CN109325102A - A kind of method identifying illegal document and identification device - Google Patents
A kind of method identifying illegal document and identification device Download PDFInfo
- Publication number
- CN109325102A CN109325102A CN201811094734.5A CN201811094734A CN109325102A CN 109325102 A CN109325102 A CN 109325102A CN 201811094734 A CN201811094734 A CN 201811094734A CN 109325102 A CN109325102 A CN 109325102A
- Authority
- CN
- China
- Prior art keywords
- document
- value
- data
- field
- aiming field
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the present application discloses a kind of method for identifying illegal document, comprising: determines the corresponding exceptional value of aiming field according to history bills data;Target document is obtained, target document includes aiming field;Judge whether aiming field corresponding value in target document matches with exceptional value;If matching, prompting target document is illegal document.The embodiment of the present application also provides corresponding identification device.Technical scheme can efficiently identify out illegal document during checking a large amount of documents, solve the problems, such as to check brought by a large amount of documents by this angle of credit score, improve verification efficiency and accuracy.
Description
Technical field
This application involves identification technology fields, and in particular to a kind of method for identifying illegal document and identification device.
Background technique
It is well known that document be economic work occur when it is acquired or fill and present, state clearly transaction, item actual conditions
Written document, such as material requistion, storage bill etc..During the financial management of enterprise, it is the original money for carrying out accounting
Material and important evidence, so the financial staff of every enterprise can spend a large amount of energy in the verification of document, for example verification is single
According to contents such as upper personnel, the amount of money, reasons.Today of financial management software is generally used in enterprise, document is checked by software
Accuracy and the normative efficiency that decide finicial administration of enterprise.
In existing technology, verification document generallys use this verification mode of credit, it is mainly with credit score
Foundation.When most, the bill of lading of the low people of credit score is paid close attention to as potential illegal document,
And the bill of lading of the people high for credit score would not be excessive concern.
Therefore, when needing to check a large amount of document, from can only being carried out from credit score using credit, angle is more single
One, it is difficult to illegal document is found in audit process.
Summary of the invention
The embodiment of the present application provides a kind of method for identifying illegal document and identification device, can be a large amount of single in verification
During, illegal document is efficiently identified out.
In view of this, the embodiment of the present application provides following scheme:
The application first aspect provides a kind of method for identifying illegal document, may be used in financial field, and the identification is non-
The method of method document may include: to determine the corresponding exceptional value of aiming field according to history bills data;Obtain target document, mesh
Marking document includes aiming field;Judge whether aiming field corresponding value in target document matches with exceptional value;If matching,
Prompt target document is illegal document.The history bills data, which can be, to be had stored in database, and aiming field can wrap
A plurality of types of fields are included, such as: value type, literal type etc..By the above first aspect as it can be seen that target document can be passed through
In the corresponding value of aiming field matched with the exceptional value determined according to history bills data, if matching, so that it may
To think the target document, there are higher illegal potential risks, and can thus prompt the document is illegal document;It solves
During checking a large amount of document, this single angle of credit score is only relied on to identify problem brought by illegal document, is had
Identify illegal document to effect.
Optionally, with reference to the above first aspect, in the first possible implementation, determined according to history bills data
The corresponding exceptional value of aiming field, may include: divide history bills data in the corresponding value of aiming field be N number of data group, N
For positive integer;It calculates the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group, abnormal accounting passes through
Abnormal document quantity and document sum are calculated, and document sum belongs to the number of institute's documentary of data group for the value of aiming field
Amount, abnormal document quantity for document illegal in institute's documentary quantity;The difference of abnormal accounting and average accounting is greater than default
The data group of threshold value is determined as target set of data, and the value in target set of data is determined as to the exceptional value of aiming field.Due to
Different fields belongs to different types, it is possible to the aiming field in history bills data is divided into different types,
It is respectively calculated the abnormal accounting and average accounting of each field in each type again, can be adapted for multiple and different scenes
Lower determining exceptional value, to determine that exceptional value provides multifarious mode.
Optionally, the first mode in the cards with reference to the above first aspect, in the second possible implementation,
Aiming field includes name field, and dividing the corresponding value of aiming field in history bills data is N number of data group, may include:
Divide corresponding each the entitled data group of name field, the quantity of title and be N;Accordingly, by target data
Value in group is determined as after the exceptional value of aiming field, judges that aiming field corresponding value in target document with exceptional value is
No matching, comprising: obtain name field corresponding title in target document;Judge obtain title whether with name field
Exceptional value is identical;If so, prompt target document is illegal document.Since target document may include a plurality of types of target words
Section, but be different aiming field needs to take different statisticals, so when aiming field is name field, so that it may
To determine exceptional value according to the corresponding statistical of name field;Again by the corresponding name of name field in target document
Title is matched with the exceptional value, effectively improves the accuracy of identification.
Optionally, in conjunction with the first mode in the cards of above-mentioned first aspect, in the third possible implementation
In, aiming field includes numeric field, and dividing the corresponding value of aiming field in history bills data is N number of data group, be can wrap
It includes: the corresponding numerical value of arrangement numeric field;Numerical value after dividing arrangement is N number of equidistant section, the numerical value one after each division
One corresponds in section;Determine that N number of equidistant section is N number of data group;Accordingly, it is determined as by the value in target set of data
After the exceptional value of aiming field, judge whether aiming field corresponding value in target document matches with exceptional value, can wrap
It includes: obtaining numeric field corresponding numerical value in target document;Judge whether the numerical value obtained falls into target set of data;If
It is then to prompt target document for illegal document.It, can basis since the corresponding numerical value of numeric field can be divided into section
The corresponding statistical of numeric field determines abnormal section, then judges that the corresponding numerical value of numeric field is in target document
It is no to have fallen in abnormal section, effectively improve the accuracy of identification.
Optionally, in conjunction with the first mode in the cards of above-mentioned first aspect, in the 4th kind of possible implementation
In, aiming field includes similar field, and dividing the corresponding value of aiming field in history bills data is N number of data group, be can wrap
It includes: determining that the similar word of word meaning is similar word in similar field, similar word combination sentence analysis software is obtained with dictionary;
Count class range number and, the number of class range and be N, class range is that the similar word of each class is determined as a class range;
Determine that N number of class range is N number of data group;Accordingly, the exceptional value that the value in target set of data is determined as to aiming field it
Afterwards, judge whether aiming field corresponding value in target document matches with exceptional value, may include: to obtain similar field in mesh
Mark corresponding word in document;Judge whether the word obtained falls into target set of data;If so, prompt target document is non-
Method document.It, can be according to similar field since the similar word of the corresponding word meaning of similar field can be divided into similar word
Corresponding statistical determines abnormal class range, then judges whether the corresponding word of similar field falls in target document
Within the scope of abnormal class, the accuracy and efficiency of identification are effectively improved.
Optionally, in conjunction with above-mentioned in a first aspect, in a fifth possible implementation, according to history bills data
Can also include: acquisition range table before determining the corresponding exceptional value of aiming field, range table include the first table, the second table with
And third table;First incidence relation and the second incidence relation are set, and the first incidence relation is external key and the second table in the first table
In major key between incidence relation, the second incidence relation is being associated between external key and the major key in third table in the second table
Relationship, the external key in the first table are the major key in the second table, and the external key in the second table is the major key in third table, and the first association is closed
System and the second incidence relation are for obtaining history bills data.It, can due to passing through the association between external key and major key between table
To get the data in the table of external key place, the consistency and integrality of data are kept.
The application second aspect provides a kind of identification device, which, which has, realizes that above-mentioned first aspect or first aspect are appointed
Anticipate a kind of possible implementation method function.The function can also be executed corresponding by hardware realization by hardware
Software realization.The hardware or software include one or more units corresponding with above-mentioned function, module or submodule.
The computer equipment that the application third aspect provides, comprising: processor and memory;The memory is for storing journey
Sequence instruction, when the device, which executes the program instruction of memory storage, so that the device executes such as above-mentioned the
The method of the illegal document of identification of any one possible implementation of one side or first aspect.
The application fourth aspect provides a kind of computer readable storage medium, is stored in the computer readable storage medium
Instruction, when run on a computer, allowing computer to execute above-mentioned first aspect or first aspect, any one can
The method for being able to achieve the illegal document of identification of mode.
The 5th aspect of the application provides a kind of computer program product comprising instruction, when run on a computer,
Computer is allowed to execute the illegal document of identification of above-mentioned first aspect or first aspect any one possible implementation
Method.
The 6th aspect of the application provides a kind of chip system, which includes processor, for supporting device to realize
Function involved in above-mentioned first aspect or first aspect any one possible implementation.In a kind of possible design
In, chip system further includes memory, and memory is used for the necessary program instruction of save set and data.The chip system, can
To be made of chip, chip and other discrete devices also may include.
Wherein, any implementation institute band in terms of second aspect, the third aspect, fourth aspect, the 5th, in the 6th aspect
The technical effect come can be found in technical effect brought by different implementations in first aspect, and details are not described herein again.
As can be seen from the above technical solutions, the embodiment of the present application has the advantage that
By dividing different types of aiming field, and in the history bills data of each type after classified types
The corresponding value of aiming field be divided into data group, accounted in conjunction with abnormal accounting and being averaged for all data groups of each data group
The corresponding exceptional value of aiming field than determining each type, then by the aiming field pair of each type in target document
The value answered is matched with the exceptional value determined, if matching, then prompting target document is illegal document;It thus can be big in verification
During measuring document, illegal document is efficiently identified out, solves by this angle of credit score and checks a large amount of documents
Brought problem improves verification efficiency and accuracy.
Detailed description of the invention
Fig. 1 is that illegal document schematic diagram of a scenario is identified in the embodiment of the present application;
Fig. 2 is one embodiment schematic diagram of the illegal document method of identification provided by the embodiments of the present application;
Fig. 3 is another embodiment schematic diagram of the illegal document method of identification provided by the embodiments of the present application;
Fig. 4 is another embodiment schematic diagram of the illegal document method of identification provided by the embodiments of the present application;
Fig. 5 is another embodiment schematic diagram of the illegal document method of identification provided by the embodiments of the present application;
Fig. 6 is one embodiment schematic diagram of identification device provided by the embodiments of the present application;
Fig. 7 is another embodiment schematic diagram of identification device provided by the embodiments of the present application;
Fig. 8 is another embodiment schematic diagram of identification device provided by the embodiments of the present application.
Specific embodiment
The embodiment of the present application provides a kind of method for identifying illegal document.The embodiment of the present application also provides corresponding dress
It sets, illegal document can be efficiently identified out during checking a large amount of documents.
Fig. 1 is that illegal document schematic diagram of a scenario is identified in the embodiment of the present application.
In the field for being related to finance, document is often the firsthand information and important evidence for carrying out accounting, it is
When economic work occurs it is acquired or fill and present, state clearly transaction, the written document of item actual conditions, such as the economic work
Involved fund, these economic interactions when who generate will all embody in document when generation.
And in financial field, attention is usually all compared to the truth of document, is required a great deal of time, energy
Document is checked at original.And field present in every document, existing content-form are different, require by warp
It tests with credit score and checks the true and false, angle is more single, cannot reasonably identify illegal document.
As shown in Figure 1, in the expenses claim sheer include multiple fields, such as the amount of money, description of use, payee, handler,
Identifier etc., these fields belong to different classifications, if the amount of money is indicated with numerical value, payee, handler and identifier
All it is that name title indicates, then belongs to text class declaration for illustrating.Therefore difference is directed to by identification device in this programme
The different statistical method judgement of the field utilization of type and the true and false for identifying the expense reimbursement document.
Identification device involved by above-mentioned Fig. 1 can be server either terminal device, specifically without limitation.
Figure 1 above is the introduction to the schematic diagram of a scenario of this programme, in order to make it easy to understand, the embodiment of the present application is described below
The method of the provided illegal document of identification.
Fig. 2 is one embodiment schematic diagram of the illegal document method of identification provided by the embodiments of the present application.
As shown in Fig. 2, one embodiment of the illegal document method of identification provided by the embodiments of the present application includes:
201, the corresponding exceptional value of aiming field is determined according to history bills data.
In this implementation, it can know which history document is illegal from the data in history document, therefore herein
On the basis of can know the corresponding exception field of the illegal document of history, then can be from the off-note in the illegal document of history
Know exceptional value.
202, target document is obtained, target document includes aiming field.
In the present embodiment, target document is the document newly got, and may include that there are many types in target document
Aiming field.Such as: aiming field may include one or more words such as name field, numeric field and similar field
Section, the similar field being previously mentioned refer to that those words similar word of anticipating is formed by field, and the value in the field is can be with
The word expressed with a variety of different literals, such as: the words such as sick, uncomfortable and medical treatment are exactly taking in a similar field
Value.
203, judge whether aiming field corresponding value in target document matches with exceptional value.
In the present embodiment, need to determine the corresponding value of aiming field in target document and according to history bills data
Exceptional value matched, and judge whether the value and exceptional value match, play the precision that one is improved identification and make
With.
If 204, matching, prompting target document is illegal document.
In the present embodiment, is judging the corresponding value of the aiming field in target document and determined according to history bills data
After exceptional value out matches, then can illustrate aiming field in the target document there are higher abnormal risk,
Prompting user's target document according to this abnormal risk result in this way is illegal document.
It should be noted that if being not match, then can think existing for the aiming field in target document
Abnormal risk is lower, can be ignored the risk.
In the present embodiment, by judging that the corresponding value of aiming field in target document is determined with according to history bills data
Whether exceptional value out matches, if matching, then prompting target document is illegal document;The embodiment can be a large amount of single in verification
During, illegal document is efficiently identified out, improves verification efficiency and accuracy.
In the technical scheme, since aiming field may include a variety of different types of fields, and each type is corresponding
Field need just determine the corresponding exceptional value of respective type using different statistical methods.
Aiming field is divided below, the illegal document of identification provided by the embodiments of the present application is described in detail respectively
Scheme.
1, aiming field includes name field;
2, aiming field includes numeric field;
3, aiming field includes similar field.
It should be noted that 3 above-mentioned schemes are provided to carry out aiming field the division of type, for inhomogeneity
The corresponding field of type determines the corresponding exceptional value of aiming field using different statisticals, and purpose, which is provided to improve, to be known
Other accuracy.
1, aiming field includes name field
The present embodiment is only illustrated so that aiming field includes name field as an example.Fig. 3 is provided by the embodiments of the present application
Identify another embodiment schematic diagram of illegal document method.
As shown in figure 3, illegal another embodiment of document method of identification provided by the embodiments of the present application includes:
301, range table is obtained, which includes the first table, the second table and third table.
In the present embodiment, since history document is potentially stored in database either cloud, and we can not be used
Whole documents carries out the determination of exceptional value, thus only by fetching portion document as sample progress exceptional value really
It is fixed.
It should be noted that above-mentioned the first table referred to can be document examination record sheet, the second table can be to be recorded with document examination
The associated table of table is set as contingency table, and third table can be and the related table of the contingency table.Range table be with have already passed through it is careful
The document of core is relevant, and the document for having already passed through audit will record in document examination record sheet, and obstructed in document examination record sheet
The document record crossed can use label record.
302, the first incidence relation and the second incidence relation are set, for obtaining history bills data.
In the present embodiment, after obtaining above range table, we do not know how we look for from these range tables
To the history bills data of needs.Such as, it is assumed that there are major key and the member of employee's field in document examination record sheet namely the first table
The relevant bills data of this field of work is stored in other documents, it is assumed that needs to count this field of employee and abnormal document
Relationship, then just employee's table and document examination record sheet must be associated, the second table and the of this sort principle of third table.Cause
This needs to be arranged the association of each table, convenient for obtaining required history bills data.
It should be noted that the first incidence relation is being associated between external key and the major key in the second table in the first table
System, the second incidence relation is the incidence relation between the major key in the external key in the second table and third table, the external key in the first table
For the major key in the second table, the external key in the second table is the major key in third table, and the first incidence relation and the second incidence relation are
For obtaining history bills data.
Such as: assuming that the first table is document examination record sheet, it include this external key of employee number in document examination record sheet, and outside this
Key is the major key in employee's table, because this major key of the employee number of employee's table can be with the data in unique identification employee's table.Than
Such as, employee number 1 is uniquely corresponding to this employee's title of Zhang San.
Document examination record sheet
Document number | Employee number |
01 | 1 |
02 | 2 |
Employee's table
Employee number | Employee's title |
1 | Zhang San |
2 | Li Si |
Second table and third it is of this sort be associated with principle.
303, each corresponding entitled data group of name field is divided according to history bills data.
In the present embodiment, since name field all includes usually one or more titles, by dividing name field
Each name is referred to as a data group by each corresponding title, and the quantity of data group is N number of at this time, and N is positive integer;
It facilitates in this way and calculates separately each title and namely calculate the document quantity for including in each data group.
It should be noted that name field may include Business Name, employee's title or document examination person's title;In practical application
In, it can also include more to illustrate other titles of the name field meaning, but as long as being related to the content in document
Name field;Specifically herein without limitation.
304, the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group are calculated.
In the present embodiment, each corresponding entitled data group of name field is being divided according to history bills data
Later, so that it may calculate the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group.
It should be noted that the corresponding abnormal accounting of each data group is the abnormal document quantity and the group by the group
Bills data sum obtain, the corresponding average accounting of N number of data group be by abnormal document quantity in N number of data group and
All document sums obtain in this N number of data group, generally use division and are handled.
Further illustrate be, it is assumed that name field be personnel's title, which may include Zhang San, Li Si, king five;This
When as N=3, it is assumed that history bills data relevant to this field of personnel's title is 10000 parts, wherein abnormal document quantity
It is 3000 parts;The corresponding document sum of this data group of Zhang San is 2000 parts, wherein abnormal document quantity is 250 parts;Li Si this
The corresponding document sum of a data group is 4000 parts, wherein abnormal document quantity is 2000 parts;This data group of king five is corresponding
Document sum is 3000 parts, wherein abnormal document quantity is 750 parts;
So, the corresponding average accounting of this 3 data groups is 2000/10000=0.2;This data group of Zhang San is corresponding
Abnormal accounting is 250/2000=0.125;The corresponding abnormal accounting of this data group of Li Si is 2000/4000=0.5;King five this
The corresponding abnormal accounting of a data group is 750/4000=0.1875.
305, the data group that the difference of abnormal accounting and average accounting is greater than preset threshold is determined as target set of data, and
Value in target set of data is determined as the corresponding exceptional value of name field.
It, can be different after calculating the abnormal accounting in above-mentioned each data group and average accounting in the present embodiment
Normal accounting and average accounting make difference calculating, and after calculating difference and preset threshold one numerical value of work compare;If big
In preset threshold, then being just determined as target set of data the corresponding data group of preset threshold is greater than, can thus determine
Value in target set of data is exactly the corresponding exceptional value of name field.
It should be noted that the preset threshold be judge a data group in value whether be exceptional value boundary.Such as:
Assuming that preset threshold can be 0.1, at this time: the corresponding difference of this data group of Zhang San be 0.125-0.2=-0.075, Li Si this
The corresponding difference of a data group is 0.5-0.2=0.3, and the corresponding difference of this data group of king five is 0.1875-0.2=-
0.0125;So at this time it is known that Li Si is exactly this target set of data, and Li Si is the corresponding exceptional value of name field;
In practical applications, preset threshold can also be other values, specifically herein without limitation.
306, target document is obtained, includes name field in target document.
In this implementation, after the value in target set of data is determined as the exceptional value of name field, so that it may by obtaining
Target document is taken to obtain name field corresponding title in target document.Such as: the name field got includes personnel
Title, the title in personnel's title includes Zhang Ming, Li Si, Wang Lin etc..
307, judge whether the title obtained is identical as the value in target set of data.
In the present embodiment, after obtaining the corresponding title of name field these values in target document, so that it may pass through
Judge whether these values i.e. title are identical as the exceptional value determined.Such as: from above-mentioned it is known that in name field
Exceptional value is Li Si, and the title in target document got includes Zhang Ming, Li Si, Wang Lin etc., and being clear can know at this time
Li Si has matched exceptional value in road target document.
308, if so, prompt target document is illegal document.
In the present embodiment, when judging that the corresponding title of name field is corresponding with the name field determined in target document
Exceptional value it is identical when, so that it may prompting the target document where the title is an illegal document.Such as: above-mentioned target list
Li Si in is exceptional value, then the target document where can prompting exceptional value Li Si is illegal document.
In the present embodiment, when aiming field is divided into name field, by calculating each of name field title
Average accounting under corresponding abnormal accounting and the name field makees abnormal accounting and average accounting after difference the difference
Compared with preset threshold, determine to be greater than the corresponding entitled exceptional value of preset threshold;By judge the title that gets with it is different
Whether constant value is identical, if identical, the target document where prompting the title is abnormal document.The embodiment can checked
During a large amount of documents, illegal document is efficiently identified out, improves verification efficiency and accuracy.
2, aiming field includes numeric field
The present embodiment is only illustrated so that aiming field includes numeric field as an example.Fig. 4 is provided by the embodiments of the present application
Identify another embodiment schematic diagram of illegal document method.
As shown in figure 4, illegal another embodiment of document method of identification provided by the embodiments of the present application includes:
401, range table is obtained, which includes the first table, the second table and third table.
402, the first incidence relation and the second incidence relation are set, for obtaining history bills data.
Step 301-302 in the present embodiment is similar with the step 201-202 in Fig. 2, is not repeated herein.
403, the corresponding numerical value of numeric field is arranged according to history bills data.
In the present embodiment, since the numerical value in numeric field may include one or more numerical value, counts, need for convenience
The corresponding numerical value of numeric field is subjected to arrangement statistics, which can be ascending order and be also possible to descending, can also be
Other arrangement modes, specifically herein without limitation.
404, the numerical value after dividing arrangement is N number of equidistant section, and the numerical value after each division corresponds in section.
In the present embodiment, in arrangement history document after the corresponding numerical value of numerical value, so that it may the number after arranging these
Value carries out the division in section, so that each numerical value has and can only be divided into one of section.
Such as: assuming that numeric field is this field of the amount of money, then in history bills data inherently comprising amount field
It being corresponding with including one or more numerical value, it is assumed that the corresponding numerical upper limits of amount field are 5000 yuan, and lower limit is 200 yuan,
He sort after numerical value may include 300,480,550,600,730,790,820 ..., 4890,4999 etc..It will if incited somebody to action at this time
Section is divided into 30 parts, i.e. when N=30, then group is away from e=(upper limit-lower limit)/30, i.e. e=(5000-200)/30=160, so
Section is just divided at this time: [200,360), [360,520), and [520,680), [680,840) ... [4840,5000).
405, determine that N number of equidistant section is N number of data group.
In the present embodiment, the corresponding numerical division of amount field be section after, so that it may each section is regarded
One data group, then this 30 groups are assured that away from the section for 160 as 30 data groups.In practical applications, certainly
It further include more sections, specifically herein without limitation.
406, the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group are calculated.
In the present embodiment, determining that each corresponding section of numeric field is a data according to history bills data
After group, so that it may calculate the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group.
It should be noted that the corresponding abnormal accounting of each data group is the abnormal document quantity and the group by the group
Document sum obtain, the corresponding average accounting of N number of data group is by the abnormal document quantity and this N in N number of data group
All document sums obtain in a data group, generally use division and are handled.
Further illustrate be, it is assumed that amount field and section using above-mentioned steps 304.Assuming that this 30 areas at this time
Between in include document quantity be 20000 parts, wherein abnormal document quantity is 3000 parts;Wherein section [200,360) the list in
Data bulk is 500 parts, and abnormal document quantity is 60 parts;Section [360,520) in document quantity be 1000 parts, abnormal document number
Amount is 50 parts;Section [520,680) in document quantity be 3000 parts, abnormal document quantity be 450 parts;Section is [680,840)
In document quantity be 1500 parts, abnormal document quantity be 450 parts;... [4840,5000) the document quantity in is 800 in section
Part, abnormal document quantity is 180 parts;
So, the corresponding average accounting of this 30 data groups is 3000/20000=0.15;Data group is [200,360) corresponding
Abnormal accounting be 60/500=0.12;[360,520) corresponding abnormal accounting is 50/1000=0.05 to data group;Data group
[520,680) corresponding abnormal accounting is 450/3000=0.15;[680,840) corresponding abnormal accounting is 450/ to data group
1500=0.3;... [4840,5000) corresponding abnormal accounting is 180/800=0.225 to data group.
407, the data group that the difference of abnormal accounting and average accounting is greater than preset threshold is determined as target set of data, and
Value in target set of data is determined as the corresponding exceptional value of numeric field.
It, can be different after calculating the abnormal accounting in above-mentioned each data group and average accounting in the present embodiment
Normal accounting and average accounting make difference calculating, and after calculating difference and preset threshold one numerical value of work compare;If big
In preset threshold, then being just determined as target set of data the corresponding data group of preset threshold is greater than, can thus determine
Value in target set of data is exactly the corresponding exceptional value of numeric field.
Such as: amount field and corresponding section using above-mentioned steps 306, it is assumed that preset threshold 0.1, at this time:
[200,360) corresponding difference is 0.12-0.15=-0.03 to data group;[360,520) corresponding difference is 0.05- to data group
0.15=-0.1;[520,680) corresponding difference is 0.15-0.15=0 to data group;Data group [680,840) corresponding difference
For 0.3-0.15=0.15;... [4840,5000) corresponding difference is 0.225-0.15=0.075 to data group;So at this time
It is known that data group [680,840) be exactly this target set of data, and data group [680,840) in numerical value be the amount of money
The corresponding exceptional value of field.
408, target document is obtained, includes numeric field in target document.
In this implementation, after the value in target set of data is determined as the exceptional value of numeric field, so that it may by obtaining
Target document is taken to obtain numeric field corresponding numerical value in target document.
Such as: the numeric field got includes amount field, and the numerical value in amount field includes 280,720 etc..
409, judge whether the numerical value obtained falls into target set of data.
In the present embodiment, after obtaining the corresponding amount of money numerical value of amount field in target document, so that it may by sentencing
Break these numerical value whether with fall into the target set of data determined.
Such as: from it is above-mentioned it is known that in amount field data group [680,840) in include exceptional value, and get
Amount of money numerical value in target document includes 280,720 etc., is clear 280 this numerical value it is known that in target document at this time
And data group is not fallen within [680,840) in.And numerical value 720 fall into data group [680,840) in, then illustrate 720 to be one different
Constant value.
410, if so, prompt target document is illegal document.
In the present embodiment, when judging that the corresponding numerical value of numeric field falls into the numeric field pair determined in target document
When in the target set of data answered, so that it may which the target document where prompting the numerical value is an illegal document.
Such as: the numerical value 720 in above-mentioned target document is exceptional value, then where can prompting the exceptional value 720
Target document be illegal document.
It include the mesh of exceptional value by judging whether the corresponding numerical value of numeric field got falls into the present embodiment
It marks in data group, if the target document where then prompting the numerical value is illegal document.The embodiment can be a large amount of single in verification
During, illegal document is efficiently identified out, improves verification efficiency and accuracy.
3, aiming field includes similar field
The present embodiment is only illustrated so that aiming field includes similar field as an example.Fig. 5 is provided by the embodiments of the present application
Identify another embodiment schematic diagram of illegal document method.
As shown in figure 5, illegal another embodiment of document method of identification provided by the embodiments of the present application includes:
501, range table is obtained, which includes the first table, the second table and third table.
502, the first incidence relation and the second incidence relation are set, for obtaining history bills data.
Step 501-502 in the present embodiment is similar with the step 301-302 in Fig. 2, is not repeated herein.
503, determine that the similar word of word meaning is similar word in similar field according to history bills data, similar word is to combine
What sentence analysis software and dictionary obtained.
In the present embodiment, it be not that the word similar in the word in similar field is anticipated can not be gone out by equipment Direct Recognition
It is the word of similar import, so being identified in conjunction with sentence analysis software with dictionary, and determines which word is can to make
For of a sort word.
It should be noted that the similar field being previously mentioned refers to that the similar word of those words meaning is formed by field, such as
Reason, annotation, remarks etc.;Word in these fields can be with diversified literal expression, but all be that expression is same
A meaning.To the field value of similar field, specifically herein without limitation.
Such as: the reason field in reimbursement document, so that it may expressed by the word of multiple similar imports.It is sick, no
The words such as suitable or medical treatment are exactly the value in this field of reason, but are all this sick meanings of expression, it is possible to will be given birth to
The words such as disease, uncomfortable or medical treatment are as similar word.
504, count class range number and, the number of class range and be N, class range is that the similar word of each class is determined as
One class range.
In the present embodiment, after obtaining the similar word in similar field to dictionary in conjunction with sentence analysis software, then just
The similar word of each class can be determined as a class range, whole class range numbers can be calculated at this time.
Such as: the reason field in above-mentioned steps 503 can also include: exceed the time limit, time-out or the similar word such as overdue, then
It can will exceed the time limit, time-out or overdue etc. be used as a class range.So at this time the number of class range and be N=2;In practical application
In, cause field further includes the similar word for more expressing the same meaning, specifically herein without limitation.
505, determine that N number of class range is N number of data group
In the present embodiment, after similar word that cause field is corresponding is determined as class range, so that it may each class model
It encloses as a data group, then this 2 class ranges are assured that as 2 data groups.In practical applications, further include certainly
More class ranges, specifically herein without limitation.
506, the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group are calculated.
In the present embodiment, determining that each corresponding class range of cause field is a number according to history bills data
After group, so that it may calculate the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group.
Assuming that using the class range of above-mentioned steps 504 and 505.Assuming that the document quantity for including in this 2 data groups at this time
It is 3000 parts, wherein abnormal document quantity is 600 parts;Wherein the document quantity in the data group where this sick word is
800 parts, abnormal document quantity is 380 parts;The document quantity in data group where this overdue word is 2200 parts, abnormal single
Data bulk is 220 parts;
So, the corresponding average accounting of this 2 data groups is 600/3000=0.2;Data where this sick word
The corresponding abnormal accounting of group is 380/800=0.475;The corresponding abnormal accounting of data group where this overdue word is 220/
2200=0.1.
507, the data group that the difference of abnormal accounting and average accounting is greater than preset threshold is determined as target set of data, and
Value in target set of data is determined as the corresponding exceptional value of similar field.
It, can be different after calculating the abnormal accounting in above-mentioned each data group and average accounting in the present embodiment
Normal accounting and average accounting make difference calculating, and after calculating difference and preset threshold make comparisons;If being greater than default threshold
Value can thus determine target data then being just determined as target set of data the corresponding data group of preset threshold is greater than
Value in group is exactly the corresponding exceptional value of similar field.
Such as: the reason of using above-mentioned steps 506 field and corresponding data group, it is assumed that preset threshold 0.1, this
When: the corresponding difference of data group where this sick word is 0.475-0.2=0.275;Number where this overdue word
It is 0.1-0.2=-0.1 according to corresponding difference is organized;So at this time it is known that the data group where this sick word is exactly this
A target set of data, and word in the data group is sick, uncomfortable or be exactly the corresponding exceptional value of the cause field.
508, target document is obtained, includes similar field in target document.
In this implementation, after the value in target set of data is determined as the exceptional value of similar field, so that it may by obtaining
Target document is taken to obtain similar field corresponding word in target document.
Such as: the similar field got includes cause field, and the word in cause field includes discomfort etc.;Specifically herein
Without limitation.
509, judge whether the word obtained falls into target set of data.
In the present embodiment, after obtaining the corresponding word of reason field in target document, so that it may by judging this
Whether a little words fall into the target set of data determined.
Such as: it include exceptional value from above-mentioned be known that in cause field, and the word in the target document got is
Discomfort is clear this uncomfortable word being known that in target document at this time and falls in data group, illustrates that discomfort is one
A exceptional value.
510, if so, prompt target document is illegal document.
In the present embodiment, when judging that the corresponding word of similar field falls into the similar field pair determined in target document
When in the target set of data answered, so that it may which the target document where prompting the word is an illegal document.
Such as: this uncomfortable word in above-mentioned target document is exceptional value, then the exceptional value can be prompted not
Target document where suitable is illegal document.
It include the mesh of exceptional value by judging whether the corresponding word of similar field got falls into the present embodiment
It marks in data group, if the target document where then prompting the word is illegal document.The embodiment can be a large amount of single in verification
During, illegal document is efficiently identified out, improves verification efficiency and accuracy.
It is above-mentioned that mainly scheme provided by the embodiments of the present application is described from unilateral angle.It can be understood that being
Realization above-mentioned function contains and executes the corresponding hardware configuration of each function and/or software module.Those skilled in the art answer
This is readily appreciated that, module described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm steps, the application energy
The combining form with hardware or hardware and computer software is reached to realize.Some function is driven actually with hardware or computer software
The mode of dynamic hardware executes, the specific application and design constraint depending on technical solution.Professional technician can be right
Each specific application is to use different methods to achieve the described function, but this realization is it is not considered that exceed the application
Range.
The embodiment of the present application can carry out the division of functional module according to above method example to device, for example, can be right
The each functional module of each function division is answered, two or more functions can also be integrated in a processing module.
Above-mentioned integrated module both can take the form of hardware realization, can also be realized in the form of software function module.It needs
Illustrate, is schematical, only a kind of logical function partition to the division of module in the embodiment of the present application, it is practical to realize
When there may be another division manner.
Fig. 6 is one embodiment schematic diagram of identification device provided by the embodiments of the present application.
As shown in fig. 6, identification device provided by the embodiments of the present application includes determination unit 601, acquiring unit 602, judgement
Unit 603, prompt unit 604;
Determination unit 601, for determining the corresponding exceptional value of aiming field according to history bills data;
Acquiring unit 602, for obtaining target document, target document includes the exceptional value pair that determination unit 601 is determined
The aiming field answered;
Judging unit 603, for judge aiming field in the target document that acquiring unit 602 obtains out corresponding value with
Whether the exceptional value that determination unit is determined matches;
Prompt unit 604, the aiming field for judging when judging unit 603 is in the corresponding value of target document and exception
When value matching, prompt target document is illegal document.
In the present embodiment, whether the corresponding value of aiming field got by judgement matches with the exceptional value determined,
If the target document where then prompting the value is illegal document.The embodiment can have during checking a large amount of documents
It identifies illegal document to effect, improves verification efficiency and accuracy.
The identification device in the embodiment of the present application is understood in detail in order to make it easy to understand, please referring to Fig. 7, Fig. 7 is
Another embodiment schematic diagram of identification device in the embodiment of the present application, including determination unit 701, acquiring unit 702, judging unit
703, prompt unit 704, it is similar with the function of above-mentioned 601-604;
Determination unit 701 in the present embodiment may include:
Division module 7011 is N number of data group for dividing the corresponding value of aiming field described in history bills data;
Computing module 7012, the corresponding abnormal accounting of each data group divided for computation partition module 7011 and draws
The corresponding average accounting of N number of data group that sub-module 7011 divides;
Determining module 7013, it is pre- for the difference of the calculated abnormal accounting of computing module 7012 and average accounting to be greater than
If the data group of threshold value is determined as target set of data, and the value in target set of data is determined as to the exceptional value of aiming field.
In the present embodiment, whether the corresponding value of aiming field got by judgement matches with the exceptional value determined,
If the target document where then prompting the value is illegal document.The embodiment can have during checking a large amount of documents
It identifies illegal document to effect, improves verification efficiency and accuracy.
The identification device in the embodiment of the present application is described from the angle of modular functionality entity above, below from hard
The identification device module in the embodiment of the present application is described in the angle of part processing, referring to Fig. 8, in the embodiment of the present application
Include: with another embodiment of identification
Input interface 801, output interface 802, processor 803 and memory 804, (the wherein processor in identification device
801 quantity can be one or more, in Fig. 8 by taking a processor 801 as an example).In some embodiments of the present application, input
Interface 801, output interface 802, processor 803 and memory 804 can be connected by bus or other means, wherein in Fig. 8 with
For being connected by bus.
By the operational order for calling memory 804 to store, processor 803, the identification for realizing above-mentioned offer is illegal
The embodiment of document.
Specifically, determination unit 601, acquiring unit 602 in Fig. 6, judging unit 603, prompt unit 604, in Fig. 7
Determination unit 701, acquiring unit 702, judging unit 703, prompt unit 704, division module 7011, computing module 7012 and
The function of determining module 7013/realization process can call the calculating stored in memory 804 by the processor 803 in Fig. 8
Machine executes instruction to realize.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the application
Portion or part steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
The above, above embodiments are only to illustrate the technical solution of the application, rather than its limitations;Although referring to before
Embodiment is stated the application is described in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features;And these
It modifies or replaces, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of method for identifying illegal document characterized by comprising
The corresponding exceptional value of aiming field is determined according to history bills data;
Target document is obtained, the target document includes the aiming field;
Judge whether the aiming field corresponding value in the target document matches with the exceptional value;
If matching, prompting the target document is illegal document.
2. the method according to claim 1, wherein determining that aiming field is corresponding different according to history bills data
Constant value, comprising:
Dividing the corresponding value of aiming field described in history bills data is N number of data group, and the N is positive integer;
Calculate the corresponding abnormal accounting of each data group and the corresponding average accounting of N number of data group, the exception accounting
It is calculated by abnormal document quantity and document sum, the document sum is that the value of aiming field belongs to the data group
The quantity of institute's documentary, it is described exception document quantity for document illegal in institute's documentary quantity;
The data group that the difference of the abnormal accounting and the average accounting is greater than preset threshold is determined as target set of data, and
Value in the target set of data is determined as to the exceptional value of the aiming field.
3. according to the method described in claim 2, dividing history list it is characterized in that, the aiming field includes name field
It is N number of data group according to the corresponding value of aiming field described in data, comprising:
Divide each corresponding entitled data group of the name field, the quantity of the title and be N;
Accordingly, after the value in the target set of data is determined as the exceptional value of the aiming field, judge the mesh
Whether marking-up section corresponding value in the target document matches with the exceptional value, comprising:
Obtain the name field corresponding title in the target document;
Judge whether the title of the acquisition is identical as the exceptional value of the name field;
If so, prompting the target document is illegal document.
4. according to the method described in claim 2, dividing history list it is characterized in that, the aiming field includes numeric field
It is N number of data group according to the corresponding value of aiming field described in data, comprising:
Arrange the corresponding numerical value of the numeric field;
Numerical value after dividing arrangement is N number of equidistant section, and the numerical value after each division corresponds in the section;
Determine that N number of equidistant section is N number of data group;
Accordingly, after the value in the target set of data is determined as the exceptional value of the aiming field, judge the mesh
Whether marking-up section corresponding value in the target document matches with the exceptional value, comprising:
Obtain the numeric field corresponding numerical value in the target document;
Judge whether the numerical value of the acquisition falls into the target set of data;
If so, prompting the target document is illegal document.
5. according to the method described in claim 2, dividing history list it is characterized in that, the aiming field includes similar field
It is N number of data group according to the corresponding value of aiming field described in data, comprising:
Determine that the similar word of word meaning is similar word in the similar field, the similar word is to combine sentence analysis software and word
What library obtained;
Count class range number and, the number of the class range and be N, the class range is that the similar word of each class is determined as
One class range;
Determine that N number of class range is N number of data group;
Accordingly, after the value in the target set of data is determined as the exceptional value of the aiming field, judge the mesh
Whether marking-up section corresponding value in the target document matches with the exceptional value, comprising:
Obtain the similar field corresponding word in the target document;
Judge whether the word of the acquisition falls into the target set of data;
If so, prompting the target document is illegal document.
6. the method according to claim 1, wherein determining that aiming field is corresponding according to history bills data
Before exceptional value, further includes:
Range table is obtained, the range table includes the first table, the second table and third table;
First incidence relation and the second incidence relation be set, first incidence relation be external key in first table with it is described
The incidence relation between major key in second table, second incidence relation are external key and the third table in second table
In major key between incidence relation, the external key in first table is the major key in second table, in second table
External key is the major key in the third table, and first incidence relation and second incidence relation are for obtaining the history
Bills data.
7. a kind of identification device characterized by comprising
Determination unit, for determining the corresponding exceptional value of aiming field according to history bills data;
Acquiring unit, for obtaining target document, the target document includes the exceptional value that the determination unit is determined
The corresponding aiming field;
Judging unit, for judging the aiming field corresponding value in the target document that the acquiring unit obtains out
Whether matched with the exceptional value that the determination unit is determined;
Prompt unit, for judging the aiming field corresponding value and institute in the target document when the judging unit
When stating exceptional value matching, prompting the target document is illegal document.
8. identification device according to claim 7, which is characterized in that the determination unit, comprising:
Division module is N number of data group for dividing the corresponding value of aiming field described in history bills data;
Computing module, for calculating the corresponding abnormal accounting of each data group and the division mould that the division module divides
The corresponding average accounting of N number of data group that block divides, the exception accounting are calculated by abnormal document quantity and document sum
It arrives, the document sum belongs to the quantity of institute's documentary of the data group, the exception document quantity for the value of aiming field
For the quantity of document illegal in institute's documentary;
Determining module, it is pre- for the difference of the calculated abnormal accounting of the computing module and the average accounting to be greater than
If the data group of threshold value is determined as target set of data, and the value in the target set of data is determined as the different of the aiming field
Constant value.
9. a kind of computer equipment, which is characterized in that the computer equipment includes: processor and memory,
Program instruction is stored in the memory;
The processor executes such as side as claimed in any one of claims 1 to 6 for executing the program instruction stored in memory
Method.
10. a kind of computer readable storage medium, including instruction, which is characterized in that when described instruction is transported on a computing device
When row, so that the computer equipment executes such as method of any of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811094734.5A CN109325102B (en) | 2018-09-19 | 2018-09-19 | Method and device for identifying illegal document |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811094734.5A CN109325102B (en) | 2018-09-19 | 2018-09-19 | Method and device for identifying illegal document |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109325102A true CN109325102A (en) | 2019-02-12 |
CN109325102B CN109325102B (en) | 2021-02-19 |
Family
ID=65266280
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811094734.5A Active CN109325102B (en) | 2018-09-19 | 2018-09-19 | Method and device for identifying illegal document |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109325102B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112766391A (en) * | 2021-01-26 | 2021-05-07 | 浪潮通用软件有限公司 | Method, system, equipment and medium for making document |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1776748A (en) * | 2005-11-23 | 2006-05-24 | 柴杰生 | Tax-controlled invoice check management method |
CN101727682A (en) * | 2008-10-17 | 2010-06-09 | 山东新北洋信息技术股份有限公司 | Electronic note processing method |
CN102208092A (en) * | 2011-05-25 | 2011-10-05 | 重庆市电力公司永川供电局 | Financial bill reimbursement automatic processing method |
CN103646266A (en) * | 2013-11-27 | 2014-03-19 | 上海电机学院 | Two-dimension-code-based bill generation system and identification method |
US20140122341A1 (en) * | 2006-01-30 | 2014-05-01 | Solutran | System and method for processing checks and check transactions |
CN108090824A (en) * | 2017-12-30 | 2018-05-29 | 平安科技(深圳)有限公司 | Verification of data method, apparatus, computer equipment and readable storage medium storing program for executing |
-
2018
- 2018-09-19 CN CN201811094734.5A patent/CN109325102B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1776748A (en) * | 2005-11-23 | 2006-05-24 | 柴杰生 | Tax-controlled invoice check management method |
US20140122341A1 (en) * | 2006-01-30 | 2014-05-01 | Solutran | System and method for processing checks and check transactions |
CN101727682A (en) * | 2008-10-17 | 2010-06-09 | 山东新北洋信息技术股份有限公司 | Electronic note processing method |
CN102208092A (en) * | 2011-05-25 | 2011-10-05 | 重庆市电力公司永川供电局 | Financial bill reimbursement automatic processing method |
CN103646266A (en) * | 2013-11-27 | 2014-03-19 | 上海电机学院 | Two-dimension-code-based bill generation system and identification method |
CN108090824A (en) * | 2017-12-30 | 2018-05-29 | 平安科技(深圳)有限公司 | Verification of data method, apparatus, computer equipment and readable storage medium storing program for executing |
Non-Patent Citations (1)
Title |
---|
刘金娣: "异常值检验方法的比较分析", 《青岛大学学报(自然科学版)》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112766391A (en) * | 2021-01-26 | 2021-05-07 | 浪潮通用软件有限公司 | Method, system, equipment and medium for making document |
Also Published As
Publication number | Publication date |
---|---|
CN109325102B (en) | 2021-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108108902B (en) | Risk event warning method and device | |
CN109545317B (en) | Method for judging hospitalization behavior based on hospitalization prediction model and related products | |
CN109461070A (en) | A kind of risk measures and procedures for the examination and approval, device, storage medium and server | |
CN109977403B (en) | Malicious comment information identification method and device | |
CN108898476A (en) | A kind of loan customer credit-graded approach and device | |
CN111242793B (en) | Medical insurance data abnormality detection method and device | |
CN112801498B (en) | Training method of risk identification model, risk identification method, device and equipment | |
CN111986792A (en) | Medical institution scoring method, device, equipment and storage medium | |
CN106325756A (en) | Data storage and data computation methods and devices | |
CN110490750B (en) | Data identification method, system, electronic equipment and computer storage medium | |
CN111709845A (en) | Medical insurance fraud behavior identification method and device, electronic equipment and storage medium | |
CN112835910B (en) | Method and device for processing enterprise information and policy information | |
Rouhollahi et al. | Towards Proactive Financial Crime and Fraud Detectionthrough Artificial Intelligence and RegTech Technologies | |
CN109325102A (en) | A kind of method identifying illegal document and identification device | |
CN109935287A (en) | A kind of similarity analysis method, device and equipment of medical record information | |
CN109065118A (en) | A kind of medical data processing method, device, terminal and readable storage medium storing program for executing | |
CN109493931A (en) | A kind of coding method of patient file, server and computer readable storage medium | |
US20160275252A1 (en) | Automated claims process management system | |
CN109447440A (en) | A kind of environmental objective appraisal management method and apparatus, terminal device and storage medium | |
CN115938608A (en) | Clinical decision early warning method and system based on prompt learning model | |
CN108960111A (en) | Face identification method, system and terminal device | |
CN114240678A (en) | Method, device, equipment and storage medium for accurate calculation temporary score based on artificial intelligence | |
CN113658009A (en) | Claim settlement information processing method and device | |
CN113298530A (en) | Transaction configuration method, device, equipment and medium based on market data classification | |
CN109523394A (en) | A kind of risk checking method based on data processing, device 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |