CN108846015A - Real estate information query method, device, computer equipment and storage medium - Google Patents
Real estate information query method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108846015A CN108846015A CN201810422089.9A CN201810422089A CN108846015A CN 108846015 A CN108846015 A CN 108846015A CN 201810422089 A CN201810422089 A CN 201810422089A CN 108846015 A CN108846015 A CN 108846015A
- Authority
- CN
- China
- Prior art keywords
- inquiry
- real estate
- human face
- information
- face photo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 13
- 238000001727 in vivo Methods 0.000 claims description 13
- 230000006399 behavior Effects 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 8
- 230000003760 hair shine Effects 0.000 claims description 5
- 238000012546 transfer Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 238000012549 training Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000013475 authorization Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 210000001747 pupil Anatomy 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000007639 printing Methods 0.000 description 3
- 229910000906 Bronze Inorganic materials 0.000 description 2
- 238000005452 bending Methods 0.000 description 2
- 239000010974 bronze Substances 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- KUNSUQLRTQLHQQ-UHFFFAOYSA-N copper tin Chemical group [Cu].[Sn] KUNSUQLRTQLHQQ-UHFFFAOYSA-N 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000000887 face Anatomy 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q50/16—Real estate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2141—Access rights, e.g. capability lists, access control lists, access tables, access matrices
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Collating Specific Patterns (AREA)
Abstract
This application discloses a kind of real estate information query method, device, computer equipment and storage mediums, carry out real estate information on-line checking for the place except Immovable Property Registration center, wherein method includes：The identity information of real estate information query system acquisition inquiry；It shoots the first human face photo of the inquiry, and calls corresponding with the identity information first to put on record picture according to the identity information to public security system；Calculate the similarity value that first human face photo puts picture on record with described first；Search access right corresponding with the similarity value is searched in the preset permissions list；Export real estate information corresponding with the search access right.Inquiry to Immovable Property Registration center need not can inquire house property information, and inquiry is facilitated to handle handling when needing real estate information service to such as bank, house property medium etc., reduce the generation of the case where false registration.
Description
Technical field
This application involves field of computer technology is arrived, a kind of real estate information query method, device, meter are especially related to
Calculate machine equipment and storage medium.
Background technique
Existing real estate information inquiry mainly includes two ways, the first inquiry mode is：To motionless under owner's line
Register is produced to be inquired, it is time-consuming and laborious；Second of inquiry mode be：Owner's on-line checking, but in order to protect inquiry
Privacy can only inquire limited information when inquiring on line.If necessary to inquire detailed real estate information, it revert to again
The first above-mentioned inquiry mode.
It is urgent need to resolve so how in the case where protecting inquiry's privacy to obtain real estate information to the maximum extent
The problem of.
Summary of the invention
The main purpose of the application be the real estate information query method that a kind of effectively management privacy authority is provided, device,
Computer equipment and storage medium.
The application proposes a kind of real estate information query method, carries out not for the place except Immovable Property Registration center
Movable property information on-line checking, the method includes：
Obtain the identity information of inquiry；
Shoot the first human face photo of the inquiry, and according to the identity information to public security system call with it is described
Identity information corresponding first is put on record picture；
Calculate the similarity value that first human face photo puts picture on record with described first；
Search access right corresponding with the similarity value is searched in the preset permissions list；
Export real estate information corresponding with the search access right.
Further, before the step of output real estate information corresponding with the search access right, including：
Extraction section real estate information is as real information from the real estate information；
It generates and the approximate error message of the real information；
Multiple-choice question is generated according to the real information and the error message, is selected for inquiry；
If receiving the answer that the inquiry selects as the real information, output and the search access right pair are executed
The step of real estate information answered.
Further, before the step of output real estate information corresponding with the search access right, including：
The first age of the inquiry is judged by first human face photo, and is obtained by the identity information
The second age of the inquiry；
Judge difference between first age and the second age whether within a preset range；
If so, executing the step of exporting real estate information corresponding with the search access right.
Further, it is described calculate first human face photo put on record with described first picture similarity value the step of it
Before, including：
First human face photo is input in preset ethnic identification model, determines that the race of the inquiry returns
Belong to, with the real eye color of the determination inquiry；
Judge whether the color of human eye in first human face photo is identical as the real eye color；
If it is different, the color of human eye in first human face photo is then reduced into the real eye color, in order to
With described first put on record picture carry out similarity-rough set.
Further, first human face photo includes the first human face photo of left view, right depending on the first human face photo and faces
First human face photo；It is described calculate first human face photo put on record with described first picture similarity value the step of include：
By first human face photo of left view, it is described it is right depending on the first human face photo with it is described face the first human face photo difference
Compared with described first puts picture progress on record as like degree, it is the first to respectively obtain corresponding first human face photo of left view, right view
Face photo and three groups of sub- similarity values for facing the first human face photo；
The three groups of sub- similarity values that will acquire are calculated according to preset weighted average rule, are calculated described the first
The similarity value that face photo puts picture on record with described first.
Further, the method also includes：
It collects the inquiry and inquires its praedial frequency and geographical distribution；
According to the frequency and the geographical distribution, the real estate sales/purchase behavior of the inquiry is predicted.
Further, after the step of the first human face photo of the shooting inquiry, including：
In vivo detection is carried out to the subject in shooting area；
If testing result is that the subject is living body, determine that first human face photo is available photo.
The application also provides a kind of real estate information query device, carries out for the place except Immovable Property Registration center
Real estate information on-line checking, described device include：
Acquiring unit, for obtaining the identity information of inquiry；
Call unit is shot, is arrived for shooting the first human face photo of the inquiry, and according to the identity information
Public security system calls corresponding with the identity information first to put on record picture；
Computing unit, the similarity value for putting picture on record with described first for calculating first human face photo；
Searching unit, for searching search access right corresponding with the similarity value in the preset permissions list；
Output unit, for exporting real estate information corresponding with the search access right.
The application also provides a kind of computer equipment, including memory and processor, and the memory is stored with computer
The step of program, the processor realizes any of the above-described the method when executing the computer program.
The application also provides a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that institute
State the step of realizing method described in any of the above embodiments when computer program is executed by processor.
Real estate information query method, device, computer equipment and the storage medium of the application, in Immovable Property Registration
Place except center carries out real estate information on-line checking, and inquiry need not can inquire house property letter to Immovable Property Registration center
Breath, facilitates inquiry to handle handling when needing real estate information service to such as bank, house property medium etc..Pass through recognition of face skill
Art, carries out the authentication of inquiry, and complete house property information can just be inquired by being only verified, in the condition of protection privacy
Under, farthest facilitate inquiry；If inquiry using deceptive information carry out the registration of real estate information, at this time if can not
Successful inquiring, and then the case where reduction false registration, occurs.
Detailed description of the invention
Fig. 1 is the flow diagram of the real estate information query method of one embodiment of the application；
Fig. 2 is the flow diagram of the real estate information query method of one embodiment of the application；
Fig. 3 is the structural schematic block diagram of the real estate information query device of one embodiment of the application；
Fig. 4 is the structural schematic block diagram of the real estate information query device of one embodiment of the application；
Fig. 5 is the structural schematic block diagram of the real estate information query device of one embodiment of the application；
Fig. 6 is the structural schematic block diagram of the real estate information query device of one embodiment of the application；
Fig. 7 is the structural schematic block diagram of the computing unit of one embodiment of the application；
Fig. 8 is the structural schematic block diagram of the real estate information query device of one embodiment of the application；
Fig. 9 is the structural schematic block diagram of the computer equipment of one embodiment of the application.
The embodiments will be further described with reference to the accompanying drawings for realization, functional characteristics and the advantage of the application purpose.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Referring to Fig.1, the application provides a kind of real estate information query method, for the field except Immovable Property Registration center
Carried out real estate information on-line checking, the method includes：
S1, the identity information for obtaining inquiry；
S2, the shooting inquiry the first human face photo, and called according to the identity information to public security system and
The identity information corresponding first is put on record picture；
S3, the similarity value that first human face photo puts picture on record with described first is calculated；
S4, search access right corresponding with the similarity value is searched in the preset permissions list；
S5, output real estate information corresponding with the search access right.
In the present embodiment, above-mentioned Immovable Property Registration center is the branch for undertaking Immovable Property Registration relevant policies, business, technology etc.
The place of work and land resources law clerical operations is supportted, corresponding office etc. can be set in different administrative regions,
Such as Shenzhen Immovable Property Registration center, mainly handle Immovable Property Registration business of Shenzhen etc..In above-mentioned Immovable Property Registration
Place except the heart carries out real estate information on-line checking, is primarily referred to as by the bank of Immovable Property Registration central authority, house property
The office space of Jie Deng enterprise is equipped with above-mentioned real estate information query system on the electronic equipments such as computer used, motionless
Producing information query system is to be connect by the interface of http agreement with the server at Immovable Property Registration center.In the present embodiment, only
The above-mentioned real estate information query system of use can be logged in by having the electronic equipments such as the computer of the enterprise of authorization.
As described in above-mentioned steps S1, Immovable Property Registration operation system is installed generally on office equipment, above-mentioned real estate is looked into
It is an on-line checking page that inquiry system, which is presented on the content on the screen of computer, the person's identity information that is provided with input inquiry
Input window etc..Wherein, identity information includes at least the identification card number of inquiry, and house property essential information to be checked includes at least
The specific address of house property.In the application, above-mentioned identity information is usually to be manually entered by the staff of bank or house property medium
Into real estate inquiry system.It in other embodiments, can also be by inputting praedial essential information reverse-direction derivation to be checked
The identity information of inquiry out, i.e., owner corresponding to real estate center finding according to praedial essential information to be checked
Information, owner's information are the inquiry's information defaulted.
As described in above-mentioned steps S2, above-mentioned real estate information query system can control camera shooting inquiry connected to it
The facial photo (generally including positive face photograph) of person, i.e., the first above-mentioned human face photo.Above-mentioned first picture of putting on record refers to inquiry
Handle picture when identity card.In the present embodiment, above-mentioned real estate information query system is the system of public security system authorization, public security
System allows real estate information query system to access its database for being stored with identity card, therefore real estate information query system can
To call identity card picture corresponding with the identity information into public security system according to the identification card number that gets, and identity card
There is face picture on picture, which is above-mentioned first to put on record picture.
As described in above-mentioned steps S3, the calculating process of similarity value is specially：First human face photo is input to preset
In human face recognition model carry out operation export the first human face photo feature vector, and by first put on record picture be input to it is above-mentioned
Human face recognition model in carry out the feature vector that picture is put in operation output first on record, then by the feature of the first human face photo to
The feature vector that amount puts picture on record with first carries out similarity calculation.Specific similarity value calculating can be used Euclid away from
With a distance from (Eucledian Distance), manhatton distance (Manhattan Distance), Minkowski
A kind of algorithm is calculated in (Minkowski distance) or cosine similarity.
As described in above-mentioned steps S4, above-mentioned preset permissions list is an one-to-one map listing, wherein having similar
One column of angle value and a column of search access right, the corresponding search access right of each similarity value.In the present embodiment, when
When permissions list can not find similarity value identical with similarity value is calculated in above-mentioned steps S3, then permission is selected to arrange
In table with calculate the smallest similarity value of similarity value difference in above-mentioned steps S3 and use.For example, calculated first face
The similarity value that photo puts picture on record with described first is 10, and not having similarity value in permissions list is 10 option, and only
There are the similarity values options such as 3,6,9,12, then selection and the close similarity value 9 of similarity value 10, then select similarity value
9 corresponding search access rights.Above-mentioned search access right refers to the search access right of inquiry, and search access right is higher, can find
Real estate information is more, if search access right is 100%, can check praedial all information to be checked etc..
It is as described in above-mentioned steps S5, i.e., above-mentioned to be checked praedial to be transferred according to search access right to Immovable Property Registration center
Information.The way of output include it is a variety of, including the printing directly by being connect with the computer for being equipped with real estate information query system
Machine prints；Alternatively, being shown by computer screen；Alternatively, played back by way of with voice broadcast, voice broadcast
Mode is conducive to use when inquiry is blind person, correspondingly, the step of the identity information of above-mentioned acquisition inquiry, can be logical
The mode for crossing speech recognition obtains, and the voice input of inquiry is such as received, then by converting speech sound input into characters etc..This implementation
In example, if the above-mentioned praedial information to be checked of inquiry is can also to give birth to the content inquired to sign relevant contract
At the documentary evidence for having real estate center official seal, for using.
In one embodiment, inquiry needs to carry out building property mortgage etc., bank when bank handles the business such as loan
Staff live can accurately view the house property information of the inquiry.Specifically, bank clerk logs in real estate
Then information query system uses the Account Logon of staff, after the identity information of input inquiry person, acquire inquiry
Current face information, and combine the inquiry in the photo of putting on record of public security system, judge whether the inquiry is room to be checked
The owner of production, if so, open whole search access right, to show praedial all information to be checked.Another specific embodiment
In, inquiry needs to check whether the inquiry meets local house-purchase condition etc. when house property medium handles the business such as house-purchase,
Intermediary staff live can accurately view the house property information of the inquiry, to judge whether the inquiry can purchase
Then room uses the Account Logon of staff, defeated specifically, intermediary staff logs in real estate information query system
After the identity information for entering inquiry, the current face information of acquisition inquiry, and combine the inquiry putting on record in public security system
Photo, judge the inquiry whether be log in identity information I, if it is, showing whole real estates of the inquiry
Information.Further, it can also be linked to surplus account or social security account, check that the common reserve fund of the inquiry and social security are paid
Situations such as receiving further facilitates the judgement of intermediary staff.
In the present embodiment, before the step S5 of above-mentioned output real estate information corresponding with the search access right, including：
S51, from the real estate information extraction section real estate information as real information；
S52, it generates and the approximate error message of the real information；
S53, the real information and the error message are generated into multiple-choice question, is selected for inquiry；
If S54, receiving the answer that the inquiry selects as the real information, executes output and weighed with the inquiry
The step of limiting corresponding real estate information.
As described in above-mentioned steps S51 to S54, above-mentioned real information, real estate as to be checked is in above-mentioned Immovable Property Registration
The information of heart registration, praedial information to be checked at this time is the whole that corresponding real estate to be checked is registered at Immovable Property Registration center
Be not related to the information of privacy information.Real information is out of in the information that above-mentioned Immovable Property Registration center is registered extract
Hold, can randomly select, it can also be according to specified rule extraction, as extracted the information in real estate information about transfer
Deng.After getting real information, the meaning of real information can be obtained, is then generated according to meaning according to speech analysis method
Approximate error message, citing, in praedial information to be checked, true transfer the possession of is recorded as transfer on October 15th, 2010,
After the part is extracted, transfer on October 15th, 2011 is generated, on November 15th, 2010 is transferred the possession of, on October 25th, 2010 turns
It the error messages of interference such as allows, " selects the real estate correct an above-mentioned correct information and three error messages formation
Four alternative answers of the multiple-choice question of the answer of transfer record ", select for inquiry, and only inquiry answers correct, can just hold
The movement of row above-mentioned steps S5.The step of multiple-choice question, is answered in setting, can further judge whether inquiry is to be checked motionless
The owner of production, to effectively prevent being exposed about praedial privacy information to be checked.In other embodiments, multiple tracks can be generated
After similar multiple-choice question, only inquiry continuously answer questions the multiple-choice question of specified quantity, the movement of above-mentioned steps S5 can be just executed.
In one embodiment, before the step S5 of above-mentioned output real estate information corresponding with the search access right, packet
It includes：
S501, the first age that the inquiry is judged by first human face photo, and believed by the identity
Breath obtains the second age of the inquiry；
S502, judge difference between first age and the second age whether within a preset range；
S503, if so, execute export real estate information corresponding with the search access right the step of.
As described in above-mentioned steps S501 to S503, above-mentioned first age is real estate inquiry system according to the first human face photo
The age deduced, specific method are that the first human face photo is input in preset age identification model, is exported by operation
Above-mentioned first age.Above-mentioned age identification model be trained based on convolutional neural networks come model, obtain first a large amount of
Human face photo, and corresponding real age is marked on each human face photo, be then input in preset convolutional neural networks into
Row training after training, is verified it by another batch of human face photo with label real age, if verifying is logical
It crosses to get above-mentioned age identification model is arrived.Above-mentioned second age is the age calculated according to identity information, such as according to input
Identification card number, obtain its date of birth, calculate second age etc. then in conjunction with current date.If current queries person is true
Real owner, then the first age and the second age should be identical, it is contemplated that according to the accuracy problem that model judges, setting
One error range (above-mentioned preset range), the difference between only the first age and the second age within the error range,
It just will be considered that inquiry may be praedial owner to be checked, then can just execute the movement of above-mentioned steps S5, with effectively anti-
Only it is exposed about praedial privacy information to be checked.If difference between the first age and the second age error range it
Outside, it can bear " not exporting the order of query result ", control real estate information query system stops output query result, or
Person generates a smaller search access right, less about praedial information to be checked to export.
In one embodiment, the similarity value that above-mentioned calculating first human face photo puts picture on record with described first
Before step S3, including：
S31, first human face photo is input in preset ethnic identification model, determines the race of the inquiry
Ownership, with the real eye color of the determination inquiry；
S32, judge whether the color of human eye in first human face photo is identical as the real eye color；
S33, if it is different, the color of human eye in first human face photo is then reduced into the real eye color, with
Convenient for described first put on record picture carry out similarity-rough set.
As described in above-mentioned steps S31 to S33, because inquiry has U.S. pupil in order to beautiful, then will affect the first
Face photo and first put picture similarity on record calculated result, so herein relatively before the first human face photo is located in advance
Reason, i.e., dispose U.S. pupil effect from the first human face photo.Specifically process is：The first human face photo is first input to race
In identification model, the race of inquiry is judged, that is, judge that inquiry is yellow, black race or white people etc., Jin Ergen
The real eye color of inquiry is determined according to its race, such as determines that inquiry is bronze bell people, then its eye should be black, such as
Human eye color is other colors in the first human face photo of fruit, then is revised as black.Above-mentioned ethnic identification model is a kind of
With model obtained from convolutional neural networks training, training method is being trained using training set for routine, test set
It tests etc., is not repeating herein.Using pretreated first human face photo, accurate first human face photo can be just obtained
Put on record with first the similarity value of picture.
In a kind of possible embodiment, above-mentioned first human face photo may include the first human face photo of left view, right view the
One human face photo and face the first human face photo；It is described to calculate first human face photo and put on record the similar of picture to described first
The step S3 of angle value, including：
S301, by first human face photo of left view, it is described it is right depending on the first human face photo with it is described face the first face shine
Compared with piece puts picture progress picture on record like degree with described first respectively, corresponding first human face photo of left view, right view are respectively obtained
First human face photo and three groups of sub- similarity values for facing the first human face photo；
S302, the sub- similarity value of will acquire three group are calculated according to preset weighted average rule, obtain described first
The similarity value that human face photo puts picture on record with described first.
As described in above-mentioned steps S301 and S302, above-mentioned the first human face photo of left view and the first human face photo of right view are point
The photo not shot from the left and right side of the face of inquiry.Because of the first human face photo of the first human face photo of left view and right view
Whole five features cannot be covered, thus with first put on record picture similarity value can relative to facing the first human face photo and
It says lower.In the present embodiment, by the first human face photo of left view, it is right depending on the first human face photo and face the first human face photo respectively with
First picture of putting on record is compared, and then obtains three groups of sub- similarity values, but is not that three groups of sub- similarity values are directly flat
It calculates, but weighted average calculation, for example, the corresponding sub- similarity value of the first human face photo of left view is multiplied by a percentage,
The corresponding sub- similarity value of the first human face photo of right view is multiplied by a percentage, and faces the corresponding sub- phase of the first human face photo
Like angle value multiplied by a percentage, then it is added and obtains final similarity value.The present embodiment shoots inquiry's different angle
Human face photo, the inquiry of non-owner can be prevented using the photo of owner, and (photo is only able to display a fixed-direction
Image, such as a positive photo of face, are not available the human face photo that the full face shoots its left and right side) deception
Real estate information query system, and obtain praedial all information to be checked.
Referring to Fig. 2, in the present embodiment, the step S5 of above-mentioned output real estate information corresponding with the search access right it
Afterwards, including：
S6, the collection inquiry inquire its praedial frequency and geographical distribution；
S7, according to the frequency and the geographical distribution, predict the real estate sales/purchase behavior of the inquiry.
As described in above-mentioned steps S7 and S8, the data of record can be uploaded to one by as above-mentioned real estate information query system
In a server, the content of record includes the query time of inquiry, where was carrying out inquiry etc..These are recorded
It is predicted according to preset method, both may determine that the real estate sales/purchase behavior of inquiry.In one embodiment, certain
For inquiry in three months, the house property medium in the different region in Shenzhen inquires its real estate information, illustrates it different
The excessively different intermediary of regional connection, and intermediary can generally verify the house-purchase condition of inquiry before introducing the source of houses to it, at this time
It needs to inquire the real estate information of the inquiry by above-mentioned real estate information query system, and then judges whether inquiry has
Buy qualification.Then the source of houses is searched according to the frequency of its inquiry and its different zones only in Shenzhen, can be both somebody's turn to do with preliminary judgement
Inquiry will buy house.And if inquiry inquired its real estate information in national most of West within three months, then
Illustrate that inquiry may investigate real estate market in China, and then carries out " building speculation " behavior.Judged according to above-mentioned
Real estate sales/purchase behavior can send relevant information to inquiry, to help inquiry to understand the house property letter of its care in time
Breath.
In the present embodiment, after the step of the first human face photo of the above-mentioned shooting inquiry, including：
S11, In vivo detection is carried out to the subject in shooting area；
If S12, testing result are that the subject is living body, determine that first human face photo is available photo.
As described in above-mentioned steps S11 and S12, In vivo detection is carried out to subject in shooting area, to prevent other people from utilizing
The photo fraud system of the corresponding owner of real estate information.The mode packet of In vivo detection is carried out to the subject in shooting area
Include it is a variety of, it is each to determine using the time domain variation and correlation of the pixel intensity data in image sequence such as according to optical flow method
From " movement " of location of pixels, the operation information of each pixel is obtained from image sequence, using Difference of Gaussian filter,
A kind of LBP (Local BinaryPattern is operator for describing image local feature) feature and support vector machines carry out
Data statistic analysis.This In vivo detection mode can realize Blind Test in the case where inquiry is without cooperation.Alternatively, being taken the photograph using 3D
As head shooting face, the 3D data of corresponding human face region are obtained, and be further analyzed based on these data, it is final to judge
This face is from living body or non-living body out.Here the source of non-living body is that comparison is extensive, including mobile phone and Pad etc. are situated between
The photos and videos of matter, various printings unlike material photo (here comprising various situations bending, fold, cut out, digging a hole
Etc. situations) etc..3D human face data based on living body and non-living body selects the feature of most discrimination to train classifier, benefit
Living body and non-living body are distinguished with trained classifier.Alternatively, carrying out ultrasonic scanning to shooting area, and receive ultrasonic wave
Back wave；The elementary contour of the object of shooting area is judged according to back wave；If profile meets preset standard, judgement is worked as
The picture of preceding shooting is true man, and principle is：If the picture of current shooting is a poster, poster must be more smooth
Expansion, its profile is a plane at this time, and if it is true man, and profile is 3d profile etc..
In one embodiment, above-mentioned that inquiry corresponding with the similarity value is searched in the preset permissions list
After the step S4 of permission, including：The open each time of each login account of real estate information query system is collected to look into
Ask permission；At the appointed time in length, if the ratio that search access right does not have wide-open number to account for total inquiry times is greater than in advance
If when ratio, generating prompting message.The prompting message includes the forms such as mail, and mail is generally sent to specified leader's postal
Case.Because real estate inquiry is carried out in bank or house property medium, bank or intermediary have corresponding account, record
Account carries out in face recognition process, inquiry and the inconsistent number of photo of putting on record (without completely open search access right), will
Inconsistent number a illustrates that the staff of the account is working if ratio is greater than default ratio than upper identification total degree b
In conscientious degree it is bad, the real information etc. of inquiry can not be well understood in time during transacting business, that is, do not have
Link up clear, with regard to carrying out the movement of real estate information inquiry, professional skill is to be improved.
In other embodiments, if the similarity value that above-mentioned first human face photo puts picture on record with described first reaches pre-
If value (explanation the first human face photo with first put on record picture be same people photo), then on the net in chasing personnel library lookup be
It is no to exist and the matched identity information of inquiry；If found in the online chasing personnel library and the matched body of inquiry
Part information, then automatic alarm.Because the first human face photo and first put on record picture be same people photo, it is possible to determination look into
Inquiry person is authentic and valid citizen.At this point, real estate information query system can AutoLink search in chasing personnel library on the net
The fugitive personal information to match with inquiry's ID card information illustrates to look into if finding identical fugitive personal information
Inquiry person is online chasing personnel, and system can backstage sending alarm signal.Alarm signal can be notice real estate information inquiry system
The administrative staff of system, such as the place of real estate information query system installation Mr. Yu bank, then alarm signal can be by rear
Platform is sent to security department of bank.It, can also be by being directly connected to 110 alarm platforms, meeting from the background in another specific implementation
The relevant informations such as corresponding address information are sent to 110 alarm platforms etc..
The real estate information query method of the present embodiment carries out real estate for the place except Immovable Property Registration center
Information on-line checking, inquiry need not can inquire house property information to Immovable Property Registration center, facilitate inquiry to such as bank, room
It produces intermediary etc. and handles handling when needing real estate information service.By face recognition technology, the authentication of inquiry is carried out,
Complete house property information can just be inquired by being only verified, and under conditions of protecting privacy, farthest facilitate inquiry
Person；If inquiry using deceptive information carry out the registration of real estate information, at this time if can not successful inquiring, and then reduce falseness step on
The case where note, occurs.
Referring to Fig. 3, the application provides a kind of real estate information query device, for the field except Immovable Property Registration center
Carried out real estate information on-line checking, described device include：
Acquiring unit 10, for obtaining the identity information of inquiry；
Call unit 20 is shot, for shooting the first human face photo of the inquiry, and according to the identity information
Corresponding with the identity information first is called to put on record picture to public security system；
Computing unit 30, the similarity value for putting picture on record with described first for calculating first human face photo；
Searching unit 40, for searching inquiry power corresponding with the similarity value in the preset permissions list
Limit；
Output unit 50, for exporting real estate information corresponding with the search access right.
In the present embodiment, above-mentioned Immovable Property Registration center is the branch for undertaking Immovable Property Registration relevant policies, business, technology etc.
The place of work and land resources law clerical operations is supportted, corresponding office etc. can be set in different administrative regions,
Such as Shenzhen Immovable Property Registration center, mainly handle Immovable Property Registration business of Shenzhen etc..In above-mentioned Immovable Property Registration
Place except the heart carries out real estate information on-line checking, is primarily referred to as by the bank of Immovable Property Registration central authority, house property
The office space of Jie Deng enterprise is equipped with above-mentioned real estate information query system on the electronic equipments such as computer used, motionless
Producing information query system is to be connect by the interface of http agreement with the server at Immovable Property Registration center.In the present embodiment, only
The above-mentioned real estate information query system of use can be logged in by having the electronic equipments such as the computer of the enterprise of authorization.
In acquiring unit 10, Immovable Property Registration operation system, above-mentioned real estate inquiry are installed generally on office equipment
It is an on-line checking page that system, which is presented on the content on the screen of computer, the person's identity information that is provided with input inquiry
Input window etc..Wherein, identity information includes at least the identification card number of inquiry.In the application, above-mentioned identity information is usually
It is manually entered into real estate inquiry system by the staff of bank or house property medium.In other embodiments, can also lead to
The identity information for inputting praedial essential information reverse push export inquiry to be checked is crossed, i.e., according to praedial basic letter to be checked
The corresponding owner's information of real estate center finding is ceased, which is the inquiry's information defaulted.
In above-mentioned shooting call unit 20, above-mentioned real estate information query system can control camera connected to it and clap
Take the photograph the facial photo (generally including positive face photograph) of inquiry, i.e., the first above-mentioned human face photo.Above-mentioned first picture of putting on record refers to
Inquiry handles picture when identity card.In the present embodiment, above-mentioned real estate information query system is that public security system authorization is
System, public security system allows real estate information query system to access its database for being stored with identity card, therefore real estate information is looked into
Inquiry system can call identity card picture corresponding with the identity information according to the identification card number got into public security system,
And have face picture on identity card picture, which is above-mentioned first to put on record picture.
In above-mentioned computing unit 30, the calculating process of similarity value is specially：First human face photo is input to default
Human face recognition model in carry out the feature vector that operation exports the first human face photo, and the first picture of putting on record is input to
The feature vector that picture is put in operation output first on record is carried out in the human face recognition model stated, then by the feature of the first human face photo
Vector sum first put on record picture feature vector carry out similarity calculation.Euclid can be used in specific similarity value calculating
Distance (Eucledian Distance), manhatton distance (Manhattan Distance), Minkowski distance
A kind of algorithm is calculated in (Minkowski distance) or cosine similarity.
In above-mentioned searching unit 40, above-mentioned preset permissions list is an one-to-one map listing, wherein there is phase
Like a column of angle value and a column of search access right, the corresponding search access right of each similarity value.In the present embodiment,
When permissions list can not find and calculate the identical similarity value of similarity value with above-mentioned computing unit 30, then right to choose
The smallest similarity value of similarity value difference is calculated with above-mentioned Liu's table in limit list to use.For example, calculated first face
The similarity value that photo puts picture on record with described first is 10, and not having similarity value in permissions list is 10 option, and only
There are the similarity values options such as 3,6,9,12, then selection and the close similarity value 9 of similarity value 10, then select similarity value
9 corresponding search access rights.Above-mentioned search access right refers to the search access right of inquiry, and search access right is higher, can find
Real estate information is more, if search access right is 100%, can check praedial all information to be checked etc..
In above-mentioned output unit 50, i.e., to transfer above-mentioned real estate to be checked according to search access right to Immovable Property Registration center
Information unit.The way of output include it is a variety of, including directly by be equipped with real estate information query system computer connect
The printer connect prints；Alternatively, being shown by computer screen；Alternatively, being played back by way of with voice broadcast, language
The mode of sound casting, is conducive to use when inquiry is blind person, correspondingly, the method for the identity information of above-mentioned acquisition inquiry,
It can be and obtained by way of speech recognition, the voice input of inquiry is such as received, then by converting speech sound input into characters
Deng.In the present embodiment, if the above-mentioned praedial information to be checked of inquiry can also will be inquired to sign relevant contract
Content generate have real estate center official seal documentary evidence, for using.
In one embodiment, inquiry needs to carry out building property mortgage etc., bank when bank handles the business such as loan
Staff live can accurately view the house property information of the inquiry.Specifically, bank clerk logs in real estate
Then information query system uses the Account Logon of staff, after the identity information of input inquiry person, acquire inquiry
Current face information, and combine the inquiry in the photo of putting on record of public security system, judge whether the inquiry is room to be checked
The owner of production, if so, open whole search access right, to show praedial all information to be checked.Another specific embodiment
In, inquiry needs to check whether the inquiry meets local house-purchase condition etc. when house property medium handles the business such as house-purchase,
Intermediary staff live can accurately view the house property information of the inquiry, to judge whether the inquiry can purchase
Then room uses the Account Logon of staff, defeated specifically, intermediary staff logs in real estate information query system
After the identity information for entering inquiry, the current face information of acquisition inquiry, and combine the inquiry putting on record in public security system
Photo, judge the inquiry whether be log in identity information I, if it is, showing whole real estates of the inquiry
Information.Further, it can also be linked to surplus account or social security account, check that the common reserve fund of the inquiry and social security are paid
Situations such as receiving further facilitates the judgement of intermediary staff.
Referring to Fig. 4, in the present embodiment, above-mentioned real estate information query device, including：
Extracting unit 51, for from the real estate information extraction section real estate information as real information；
Generation unit 52, for generating and the approximate error message of the real information；
Mixed cell 53 is selected for the real information and the error message to be generated multiple-choice question for inquiry；
Generation unit 54 is received, if the answer for receiving inquiry's selection, executes output and the inquiry
The step of permission corresponding real estate information.
In above-mentioned extracting unit 51, generation unit 52, mixed cell 53 and receive in generation unit 54, it is above-mentioned praedial
Real information, the information that real estate as to be checked is registered at above-mentioned Immovable Property Registration center, praedial information to be checked at this time
Being corresponding real estate to be checked whole is not related to the information of privacy information what Immovable Property Registration center was registered.Real information be from
The content extracted in the information of above-mentioned Immovable Property Registration center registration, can randomly select, can also be according to specified
Rule extraction, such as extract the information in real estate information about transfer.It, can be according to speech analysis after getting real information
Method obtains the meaning of real information, then generates approximate error message, citing ground, praedial letter to be checked according to meaning
In breath, true transfer the possession of is recorded as transfer on October 15th, 2010, after which is extracted, generates on October 15th, 2011
The error message for the interference such as transfer, on November 15th, 2010 are transferred the possession of, on October 25th, 2010 is transferred the possession of, above-mentioned one is just being firmly believed
Breath and three error messages form four alternative answers of the multiple-choice question of " real estate is selected correctly to transfer the possession of the answer of record ",
It is selected for inquiry, only inquiry answers correct, can just export the real estate information of corresponding search access right.Selection is answered in setting
The step of topic, can further judge whether inquiry is praedial owner to be checked, with effectively prevent about it is to be checked not
The privacy information of movable property is exposed.In other embodiments, the similar multiple-choice question of multiple tracks can be generated, only inquiry continuously answers questions
After the multiple-choice question of specified quantity, the real estate information of corresponding search access right can be just exported.
Referring to Fig. 5, in one embodiment, above-mentioned real estate information query device, including：
Age acquiring unit 501, for judging the first age of the inquiry by first human face photo, and
The second age of the inquiry is obtained by the identity information；
Judging unit 502, for whether within a preset range to judge the difference between first age and the second age；
Command unit 503 is generated, if within a preset range for the difference between the first age and the second age, executing
The step of exporting real estate information corresponding with the search access right.
It in above-mentioned age acquiring unit 501, judging unit 502 and generates in command unit 503, above-mentioned first age is not
The age that movable property inquiry system is deduced according to the first human face photo, specific method are to be input to the first human face photo default
Age identification model in, export above-mentioned first age by operation.Above-mentioned age identification model is based on convolutional neural networks
The model come is trained, obtains a large amount of human face photo first, and mark corresponding real age on each human face photo, then
It is input in preset convolutional neural networks and is trained, after training, in the people for having another crowd label real age
Face photo verifies it, if the verification passes to get arrive above-mentioned age identification model.Above-mentioned second age is according to body
The age that part information calculates obtains its date of birth, calculates then in conjunction with current date such as according to the identification card number of input
Second age etc..If current queries person is true owner, the first age and the second age should be identical, it is contemplated that
According to the accuracy problem that model judges, an error range (above-mentioned preset range), only the first age and second are set
Difference between age within the error range, just will be considered that inquiry may be praedial owner to be checked, then just can
The real estate information of corresponding search access right is exported, to effectively prevent being exposed about praedial privacy information to be checked.If the
Difference between one age and the second age can be born " not exporting the order of query result " except error range, control
Real estate information query system stops output query result, alternatively, a smaller search access right is generated, to export less pass
In praedial information to be checked.
Referring to Fig. 6, in one embodiment, above-mentioned real estate information query device, including：
Judging unit 31, for first human face photo to be input in preset ethnic identification model, described in judgement
Race's ownership of inquiry, with the real eye color of the determination inquiry；
Color judging unit 32, for judge human eye in first human face photo color whether with the real eye
Color is identical；
Reduction unit 33, if not identical for the color of human eye in the first human face photo and the real eye color,
The color of human eye in first human face photo is reduced into the real eye color, in order to put on record picture with described first
Carry out similarity-rough set.
In above-mentioned judging unit 31, color judging unit 32 and reduction unit 33 because inquiry in order to beautiful band
Have U.S. pupil, then will affect the first human face photo and first put picture similarity on record calculated result, so before comparing herein
First human face photo is pre-processed, i.e., is disposed U.S. pupil effect from the first human face photo.Specifically process is：First will
First human face photo is input in ethnic identification model, judges the race of inquiry, that is, judge inquiry be yellow, it is black
Kind people or white people etc., and then according to the real eye color of the determining inquiry of its race, such as determine that inquiry is bronze bell people, that
Its eye should be black, if human eye color is other colors in the first human face photo, be revised as black.It is above-mentioned
Ethnic identification model be it is a kind of there is model obtained from convolutional neural networks training, training method is conventional to utilize instruction
Practice collection to be trained, test set is tested etc., is not being repeated herein.Using pretreated first human face photo, could obtain
Put on record the similarity value of picture to accurate first human face photo and first.
Referring to Fig. 7, in a kind of possible embodiment, above-mentioned first human face photo may include that the first face of left view shines
Piece right depending on the first human face photo and faces the first human face photo；Above-mentioned computing unit 30, including：
It is respectively compared module 301, for by first human face photo of left view, the first human face photo of the right view and described
The first human face photo picture of putting on record with described first respectively is faced to carry out as compared with like degree, respectively obtaining the corresponding left view first
Human face photo right depending on the first human face photo and faces three groups of sub- similarity values of the first human face photo；
Weighted calculation module 302, three groups of sub- similarity values by will acquire according to preset weighted average rule based on
It calculates, obtains the similarity value that first human face photo puts picture on record with described first.
It is respectively compared in module 301 and weighted calculation module 302 above-mentioned, above-mentioned the first human face photo of left view and right view the
One human face photo is the photo shot respectively from the left and right side of the face of inquiry.Because the first human face photo of left view and
It is right to cover whole five features depending on the first human face photo, so the similarity value for putting picture on record with first can be relative to just
It is lower depending on for the first human face photo.In the present embodiment, by the first human face photo of left view, right depending on the first human face photo and is faced
One human face photo picture of putting on record respectively with first is compared, and then obtains three groups of sub- similarity values, but is not by three groups
The sub- direct average computation of similarity value, but weighted average calculation, for example, the corresponding sub- similarity value of the first human face photo of left view
Multiplied by a percentage, the corresponding sub- similarity value of the first human face photo of right view is multiplied by a percentage, and faces the first
Then the corresponding sub- similarity value of face photo is added multiplied by a percentage and obtains final similarity value.The present embodiment shooting
The human face photo of inquiry's different angle, the inquiry of non-owner can be prevented using the photo of owner, and (photo can only be shown
Show the image of a fixed-direction, such as a positive photo of face, is not available the full face and shoots its left side and the right side
The human face photo of side) deception real estate information query system, and obtain praedial all information to be checked.
Referring to Fig. 8, in the present embodiment, above-mentioned real estate information query device further includes：
Collector unit 60 inquires its praedial frequency and geographical distribution for collecting the inquiry；
Predicting unit 70, for predicting the real estate sales/purchase of the inquiry according to the frequency and the geographical distribution
Behavior.
In above-mentioned collector unit 60 and predicting unit 70, above-mentioned real estate information query system can will be in the data of record
It passes in a server, the content of record includes the query time of inquiry, where carrying out inquiry etc..By this
A little records are predicted according to preset method, both may determine that the real estate sales/purchase behavior of inquiry.In a specific implementation
Example in, for certain inquiry in three months, the house property medium in the different region in Shenzhen inquires its real estate information, illustrate its
The excessively different intermediary of different regional connections, and intermediary can generally verify the house-purchase item of inquiry before introducing the source of houses to it
Part, needs to inquire at this time the real estate information of the inquiry by above-mentioned real estate information query system, and then judges inquiry
Whether there is purchase qualification.Then the source of houses is searched according to the frequency of its inquiry and its different zones only in Shenzhen, it both can be first
Step determines that the inquiry will buy house.And if within three months, it is motionless that inquiry in national most of West inquired its
Information is produced, then illustrates that inquiry may investigate real estate market in China, and then carry out " building speculation " behavior.According to above-mentioned
The real estate sales/purchase behavior judged can send relevant information to inquiry, to help inquiry to understand its care in time
House property information.
In the present embodiment, above-mentioned real estate information query device further includes：
In vivo detection unit, for carrying out In vivo detection to the subject in shooting area；
Living body judging unit determines that first face shines if being the subject for testing result is living body
Piece is available photo.
In vivo detection is carried out to subject in shooting area, to prevent other people from utilizing the corresponding owner's of real estate information
Photo fraud system.It includes a variety of that the mode of In vivo detection is carried out to the subject in shooting area, such as according to optical flow method, benefit
" movement " that respective location of pixels is determined with the variation of the time domain of the pixel intensity data in image sequence and correlation, from image
The operation information that each pixel is obtained in sequence, using Difference of Gaussian filter, LBP, (Local Binary Pattern is
A kind of operator for describing image local feature) feature and support vector machines carry out data statistic analysis.This In vivo detection
Mode can realize Blind Test in the case where inquiry is without cooperation.Alternatively, shooting face using 3D camera, corresponding people is obtained
The 3D data in face region, and being further analyzed based on these data, finally judge this face be from living body or
Non-living body.Here the source of non-living body is that comparison is extensive, photos and videos, various printings including the media such as mobile phone and Pad
The photo (bending comprising various situations here such as folds, cuts out, digging a hole at the situations) of unlike material etc..Based on living body and non-
The 3D human face data of living body is selected the feature of most discrimination to train classifier, is distinguished using trained classifier
Living body and non-living body.Alternatively, carrying out ultrasonic scanning to shooting area, and receive the back wave of ultrasonic wave；Sentenced according to back wave
The elementary contour of the object of disconnected shooting area；If profile meets preset standard, determine that the picture of current shooting is true man,
Principle is：If the picture of current shooting is a poster, the expansion that poster must be more smooth, its profile is one at this time
A plane, and if it is true man, profile is 3d profile etc..
In one embodiment, above-mentioned real estate information query device further includes：Permission unit is collected, for collecting not
The search access right open each time of each login account of movable property information query system；Reminding unit, for when specified
Between in length, if search access right does not have wide-open number to account for the ratios of total inquiry times when being greater than default ratio, generation is mentioned
Awake information.The prompting message includes the forms such as mail, and mail is generally sent to specified leader's mailbox.Because real estate is inquired
It is to be carried out in bank or house property medium, so bank or intermediary have corresponding account, record account carries out recognition of face
In the process, inquiry and the inconsistent number of photo of putting on record (without completely open search access right), by inconsistent number a than upper
Identify total degree b, if ratio is greater than default ratio, illustrating the staff of the account, conscientious degree is bad at work,
The real information etc. of inquiry can not be well understood during transacting business in time, i.e., it is clear without linking up, with regard to carrying out not
The movement of movable property information inquiry, professional skill are to be improved.
In other embodiments, if the similarity value that above-mentioned first human face photo puts picture on record with described first reaches pre-
If value (explanation the first human face photo with first put on record picture be same people photo), then on the net in chasing personnel library lookup be
It is no to exist and the matched identity information of inquiry；If found in the online chasing personnel library and the matched body of inquiry
Part information, then automatic alarm.Because the first human face photo and first put on record picture be same people photo, it is possible to determination look into
Inquiry person is authentic and valid citizen.At this point, real estate information query system can AutoLink search in chasing personnel library on the net
The fugitive personal information to match with inquiry's ID card information illustrates to look into if finding identical fugitive personal information
Inquiry person is online chasing personnel, and system can backstage sending alarm signal.Alarm signal can be notice real estate information inquiry system
The administrative staff of system, such as the place of real estate information query system installation Mr. Yu bank, then alarm signal can be by rear
Platform is sent to security department of bank.It, can also be by being directly connected to 110 alarm platforms, meeting from the background in another specific implementation
The relevant informations such as corresponding address information are sent to 110 alarm platforms etc..
The real estate information query device of the present embodiment carries out real estate for the place except Immovable Property Registration center
Information on-line checking, inquiry need not can inquire house property information to Immovable Property Registration center, facilitate inquiry to such as bank, room
It produces intermediary etc. and handles handling when needing real estate information service.By face recognition technology, the authentication of inquiry is carried out,
Complete house property information can just be inquired by being only verified, and under conditions of protecting privacy, farthest facilitate inquiry
Person；If inquiry using deceptive information carry out the registration of real estate information, at this time if can not successful inquiring, and then reduce falseness step on
The case where note, occurs.
Referring to Fig. 9, a kind of computer equipment is also provided in the embodiment of the present application, which can be server,
Its internal structure can be as shown in Figure 9.The computer equipment includes processor, the memory, network connected by system bus
Interface and database.Wherein, the processor of the Computer Design is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program
And database.The internal memory provides environment for the operation of operating system and computer program in non-volatile memory medium.It should
The database of computer equipment is for storing the data such as human face recognition model.The network interface of the computer equipment is used for and outside
Terminal by network connection communication.To realize a kind of real estate information issuer when the computer program is executed by processor
Method.
Above-mentioned processor executes above-mentioned real estate information query method, for the place except Immovable Property Registration center into
Row real estate information on-line checking, specific steps include：Obtain the identity information of inquiry；Shoot the first of the inquiry
Face photo, and call corresponding with the identity information first to put on record picture according to the identity information to public security system；Meter
Calculate the similarity value that first human face photo puts picture on record with described first；Lookup and institute in the preset permissions list
State the corresponding search access right of similarity value；Export real estate information corresponding with the search access right.
In one embodiment, before the step of above-mentioned output corresponding with search access right real estate information, including：From
Extraction section real estate information is as real information in the real estate information；It generates and believes with the approximate mistake of the real information
Breath；Multiple-choice question is generated according to the real information and the error message, is selected for inquiry；If receiving inquiry's choosing
The answer selected is the real information, then executes the step of exporting real estate information corresponding with the search access right.
In one embodiment, before the step of above-mentioned output corresponding with search access right real estate information, including：It is logical
The first age that first human face photo judges the inquiry is spent, and the inquiry is obtained by the identity information
The second age；Judge difference between first age and the second age whether within a preset range；If so, executing defeated
The step of real estate information corresponding with the search access right out.
In one embodiment, above-mentioned calculating first human face photo with described first put on record picture similarity value step
Before rapid, including：First human face photo is input in preset ethnic identification model, determines the race of the inquiry
Ownership, with the real eye color of the determination inquiry；Judge human eye in first human face photo color whether with institute
It is identical to state real eye color；If it is different, the color of human eye in first human face photo is then reduced into the real eye
Color, in order to described first put on record picture carry out similarity-rough set.
In one embodiment, above-mentioned first human face photo include the first human face photo of left view, the first human face photo of right view and
Face the first human face photo；Above-mentioned calculating first human face photo with described first put on record picture similarity value the step of packet
It includes：By first human face photo of left view, it is described it is right depending on the first human face photo and it is described face the first human face photo respectively with institute
It states first and puts picture progress on record as comparing like degree, respectively obtain corresponding first human face photo of left view, the first face of right view shines
Piece and three groups of sub- similarity values for facing the first human face photo；The three groups of sub- similarity values that will acquire are flat according to preset weighting
Rule calculates, and obtains the similarity value that first human face photo puts picture on record with described first.
In one embodiment, after the step of above-mentioned output corresponding with search access right real estate information, including：It receives
Collect the inquiry and inquires its praedial frequency and geographical distribution；According to the frequency and the geographical distribution, described in prediction
The real estate sales/purchase behavior of inquiry.
In one embodiment, after the step of the first human face photo of the above-mentioned shooting inquiry, including：To shooting area
Subject in domain carries out In vivo detection；If testing result is that the subject is living body, determine that first face shines
Piece is available photo.
The embodiment of the present application also provides a kind of computer readable storage medium, is stored thereon with computer program, computer
A kind of real estate information query method is realized when program is executed by processor, for the place except Immovable Property Registration center into
Row real estate information on-line checking, the method includes：The identity information of real estate information query system acquisition inquiry；Shooting
The first human face photo of the inquiry, and it is corresponding with the identity information to public security system calling according to the identity information
First put on record picture；Calculate the similarity value that first human face photo puts picture on record with described first；Described preset
Search access right corresponding with the similarity value is searched in permissions list；Export real estate letter corresponding with the search access right
Breath.
The computer program of above-mentioned computer-readable recording medium storage, the place except Immovable Property Registration center carry out
Real estate information on-line checking, inquiry need not can inquire house property information to Immovable Property Registration center, facilitate inquiry to such as
Bank, house property medium etc. handle handling when needing real estate information service.By face recognition technology, the body of inquiry is carried out
Part verifying, complete house property information can just be inquired by being only verified, and under conditions of protecting privacy, farthest be facilitated
Inquiry；If inquiry using deceptive information carry out the registration of real estate information, at this time if can not successful inquiring, and then reduce
The case where false registration, occurs.
In one embodiment, above-mentioned processor export the step of real estate information corresponding with the search access right it
Before, including：Extraction section real estate information is as real information from the real estate information；It generates close with the real information
As error message；Multiple-choice question is generated according to the real information and the error message, is selected for inquiry；If receiving institute
The answer that inquiry selects is stated as the real information, then executes the step for exporting real estate information corresponding with the search access right
Suddenly.
In one embodiment, before above-mentioned processor exports the step of real estate information corresponding with the search access right,
Including：The first age of the inquiry is judged by first human face photo, and institute is obtained by the identity information
State the second age of inquiry；Judge difference between first age and the second age whether within a preset range；If so,
Then execute the step of exporting real estate information corresponding with the search access right.
In implementing one, before the step of above-mentioned processor exports real estate information corresponding with the search access right, wrap
It includes：The first age of the inquiry is judged by first human face photo, and by described in identity information acquisition
The second age of inquiry；Judge difference between first age and the second age whether within a preset range；If so,
Execute the step of exporting real estate information corresponding with the search access right.
In one embodiment, above-mentioned processor calculates the similarity that first human face photo puts picture on record with described first
Before the step of value, including：First human face photo is input in preset ethnic identification model, determines the inquiry
Race ownership, with the real eye color of the determination inquiry；Judging the color of human eye in first human face photo is
It is no identical as the real eye color；If it is different, then the color of human eye in first human face photo is reduced into described true
Real eye color, in order to described first put on record picture carry out similarity-rough set.
In one embodiment, above-mentioned first human face photo include the first human face photo of left view, the first human face photo of right view and
Face the first human face photo, above-mentioned processor calculates the similarity value that first human face photo puts picture on record with described first
Step includes：By first human face photo of left view, it is described it is right depending on the first human face photo with first human face photo point faced
Compared with picture of not putting on record with described first carries out picture like degree, corresponding first human face photo of left view, right view first are respectively obtained
Human face photo and three groups of sub- similarity values for facing the first human face photo；The three groups of sub- similarity values that will acquire are according to preset
Weighted average rule calculates, and the similarity value that first human face photo puts picture on record with described first is calculated.
In one embodiment, after above-mentioned processor exports the step of real estate information corresponding with the search access right,
Including：It collects the inquiry and inquires its praedial frequency and geographical distribution；According to the frequency and the geographical distribution, in advance
Survey the real estate sales/purchase behavior of the inquiry.
In one embodiment, after above-mentioned processor shoots the step of the first human face photo of the inquiry, including：It is right
Subject in shooting area carries out In vivo detection；If testing result is that the subject is living body, described first is determined
Human face photo is available photo.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can store and a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
Any reference used in provided herein and embodiment to memory, storage, database or other media,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, mono- diversified forms of RAM can obtain,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double speed are according to rate SDRAM (SSRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, device, article or the method that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, device, article or method institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, device of element, article or method.
The foregoing is merely preferred embodiment of the present application, are not intended to limit the scope of the patents of the application, all utilizations
Equivalent structure or equivalent flow shift made by present specification and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, similarly include in the scope of patent protection of the application.
Claims (10)
1. a kind of real estate information query method, which is characterized in that carried out not for the place except Immovable Property Registration center
Movable property information on-line checking, the method includes：
Obtain the identity information of inquiry；
The first human face photo of the inquiry is shot, and is called and the identity according to the identity information to public security system
Information corresponding first is put on record picture；
Calculate the similarity value that first human face photo puts picture on record with described first；
Search access right corresponding with the similarity value is searched in the preset permissions list；
Export real estate information corresponding with the search access right.
2. real estate information query method according to claim 1, which is characterized in that the output and the search access right
Before the step of corresponding real estate information, including：
Extraction section real estate information is as real information from the real estate information；
It generates and the approximate error message of the real information；
Multiple-choice question is generated according to the real information and the error message, is selected for inquiry；
If receiving the answer that the inquiry selects as the real information, it is corresponding with the search access right to execute output
The step of real estate information.
3. real estate information query method according to claim 1, which is characterized in that the output and the search access right
Before the step of corresponding real estate information, including：
The first age of the inquiry is judged by first human face photo, and by described in identity information acquisition
The second age of inquiry；
Judge difference between first age and the second age whether within a preset range；
If so, executing the step of exporting real estate information corresponding with the search access right.
4. real estate information query method according to claim 1, which is characterized in that described to calculate the first face photograph
Piece with described first put on record picture similarity value the step of before, including：
First human face photo is input in preset ethnic identification model, determines race's ownership of the inquiry, with
Determine the real eye color of the inquiry；
Judge whether the color of human eye in first human face photo is identical as the real eye color；
If it is different, the color of human eye in first human face photo is then reduced into the real eye color, in order to institute
State first put on record picture carry out similarity-rough set.
5. real estate information query method according to claim 1, which is characterized in that first human face photo includes a left side
Depending on the first human face photo, right depending on the first human face photo and face the first human face photo；It is described calculate first human face photo with
Described first put on record picture similarity value the step of include：
By first human face photo of left view, it is described it is right depending on the first human face photo and it is described face the first human face photo respectively with institute
It states first and puts picture progress on record as comparing like degree, respectively obtain corresponding first human face photo of left view, the first face of right view shines
Piece and three groups of sub- similarity values for facing the first human face photo；
The three groups of sub- similarity values that will acquire are calculated according to preset weighted average rule, obtain first human face photo with
Described first similarity value for putting picture on record.
6. real estate information query method according to claim 1, which is characterized in that the method also includes：
It collects the inquiry and inquires its praedial frequency and geographical distribution；
According to the frequency and the geographical distribution, the real estate sales/purchase behavior of the inquiry is predicted.
7. real estate information query method according to claim 1, which is characterized in that the of the shooting inquiry
After the step of one human face photo, including：
In vivo detection is carried out to the subject in shooting area；
If testing result is that the subject is living body, determine that first human face photo is available photo.
8. a kind of real estate information query device, which is characterized in that carried out not for the place except Immovable Property Registration center
Movable property information on-line checking, described device include：
Acquiring unit obtains the identity information of inquiry for real estate information query system；
Call unit is shot, for shooting the first human face photo of the inquiry, and according to the identity information to public security
System calls corresponding with the identity information first to put on record picture；
Computing unit, the similarity value for putting picture on record with described first for calculating first human face photo；
Searching unit, for searching search access right corresponding with the similarity value in the preset permissions list；
Output unit, for exporting real estate information corresponding with the search access right.
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 7 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 7 is realized when being executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810422089.9A CN108846015A (en) | 2018-05-04 | 2018-05-04 | Real estate information query method, device, computer equipment and storage medium |
| PCT/CN2018/095387 WO2019210575A1 (en) | 2018-05-04 | 2018-07-12 | Real estate information enquiry method and apparatus, and computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810422089.9A CN108846015A (en) | 2018-05-04 | 2018-05-04 | Real estate information query method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108846015A true CN108846015A (en) | 2018-11-20 |
Family
ID=64212802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810422089.9A Pending CN108846015A (en) | 2018-05-04 | 2018-05-04 | Real estate information query method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108846015A (en) |
| WO (1) | WO2019210575A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636318A (en) * | 2018-11-23 | 2019-04-16 | 南宁市国土测绘地理信息中心 | A kind of method of Immovable Property Registration system and Immovable Property Registration |
| CN109656962A (en) * | 2018-12-12 | 2019-04-19 | 南宁市国土测绘地理信息中心 | A kind of real estate network administration of justice check and control platform |
| CN111611418A (en) * | 2019-02-25 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Data storage method and data query method |
| CN112667718A (en) * | 2020-12-24 | 2021-04-16 | 广西中科曙光云计算有限公司 | Real estate information sharing query method and system |
| TWI739372B (en) * | 2020-04-07 | 2021-09-11 | 中華誠信資產管理顧問股份有限公司 | Real estate comparative price geographic information evaluation method and system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111383032B (en) * | 2020-02-12 | 2023-11-14 | 北京城市网邻信息技术有限公司 | Method and device for detecting authenticity of house source information |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203294A (en) * | 2016-06-30 | 2016-12-07 | 广东微模式软件股份有限公司 | The testimony of a witness unification auth method analyzed based on face character |
| CN106981140A (en) * | 2017-03-30 | 2017-07-25 | 广东微模式软件股份有限公司 | A kind of phonecard Self-Service integrated apparatus and its method |
| CN107301551A (en) * | 2017-07-15 | 2017-10-27 | 刘兴丹 | Method, device, the system searched for, inquire about, verified before a kind of network payment |
| CN107315782A (en) * | 2017-06-08 | 2017-11-03 | 北京奇艺世纪科技有限公司 | A kind of data query method and device |
| CN107680294A (en) * | 2017-09-11 | 2018-02-09 | 平安科技（深圳）有限公司 | House property information querying method, system, terminal device and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1779704A (en) * | 2004-11-18 | 2006-05-31 | 黄金富 | Credit data inquiry system and method |
| US9032490B1 (en) * | 2012-09-12 | 2015-05-12 | Emc Corporation | Techniques for authenticating a user with heightened security |
-
2018
- 2018-05-04 CN CN201810422089.9A patent/CN108846015A/en active Pending
- 2018-07-12 WO PCT/CN2018/095387 patent/WO2019210575A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203294A (en) * | 2016-06-30 | 2016-12-07 | 广东微模式软件股份有限公司 | The testimony of a witness unification auth method analyzed based on face character |
| CN106981140A (en) * | 2017-03-30 | 2017-07-25 | 广东微模式软件股份有限公司 | A kind of phonecard Self-Service integrated apparatus and its method |
| CN107315782A (en) * | 2017-06-08 | 2017-11-03 | 北京奇艺世纪科技有限公司 | A kind of data query method and device |
| CN107301551A (en) * | 2017-07-15 | 2017-10-27 | 刘兴丹 | Method, device, the system searched for, inquire about, verified before a kind of network payment |
| CN107680294A (en) * | 2017-09-11 | 2018-02-09 | 平安科技（深圳）有限公司 | House property information querying method, system, terminal device and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636318A (en) * | 2018-11-23 | 2019-04-16 | 南宁市国土测绘地理信息中心 | A kind of method of Immovable Property Registration system and Immovable Property Registration |
| CN109656962A (en) * | 2018-12-12 | 2019-04-19 | 南宁市国土测绘地理信息中心 | A kind of real estate network administration of justice check and control platform |
| CN111611418A (en) * | 2019-02-25 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Data storage method and data query method |
| TWI739372B (en) * | 2020-04-07 | 2021-09-11 | 中華誠信資產管理顧問股份有限公司 | Real estate comparative price geographic information evaluation method and system |
| CN112667718A (en) * | 2020-12-24 | 2021-04-16 | 广西中科曙光云计算有限公司 | Real estate information sharing query method and system |
| CN112667718B (en) * | 2020-12-24 | 2021-07-16 | 广西中科曙光云计算有限公司 | Real estate information sharing query method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019210575A1 (en) | 2019-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108846015A (en) | Real estate information query method, device, computer equipment and storage medium | |
| Buolamwini | Gender shades: intersectional phenotypic and demographic evaluation of face datasets and gender classifiers | |
| CN109636318B (en) | Real estate registration system and real estate registration method | |
| CN109377189B (en) | Real estate electronic ticket system | |
| CN107025397B (en) | Identity information acquisition method and device | |
| CN109872233A (en) | Contract signing method, apparatus, computer equipment and storage medium | |
| EP3076348A1 (en) | System and method for candidate profile screening | |
| CN109816200A (en) | Task method for pushing, device, computer equipment and storage medium | |
| CN110503099B (en) | Information identification method based on deep learning and related equipment | |
| WO2019200737A1 (en) | Real estate data uploading method and apparatus, computer device, and storage medium | |
| CN110392041A (en) | Electronic authorization method, apparatus, storage equipment and storage medium | |
| CN111125290B (en) | Intelligent river patrol method and device based on river growth system and storage medium | |
| US20210224588A1 (en) | Recruitment process graph based unsupervised anomaly detection | |
| CN113591603A (en) | Certificate verification method and device, electronic equipment and storage medium | |
| CN110807630B (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
| CN110351268B (en) | Digital law enforcement system for smart city | |
| KR20220058290A (en) | Method and apparatus for collecting real-state information | |
| CN116186543B (en) | Financial data processing system and method based on image recognition | |
| CN111091354A (en) | Real estate information processing system based on big data | |
| Pawade et al. | Blockchain based secure traffic police assistant system | |
| CN112380582B (en) | Garbage throwing recording method and device based on block chain and computer equipment | |
| CN110147998A (en) | Client's networking processing method, device, computer equipment and storage medium | |
| CN112053051A (en) | Due diligence application system and information processing method thereof | |
| Kamyshanskyi et al. | Conduct of search actions in the investigation of fraud with financial resources. | |
| CN117764710B (en) | Monitoring method for housing financial risk behaviors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181120 |
|
| RJ01 | Rejection of invention patent application after publication |