CN109785111A - Produce verification process test method, device, computer equipment and storage medium - Google Patents
Produce verification process test method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109785111A CN109785111A CN201811530396.5A CN201811530396A CN109785111A CN 109785111 A CN109785111 A CN 109785111A CN 201811530396 A CN201811530396 A CN 201811530396A CN 109785111 A CN109785111 A CN 109785111A
- Authority
- CN
- China
- Prior art keywords
- data
- production
- initial data
- loan
- verification process
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 110
- 230000008569 process Effects 0.000 title claims abstract description 102
- 238000010998 test method Methods 0.000 title claims abstract description 25
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000004519 manufacturing process Methods 0.000 claims abstract description 99
- 238000012360 testing method Methods 0.000 claims abstract description 37
- 230000008859 change Effects 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 24
- 230000001815 facial effect Effects 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 241001269238 Data Species 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 5
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 10
- 239000010931 gold Substances 0.000 description 10
- 229910052737 gold Inorganic materials 0.000 description 10
- 230000008901 benefit Effects 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 4
- 238000012550 audit Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241000416536 Euproctis pseudoconspersa Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
This application involves loan production verification process technical field more particularly to a kind of production verification process test method, device, computer equipment and storage mediums.A kind of production verification process test method, comprising: the initial data for obtaining loan production verifying assigns the initial data with verification mark；According to the verification mark, situation of change of the initial data in loan production verification process is tracked, the final data obtained after loan production verifying is recorded；The final data is decomposed into several subdata groups；Preset matching degree threshold value is obtained, each subdata group is matched with the content in expected results table.The technical program carries out amount of money conversion and data markers for consumption installment credit production verification process, eliminates the generation of dirty data, and test data and normal data are removed, does not influence normal loan process.
Description
Technical field
This application involves loan production verification process technical field more particularly to a kind of production verification process test method,
Device, computer equipment and storage medium.
Background technique
Production verification process refers to after the design of product is recognized, before batch production, Production Engineer or product matter
Engineer is measured in order to prove to have to produce in batches to meet client technologies specification and product design requirement.
Currently, operator will use real user account to carry out when consumptive loan carries out production verification process test
The problems such as verifying, but being limited due to user right, can only carry out the test of part scene, be unable to all standing；Production verifying meeting
Dirty data is generated, has certain influence, such as report form statistics, order statistics to system；During consuming installment credit, have
Special process: user needs to pay intention gold after valuing a vehicle, can just be divided after payment completion intention gold
The submission of phase loan data, needs branch to pay earnest money, needs to pay the bigger amount of money in verification process, then can not after the completion of audit
It carries out.
Moreover, needing multiple and different nodes to audit in production verifying process, and corresponding different role, but produce
System verifying generally morning carry out, and coordinate at this time specific auditor carry out audit easily cause waste of human resource；It is raw
Produce the function point that verification item report needs artificial statistical testing of business cycles.
Summary of the invention
In view of this, it is necessary to which for existing consumptive loan production verifying link, that there is the degree of automation is low, is also easy to produce
The problem of dirty data, provides a kind of loan production verification method, system, computer equipment and storage medium.
A kind of production verification process test method, includes the following steps:
The initial data for obtaining loan production verifying, assigns the initial data with verification mark；
According to the verification mark, situation of change of the initial data in loan production verification process, record are tracked
The final data obtained after loan production verifying；
The final data is decomposed into several subdata groups；
Preset matching degree threshold value is obtained, each subdata group is gone through with the production verification process in expected results table
History data are matched, if the number of successful match is greater than preset matching degree threshold value, the final data are removed, otherwise
The initial data is re-flagged, the expected results table storage is in the database.
In one of the embodiments, it is described obtain loan production verifying initial data, assign the initial data with
Verification mark, comprising:
Input data instruction is sent to loan application terminal, obtains the initial data of the loan application terminal input；
The initial data is inquired, the text information extracted in the initial data forms a character block, extracts the original
Numerical information in beginning data forms a blocks of values；
Keyword retrieval is carried out to the character block, obtains the most keyword of frequency of occurrence in the character block, with
The most keyword of the frequency of occurrence is that letter symbol carries out word marking to the initial data；
The greatest measure in the blocks of values is extracted, the greatest measure is subjected to color mark, is realized to described original
The numeric indicia of data.
It is described according to the verification mark in one of the embodiments, it tracks the initial data and is tested in loan production
Situation of change during card records the final data obtained after loan production verifying, comprising:
Several timing nodes that preset data are extracted are obtained, when any timing node arrives, loan is produced
Data in verification process extract, and obtain several process datas；
The process data is retrieved according to the verification mark, extraction belt has the number of passes excessively of the verification mark
According to；
The data of verification mark will be had in the quantity and the initial data of process data with the verification mark
Quantity be compared, the difference both obtained；
The normal distribution for establishing the difference obtains maximum difference from the normal distribution；
Data corresponding to maximum difference are extracted, by the data for terminating timing node and number corresponding to the maximum difference
The final data is formed according to superposition.
The decomposition final data includes: at several subdata groups in one of the embodiments,
Obtain the final data；
The data with the verification mark are identified from the final data, obtain the number for having the verification mark
According to position；
Using the Data Position as node, the final data is divided into several subdata groups.
It is described in one of the embodiments, to obtain preset matching degree threshold value, by each subdata group and expection
As a result the production verification process historical data in table is matched, if the number of successful match is greater than preset matching degree threshold value,
Then the final data is removed, otherwise the initial data is re-flagged, the expected results table is stored in data
In library, comprising:
The generation time for obtaining each subdata group, the subdata group is ranked up sequentially in time；
A m*n subdata group matrix is established, according to the generation time sequencing successively using the subdata group as matrix
Element is input in the subdata matrix, and wherein m represents the line number removed after gauge outfit in expected results table, and n represents expected knot
The columns of fruit table；
The matrix element is matched with the production verification process historical data in the expected results table, acquisition
With the consistent matrix element；
The quantity of the consistent matrix element of statistical match, is compared, if successful match with the matching degree threshold value
Number be greater than the matching degree threshold value, then the final data is removed, otherwise the initial data is re-flagged.
In one of the embodiments, it is described obtain loan production verifying initial data, assign the initial data with
Verification mark further includes the process that authentication is carried out to loan application people, is specifically included:
The facial image for acquiring the loan application people carries out moire fringes identification to the facial image, is tied according to identification
Fruit rejects reproduction picture；
It obtains and identifies the characteristic point in the facial image by moire fringes, by the people in the characteristic point and face picture library
Face image is compared, and obtains and compares identity information corresponding to consistent facial image, and the face picture library is stored in data
In library.
In one of the embodiments, it is described obtain loan production verifying initial data, assign the initial data with
Verification mark further includes the process audited to number of providing a loan in the initial data, is specifically included:
The initial data is subjected to element sepatation, to each element setting element value and assigns different weights；
Each element value is subjected to normal distribution according to the weight, extracts the element value that weight is in front three,
It carries out that element mean value is calculated using mean function；
The element mean value is compared with preset loan amount threshold value, calculates whether error meets preset value, if
Error is less than the preset value, then obtains the initial data, otherwise do not obtain.
A kind of production verification process test device, including following module:
Mark raw data module, be set as obtain loan production verifying initial data, assign the initial data with
Verification mark；
Final data module is obtained, is set as tracking the initial data according to the verification mark and testing in loan production
Situation of change during card records the final data obtained after loan production verifying；
Final data module is decomposed, is set as decomposing the final data into several subdata groups；
Test result analysis module is set as obtaining preset matching degree threshold value, by each subdata group and expection
As a result the production verification process historical data in table is matched, if the number of successful match is greater than preset matching degree threshold value,
Then the final data is removed, otherwise the initial data is re-flagged, the expected results table is stored in data
In library.
A kind of computer equipment, including memory and processor are stored with computer-readable instruction in the memory, institute
When stating computer-readable instruction and being executed by the processor, so that the processor executes above-mentioned production verification process test method
The step of.
A kind of storage medium being stored with computer-readable instruction, the computer-readable instruction are handled by one or more
When device executes, so that the step of one or more processors execute above-mentioned production verification process test method.
Above-mentioned production verification process test method, device, computer equipment and storage medium, including obtain loan production and test
The initial data of card assigns the initial data with verification mark；According to the verification mark, tracks the initial data and borrowing
Money produces the situation of change in verification process, records the final data obtained after loan production verifying；Decompose the final number
According at several subdata groups；Preset matching degree threshold value is obtained, by the production in each subdata group and expected results table
Verification process historical data is matched, if the number of successful match is greater than preset matching degree threshold value, by the final number
According to removing, otherwise the initial data is re-flagged, the expected results table storage is in the database.The technical program
Amount of money conversion and data markers are carried out for consumption installment credit production verification process, eliminate the generation of dirty data, and will
Test data is removed with normal data, does not influence normal loan process.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the application
Limitation.
Fig. 1 is a kind of overall flow figure for producing verification process test method of the application；
Fig. 2 is a kind of acquisition initial data process schematic produced in verification process test method of the application；
Fig. 3 is a kind of acquisition final data process schematic produced in verification process test method of the application；
Fig. 4 is a kind of test result analysis process schematic produced in verification process test method of the application；
Fig. 5 is a kind of structure chart for producing verification process test method device of the application.
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, and
It is not used in restriction the application.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in the description of the present application
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.
Fig. 1 is the flow chart of the loan production verification method in the application one embodiment, as shown in Figure 1, a kind of loan
Produce verification method, comprising the following steps:
Step S1, the initial data for obtaining loan production verifying, assigns the initial data with verification mark；
Specifically, obtaining the IP address of the pre- terminal for participating in production validation test, domain name system is carried out to the IP address
Dns resolution obtains dns resolution code, is compared according to dns resolution code with preset DNS code, if comparing unanimously, assigns
The corresponding pre- terminal for participating in production validation test is given to upload the permission of initial data, and according to corresponding to different terminals
IP address assigns initial data with different verification marks.
Step S2, according to the verification mark, variation feelings of the initial data in loan production verification process are tracked
Condition records the final data obtained after loan production verifying；
Specifically, such as applicant assigns the order of input intention gold, applicant terminal is receiving applicant's input
After 1000 yuan of intention gold, 0.01 yuan is converted thereof into, and " test " label is carried out to this numerical value, be then stored into applicant's Information Number
According on the test zone in library, " test " need to only be marked and be identified during carrying out production validation test, can obtained
The situation of change of the amount of money.
Step S3, the final data is decomposed into several subdata groups；
Specifically, the precedence that can be generated according to final data carries out when being split in groups to final data
Grouping, for example several timing nodes are set, when sometime node arrives, then by a upper timing node to the institute of intermediate node at this time
The final data of generation is packaged into a subdata group；Or Clustering is carried out to final data, for example verification process will be produced
The intention gold final data of generation is clustered into intention gold data group, will produce the deposit final data generated in verification process and clusters
At deposit data group.
Step S4, preset matching degree threshold value is obtained, each subdata group is tested with the production in expected results table
Card Process History data are matched, if the number of successful match is greater than preset matching degree threshold value, by the final data
It removes, otherwise the initial data is re-flagged, the expected results table storage is in the database.
Specifically, matching degree threshold value is to be weighted to obtain according to historical data, closer gone through apart from current time
The Weighted Index of history data is bigger, and the Weighted Index of the historical data remoter apart from present moment is smaller, if the number of successful match
Mesh is greater than preset matching degree threshold value, then the precedence generated according to data each in final data, and it is clear successively to carry out data
It removes.If the data in each subdata group are not greater than preset matching degree threshold value, matching degree threshold value is adjusted, and
And error log is sent to the server for producing verifying system.
In the present embodiment, by carrying out amount of money conversion and data markers to production verification process test, dirty data is eliminated
Generation, and test data and normal data are removed, do not influence normal loan process.
Fig. 2 in one embodiment, is established for the application and is obtained initial data process schematic, as shown, described obtain
The initial data for taking loan production verifying, assigns the initial data with verification mark, comprising:
S101, input data instruction is sent to loan application terminal, obtains the original number of the loan application terminal input
According to；
Specifically, can also include the operation to application terminal when carrying out acquisition initial data to loan application terminal
Person carries out the process of authentication, and authentication may include living things feature recognition, as recognition of face, fingerprint recognition, iris are known
Not etc., the identity of the operator of application terminal can also be identified using verifying account, the form of password, when operator's body
After part meets the personal information of storage in the database, then the permission for inputting initial data is assigned to application terminal.
S102, the inquiry initial data, the text information extracted in the initial data form a character block, extract institute
The numerical information stated in initial data forms a blocks of values；
Specifically, application structure query language SQL inquires initial data, mainly to the text in initial data
Word and number are inquired, and can first be inquired the number in data block, and the text information of number front and back, root are then obtained
Initial data is first divided into several sub-blocks according to text information, then is partitioned into digital information and text information in a sub-block, and will
Digital information is as the identification marking in character block, using text information as the identification marking of digital block, in order in character block
In or blocks of values in carry out information inquiry.
S103, keyword retrieval is carried out to the character block, obtains the most key of frequency of occurrence in the character block
Word carries out word marking to the initial data using the most keyword of the frequency of occurrence as letter symbol；
Wherein, the keyword in character block mainly includes；" intention gold ", " deposit ", " transaction " etc., the keyword of blocks of values
The numerical value of an order of magnitude that mainly to include as " 0.01 " be not obviously with other numerical value；If the keyword in character block
The number that " deposit " occurs is most, then using " deposit " as the words identification of the initial data, i.e. the feature of this initial data
Word segment is " deposit " in label.
S104, the greatest measure extracted in the blocks of values realize greatest measure progress color mark to described
The numeric indicia of initial data.
Specifically, the two greatest measures are subjected to color mark if there is two greatest measures in blocks of values,
First with red, then second with blue to be distinguish；It simultaneously can also be using numerically side plus horizontal line etc. in this step
Greatest measure is marked in mode, in order to distinguish.
In the present embodiment, initial data can be preferably tracked in production verification process by the way that initial data is marked
Situation of change when test, while if mistake occurs in the variation that a certain numerical value occurs in subsequent step, color change can also be used
Etc. modes intuitively reflect.
Fig. 3 in one embodiment, is established for the application and is obtained final data process schematic, as shown, described
According to the verification mark, situation of change of the initial data in loan production verification process is tracked, record is produced through loan
The final data obtained after verifying, comprising:
S201, several timing nodes that preset data are extracted are obtained, when any timing node arrives, to loan
Data in production verification process extract, and obtain several process datas；
Specifically, several timing nodes that preset data are extracted are the history numbers tested according to all previous production verification process
According to what is obtained, timing node is generally chosen: start to carry out the test of production verification process, terminate the test of production verification process and
The timing node of intermediate link can increase timing node according to the variation tendency of historical data for intermediate a certain link
Quantity or the quantity for reducing timing node, and can establish trend prediction model, it is better anticipated according to trend prediction model
The time point and quantity that timing node is chosen.
S202, the process data is retrieved according to the verification mark, extraction belt has the mistake of the verification mark
Number of passes evidence；
Specifically, when carrying out verification mark retrieval to process data, it can be first according to the words identification assigned in advance
" test " label is retrieved, and all process datas with " test " are extracted, and is arranged successively sequentially in time,
Form a row matrix, then carry out numerical value retrieval to the data after " test " label are extracted, such as the conversion value " 0.01 " of intention gold,
Next step is carried out if not having " 0.01 " in remaining data, otherwise reports error log to system server.
S203, verification mark will be had in the quantity and the initial data of the process data with the verification mark
The quantity of data is compared, and obtains the difference of the two；
Specifically, different data pick-up timing nodes can be set when carrying out difference quantities statistics, if certain two number
Then the latter timing node is removed without quantity variation according between extraction timing node, that is, extends the time interval of data pick-up.
S204, the normal distribution for establishing the difference, obtain maximum difference from the normal distribution；
Wherein, if there is two or above maximum difference in normal distribution, need to data pick-up when
Intermediate node is reset, until only one maximum difference on normal distribution.
S205, data corresponding to maximum difference are extracted, the data and the maximum difference institute that terminate timing node are right
The data investigation answered forms the final data.
Specifically, assigning maximum difference according to the time difference of timing node and termination timing node where maximum difference
One obtains revised maximum difference with different coefficients, then by the data of revised maximum difference and termination timing node
Addition obtains final data, such as: the timing node of maximum difference and the difference for terminating timing node are 5min, then assign maximum
Difference A is with coefficient 0.5, and the data for terminating timing node are B, then final data C=0.5A+B.
In the present embodiment, by being modified the number for making it be better able to reflection production verification process test to final data
According to variation, so that finally obtained data result be made to be more in line with truth.
In one embodiment, the decomposition final data includes: at several subdata groups
Obtain the final data；
The data with the verification mark are identified from the final data, obtain the number for having the verification mark
According to position；
Using the Data Position as node, the final data is divided into several subdata groups.
Specifically, by using the Data Position as node, when the final data is divided into several subdata groups,
Data Position can be different application terminal, be also possible to what same application terminal was stored in the data that different moments generate
Position.
In the present embodiment, by being grouped to final data, different application terminals are produced under the conditions of can coping with high concurrent
Raw identical verify data, to improve the test speed of production verification process test.
Fig. 4 be the application in one embodiment, test result analysis process schematic, as shown, obtain it is preset
Matching degree threshold value matches each subdata group with the production verification process historical data in expected results table, if
The number of successful match be greater than preset matching degree threshold value, then the final data is removed, otherwise to the initial data into
Row re-flags, and the expected results table storage is in the database, comprising:
S401, the generation time for obtaining each subdata group, the subdata group is arranged sequentially in time
Sequence；
Wherein, subdata group is ranked up sequentially in time, it can it is ranked up according to the successive of time is generated,
The subdata group generated in certain time period can also be carried out being packaged into a grade subdata group, be then ranked up again, this
Sample can reduce sorting time.
S402, establish a m*n subdata group matrix, according to the generation time sequencing successively using the subdata group as
Matrix element is input in the subdata matrix, and wherein m represents the line number removed after gauge outfit in expected results table, and n represents pre-
The columns of phase result table；
Specifically, if filling out discontented situation in submatrix there is element, being accounted for 0 when establishing subdata matrix
Position.
S403, the matrix element is matched with the production verification process historical data in the expected results table,
It obtains and matches the consistent matrix element；
Specifically, the production verification process historical data in expected results table is established an expected results matrix, first
The clause name in expected results matrix is inquired, obtains the knot for meeting clause name from expected results matrix according to clause name
Then fruit matrix element extracts these elements, carry out this entry twice if the content that an element meets two entries
Matching, and assign special label.
The quantity of the consistent matrix element of S404, statistical match, is compared with the matching degree threshold value, if matching
Successful number is greater than the matching degree threshold value, then removes the final data, otherwise carries out again to the initial data
Label.
Wherein, when re-flagging to initial data, the mark mode of use and the label of last time are different, can will anticipate
It is modified to the numerical value conversion value of gold, or is identified using different colors.
In the present embodiment, matching degree comparison is carried out by the data in subdata group, preferably production can be verified
Procedural test result is accurately judged, to promote the accuracy of judgement.
In one embodiment, the initial data for obtaining loan production verifying, assigns the initial data to verify
Label further includes the process that authentication is carried out to loan application people, is specifically included:
The facial image for acquiring the loan application people carries out moire fringes identification to the facial image, is tied according to identification
Fruit rejects reproduction picture；
Specifically, can be rubbed using local binary patterns LBP algorithm when carrying out moire fringes identification to facial image
Your line identification generates training sample, then training sample is entered ginseng and is trained to support vector machines model, is rubbed after joining out
The identification model of your line identification, unknown images, which are input to identification model, can be completed identification.
It obtains and identifies the characteristic point in the facial image by moire fringes, by the people in the characteristic point and face picture library
Face image is compared, and obtains and compares identity information corresponding to consistent facial image, and the face picture library is stored in data
In library.
Specifically, extracting for characteristic point can use profile of the Dlib extraction method to face, the faces such as nozzle type, eye shape
Feature carries out Dynamic Recognition, then these facial characteristics are carried out with the characteristic point indicated on facial image in the database is prestored
Otherness compares, and the process of authentication can be completed.
In the present embodiment, the safety of production verification process test can be increased by carrying out authentication to loan application people
Property, while operating process during formal loan can also be simulated.
In one embodiment, the initial data for obtaining loan production verifying, assigns the initial data to verify
Label further includes the process audited to number of providing a loan in the initial data, is specifically included:
The initial data is subjected to element sepatation, to each element setting element value and assigns different weights；
Specifically, when carrying out element sepatation to initial data, mainly according to the attribute of different data in initial data
Separated, for example, in initial data intention gold and deposit, then assign intention gold with lower weight, and assign deposit with
Higher weight.
Each element value is subjected to normal distribution according to the weight, extracts the element value that weight is in front three,
It carries out that element mean value is calculated using mean function；
Specifically, applying electronic table procedure, such as the included mean function of Excel carries out the calculating of average value,
Weight is extracted when be in the element value of front three, if occur there are two or the element value in third position weight above,
The numerical value that one of them is third position weight is arbitrarily chosen, if the element value in second or first weight is more than one
It is a, then one is only chosen, the how corresponding element value of subsequent weight then will be come and fill vacancies in the proper order.
The element mean value is compared with preset loan amount threshold value, calculates whether error meets preset value, if
Error is less than the preset value, then obtains the initial data, otherwise do not obtain.
Specifically, can use error correction model when calculating error, there are many clear advantages: a) first-order difference
The use of item eliminates variable trend factor that may be present, so as to avoid False value problem；B) first-order difference item makes
With also elimination model Problems of Multiple Synteny that may be present；C) introducing of error correction item ensure that the information of variable level value
It is not ignored；D) due to the stationarity of error correction item itself, the homing method of model classics is estimated
Meter, Difference Terms can be used common t inspection and be examined with F to be chosen especially in model.
In the present embodiment, is audited by number of providing a loan in initial data, can preferably track initial data in life
The data variation during verification process test carries out is produced, to promote the accuracy of production verification process test.
In one embodiment it is proposed that a kind of production verification process test device, as shown in figure 5, including following module:
Mark raw data module, be set as obtain loan production verifying initial data, assign the initial data with
Verification mark；
Final data module is obtained, is set as tracking the initial data according to the verification mark and testing in loan production
Situation of change during card records the final data obtained after loan production verifying；
Final data module is decomposed, is set as decomposing the final data into several subdata groups；
Test result analysis module is set as obtaining preset matching degree threshold value, by each subdata group and expection
As a result the production verification process historical data in table is matched, if the number of successful match is greater than preset matching degree threshold value,
Then the final data is removed, otherwise the initial data is re-flagged, the expected results table is stored in data
In library.
A kind of computer equipment, including memory and processor are stored with computer-readable instruction in the memory, institute
When stating computer-readable instruction and being executed by the processor, so that the processor executes above-mentioned production verification process test method
The step of.
A kind of storage medium being stored with computer-readable instruction, the computer-readable instruction are handled by one or more
When device executes, so that the step of one or more processors execute above-mentioned production verification process test method.The storage medium
It can be non-volatile memory medium.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies 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, all should be considered as described in this specification.
The some exemplary embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but
It cannot be understood as the limitations to the application the scope of the patents.It should be pointed out that for the ordinary skill people of this field
For member, without departing from the concept of this application, various modifications and improvements can be made, these belong to the application's
Protection scope.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of production verification process test method characterized by comprising
The initial data for obtaining loan production verifying, assigns the initial data with verification mark；
According to the verification mark, situation of change of the initial data in loan production verification process is tracked, is recorded through borrowing
The final data obtained after money production verifying；
The final data is decomposed into several subdata groups；
Preset matching degree threshold value is obtained, by the production verification process history number in each subdata group and expected results table
According to being matched, if the number of successful match is greater than preset matching degree threshold value, the final data is removed, otherwise to institute
It states initial data to be re-flagged, the expected results table storage is in the database.
2. production verification process test method according to claim 1, which is characterized in that the acquisition loan production verifying
Initial data, assign the initial data with verification mark, comprising:
Input data instruction is sent to loan application terminal, obtains the initial data of the loan application terminal input；
The initial data is inquired, the text information extracted in the initial data forms a character block, extracts the original number
Numerical information in forms a blocks of values；
Keyword retrieval is carried out to the character block, the most keyword of frequency of occurrence in the character block is obtained, with described
The most keyword of frequency of occurrence is that letter symbol carries out word marking to the initial data；
The greatest measure in the blocks of values is extracted, the greatest measure is subjected to color mark, is realized to the initial data
Numeric indicia.
3. production verification process test method according to claim 1, which is characterized in that described to be marked according to the verifying
Note tracks situation of change of the initial data in loan production verification process, what record obtained after loan production verifying
Final data, comprising:
Several timing nodes that preset data are extracted are obtained, when any timing node arrives, to loan production verifying
Data in the process extract, and obtain several process datas；
The process data is retrieved according to the verification mark, extraction belt has the process data of the verification mark；
By the number of the data with verification mark in the quantity and the initial data of the process data with the verification mark
Amount is compared, and obtains the difference of the two；
The normal distribution for establishing the difference obtains maximum difference from the normal distribution；
Data corresponding to maximum difference are extracted, by the data for terminating timing node and stacked data corresponding to the maximum difference
Add to form the final data.
4. production verification process test method according to claim 1, which is characterized in that described to decompose the final data
Include: at several subdata groups
Obtain the final data；
The data with the verification mark are identified from the final data, obtain the data bit for having the verification mark
It sets；
Using the Data Position as node, the final data is divided into several subdata groups.
5. production verification process test method according to claim 1, which is characterized in that described to obtain preset matching degree
Threshold value matches each subdata group with the production verification process historical data in expected results table, if matching at
The number of function is greater than preset matching degree threshold value, then removes the final data, otherwise carries out again to the initial data
Label, the expected results table storage is in the database, comprising:
The generation time for obtaining each subdata group, the subdata group is ranked up sequentially in time；
A m*n subdata group matrix is established, according to the generation time sequencing successively using the subdata group as matrix element
It is input in the subdata matrix, wherein m represents the line number removed after gauge outfit in expected results table, and n represents expected results table
Columns；
The matrix element is matched with the production verification process historical data in the expected results table, obtains matching one
The matrix element caused；
The quantity of the consistent matrix element of statistical match, is compared with the matching degree threshold value, if the number of successful match
Mesh is greater than the matching degree threshold value, then removes the final data, otherwise re-flag to the initial data.
6. production verification process test method according to claim 1, which is characterized in that the acquisition loan production verifying
Initial data, assign the initial data with verification mark further include to loan application people carry out authentication process, tool
Body includes:
The facial image for acquiring the loan application people carries out moire fringes identification to the facial image, is picked according to recognition result
Except reproduction picture；
It obtains and identifies the characteristic point in the facial image by moire fringes, by the face figure in the characteristic point and face picture library
It as being compared, obtains and compares identity information corresponding to consistent facial image, the face picture library storage is in the database.
7. production verification process test method according to claim 1, which is characterized in that the acquisition loan production verifying
Initial data, assign the initial data with verification mark further include in the initial data provide a loan number audited
Process specifically includes:
The initial data is subjected to element sepatation, to each element setting element value and assigns different weights；
Each element value is subjected to normal distribution according to the weight, the element value that weight is in front three is extracted, utilizes
Mean function carries out that element mean value is calculated；
The element mean value is compared with preset loan amount threshold value, calculates whether error meets preset value, if error
Less than the preset value, then the initial data is obtained, is not otherwise obtained.
8. a kind of production verification process test device characterized by comprising
Raw data module is marked, is set as obtaining the initial data of loan production verifying, assigns the initial data to verify
Label；
Final data module is obtained, is set as that it is authenticated in loan production to track the initial data according to the verification mark
Situation of change in journey records the final data obtained after loan production verifying；
Final data module is decomposed, is set as decomposing the final data into several subdata groups；
Test result analysis module is set as obtaining preset matching degree threshold value, by each subdata group and expected results
Production verification process historical data in table is matched, will if the number of successful match is greater than preset matching degree threshold value
The final data is removed, and is otherwise re-flagged to the initial data, and the expected results table storage is in the database.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor executes such as any one of claims 1 to 7 right
It is required that the step of production verification process test method.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execution production as described in any one of claims 1 to 7 claim is authenticated
The step of journey test method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811530396.5A CN109785111A (en) | 2018-12-14 | 2018-12-14 | Produce verification process test method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811530396.5A CN109785111A (en) | 2018-12-14 | 2018-12-14 | Produce verification process test method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109785111A true CN109785111A (en) | 2019-05-21 |
Family
ID=66495951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811530396.5A Pending CN109785111A (en) | 2018-12-14 | 2018-12-14 | Produce verification process test method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109785111A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090001526A (en) * | 2007-04-23 | 2009-01-09 | 인피언컨설팅 주식회사 | Testing system of user interface for financial contract and testing method using thereof |
| CN104461863A (en) * | 2014-10-29 | 2015-03-25 | 中国建设银行股份有限公司 | Service system testing method, device and system |
| CN106294125A (en) * | 2016-07-25 | 2017-01-04 | 重庆农村商业银行股份有限公司 | Core banking system data processing method |
| CN107749031A (en) * | 2017-11-29 | 2018-03-02 | 南京甄视智能科技有限公司 | Risk control system after the automatic update method of risk control system, loan after loan |
| CN108334452A (en) * | 2018-02-08 | 2018-07-27 | 深圳壹账通智能科技有限公司 | Regular data transfers test method, device, computer equipment and storage medium |
| CN108958728A (en) * | 2018-05-18 | 2018-12-07 | 深圳壹账通智能科技有限公司 | Loan product development approach, device, equipment and computer storage medium |
-
2018
- 2018-12-14 CN CN201811530396.5A patent/CN109785111A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090001526A (en) * | 2007-04-23 | 2009-01-09 | 인피언컨설팅 주식회사 | Testing system of user interface for financial contract and testing method using thereof |
| CN104461863A (en) * | 2014-10-29 | 2015-03-25 | 中国建设银行股份有限公司 | Service system testing method, device and system |
| CN106294125A (en) * | 2016-07-25 | 2017-01-04 | 重庆农村商业银行股份有限公司 | Core banking system data processing method |
| CN107749031A (en) * | 2017-11-29 | 2018-03-02 | 南京甄视智能科技有限公司 | Risk control system after the automatic update method of risk control system, loan after loan |
| CN108334452A (en) * | 2018-02-08 | 2018-07-27 | 深圳壹账通智能科技有限公司 | Regular data transfers test method, device, computer equipment and storage medium |
| CN108958728A (en) * | 2018-05-18 | 2018-12-07 | 深圳壹账通智能科技有限公司 | Loan product development approach, device, equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107066616A (en) | Method, device and electronic equipment for account processing | |
| CN109241711A (en) | User behavior recognition method and device based on prediction model | |
| CN109376766B (en) | Portrait prediction classification method, device and equipment | |
| CN105844283A (en) | Method for identifying category of image, image search method and image search device | |
| CN111767707A (en) | Method, device, equipment and storage medium for detecting Rayleigh case | |
| CN108665166A (en) | A kind of training method and device of risk control model | |
| CN109034194A (en) | Transaction swindling behavior depth detection method based on feature differentiation | |
| CN106529110A (en) | Classification method and equipment of user data | |
| CN111652280A (en) | Behavior-based target object data analysis method and device and storage medium | |
| CN103871044A (en) | Image signature generating method and image verifying method and device | |
| CN108268886A (en) | For identifying the method and system of plug-in operation | |
| CN106874306B (en) | Method for evaluating key performance index of population information portrait comparison system | |
| CN110502694A (en) | Lawyer's recommended method and relevant device based on big data analysis | |
| CN116012131A (en) | Method, system, device and medium for evaluating credit risk of user | |
| CN114090985A (en) | Method and device for setting user operation permission in block chain and electronic equipment | |
| CN114639152A (en) | Multi-modal voice interaction method, device, equipment and medium based on face recognition | |
| CN114663705A (en) | Video auditing model training method, video auditing method and related device | |
| CN106355066A (en) | Face authentication method and face authentication device | |
| CN113724061A (en) | Consumer financial product credit scoring method and device based on customer grouping | |
| CN107402878A (en) | Method of testing and device | |
| CN110555007B (en) | Method and device for discriminating theft behavior, computing equipment and storage medium | |
| CN117235633A (en) | Mechanism classification method, mechanism classification device, computer equipment and storage medium | |
| CN109785111A (en) | Produce verification process test method, device, computer equipment and storage medium | |
| Garris et al. | NIST fingerprint evaluations and developments | |
| CN113946579A (en) | Model-based data generation method and device, computer equipment and storage medium |
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 |