CN109242740A - Identity information risk assessment method, apparatus, computer equipment and storage medium - Google Patents
Identity information risk assessment method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109242740A CN109242740A CN201810791449.2A CN201810791449A CN109242740A CN 109242740 A CN109242740 A CN 109242740A CN 201810791449 A CN201810791449 A CN 201810791449A CN 109242740 A CN109242740 A CN 109242740A
- Authority
- CN
- China
- Prior art keywords
- data
- risk
- identity
- probability
- evaluation model
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012502 risk assessment Methods 0.000 title claims abstract description 31
- 238000013210 evaluation model Methods 0.000 claims abstract description 93
- 238000012795 verification Methods 0.000 claims abstract description 73
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 42
- 238000003066 decision tree Methods 0.000 claims description 38
- 238000012360 testing method Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 27
- 230000008859 change Effects 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013075 data extraction Methods 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 238000007689 inspection Methods 0.000 description 25
- 238000006243 chemical reaction Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 239000012141 concentrate Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of identity information risk assessment method, apparatus, computer equipment and storage mediums.The described method includes: receiving identity data；Identity characteristic parameter is extracted from identity data；The corresponding historical verification data of identity data are searched, is extracted from historical verification data and verifies time parameter；Identity characteristic parameter and verification time parameter are inputted into default risk evaluation model and obtain identity risk probability；Risk evaluation result is generated according to identity risk probability.Security protection can be improved using this method and check accuracy rate.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of identity information risk assessment method, apparatus, meter
Calculate machine equipment and storage medium.
Background technique
Airport, port etc. enter and leave the border place daily all can a large amount of passenger's clearances, wherein being no lack of some smuggle, steal into another country etc. no
Method molecule.
The security protection security staff in entry and exit place usually passes through according to itself work when carrying out safety inspection to passenger
It tests and is watched the mood and guessed the thoughts to passenger to judge passenger with the presence or absence of security risk.But very due to the flow of the people of daily clearance
Greatly, be only by the passenger with security risk that can check of manual inspection of security staff it is very limited, cause
The accuracy rate of immigration place security protection inspection is very low, and many criminals is made to become fish that has escape the net.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of identity letter that can be improved security protection and check accuracy rate
Relieve the wind syndrome danger assessment method, device, computer equipment and storage medium.
A kind of identity information risk assessment method, which comprises
Receive identity data；
Identity characteristic parameter is extracted from the identity data；
The corresponding historical verification data of the identity data are searched, is extracted from the historical verification data and verifies the time
Parameter；
The identity characteristic parameter and the verification time parameter are inputted into default risk evaluation model and obtain identity risk
Probability；
Risk evaluation result is generated according to the identity risk probability.
The generating mode of the default risk evaluation model in one of the embodiments, comprising:
The sample data is divided into training set data and test set data by collecting sample data；
Fisrt feature parameter and first object classification are extracted from the training set data；
Attribute gain assessment is carried out according to the fisrt feature parameter and the first object classification, and is increased according to feature
Beneficial assessment result carries out feature selecting, is classified to obtain initial decision tree risk evaluation model, root according to selected feature
The risk probability of each class node in the initial decision tree risk evaluation model is calculated according to the training set data；
Second feature parameter and the second target category are extracted from the test set data；
According to the second feature parameter and second target category in the initial decision tree risk evaluation model
The risk probability of each class node is verified, and is adjusted according to verification result to the initial decision tree risk evaluation model
The default risk evaluation model of whole and generation.
In one of the embodiments, further include:
When reaching verification data renewal time, the verification data of update are loaded；
Third feature parameter corresponding with the default risk evaluation model and risk mesh are extracted from the verification data
Mark label；
According to the third feature parameter and the risk target label to respectively classifying in the default risk evaluation model
The risk probability of node is verified, and is optimized according to verification result to the default risk evaluation model.
It is described in one of the embodiments, that risk evaluation result is generated according to the identity risk probability, comprising:
The corresponding decision path of the maximum identity risk probability of probability value is searched from the default risk evaluation model；
Obtain the node data of the decision path；
Path profile is discovered and seized according to the node data and the maximum identity risk probability generation of the probability value and is exported.
It is described in one of the embodiments, that risk evaluation result is generated according to the identity risk probability, comprising:
The maximum identity risk probability of acquisition probability value；
It obtains current security protection manpower data, searches security protection passenger flow threshold value corresponding with the current security protection manpower data；
Preset threshold change data is obtained, is calculated according to the security protection passenger flow threshold value and the preset threshold change data
Risk probability threshold value；
When the maximum identity risk probability of the probability value is more than the risk probability threshold value, it is pre- to generate detection risk
It is alert to prompt and export.
It is described in one of the embodiments, that identity characteristic parameter is extracted from the identity data, comprising:
Passport NO. is extracted from the identity data；
Certificate format identification is carried out to the passport NO., searches type of credential corresponding with format recognition result；
The passport NO. is segmented to obtain participle string according to the type of credential；
Search identity characteristic parameter corresponding with each participle string.
A kind of identity information risk assessment device, described device include:
Identity data obtains module, for receiving identity data；
Identification parameters extraction module, for extracting identity characteristic parameter from the identity data；
Time parameter obtains module, for searching the corresponding historical verification data of the identity data, from the history core
It looks into extract in data and verifies time parameter；
Risk probability obtains module, for the identity characteristic parameter and the verification time parameter to be inputted default wind
Dangerous assessment models obtain identity risk probability；
Risk Results generation module, for generating risk evaluation result according to the identity risk probability.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the place
Manage the step of realizing the above method when device executes the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of above method is realized when row.
Above-mentioned identity information risk assessment method, apparatus, computer equipment and storage medium, from passenger's identity of acquisition
Identity characteristic parameter is extracted in data, and searches historical verification data corresponding with the identity characteristic parameter extracted, and is set in advance
Determine risk evaluation model, identity characteristic parameter and corresponding historical verification data, which are inputted default risk evaluation model, to be obtained
To the risk probability of passenger, so as to scientifically be counted according to passenger's feature and historical data to the security risk of passenger
Assessment is calculated, security protection is improved and checks accuracy rate.
Detailed description of the invention
Fig. 1 is the application scenario diagram of identity information risk assessment method in one embodiment；
Fig. 2 is the flow diagram of identity information risk assessment method in one embodiment；
Fig. 3 is the flow diagram that risk evaluation model generation method is preset in one embodiment；
Fig. 4 is the structural block diagram of identity information risk assessment device in one embodiment；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
In order to which the objects, technical solutions and advantages of the application are more clearly understood, with reference to the accompanying drawings and embodiments,
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to paraphrase the application,
It is not used to limit the application.
Identity information risk assessment method provided by the present application, can be applied in application environment as shown in Figure 1.Its
In, terminal 102 is communicated by network with server 104.Server 104 receives passenger's identity number that terminal 102 is sent
According to extracting identity characteristic parameter from received identity data, search the corresponding historical verification data of identity data, from described
It is extracted in historical verification data and verifies time parameter, by identity characteristic parameter and verify the default risk assessment of time parameter input
Model obtains identity risk probability, generates risk evaluation result according to identity risk probability, server 104 is by the risk of generation
Assessment result returns to terminal 102.Wherein, terminal 102 can be, but not limited to be various personal computers, laptop, intelligence
Energy mobile phone, tablet computer and portable wearable device, server 104 can use the either multiple services of independent server
The server cluster of device composition is realized.
In one embodiment, it as shown in Fig. 2, providing a kind of identity information risk assessment method, applies in this way
It is illustrated for server 104 in Fig. 1, comprising the following steps:
Step 210, identity data is received.
Identity data is the data that can uniquely determine passenger's identity, such as identity card, visa, student's identity card identity document
Certificate classification, passport NO. etc..
The staff of security terminal can be acquired by identity information acquisition equipment such as POS etc. by the passenger of safety check
Identity data, the identity data of the passenger of acquisition is transferred to security terminal by identity information acquisition equipment, and staff can also
In the identity data of security terminal typing passenger.The identity data for the passenger that security terminal will acquire is sent to server, clothes
Business device receives the identity data that security terminal is sent.
Step 220, identity characteristic parameter is extracted from identity data.
Identity characteristic parameter is the parameter for characterizing passenger's feature, and identity characteristic parameter may include passenger's age, trip
The parameters such as settler from another province passes through, passenger's gender.It include the characteristic parameter of passenger in the identity data of passenger, server is from received identity
Identity characteristic parameter is extracted in data.
In one embodiment, the step of identity characteristic parameter is extracted from identity data may include: from identity data
Middle extraction passport NO.；Certificate format identification is carried out to passport NO., searches type of credential corresponding with format recognition result；
Passport NO. is segmented according to type of credential to obtain participle string；It is special to search identity corresponding with each participle string
Levy parameter.
Server extracts passport NO. from identity data.Server carries out certificate format identification, identification to passport NO.
The certificates format such as the number length of passport NO., alphanumeric composition situation out.The mapping relations of type of credential and certificate format
It being previously stored in the server, server searches type of credential corresponding with the certificate format identified, in embodiment, card
Part classification may include the classifications such as identity card, the pass, home return permit, passport.
The character string of predeterminated position corresponds to a certain identity characteristic parameter, service in the passport NO. of different type of credential
Device obtains the corresponding character string predeterminated position of type of credential and preset length, according to character string predeterminated position and preset length pair
Passport NO. is segmented, and participle string is obtained.Server obtains the data of each preset characters string corresponding with type of credential
Conversion table, the specific character string value that each preset characters string is stored in data conversion table corresponding with identity characteristic parameter are closed
System.Server searches identity characteristic parameter corresponding with each participle string from data conversion table.
If type of credential is identity card, after ID card No. participle, the front three of ID card No. is a participle word
Symbol string, and the corresponding identity characteristic of ID card No. front three is passenger's native place, and server obtains ID card No. front three
Corresponding data conversion table, if ID card No. front three is " 410 ", what is found from data conversion table is corresponding with " 410 "
Passenger's native place parameter be " Henan ".Using the above method, server searches identity characteristic corresponding with all participle strings
Parameter.
Step 230, the corresponding historical verification data of identity data are searched, is extracted from historical verification data and verifies the time
Parameter.
Historical verification data are the historical record data that passenger carries out safety inspection, and historical record data may include trip
The data such as safety check time, safety check result when objective all previous carry out safety inspection.Server is according to the certificate in passenger's identity data
Number searching historical verification data corresponding with passenger.
Verifying time parameter may include that passenger passes in and out the frequency of safety check place progress safety inspection, pacifies every time
The period of total inspection, the parameters such as period belonging to the current safety check moment can specifically set the frequency of safety inspection
It is set to daily safety check frequency, weekly safety check frequency and monthly safety check frequency etc., the frequency of safety inspection can be by staff's root
Factually safety check demand in border is specifically set.Server carries out data statistics to historical verification data, therefrom counts every core
Look into time parameter.
Step 240, identity characteristic parameter and verification time parameter are inputted into default risk evaluation model and obtains identity risk
Probability.
Server obtains default risk evaluation model, and it is preset to passenger safety wind for presetting risk evaluation model
The model that danger is assessed.The input of default risk evaluation model is every identity characteristic parameter and verification time parameter, output
For passenger, there are the probability of security risk.Server is by the every identity characteristic parameter extracted and verifies time parameter input
Default risk evaluation model, default risk evaluation model obtain identity risk probability after carrying out calculation process to parameters.
Step 250, risk evaluation result is generated according to identity risk probability.
Server generates risk evaluation result according to the identity risk probability that is calculated, can be in risk evaluation result
Including information such as identity risk probability, passenger's history safety check information and security protection deployment recommendations.
In the present embodiment, server extracts identity characteristic parameter from the identity data of received passenger, and searches
Historical verification data corresponding with the identity characteristic parameter of extraction, and risk evaluation model is preset, by identity characteristic parameter
The identity risk probability of passenger can be obtained by inputting default risk evaluation model with corresponding historical verification data, so as to
The security risk of passenger scientifically calculate according to passenger's feature and historical data and is assessed, security protection is improved and checks accuracy rate.
In one embodiment, as shown in figure 3, the generating mode of default risk evaluation model, comprising:
Step 201, sample data is divided into training set data and test set data by collecting sample data.
Sample data is the historical data that true security places carry out safety inspection, collection of server preset time model
Enclose interior history safety inspection data, preset time range can be set as 1 month, 3 months, half a year etc., and server is by the sample of acquisition
Notebook data carries out random division, is divided into training set data and test set data, includes in training set data and test set data
Sample size can be the same or different.
Step 203, fisrt feature parameter and first object classification are extracted from training set data.
Sample data can be divided into positive sample data and negative sample data, positive sample according to the inspection result of safety inspection
Notebook data is the history safety inspection data that inspection result is normal passenger, and negative sample data are that inspection result is abnormal passenger
History safety inspection data.It in training set data and both include positive sample data and negative sample data in test set data.
Server extracts fisrt feature parameter and first object classification from each sample of training set data one by one.
Wherein, fisrt feature parameter includes identity characteristic parameter and verifies time parameter, i.e., in fisrt feature parameter and practical safety check from
The identity characteristic parameter extracted in passenger's identity data and the verification time parameter extracted from passenger's historical verification data are opposite
It answers.First object classification be safety inspection resulting class, first object classification be divided into safety check normally and safety check extremely two classes.
Step 205, attribute gain assessment is carried out according to fisrt feature parameter and first object classification, and is increased according to feature
Beneficial assessment result carries out feature selecting, is classified to obtain initial decision tree risk evaluation model, root according to selected feature
The risk probability of each class node in initial decision tree risk evaluation model is calculated according to training set data.
In the present embodiment, the default risk evaluation model of building is decision-tree model.Decision tree be it is a kind of by node and
The tree structure for classifying to example of directed edge composition, there are two types of the types of node: internal node and leaf section
Point.Wherein, internal node indicates the test condition of feature or attribute, leaf node presentation class.It is carried out using decision-tree model
The specific method of classification is: since root node, testing a certain feature of example, is divided example according to test result
It is fitted on its child node.When being likely to be breached leaf node along the branch or reaching another internal node, then new test is used
The execution of condition recurrence is gone down, and until arriving at a leaf node, when reaching leaf node, then obtains final classification as a result, will
Leaf node is as class node.
In the present embodiment, initial decision tree risk evaluation model is constructed using ID3 algorithm, ID3 algorithm is to each feature
Information gain assessment is carried out, selecting the maximum characteristic parameter of information gain as judgment module establishes child node every time.Server
The information gain of the corresponding each feature of fisrt feature parameter is calculated, chooses the maximum feature of information gain as judgment module
Child node is established, the corresponding training set data of child node is divided into subset data, subset data is divided in a recursive manner
Zhi Jianli branch node, until all branch nodes correspond to identical first object classification.
Specifically, server calculates the information gain of the corresponding each feature of fisrt feature parameter using following equation (1):
G (D, A)=H (D)-H (D | A) (1)
Wherein, g (D, A) is characterized A to the information gain of training dataset D, and H (D) is the empirical entropy of training dataset D,
H (D | A) A is characterized to the empirical condition entropy of data set D.
Server calculates the empirical entropy H (D) of training dataset D using following equation (2):
Wherein, CkFor the corresponding sample size of first object classification, K is the categorical measure of first object classification, in this reality
It applies in example, first object classification is divided into safety check normally and safety check is two kinds abnormal.
Server calculates feature A to the empirical condition entropy H of training dataset D (D | A) using following equation (3):
Wherein, value (A) is all value set of feature A, and i is a value of feature A, DiIt is training dataset
Feature A value is the sample set of i in D, | Di| indicate that value is the sample size of the sample set of i, | D | it indicates to carry out sample
The total quantity of sample before example set divides.If the corresponding feature A of sex character parameter all values are male and female, as male can
To be indicated with 0, female can be indicated with 1, and value (A) is (0,1).
Server establishes decision tree using the recursive fashion of Hunt algorithm, when the information gain for calculating each characteristic parameter
And after carrying out feature selecting, the corresponding training set data subset of the maximum characteristic parameter of information gain is obtained, and using identical
Mode carries out feature selecting to training set data subset, so that training dataset to be gradually divided into purer subset.
The recursive definition of Hunt algorithm is as follows: setting Dt is training data subset associated with node t, and y=y1,
Y2 ... ..., yc } it is target category label, if all sample datas belong to the same classification in Dt, t is leaf node,
It is marked with yt；If in Dt including the sample data for belonging to multiple classifications, a characteristic test condition is selected, by sample number
According to being divided into lesser subset.Each output for test condition creates a branch node, and will according to test result
Sample data in Dt is distributed in branch node.For each branch node, the algorithm is recursively called.
After server construction goes out initial decision tree risk evaluation model, the first spy of various kinds sheet is concentrated according to training data
Parameter and first object classification are levied, is counted and section of respectively classifying in initial decision tree risk evaluation model from training data concentration
The negative sample data of the negative sample data of the corresponding characteristic parameter combinations matches of point, counting statistics are concentrated always in training data
Shared ratio in negative sample data, using the risk probability of the ratio each class node as in.
Step 207, second feature parameter and the second target category are extracted from test set data.
Server extracts second feature parameter and the second target category from each sample of test set data one by one.
Wherein, second feature parameter includes identity characteristic parameter and verifies time parameter, i.e., in second feature parameter and practical safety check from
The identity characteristic parameter extracted in passenger's identity data and the verification time parameter extracted from passenger's historical verification data are opposite
It answers.Second target category be safety inspection resulting class, the second target category be divided into safety check normally and safety check extremely two classes.
Step 209, according to second feature parameter and the second target category to each point in initial decision tree risk evaluation model
The risk probability of class node is verified, and initial decision tree risk evaluation model is adjusted and is generated according to verification result
Default risk evaluation model.
Server concentrates the second feature parameter and the second target category of various kinds sheet according to test data, from test data
Concentrate the negative sample for counting characteristic parameter combinations matches corresponding with class node each in initial decision tree risk evaluation model
Data, the negative sample data of counting statistics concentrate ratio shared in total negative sample data in test data, and according to calculating
Ratio out verifies the risk probability of class node each in decision-tree model.In verifying, server can set pre-
If fault-tolerant error, when the absolute difference of calculated ratio and risk probability, which is less than, presets fault-tolerant error, it is verified, when
Greater than when presetting fault-tolerant error, verifying does not pass through the absolute difference of calculated ratio and risk probability.When verifying does not pass through
When, the sample data that server can concentrate test data is added training data and concentrates, and enlarged sample capacity is to initial decision
Tree risk evaluation model is trained, and default risk assessment mould is generated after being adjusted to initial decision tree risk evaluation model
Type.
In one embodiment, identity information risk assessment method can also include: when data renewal time is verified in arrival
When, load the verification data of update；From verify in data extract corresponding with default risk evaluation model third feature parameter and
Risk target label；According to third feature parameter and risk target label to each class node in default risk evaluation model
Risk probability is verified, and is optimized according to verification result to default risk evaluation model.
Server, which is preset, verifies data renewal time, and verifying data renewal time is to examine to the safety of security places
Look into the time that data are updated.After reaching preset verification data renewal time, the verification number of server load update
According to, verify identity characteristic data that data include passenger, verify time and safety inspection as a result, security terminal can actively or
The verification data updated are passively sent to server.
Server extracts third feature parameter and risk target label from verifying in data, third feature parameter and pre-
If the feature set in risk evaluation model is corresponding, risk target label is safety inspection result queue, is divided into no safety wind
Danger label and two class of security risk label.
Server is according to the third feature parameter and risk target label for verifying each sample in data, from verification data
The negative sample data of characteristic parameter combinations matches corresponding with class node each in default risk evaluation model are counted, are calculated
The negative sample data of statistics are verifying ratio shared in the total negative sample data of data, and according to calculated ratio to pre-
If the risk probability of each class node is verified in risk evaluation model.In verifying, server can set default inclined
Difference is verified when the absolute difference of calculated ratio and risk probability is less than predetermined deviation；When calculated ratio
When being greater than predetermined deviation with the absolute difference of risk probability, verifying does not pass through.Obstructed out-of-date when verifying, server can be by core
It looks into data to continue that default risk evaluation model is trained and is adjusted, thus according to data are verified to default risk assessment mould
Type is continued to optimize, thus by the training of big data so that the risk assessment knot obtained by presetting risk evaluation model
Fruit is more and more accurate.
In one embodiment, the step of generating risk evaluation result according to identity risk probability may include: from default
The corresponding decision path of the maximum identity risk probability of probability value is searched in risk evaluation model；Obtain the node of decision path
Data；Path profile is discovered and seized according to node data and the maximum identity risk probability generation of probability value and is exported.
After the identity characteristic parameter extracted and verification time parameter are inputted default risk evaluation model by server,
Identity characteristic parameter and verification time parameter may be with the characteristic parameter phases in a plurality of decision path in default risk evaluation model
Matching, accordingly, it is possible to which the corresponding identity risk probability of multiple matched class nodes can be obtained.Such as default risk evaluation model
In the corresponding characteristic parameter of class node be clearance frequency, then the parameter inputted may both meet class node be " work as Tian An
Inspection number ", node diagnostic value are the decision path one of " being greater than twice ", and it is " last naturally all for being able to satisfy class node
Safety check number ", the decision path two that node diagnostic value is " between 8-15 days ", the corresponding identity risk of decision path one are general
Rate is 21%, and the corresponding identity risk probability of decision path two is 25%.Calculating knot of the server from default risk evaluation model
The corresponding decision path of the maximum identity risk probability of probability value is found out in fruit.
Server obtains the corresponding characteristic parameter of each node in the decision path that finds out, and node includes internal branch
Node and classification leaf node.Server discovers and seizes path profile according to the generation that is together in series of the characteristic parameter of all nodes, and will most
The identity risk probability of data, which is also added to, afterwards discovers and seizes in path profile, will discover and seize path profile and returns to security terminal, so that security protection
Terminal will discover and seize path profile and show, i.e., visualize to the output result of default risk evaluation model, so as to
So that security personnel have a clear understanding of the various features and existing potential security risk of current passenger, discovered and seized according to visualization
Path profile determines whether to take further inspection to current passenger.
For example, the identity characteristic parameter of the passenger of input model and verification time parameter are that " Zhang San, male are 24 years old, Chinese
Nationality, birthplace Guangdong, this month third time are verified ", meet in default risk evaluation model " in the age bracket of male -20-30 years old -
The decision path of nationality-birthplace south China-this month verification 3-5 times ", it is all that the risk probability of the decision path, which is 30%,
The maximum decision path of probability value in the matched decision path of characteristic parameter, it is raw according to decision path and corresponding risk probability
At discovering and seizing path profile.
In one embodiment, the step of generating risk evaluation result according to identity risk probability may include: to obtain generally
Rate is worth maximum identity risk probability；Current security protection manpower data are obtained, security protection corresponding with current security protection manpower data is searched
Passenger flow threshold value；Preset threshold change data is obtained, according to security protection passenger flow threshold value and preset threshold change data calculation risk probability
Threshold value；When the maximum identity risk probability of probability value is more than risk probability threshold value, generation detection risk early warning is simultaneously defeated
Out.
Server obtains the identity risk probability of the corresponding output of each class node of default risk evaluation model, and therefrom
Select the maximum identity risk probability of probability value.
Security protection passenger flow threshold value is the maximum of the passenger traffic volume that can carry out safety inspection corresponding with current security protection manpower
Value.Server obtains current security protection manpower data, and current security protection manpower data may include the total of current safety check place deployment
Security protection manpower, the data such as security protection manpower of the corresponding current security check deployment of security terminal.Server obtains the security protection people prestored
The mapping relations of force data and security protection passenger flow threshold value, the mapping relations including total security protection manpower Yu total security protection passenger flow threshold value, and work as
The mapping relations of the security protection manpower of preceding security check and corresponding security protection passenger flow threshold value.Server is searched and current total security protection manpower
Corresponding total security protection passenger flow threshold value, and search security check security protection passenger flow threshold value corresponding with the security protection manpower of current security check.
Risk probability threshold value is that can determine that passenger has the minimum value of the identity risk probability of security risk, and risk is general
Rate threshold value is not fixed, is adjusted according to security protection manpower, and when security protection abundant manpower, risk probability threshold value is set
It is relatively smallerly fixed, conversely, risk probability threshold value is set to relatively larger.
Server obtains preset threshold change data, and preset threshold change data is security protection passenger flow threshold value and risk probability
The change data converted between threshold value, change data can close for the mapping of security protection passenger flow threshold value and risk probability threshold value
It is table, or preset conversion calculation formula etc..Server calculates and security protection passenger flow according to preset threshold change data
The corresponding risk probability threshold value of threshold value, including the first risk probability threshold value corresponding with total security protection passenger flow threshold value and security check peace
The corresponding second risk probability threshold value of anti-passenger flow threshold value, and will be in the first risk probability threshold value and the second risk probability threshold value
Minimum value is as risk probability threshold value.
The maximum identity risk probability of the probability value that server will acquire is compared with calculated risk probability threshold value
Compared with when the maximum identity risk probability of probability value is less than or equal to risk probability threshold value, current passenger's safety check passes through, server
Safety check qualification can be generated to notify and return to security terminal；When the maximum identity risk probability of probability value is more than risk probability
When threshold value, server generates detection risk early warning, can carry calculated current passenger in detection risk early warning
Identity risk probability, when the history historical verification data of current passenger are there are when safety check exception record, by exception record information
It is also added in detection risk early warning, the detection risk early warning of generation is sent to security terminal by server, to mention
Show that the staff of the security check passenger has definitely security risk, needs to carry out further safety inspection.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 2-3 at least
A part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
Moment executes completion, but can execute at different times, and the execution sequence in these sub-steps or stage is also not necessarily
Successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or
Alternately execute.
In one embodiment, as shown in figure 4, providing a kind of identity information risk assessment device, comprising: identity number
According to obtaining, module 410, identification parameters extraction module 420, time parameter obtain module 430, risk probability obtains 440 and of module
Risk Results generation module 450, in which:
Identity data obtains module 410, for receiving identity data.
Identification parameters extraction module 420, for extracting identity characteristic parameter from identity data.
Time parameter obtains module 430, for searching the corresponding historical verification data of identity data, from historical verification number
Time parameter is verified according to middle extraction.
Risk probability obtains module 440, for identity characteristic parameter and verification time parameter to be inputted default risk assessment
Model obtains identity risk probability.
Risk Results generation module 450, for generating risk evaluation result according to identity risk probability.
In one embodiment, device can also include:
Data acquisition module is used for collecting sample data, sample data is divided into training set data and test set number
According to.
Training data extraction module, for extracting fisrt feature parameter and first object classification from training set data.
Initial model constructs module, for carrying out attribute gain assessment according to fisrt feature parameter and first object classification,
And feature selecting is carried out according to attribute gain assessment result, classified to obtain initial decision tree wind according to selected feature
Dangerous assessment models calculate the risk probability of each class node in initial decision tree risk evaluation model according to training set data.
Test data extraction module, for extracting second feature parameter and the second target category from test set data.
Evaluation module generation module is used for according to second feature parameter and the second target category to initial decision tree risk
The risk probability of each class node is verified in assessment models, according to verification result to initial decision tree risk evaluation model
It is adjusted and generates default risk evaluation model.
In one embodiment, device can also include:
Data loading module is verified, for loading the verification data of update when reaching verification data renewal time.
Data extraction module is verified, for special from extraction third corresponding with default risk evaluation model in data is verified
Levy parameter and risk target label.
Model optimization module is used for according to third feature parameter and risk target label in default risk evaluation model
The risk probability of each class node is verified, and is optimized according to verification result to default risk evaluation model.
In one embodiment, Risk Results generation module 450 may include:
Path searching module, for searching the maximum identity risk probability pair of probability value from default risk evaluation model
The decision path answered.
Path data obtains module, for obtaining the node data of decision path.
Path profile generation module, for discovering and seizing road according to node data and the maximum identity risk probability generation of probability value
Diameter figure simultaneously exports.
In one embodiment, Risk Results generation module 450 may include:
Probability obtains module, is used for the maximum identity risk probability of acquisition probability value.
Security protection threshold value searching module is searched corresponding with current security protection manpower data for obtaining current security protection manpower data
Security protection passenger flow threshold value.
Risk threshold value computing module, for obtaining preset threshold change data, according to security protection passenger flow threshold value and preset threshold
Change data calculation risk probability threshold value.
Early warning generation module is used for when the maximum identity risk probability of probability value is more than risk probability threshold value, raw
At detection risk early warning and export.
In one embodiment, identification parameters extraction module 420 may include:
Number retention module, for extracting passport NO. from identity data.
Type of credential searching module is searched and format recognition result pair for carrying out certificate format identification to passport NO.
The type of credential answered.
Word segmentation module obtains participle string for being segmented according to type of credential to passport NO..
Parameter searching module, for searching identity characteristic parameter corresponding with each participle string.
Specific restriction about identity information risk assessment device may refer to above for identity information risk assessment
The restriction of method, details are not described herein.Modules in above-mentioned identity information risk assessment device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be server, inside
Structure chart can be as shown in Figure 5.The computer equipment includes processor, the memory, network interface connected by system bus
And database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The storage of the computer equipment
Device includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program
And database.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.
The database of the computer equipment is used to store the related data of identity information risk assessment.The network of the computer equipment connects
Mouth with external terminal by network connection for being communicated.To realize a kind of identity when the computer program is executed by processor
Information Risk assessment method.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme
The block diagram of structure, does not constitute the restriction for the computer equipment being applied thereon to application scheme, and specific computer is set
Standby may include perhaps combining certain components or with different component cloth than more or fewer components as shown in the figure
It sets.
In one embodiment, a kind of computer equipment, including memory and processor, memory storage are provided
There is computer program, which performs the steps of reception identity data when executing computer program；From identity data
Extract identity characteristic parameter；The corresponding historical verification data of identity data are searched, is extracted from historical verification data and verifies the time
Parameter；Identity characteristic parameter and verification time parameter are inputted into default risk evaluation model and obtain identity risk probability；According to body
Part risk probability generates risk evaluation result.
In one embodiment, collecting sample data are also performed the steps of when processor executes computer program, it will
Sample data is divided into training set data and test set data；Fisrt feature parameter and the first mesh are extracted from training set data
Mark classification；Attribute gain assessment is carried out according to fisrt feature parameter and first object classification, and according to attribute gain assessment result
Feature selecting is carried out, is classified to obtain initial decision tree risk evaluation model according to selected feature, according to training set number
According to the risk probability for calculating each class node in initial decision tree risk evaluation model；It is special that second is extracted from test set data
Levy parameter and the second target category；According to second feature parameter and the second target category to initial decision tree risk evaluation model
In the risk probability of each class node verified, initial decision tree risk evaluation model is adjusted according to verification result
And generate default risk evaluation model.
In one embodiment, it is also performed the steps of when processor executes computer program when arrival verifies data more
When the new time, the verification data of update are loaded；Third feature corresponding with default risk evaluation model is extracted in data from verifying
Parameter and risk target label；According to third feature parameter and risk target label to respectively classifying in default risk evaluation model
The risk probability of node is verified, and is optimized according to verification result to default risk evaluation model.
In one embodiment, realize that generating risk according to identity risk probability comments when processor executes computer program
It is also used to when estimating the step of result: it is corresponding to search the maximum identity risk probability of probability value from default risk evaluation model
Decision path；Obtain the node data of decision path；It is looked into according to node data and the maximum identity risk probability generation of probability value
It obtains path profile and exports.
In one embodiment, realize that generating risk according to identity risk probability comments when processor executes computer program
It is also used to when estimating the step of result: the maximum identity risk probability of acquisition probability value；Current security protection manpower data are obtained, are searched
Security protection passenger flow threshold value corresponding with current security protection manpower data；Obtain preset threshold change data, according to security protection passenger flow threshold value and
Preset threshold change data calculation risk probability threshold value；When the maximum identity risk probability of probability value is more than risk probability threshold value
When, it generates detection risk early warning and exports.
In one embodiment, it is realized when processor executes computer program and extracts identity spy from the identity data
It is also used to when levying the step of parameter: extracting passport NO. from identity data；Certificate format identification is carried out to passport NO., is looked into
Look for type of credential corresponding with format recognition result；Passport NO. is segmented according to type of credential to obtain participle string；
Search identity characteristic parameter corresponding with each participle string.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is counted
Calculation machine program performs the steps of reception identity data when being executed by processor；Identity characteristic ginseng is extracted from identity data
Number；The corresponding historical verification data of identity data are searched, is extracted from historical verification data and verifies time parameter；By identity spy
Sign parameter and verification time parameter input default risk evaluation model and obtain identity risk probability；It is raw according to identity risk probability
At risk evaluation result.
In one embodiment, collecting sample data are also performed the steps of when computer program is executed by processor,
Sample data is divided into training set data and test set data；Fisrt feature parameter and first is extracted from training set data
Target category；Attribute gain assessment is carried out according to fisrt feature parameter and first object classification, and is assessed and is tied according to attribute gain
Fruit carries out feature selecting, is classified to obtain initial decision tree risk evaluation model according to selected feature, according to training set
Data calculate the risk probability of each class node in initial decision tree risk evaluation model；Second is extracted from test set data
Characteristic parameter and the second target category；According to second feature parameter and the second target category to initial decision tree risk assessment mould
The risk probability of each class node is verified in type, is adjusted according to verification result to initial decision tree risk evaluation model
The default risk evaluation model of whole and generation.
In one embodiment, it is also performed the steps of when computer program is executed by processor when data are verified in arrival
When renewal time, the verification data of update are loaded；Third spy corresponding with default risk evaluation model is extracted from verifying in data
Levy parameter and risk target label；According to third feature parameter and risk target label to each point in default risk evaluation model
The risk probability of class node is verified, and is optimized according to verification result to default risk evaluation model.
In one embodiment, it is realized when computer program is executed by processor and risk is generated according to identity risk probability
It is also used to when the step of assessment result: it is corresponding to search the maximum identity risk probability of probability value from default risk evaluation model
Decision path；Obtain the node data of decision path；It is generated according to node data and the maximum identity risk probability of probability value
It discovers and seizes path profile and exports.
In one embodiment, it is realized when computer program is executed by processor and risk is generated according to identity risk probability
It is also used to when the step of assessment result: the maximum identity risk probability of acquisition probability value；Current security protection manpower data are obtained, are looked into
Look for security protection passenger flow threshold value corresponding with current security protection manpower data；Preset threshold change data is obtained, according to security protection passenger flow threshold value
With preset threshold change data calculation risk probability threshold value；When the maximum identity risk probability of probability value is more than risk probability threshold
When value, generates detection risk early warning and export.
In one embodiment, realization is also performed the steps of when computer program is executed by processor from the identity
It is also used to when extracting the step of identity characteristic parameter in data: extracting passport NO. from identity data；Passport NO. is carried out
Certificate format identification searches type of credential corresponding with format recognition result；Passport NO. is segmented according to type of credential
Obtain participle string；Search identity characteristic parameter corresponding with each participle string.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can
It is completed with instructing relevant hardware by computer program, the computer program can be stored in a non-volatile meter
In calculation machine read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.
Wherein, any of memory, storage, database or other media is drawn used in each embodiment provided herein
With may each comprise non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), can
Programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile storage
Device may include random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is with more
Kind form can obtain, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram
(DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus
(Rambus) direct RAM (RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram
(RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the guarantor of the application
Protect range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of identity information risk assessment method, which comprises
Receive identity data；
Identity characteristic parameter is extracted from the identity data；
The corresponding historical verification data of the identity data are searched, is extracted from the historical verification data and verifies time parameter；
The identity characteristic parameter and the verification time parameter are inputted into default risk evaluation model and obtain identity risk probability；
Risk evaluation result is generated according to the identity risk probability.
2. the method according to claim 1, wherein the generating mode of the default risk evaluation model, comprising:
The sample data is divided into training set data and test set data by collecting sample data；
Fisrt feature parameter and first object classification are extracted from the training set data；
Attribute gain assessment is carried out according to the fisrt feature parameter and the first object classification, and is assessed according to attribute gain
As a result feature selecting is carried out, is classified to obtain initial decision tree risk evaluation model according to selected feature, according to described
Training set data calculates the risk probability of each class node in the initial decision tree risk evaluation model；
Second feature parameter and the second target category are extracted from the test set data；
According to the second feature parameter and second target category to each point in the initial decision tree risk evaluation model
The risk probability of class node is verified, and the initial decision tree risk evaluation model is adjusted and is given birth to according to verification result
At default risk evaluation model.
3. according to the method described in claim 2, it is characterized in that, the method also includes:
When reaching verification data renewal time, the verification data of update are loaded；
Third feature parameter corresponding with the default risk evaluation model and risk target mark are extracted from the verification data
Note；
According to the third feature parameter and the risk target label to each class node in the default risk evaluation model
Risk probability verified, the default risk evaluation model is optimized according to verification result.
4. according to the method described in claim 2, it is characterized in that, described generate risk assessment according to the identity risk probability
As a result, comprising:
The corresponding decision path of the maximum identity risk probability of probability value is searched from the default risk evaluation model；
Obtain the node data of the decision path；
Path profile is discovered and seized according to the node data and the maximum identity risk probability generation of the probability value and is exported.
5. according to the method described in claim 2, it is characterized in that, described generate risk assessment according to the identity risk probability
As a result, comprising:
The maximum identity risk probability of acquisition probability value；
It obtains current security protection manpower data, searches security protection passenger flow threshold value corresponding with the current security protection manpower data；
Preset threshold change data is obtained, it is general according to the security protection passenger flow threshold value and the preset threshold change data calculation risk
Rate threshold value；
When the maximum identity risk probability of the probability value is more than the risk probability threshold value, detection risk early warning is generated
And it exports.
6. the method according to claim 1, wherein described extract identity characteristic ginseng from the identity data
Number, comprising:
Passport NO. is extracted from the identity data；
Certificate format identification is carried out to the passport NO., searches type of credential corresponding with format recognition result；
The passport NO. is segmented to obtain participle string according to the type of credential；
Search identity characteristic parameter corresponding with each participle string.
7. a kind of identity information risk assessment device, which is characterized in that described device includes:
Identity data obtains module, for receiving identity data；
Identification parameters extraction module, for extracting identity characteristic parameter from the identity data；
Time parameter obtains module, for searching the corresponding historical verification data of the identity data, from the historical verification number
Time parameter is verified according to middle extraction；
Risk probability obtains module, for the identity characteristic parameter and the verification time parameter to be inputted default risk assessment
Model obtains identity risk probability；
Risk Results generation module, for generating risk evaluation result according to the identity risk probability.
8. device according to claim 7, which is characterized in that described device further include:
Data acquisition module is used for collecting sample data, the sample data is divided into training set data and test set data；
Training data extraction module, for extracting fisrt feature parameter and first object classification from the training set data；
Initial model constructs module, comments for carrying out attribute gain according to the fisrt feature parameter and the first object classification
Estimate, and feature selecting is carried out according to attribute gain assessment result, is classified to obtain initial decision tree according to selected feature
Risk evaluation model calculates the wind of each class node in the initial decision tree risk evaluation model according to the training set data
Dangerous probability；
Test data extraction module, for extracting second feature parameter and the second target category from the test set data；
Evaluation module generation module is used for according to the second feature parameter and second target category to the initial decision
The risk probability of each class node is verified in tree risk evaluation model, according to verification result to the initial decision tree risk
Assessment models are adjusted and generate default risk evaluation model.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810791449.2A CN109242740A (en) | 2018-07-18 | 2018-07-18 | Identity information risk assessment method, apparatus, computer equipment and storage medium |
| PCT/CN2018/104806 WO2020015089A1 (en) | 2018-07-18 | 2018-09-10 | Identity information risk assessment method and apparatus, and computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810791449.2A CN109242740A (en) | 2018-07-18 | 2018-07-18 | Identity information risk assessment method, apparatus, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242740A true CN109242740A (en) | 2019-01-18 |
Family
ID=65072033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810791449.2A Withdrawn CN109242740A (en) | 2018-07-18 | 2018-07-18 | Identity information risk assessment method, apparatus, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109242740A (en) |
| WO (1) | WO2020015089A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992119A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Method and system for sequencing risk orders |
| CN111445106A (en) * | 2020-03-02 | 2020-07-24 | 国网辽宁省电力有限公司电力科学研究院 | Power utilization acquisition equipment fault processing operation site safety control method and system |
| CN112883061A (en) * | 2020-12-07 | 2021-06-01 | 浙江大华技术股份有限公司 | Dangerous article detection method, device and system and computer equipment |
| CN113052413A (en) * | 2019-12-26 | 2021-06-29 | 北京中科闻歌科技股份有限公司 | Risk passenger assessment method, device, terminal and computer readable medium |
| CN113642820A (en) * | 2020-12-18 | 2021-11-12 | 航天信息股份有限公司广州航天软件分公司 | Method and system for evaluating and managing personnel data information based on big data |
| CN113671589A (en) * | 2021-09-14 | 2021-11-19 | 清华大学 | Safety detection match physical system |
| CN114756716A (en) * | 2022-04-18 | 2022-07-15 | 马上消费金融股份有限公司 | Information processing method, device, equipment and storage medium |
| CN115146725A (en) * | 2022-06-30 | 2022-10-04 | 北京百度网讯科技有限公司 | Determination method of object classification mode, object classification method, device and equipment |
| CN116797357A (en) * | 2023-08-24 | 2023-09-22 | 杭银消费金融股份有限公司 | Financial terminal-based credit authorization processing method and equipment |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111404721B (en) * | 2020-02-13 | 2023-07-25 | 中国平安人寿保险股份有限公司 | Visual processing method, device and equipment for model training process data based on web |
| CN111427883A (en) * | 2020-02-18 | 2020-07-17 | 深圳壹账通智能科技有限公司 | Data processing method and device based on AeroPike, computer equipment and storage medium |
| CN111738331A (en) * | 2020-06-19 | 2020-10-02 | 北京同邦卓益科技有限公司 | User classification method and device, computer-readable storage medium and electronic device |
| CN112465626B (en) * | 2020-11-24 | 2023-08-29 | 平安科技（深圳）有限公司 | Combined risk assessment method based on client classification aggregation and related equipment |
| CN112750031A (en) * | 2021-01-20 | 2021-05-04 | 北京赛思信安技术股份有限公司 | Multidimensional risk verification device applied to financing guarantee mechanism |
| CN113807858B (en) * | 2021-09-23 | 2024-04-26 | 中科软科技股份有限公司 | Data processing method and related equipment based on decision tree model |
| CN116319083B (en) * | 2023-05-17 | 2023-08-04 | 南京哲上信息科技有限公司 | Data transmission security detection method and system |
| CN116308762B (en) * | 2023-05-19 | 2023-08-11 | 杭州钱袋数字科技有限公司 | Credibility evaluation and trust processing method based on artificial intelligence |
| CN117634873A (en) * | 2023-11-15 | 2024-03-01 | 中国人寿保险股份有限公司江苏省分公司 | System and method for evaluating risk of sales personnel in insurance industry |
| CN117675387B (en) * | 2023-12-12 | 2024-06-14 | 广州达悦信息科技有限公司 | Network security risk prediction method and system based on user behavior analysis |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260628B (en) * | 2014-06-03 | 2019-01-11 | 腾讯科技（深圳）有限公司 | Classifier training method and apparatus, auth method and system |
| CN108198116A (en) * | 2016-12-08 | 2018-06-22 | 同方威视技术股份有限公司 | For being detected the method and device of staffing levels in safety check |
| CN108009914A (en) * | 2017-12-19 | 2018-05-08 | 马上消费金融股份有限公司 | Credit risk assessment method, system, equipment and computer storage medium |
| CN108269012A (en) * | 2018-01-12 | 2018-07-10 | 中国平安人寿保险股份有限公司 | Construction method, device, storage medium and the terminal of risk score model |
-
2018
- 2018-07-18 CN CN201810791449.2A patent/CN109242740A/en not_active Withdrawn
- 2018-09-10 WO PCT/CN2018/104806 patent/WO2020015089A1/en active Application Filing
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992119A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Method and system for sequencing risk orders |
| CN113052413A (en) * | 2019-12-26 | 2021-06-29 | 北京中科闻歌科技股份有限公司 | Risk passenger assessment method, device, terminal and computer readable medium |
| CN111445106A (en) * | 2020-03-02 | 2020-07-24 | 国网辽宁省电力有限公司电力科学研究院 | Power utilization acquisition equipment fault processing operation site safety control method and system |
| CN111445106B (en) * | 2020-03-02 | 2023-12-01 | 国网辽宁省电力有限公司电力科学研究院 | Safety control method and system for fault processing operation site of electricity acquisition equipment |
| CN112883061A (en) * | 2020-12-07 | 2021-06-01 | 浙江大华技术股份有限公司 | Dangerous article detection method, device and system and computer equipment |
| CN113642820A (en) * | 2020-12-18 | 2021-11-12 | 航天信息股份有限公司广州航天软件分公司 | Method and system for evaluating and managing personnel data information based on big data |
| CN113642820B (en) * | 2020-12-18 | 2024-05-28 | 航天信息股份有限公司广州航天软件分公司 | Method and system for evaluating and managing personnel data information based on big data |
| CN113671589A (en) * | 2021-09-14 | 2021-11-19 | 清华大学 | Safety detection match physical system |
| CN114756716A (en) * | 2022-04-18 | 2022-07-15 | 马上消费金融股份有限公司 | Information processing method, device, equipment and storage medium |
| CN115146725A (en) * | 2022-06-30 | 2022-10-04 | 北京百度网讯科技有限公司 | Determination method of object classification mode, object classification method, device and equipment |
| CN116797357A (en) * | 2023-08-24 | 2023-09-22 | 杭银消费金融股份有限公司 | Financial terminal-based credit authorization processing method and equipment |
| CN116797357B (en) * | 2023-08-24 | 2023-11-21 | 杭银消费金融股份有限公司 | Financial terminal-based credit authorization processing method and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020015089A1 (en) | 2020-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109242740A (en) | Identity information risk assessment method, apparatus, computer equipment and storage medium | |
| US20210257066A1 (en) | Machine learning based medical data classification method, computer device, and non-transitory computer-readable storage medium | |
| WO2020077895A1 (en) | Signing intention determining method and apparatus, computer device, and storage medium | |
| CN109002988B (en) | Risk passenger flow prediction method, apparatus, computer device and storage medium | |
| WO2019218699A1 (en) | Fraud transaction determining method and apparatus, computer device, and storage medium | |
| CN109523153A (en) | Acquisition methods, device, computer equipment and the storage medium of illegal fund collection enterprise | |
| CN110598206A (en) | Text semantic recognition method and device, computer equipment and storage medium | |
| Ounacer et al. | Using Isolation Forest in anomaly detection: the case of credit card transactions | |
| CN111191568B (en) | Method, device, equipment and medium for identifying flip image | |
| CN109063984B (en) | Method, apparatus, computer device and storage medium for risky travelers | |
| CN110222992A (en) | A kind of network swindle method for early warning and device based on group's portrait of being deceived | |
| CN109949154A (en) | Customer information classification method, device, computer equipment and storage medium | |
| CN109325118A (en) | Uneven sample data preprocess method, device and computer equipment | |
| CN114298176A (en) | Method, device, medium and electronic equipment for detecting fraudulent user | |
| CN109102159A (en) | Passenger's rating model generation method, device, computer equipment and storage medium | |
| WO2023024670A1 (en) | Device clustering method and apparatus, and computer device and storage medium | |
| Wu et al. | Dual autoencoders generative adversarial network for imbalanced classification problem | |
| Divakar et al. | Performance evaluation of credit card fraud transactions using boosting algorithms | |
| Hou et al. | Mahalanobis distance based adversarial network for anomaly detection | |
| Zhou et al. | Credit card fraud identification based on principal component analysis and improved AdaBoost algorithm | |
| CN110399432A (en) | A kind of classification method of table, device, computer equipment and storage medium | |
| CN110413994A (en) | Hot topic generation method, device, computer equipment and storage medium | |
| CN109101984B (en) | Image identification method and device based on convolutional neural network | |
| CN114168788A (en) | Audio audit processing method, device, equipment and storage medium | |
| CN114359811A (en) | Data authentication method and device, electronic 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190118 |