated by investigating by weight in data
The content recorded again carries out examination delete processing；By the exception in method for detecting abnormality discovery data, with reference to historical auditing knot
Fruit database and business understand whether the abnormal data that investigation algorithm is found is genuine exception, it is abnormal the reason for etc., and according to
The result of investigation processing is modified to abnormal data.
S103, exploratory analysis is carried out to Audit data and obtains data characteristics, may include steps of：
Using Exploring Analysis and correlation analysis method, exploratory analysis is carried out to the Audit data, determines audit risk
The data characteristics and the regularity of distribution of data；Wherein, the data characteristics includes average, quantile and/or variance.
Specifically, the feature and the regularity of distribution of Audit data are determined by Exploring Analysis, so as to be to excavating when modeling
The selection of algorithm and parameter setting provide foundation.
As embodiment, Exploring Analysis and correlation analysis method, the regularity of distribution of Exploring Analysis Audit data can be used
And the characteristic statistic such as average, quantile, variance, correlation analysis are closed between can verifying each situational variables with the presence or absence of related
System and the degree of strength of dependency relation.
S20, the audit risk data are sampled and are divided into test set and training set, it is special according to the data
Sign is closed in training set establishes forecast model, and forecast model is trained to obtain risk forecast model using test set.
In above-mentioned steps, relate generally to risk forecast model establishes process, can close foundation prediction mould in training set
Type, continued to optimize by test data, so as to finally give risk forecast model.Generally, regression analysis can be used
Method is modeled.
In one embodiment, with reference to shown in figure 3, Fig. 3 is the step S20 of one embodiment flow chart, can be included
Following steps：
S201, the audit risk data are sampled and are divided into test set and training set, can be included as follows：
Using arbitrary sampling method, the audit risk data are sampled and are divided into multiple test set and training set
Close, wherein, training set is shared in establishing model, and test set is shared in test tuning model.
Specifically, division can be sampled to unit under auditing historical auditing risk data, it is divided into test set and instruction
Practice set.Using arbitrary sampling method, multiple test set of sampling out, the precision based on multiple test set guarantee forecast models
And generalization ability.
S202, closed according to the data characteristics in training set and establish forecast model, may include steps of：
Corresponding mining algorithm and arrange parameter value are selected according to the data characteristics of audit risk data and the regularity of distribution
Closed in training set and establish forecast model.
Specifically, selecting suitable mining algorithm and parameter value according to data characteristics, foundation prediction mould is closed in training set
Type.
As embodiment, neural net regression analysis method and support vector machine regression method can be used to want to combine
Mode be modeled, so as to evade using effect deviation is modeled caused by single algorithm, wherein forecast model establish process and
Model measurement process, which is intersected, to be carried out, and is closed and is tested in test set by the forecast model of foundation, determined according to test result
Whether forecast model further optimizes and how to optimize.
S203, forecast model is trained to obtain risk forecast model using test set, may include steps of：
Closed and tested in test set using the forecast model；If the test rating that forecast model closes in test set
Value exceedes setting threshold values, then by testing and being arranged to candidate prediction model, goes to step S204；Otherwise, according to step S202 weights
Corresponding mining algorithm or the adjustment parameter value are newly selected, closes in test set and is tested again.
Specifically, if forecast model is superior in the performance that test set closes, i.e., the inspection that forecast model closes in test set
Desired value exceedes setting threshold values, then it is assumed that and forecast model is by test, otherwise it is assumed that forecast model could be improved, improvement side
To being probably that the adjustment of parameter value is also likely to be reselecting for algorithm.
S204, optimal model is selected from candidate prediction model as risk forecast model, specifically, by it is individual repeatedly
Test modifications, a variety of forecast models are established using tuning gimmick, test obtains candidate prediction model, finally according to it in test set
The performance closed, optimal candidate prediction model is selected as risk forecast model.
S30, risk profile is carried out to the Audit data of the audit target of input using the risk forecast model, identification is examined
The risk classifications counted.
In above-mentioned steps, using the risk forecast model established, risk profile determination is carried out to the Audit data of input
Its risk classifications.For example, prediction unit under auditing there is a possibility that certain class risk, so as to provide number for the expansion of audit work
According to support.
Described, technical scheme provided by the present invention, can be learnt by regression analysis based on the various embodiments described above
The Audit data of history discovery is cashed with temporal variation rule, formation risk forecast model, so as to being cashed by audit by audit
There is a possibility that all kinds of audit risks are predicted.
Relative in general Audit data method for digging, there is obvious advantage：
, as analyze data, to find the rule of itself by the Audit data that audit target history occurs；To find to be examined
It is target that unit history discovery audit issues, which is counted, with the rule of time-evolution；Based on being learnt automatically with machine, human intervention factor
Less, the renewal efficiency of modeling process and model is fast.
With reference to shown in figure 4, Fig. 4 is the audit data processing system structure diagram of one embodiment, including：
Data acquisition module 10, for being extracted from historical auditing database by the Audit data of the audit target, to described
Audit data carries out data cleansing, and carries out exploratory analysis and obtain data characteristics；
Data modeling module 20, test set and training set are divided into for being sampled to the audit risk data
Close, closed according to the data characteristics in training set and establish forecast model, and forecast model is trained using test set
Obtain risk forecast model；
Risk profile module 30, for being carried out using the risk forecast model to the Audit data of the audit target of input
Risk profile, identify the risk classifications of Audit data.
The audit data processing method of the audit data processing system of the present invention and the present invention corresponds, in above-mentioned audit
The technical characteristic and its advantage that the embodiment of data processing method illustrates are applied to the implementation of audit data processing system
In example, hereby give notice that.
In order to become apparent from technical solution of the present invention, continue with elaboration and be based on audit data processing provided by the present invention
The application example of method.
With reference to shown in figure 5, Fig. 5 be based on the present invention audit data processing method forecasting system structural representation, institute
Stating forecasting system includes data acquisition module A10, data analysis module A20 and audit risk prediction module A30；Wherein, it is described
Data acquisition module A10 is used for the audit issues data for gathering the discovery of unit under auditing history, and data are handled and visited
Rope is analyzed；The various dimensions chart for the audit issues that the data analysis module A20 is used to find history shows；The audit wind
Dangerous prediction module A30 is used for foundation, test and the application of forecast model.
With reference to shown in figure 6, Fig. 6 is the schematic diagram of the forecasting system modules of one embodiment, the data acquisition module
Block A10 includes ETL module A11, Data Mining modules A 12.Described ETL module A11 is used for extraction, conversion, the loading of data.
Described Data Mining modules A 12 is used for analyze data feature and distribution situation.
With reference to shown in figure 6, the data analysis module A20 includes dimension management module A21, front end display module A22；Institute
The foundation for the relation that the dimension management module A21 stated is used between the establishment, modification and deletion and dimension of dimension；The front end
Display module A22 is used for the audit issues and its frequency that multi-angle dynamic shows history discovery.
Continue shown in Fig. 6, the audit risk prediction module A30 includes model building module A31 and audit risk is predicted
Modules A 32；The model building module A31 is used for foundation, test and the tuning of forecast model；The audit risk prediction module
A32 is used for the application of model, i.e., there is a possibility that certain class audit risk using model prediction unit under auditing.
The above-mentioned forecasting system using example, the audit data processing method provided based on the embodiment of the present invention, use
Data mining technology, by analyzing audit issues and its frequency that unit under auditing history is found, risk forecast model is established, from
And unit under auditing is predicted with the presence or absence of certain class audit risk.Avoid and analyzed present in existing Audit data excavation
Data sheet one, Machine self-learning degree be low, the less evolution characteristics considered in sign variable one's duty feature and data time dimension
The problems such as.
Based on example as described above, a kind of computer equipment is also provided in one embodiment, the computer equipment bag
The computer program that includes memory, processor and storage on a memory and can run on a processor, wherein, computing device
Any one audit data processing method in each embodiment as described above is realized during described program.
Above computer equipment, by the computer program run on the processor, realize to by audit target institute
There is a possibility that all kinds of audit risks are predicted.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, it is non-volatile computer-readable that described program can be stored in one
Take in storage medium, in the embodiment of the present invention, the program can be stored in the storage medium of computer system, and is calculated by this
At least one computing device in machine system, include as described above the respectively flow of the embodiment of sleep householder method to realize.Its
In, described storage medium can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) or random storage
Memory body (Random Access Memory, RAM) etc..
Accordingly, a kind of storage medium is also provided in one embodiment, is stored thereon with computer program, wherein, the journey
Any one audit data processing method in each embodiment as described above is realized when sequence is executed by processor.
Above computer storage medium, by the computer program of its storage, realize to each present in the audit target
The possibility of class audit risk is predicted.
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more specific and detailed, but simultaneously
Can not therefore it be construed as limiting the scope of the patent.It should be pointed out that come for one of ordinary skill in the art
Say, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
- A kind of 1. audit data processing method, it is characterised in that comprise the following steps：Extracted from historical auditing database by the Audit data of the audit target, data cleansing is carried out to the Audit data, and Carry out exploratory analysis and obtain data characteristics；The audit risk data are sampled and are divided into test set and training set, are being trained according to the data characteristics Collection, which closes, establishes forecast model, and forecast model is trained to obtain risk forecast model using test set；Risk profile is carried out to the Audit data of the audit target of input using the risk forecast model, identifies Audit data Risk classifications.
- 2. audit data processing method according to claim 1, it is characterised in that taken out in the database from historical auditing The step of taking the Audit data by the audit target includes：Extracted using ETL instruments from historical auditing database by the Audit data of the audit target, the Audit data is changed Obtained for unified form by the historical auditing risk data of the audit target, analyze data is arrived into the storage of historical auditing risk data In storehouse.
- 3. audit data processing method according to claim 1, it is characterised in that described that line number is entered to the Audit data Include according to the step of cleaning：Investigation processing is carried out to the content that record is repeated in the Audit data, and delete processing is carried out to duplicate contents；Exception in the Audit data is checked, exception is determined according to historical auditing result database and business tine Data；Abnormal data is modified according to the result of the investigation processing.
- 4. audit data processing method according to claim 1, it is characterised in that the progress exploratory analysis number Include according to the step of feature：Using Exploring Analysis and correlation analysis method, exploratory analysis is carried out to the Audit data, determines audit risk data Data characteristics and the regularity of distribution；Wherein, the data characteristics includes average, quantile and/or variance.
- 5. audit data processing method according to claim 1, it is characterised in that described that the audit risk data are entered Line sampling is divided into test set and training set, closes the step of establishing forecast model in training set according to the data characteristics Including：Using arbitrary sampling methods, the audit risk data are sampled and are divided into multiple test set and training set, Wherein, training set is shared in establishing model, and test set is shared in test tuning model；Corresponding mining algorithm and arrange parameter value is selected to instruct according to the data characteristics of audit risk data and the regularity of distribution White silk collection, which closes, establishes forecast model.
- 6. audit data processing method according to claim 5, it is characterised in that successively using neural net regression analysis Method and support vector machine regression method are closed in training set and establish forecast model.
- 7. audit data processing method according to claim 1, it is characterised in that described to be gathered using test to predicting mould The step of type is trained to obtain risk forecast model includes：Closed and tested in test set using the forecast model；If forecast model exceedes setting threshold values in the test rating value that test set closes, by testing and being arranged to candidate prediction Model；Otherwise, corresponding mining algorithm or the adjustment parameter value are reselected, closes in test set and is tested again；Optimal model is selected from candidate prediction model as risk forecast model.
- A kind of 8. audit data processing system, it is characterised in that including：Data acquisition module, for being extracted from historical auditing database by the Audit data of the audit target, to the audit number According to progress data cleansing, and carry out exploratory analysis and obtain data characteristics；Data modeling module, test set and training set are divided into for being sampled to the audit risk data, according to The data characteristics is closed in training set establishes forecast model, and forecast model is trained to obtain risk using test set Forecast model；Risk profile module, it is pre- for carrying out risk to the Audit data of the audit target of input using the risk forecast model Survey, identify the risk classifications of Audit data.
- 9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be in the processor The computer program of upper operation, it is characterised in that described in the computing device during computer program realize as claim 1 to Audit data processing method described in 7 any one.
- 10. a kind of computer-readable storage medium, is stored thereon with computer program, it is characterised in that the program is executed by processor Audit data processing methods of the Shi Shixian as described in claim 1 to 7 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711124937.XA CN107832429A (en) | 2017-11-14 | 2017-11-14 | audit data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711124937.XA CN107832429A (en) | 2017-11-14 | 2017-11-14 | audit data processing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107832429A true CN107832429A (en) | 2018-03-23 |
Family
ID=61655419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711124937.XA Pending CN107832429A (en) | 2017-11-14 | 2017-11-14 | audit data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107832429A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064000A (en) * | 2018-07-25 | 2018-12-21 | 天图软件科技有限公司 | The methods, devices and systems of natural resources audit |
| CN109409720A (en) * | 2018-10-17 | 2019-03-01 | 大国创新智能科技(东莞)有限公司 | Personalized auditing method and robot system based on big data and deep learning |
| CN109409717A (en) * | 2018-10-17 | 2019-03-01 | 大国创新智能科技(东莞)有限公司 | Active auditing method and robot system based on big data and deep learning |
| CN110532301A (en) * | 2019-08-30 | 2019-12-03 | 广西电网有限责任公司南宁供电局 | Auditing method, system and readable storage medium storing program for executing |
| CN110543565A (en) * | 2019-08-30 | 2019-12-06 | 广西电网有限责任公司南宁供电局 | Auditing method, system and readable storage medium based on convolutional neural network model |
| WO2019232964A1 (en) * | 2018-06-07 | 2019-12-12 | 平安科技（深圳）有限公司 | Risk management data processing method and apparatus, computer device, and storage medium |
| CN110633314A (en) * | 2018-06-05 | 2019-12-31 | 上海博泰悦臻网络技术服务有限公司 | Internet of vehicles data processing method and device |
| CN110781173A (en) * | 2019-10-12 | 2020-02-11 | 杭州城市大数据运营有限公司 | Data identification method and device, computer equipment and storage medium |
| CN110858214A (en) * | 2018-08-22 | 2020-03-03 | 北京国双科技有限公司 | Recommendation model training and further auditing program recommendation method, device and equipment |
| CN111177779A (en) * | 2019-12-24 | 2020-05-19 | 深圳昂楷科技有限公司 | Database auditing method, device thereof, electronic equipment and computer storage medium |
| CN111967709A (en) * | 2020-07-01 | 2020-11-20 | 李蓓然 | Method for avoiding major error risk in audit sampling |
| CN112308388A (en) * | 2020-10-22 | 2021-02-02 | 国网天津市电力公司 | Electric power engineering overhaul project risk auditing method based on semantic analysis |
| CN112465397A (en) * | 2020-12-15 | 2021-03-09 | 广东电网有限责任公司 | Audit data analysis method and device |
| CN112651618A (en) * | 2020-12-21 | 2021-04-13 | 国家电网有限公司大数据中心 | Construction method of audit dimension model for online audit of metering data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110089A (en) * | 2007-09-04 | 2008-01-23 | 华为技术有限公司 | Method and system for data digging and model building |
| CN101620691A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Automatic data mining platform in telecommunications industry |
| CN105630957A (en) * | 2015-12-24 | 2016-06-01 | 北京大学 | User management application behavior-based application quality distinguishing method and system |
| CN106933956A (en) * | 2017-01-22 | 2017-07-07 | 深圳市华成峰科技有限公司 | Data digging method and device |
| CN107038167A (en) * | 2016-02-03 | 2017-08-11 | 普华诚信信息技术有限公司 | Big data excavating analysis system and its analysis method based on model evaluation |
| CN107229849A (en) * | 2016-03-24 | 2017-10-03 | 全球能源互联网研究院 | Towards the database user behavior safety auditing method on power information intranet and extranet border |
-
2017
- 2017-11-14 CN CN201711124937.XA patent/CN107832429A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110089A (en) * | 2007-09-04 | 2008-01-23 | 华为技术有限公司 | Method and system for data digging and model building |
| CN101620691A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Automatic data mining platform in telecommunications industry |
| CN105630957A (en) * | 2015-12-24 | 2016-06-01 | 北京大学 | User management application behavior-based application quality distinguishing method and system |
| CN107038167A (en) * | 2016-02-03 | 2017-08-11 | 普华诚信信息技术有限公司 | Big data excavating analysis system and its analysis method based on model evaluation |
| CN107229849A (en) * | 2016-03-24 | 2017-10-03 | 全球能源互联网研究院 | Towards the database user behavior safety auditing method on power information intranet and extranet border |
| CN106933956A (en) * | 2017-01-22 | 2017-07-07 | 深圳市华成峰科技有限公司 | Data digging method and device |
Non-Patent Citations (2)
| Title |
|---|
| MAX KUHN 等: "《应用预测模型》", 31 May 2016 * |
| 吴迪: "《基于场景理论的我国城市择居行为及房价空间差异问题研究》", 31 July 2013 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633314A (en) * | 2018-06-05 | 2019-12-31 | 上海博泰悦臻网络技术服务有限公司 | Internet of vehicles data processing method and device |
| WO2019232964A1 (en) * | 2018-06-07 | 2019-12-12 | 平安科技（深圳）有限公司 | Risk management data processing method and apparatus, computer device, and storage medium |
| CN109064000A (en) * | 2018-07-25 | 2018-12-21 | 天图软件科技有限公司 | The methods, devices and systems of natural resources audit |
| CN110858214A (en) * | 2018-08-22 | 2020-03-03 | 北京国双科技有限公司 | Recommendation model training and further auditing program recommendation method, device and equipment |
| CN109409720A (en) * | 2018-10-17 | 2019-03-01 | 大国创新智能科技(东莞)有限公司 | Personalized auditing method and robot system based on big data and deep learning |
| CN109409717A (en) * | 2018-10-17 | 2019-03-01 | 大国创新智能科技(东莞)有限公司 | Active auditing method and robot system based on big data and deep learning |
| CN109409717B (en) * | 2018-10-17 | 2021-06-25 | 大国创新智能科技(东莞)有限公司 | Active auditing method based on big data and deep learning and robot system |
| CN109409720B (en) * | 2018-10-17 | 2020-12-22 | 大国创新智能科技(东莞)有限公司 | Personalized auditing method based on big data and deep learning and robot system |
| CN110543565A (en) * | 2019-08-30 | 2019-12-06 | 广西电网有限责任公司南宁供电局 | Auditing method, system and readable storage medium based on convolutional neural network model |
| CN110532301A (en) * | 2019-08-30 | 2019-12-03 | 广西电网有限责任公司南宁供电局 | Auditing method, system and readable storage medium storing program for executing |
| CN110532301B (en) * | 2019-08-30 | 2023-08-22 | 广西电网有限责任公司南宁供电局 | Audit method, system and readable storage medium |
| CN110781173A (en) * | 2019-10-12 | 2020-02-11 | 杭州城市大数据运营有限公司 | Data identification method and device, computer equipment and storage medium |
| CN111177779A (en) * | 2019-12-24 | 2020-05-19 | 深圳昂楷科技有限公司 | Database auditing method, device thereof, electronic equipment and computer storage medium |
| CN111967709A (en) * | 2020-07-01 | 2020-11-20 | 李蓓然 | Method for avoiding major error risk in audit sampling |
| CN112308388A (en) * | 2020-10-22 | 2021-02-02 | 国网天津市电力公司 | Electric power engineering overhaul project risk auditing method based on semantic analysis |
| CN112465397A (en) * | 2020-12-15 | 2021-03-09 | 广东电网有限责任公司 | Audit data analysis method and device |
| CN112651618A (en) * | 2020-12-21 | 2021-04-13 | 国家电网有限公司大数据中心 | Construction method of audit dimension model for online audit of metering data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107832429A (en) | audit data processing method and system | |
| Zini et al. | A quality-based automated procedure for operational modal analysis | |
| Galende-Hernández et al. | Monitor-While-Drilling-based estimation of rock mass rating with computational intelligence: The case of tunnel excavation front | |
| CN103870751B (en) | Method and system for intrusion detection | |
| CN112114579B (en) | Industrial control system safety measurement method based on attack graph | |
| KR101811270B1 (en) | Method and system for checking goods | |
| CN110210227A (en) | Risk checking method, device, equipment and storage medium | |
| US20090106174A1 (en) | Methods, systems, and computer program products extracting network behavioral metrics and tracking network behavioral changes | |
| Yu et al. | Experience in predicting fault-prone software modules using complexity metrics | |
| KR102090423B1 (en) | Method of application malware detection based on dynamic api extraction, readable medium and apparatus for performing the method | |
| CN110232499A (en) | A kind of power distribution network information physical side method for prewarning risk and system | |
| Erturk et al. | Software fault prediction using Mamdani type fuzzy inference system | |
| CN111557011A (en) | Enterprise yield-breaking prediction system and operation method thereof | |
| CN109002810A (en) | Model evaluation method, Radar Signal Recognition method and corresponding intrument | |
| CN103957116A (en) | Decision-making method and system of cloud failure data | |
| CN110716957B (en) | Intelligent mining and analyzing method for class case suspicious objects | |
| Prabhakaran et al. | Towards prediction of paradigm shifts from scientific literature | |
| Zivkovic et al. | Software defects prediction by metaheuristics tuned extreme gradient boosting and analysis based on shapley additive explanations | |
| CN113313304A (en) | Power grid accident abnormity analysis method and system based on big data decision tree | |
| CN107025293A (en) | A kind of second power equipment defective data method for digging and system | |
| Dawoud et al. | A global measure for estimating the degree of organization of terrorist networks | |
| Lehavi et al. | Feature Reduction Method Comparison Towards Explainability and Efficiency in Cybersecurity Intrusion Detection Systems | |
| Pei | Construction of a legal system of corporate social responsibility based on big data analysis technology | |
| CN114416422A (en) | Problem locating method, apparatus, device, medium and program product | |
| Jabeen et al. | A unified measurable software trustworthy model based on vulnerability loss speed index |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180323 |