CN110033284A - Source of houses verification method, apparatus, equipment and storage medium - Google Patents
Source of houses verification method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN110033284A CN110033284A CN201910188708.7A CN201910188708A CN110033284A CN 110033284 A CN110033284 A CN 110033284A CN 201910188708 A CN201910188708 A CN 201910188708A CN 110033284 A CN110033284 A CN 110033284A
- Authority
- CN
- China
- Prior art keywords
- information
- source
- real estate
- houses
- verified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012795 verification Methods 0.000 title claims abstract description 145
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000007477 logistic regression Methods 0.000 claims abstract description 30
- 239000000284 extract Substances 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 18
- 238000012552 review Methods 0.000 claims description 13
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 239000006185 dispersion Substances 0.000 description 5
- 238000011478 gradient descent method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Abstract
The present invention relates to data modeling technical fields, disclose a kind of source of houses verification method, device, equipment and storage medium, the method is through obtaining information of real estate to be verified, extract the characteristic information of the information of real estate to be verified, the characteristic information extracted is handled by source of houses Logic Regression Models, obtain logistic regression function value, compare the logistic regression function value and preset threshold, the verification result to the information of real estate to be verified is obtained according to comparison result, it can be realized the verification to the information of real estate to be verified, to reduce by the workload of manual verification's information of real estate authenticity, and improve source of houses verification efficiency.
Description
Technical field
The present invention relates to data modeling technical fields more particularly to a kind of source of houses verification method, apparatus, equipment and storage to be situated between
Matter.
Background technique
The source of houses, the authenticity for the source of houses of renting a house of buying house are to measure the important indicator of a house transaction platform source of houses superiority and inferiority, are
The authenticity of the listed source of houses is improved, at present in the industry mainly by the authenticity for the information that manually carries out renting a house by way of examining on the spot
Judgement, cause each house transaction platform in the case where reducing cost, sales force needed to handle except sales services,
The work for also needing additionally to increase verifying information of real estate authenticity, to substantially reduce working efficiency.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of source of houses verification method, apparatus, equipment and storage mediums, it is intended to solve
The technical issues of certainly how improving source of houses verification efficiency.
To achieve the above object, the present invention provides a kind of source of houses verification methods, and the source of houses verification method includes following
Step:
Obtain information of real estate to be verified；
Extract the characteristic information of the information of real estate to be verified；
The characteristic information extracted is handled by source of houses Logic Regression Models, obtains logistic regression function value；
Compare the logistic regression function value and preset threshold, is obtained according to comparison result to the information of real estate to be verified
Verification result.
Preferably, the characteristic information extracted is handled by source of houses Logic Regression Models, obtains the step of logistic regression function value
Before rapid, the source of houses verification method further include:
Obtain history information of real estate and corresponding judgement result information；
The characteristic information for extracting history information of real estate generates instruction according to the characteristic information of extraction and the judgement result information
Experienced information aggregate；
Trained Logic Regression Models are treated with information aggregate according to the training to be trained, and are obtained the source of houses logic and are returned
Return model.
Preferably, the logistic regression function value and preset threshold are obtained according to comparison result to described to be verified
After the step of verification result of information of real estate, the source of houses verification method further include:
The information of real estate to be verified for having obtained verification result is extracted, the information of real estate to be verified for obtaining extraction is corresponding artificial
Review result；
When the artificial reinspection result and inconsistent corresponding verification result, according to the artificial reinspection result and described
The characteristic information of information of real estate to be verified updates trained information aggregate.
Preferably, when the artificial reinspection result and inconsistent corresponding verification result, according to the artificial reinspection knot
The characteristic information of fruit and the information of real estate to be verified updates the step of training information aggregate, specifically includes:
When it is true that verification result, which is false and artificial reinspection result, believed according to artificial reinspection result and the source of houses to be verified
The characteristic information of breath generates trained information of real estate, and the training of the generation is added into training information collection with information of real estate
It closes；And/or
It is fictitious time when verification result is true and artificial reinspection result, is searched in trained information aggregate and described artificial multiple
Result and the corresponding trained information of real estate of the information of real estate to be verified are tested, the training information of real estate found is deleted.
Preferably, the information of real estate to be verified for having obtained verification result is extracted, the information of real estate pair to be verified of extraction is obtained
It the step of artificial reinspection result answered, specifically includes:
According to the content for each information of real estate to be verified for having obtained verification result, statistics has obtained each to be tested of verification result
Demonstrate,prove the corresponding classification of information of real estate；
Extract the information of real estate to be verified to belong to a different category；
Obtain the artificial reinspection result of the information of real estate to be verified extracted.
Preferably, each information of real estate to be verified for having obtained verification result includes source of houses location information and/or information source
Record；
According to the content for each information of real estate to be verified for having obtained verification result, statistics has obtained each to be tested of verification result
The step of demonstrate,proving information of real estate corresponding classification, specifically includes:
According to the source of houses location information for each information of real estate to be verified for having obtained verification result or information come source record, system
Meter has obtained the corresponding classification of each information of real estate to be verified of verification result.
Preferably, the step of extracting the characteristic information of the information of real estate to be verified, specifically includes:
According to the information of real estate to be verified, corresponding verifying reference information is searched；
Compare the information of real estate to be verified and the verifying reference information found；
When the information of real estate to be verified is consistent with the verifying reference information found, the room to be verified is extracted
The characteristic information of source information.
In addition, to achieve the above object, the present invention also proposes a kind of source of houses verification device, comprising:
Module is obtained, for obtaining information of real estate to be verified；
Extraction module, for extracting the characteristic information of the information of real estate to be verified；
The module that obtains is also used to handle the characteristic information extracted by source of houses Logic Regression Models, obtains logistic regression
Functional value；
Comparison module, the logistic regression function value and preset threshold are obtained according to comparison result to described to be tested
Demonstrate,prove the verification result of information of real estate.
In addition, to achieve the above object, the present invention also proposes a kind of source of houses verification equipment, the source of houses verification equipment packet
It includes: memory, processor and the source of houses verification program that is stored on the memory and can run on the processor, it is described
Source of houses verification program is arranged for carrying out the step of source of houses verification method as described above.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, the source of houses is stored on the storage medium
The step of verification program, the source of houses verification program realizes source of houses verification method as described above when being executed by processor.
In technical solution of the present invention, information of real estate to be verified is obtained, the feature of the information of real estate to be verified is extracted
Information handles the characteristic information extracted by source of houses Logic Regression Models, to obtain logistic regression function value, the logic
Regression function value and preset threshold obtain the verification result to the information of real estate to be verified according to comparison result, can be realized
To the verification of the information of real estate to be verified, to reduce by the workload of manual verification's information of real estate authenticity, and improve
Source of houses verification efficiency.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the source of houses verification equipment for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is the flow diagram of source of houses verification method first embodiment of the present invention；
Fig. 3 is the flow diagram of source of houses verification method second embodiment of the present invention；
Fig. 4 is the flow diagram of source of houses verification method 3rd embodiment of the present invention；
Fig. 5 is the flow diagram of source of houses verification method fourth embodiment of the present invention；
Fig. 6 is the flow diagram of the 5th embodiment of source of houses verification method of the present invention；
Fig. 7 is the flow diagram of source of houses verification method sixth embodiment of the present invention；
Fig. 8 is the structural block diagram of the first embodiment of source of houses verification device of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the source of houses verification device structure signal for the hardware running environment that the embodiment of the present invention is related to
Figure.
As shown in Figure 1, the source of houses verification equipment may include: processor 1001, such as central processing unit (Central
Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005.Wherein,
Communication bus 1002 is for realizing the connection communication between these components.User interface 1003 may include display screen
(Display), input unit such as keyboard (Keyboard), optional user interface 1003 can also include that the wired of standard connects
Mouth, wireless interface.Network interface 1004 optionally may include standard wireline interface and wireless interface (such as Wireless Fidelity
(WIreless-FIdelity, WI-FI) interface).Memory 1005 can be the random access memory (Random of high speed
Access Memory, RAM), it is also possible to stable nonvolatile memory (Non-Volatile Memory, NVM), such as
Magnetic disk storage.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
It will be understood by those skilled in the art that structure shown in Fig. 1 does not constitute the restriction to source of houses verification equipment, it can
To include perhaps combining certain components or different component layouts than illustrating more or fewer components.
As shown in Figure 1, as may include operating system, data storage mould in a kind of memory 1005 of storage medium
Block, network communication module, Subscriber Interface Module SIM and source of houses verification program.
In source of houses verification equipment shown in Fig. 1, network interface 1004 is mainly used for logical with network server progress data
Letter；User interface 1003 is mainly used for carrying out data interaction with user；Processor 1001 in source of houses verification equipment of the present invention is deposited
Reservoir 1005 can be set in source of houses verification equipment, and the source of houses verification equipment calls memory 1005 by processor 1001
The source of houses verification program of middle storage, and execute source of houses verification method provided in an embodiment of the present invention.
It is source of houses verification method of the present invention the referring to Fig. 2, Fig. 2 the embodiment of the invention provides a kind of source of houses verification method
The flow diagram of one embodiment.
In the present embodiment, the source of houses verification method the following steps are included:
Step S100: information of real estate to be verified is obtained；
It should be noted that the information of real estate to be verified, refers to and is issued out by house property owner etc. or intended publication
Information of real estate out, house transaction platform are needed to carry out verification to information of real estate to be verified, could be improved on house transaction platform
The authenticity of information of real estate.
Step S200: the characteristic information of the information of real estate to be verified is extracted；
It should be noted that the characteristic information of the information of real estate to be verified can specifically include house-owner's information, source of houses valence
Lattice information, source of houses location information, Financial Information and insurance information etc..The Financial Information can working as financial institution's record
The credit information etc. of the preceding source of houses, the insurance information are the insurance information etc. of the current source of houses of insurance institution's record.The spy of extraction
Reference ceases the form for being specifically as follows multi-C vector, is brought into source of houses Logic Regression Models with facilitating, and carries out logistic regression function
The calculating of value.
In the concrete realization, characteristic information can be extracted to all informations of real estate to be verified of acquisition, it can also be only
In the case where being difficult to judge that information of real estate to be verified is true and false with the method routinely compared, characteristic information is extracted, and further lead to
It crosses Logic Regression Models and carries out verification.
Step S300: the characteristic information extracted is handled by source of houses Logic Regression Models, obtains logistic regression function value；
It should be noted that the Logic Regression Models refer to a kind of discrete back-and-forth method model, it can be used for the statistics of data
Proof analysis can generate logistic regression function value, the logistic regression letter of generation according to characteristic information by Logic Regression Models
Numerical value can be used in verifying the true and false of information of real estate to be verified.Typically, logistic regression function value can pass through formula p (y
=1 | x)=1/ (1+exp (- θTX) it) is calculated, wherein θ expression logistic regression parameter, y presentation class data (such as: when
When information is true, y takes 1；When information is-fictitious time, 0) y is taken, x indicates characteristic information.
It will be appreciated that the information of real estate amount due to house transaction platform is very big, generally can not to all informations of real estate into
Row manual verification, also, during carrying out source of houses verification, it often encounters due to a lack of information source, and can not find can
The case where reliable reference information (such as: official announce information) for verification, for the above two aspects reason, the present embodiment
In, the verification of the judgement of the logic-based as obtained from Logic Regression Models is as a result, true and false to the source of houses carry out having reference value
Judgement.The characteristic information may be numerical value, such as: the numerical value of House Property Area Surveying, characteristic information may also be text, such as " XX
Cell ", for convenience of utilize Logic Regression Models calculating logic regression function value, in calculating process, can to characteristic information into
Line number value.Concrete mode of the present invention for characteristic information numerical value to be turned to x with no restriction, in the concrete realization, can incite somebody to action
Characteristic information is as character string, according to ASCII (American Standard Code for Information
Interchange, ASCII) the code table of comparisons, number successively is converted by each character in characteristic information, to realize to feature
The numeralization of information can also search preset numerical tabular according to characteristic information, by searching for Numerical Implementation to characteristic information
Numeralization.Further, it is also possible to first classify to characteristic information, realized by the modes such as table look-up to characteristic information further according to classification
Numeralization.
Step S400: the logistic regression function value and preset threshold are obtained according to comparison result to described to be tested
Demonstrate,prove the verification result of information of real estate.
It should be noted that typically, preset threshold is set as 0.5, in the present embodiment, when comparison result is described patrols
When collecting regression function value not less than 0.5, then the verification result of the information of real estate to be verified is true, that is, according to verification result,
The information of real estate to be verified is true information of real estate；When comparison result be the logistic regression function value less than 0.5 when, then it is described
The verification result of information of real estate to be verified is false, that is, the information of real estate to be verified is non-genuine source of houses letter according to verification result
Breath.
It in the concrete realization, can be further to verifying after obtaining to the verification result of the information of real estate to be verified
It is put in storage for true information of real estate, for user query.
In the present embodiment, information of real estate to be verified is obtained, the characteristic information of the information of real estate to be verified is extracted, passes through
The characteristic information that the processing of source of houses Logic Regression Models is extracted, to obtain logistic regression function value, the logistic regression function
Value and preset threshold are obtained according to comparison result to the verification result of the information of real estate to be verified, can be realized to it is described to
The verification for verifying information of real estate, to reduce by the workload of manual verification's information of real estate authenticity, and improves the source of houses and tests
True efficiency.
With reference to Fig. 3, Fig. 3 is the flow diagram of source of houses verification method second embodiment of the present invention.
Based on above-mentioned first embodiment, before the step S300, the source of houses verification method further includes following steps:
Step S210: history information of real estate and corresponding judgement result information are obtained；
It should be noted that the history information of real estate refers to, what is obtained in history is able to confirm that the information true and false ground source of houses
Information, it is described to determine that result information is the true and false information of history information of real estate.In the concrete realization, the history information of real estate
And corresponding judgement result information, it can be obtained by collecting in history by the result that manual verification obtains.
Step S220: the characteristic information of history information of real estate is extracted, according to the characteristic information of extraction and the judgement result
Information generates trained information aggregate；
It should be noted that training information aggregate is the data set of the Logic Regression Models to be trained for training
It closes.Specifically, the trained information aggregate can be by multiple characteristic informations and multiple corresponding judgement result information groups
At, specifically, training can be expressed as x={ x1, x2 ..., xm } with the characteristic information in information aggregate, and by trained letter
Judgement result information in breath set is expressed as y={ y1, y2 ..., ym }, according to x and y, logic can be obtained by calculation and return
Return the logistic regression parameter θ in model, to realize the building to Logic Regression Models.Specifically, training information collection
Conjunction can be preset with user interface, can receive the inquiry instruction of user by preset user interface, to extract trained use
Corresponding data in information aggregate, and then realize the service externally exported.
In the concrete realization, history source of houses data can be screened, extracts the history information of real estate that screening obtains
Characteristic information, and trained information aggregate is generated according to the characteristic information of extraction and the judgement result information.It in this way can be
While reducing the calculation amount for obtaining the process of source of houses Logic Regression Models, the accurate of the source of houses Logic Regression Models of acquisition is improved
Degree.For example, history source of houses data can be screened according to the acquisition time section of history source of houses data, it can also basis
The corresponding source of houses location information of history source of houses data screens history source of houses data, so that extracting history source of houses data
Characteristic information it is representative, thus realize reduce obtain source of houses Logic Regression Models process calculation amount while,
Improve the accuracy of the source of houses Logic Regression Models obtained.
Step S230: trained Logic Regression Models are treated with information aggregate according to the training and are trained, described in acquisition
Source of houses Logic Regression Models.
In the concrete realization, it can be solved by the methods of Newton method, gradient descent method and obtain source of houses Logic Regression Models.
It is illustrated by taking gradient descent method as an example in the present embodiment, solves to obtain the mistake of source of houses Logic Regression Models using gradient descent method
Journey is as follows:
According to probability theory, for single sample, posterior probability are as follows:
P (y | x, θ)=(hθ(x))y(1-hθ(x))1-y, wherein y=1 (or 0),
So available maximum likelihood function are as follows:
Log likelihood are as follows:
θ, i.e. θ are calculated below by way of gradient descent method*=argmin (l (θ)), to realize the structure to Logic Regression Models
It builds, the calculating process of gradient descent method is as follows:
Pass through iteration θ to convergence: θ in this wayj:=θj+α(y(i)-hθ(x(i)))xj (i), wherein α indicates learning rate,
x(i)Indicate ith feature data, hθ(x(i)) indicating the Logic Regression Models established, y presentation class data, θ indicates that logic is returned
Return parameter, thus by logistic regression parameter θ, can establish the default source of houses Logic Regression Models is p (y=1 | x)=1/
(1+exp(-θTx))。
In the present embodiment, trained information aggregate is generated according to the characteristic information of extraction and the judgement result information, and
Trained Logic Regression Models are treated with information aggregate according to training to be trained, and source of houses Logic Regression Models are obtained, conducive to ensuring
The accuracy of source of houses Logic Regression Models.
With reference to Fig. 4, Fig. 4 is the flow diagram of source of houses verification method 3rd embodiment of the present invention.
Based on above-mentioned first embodiment, after the step S400, the source of houses verification method further includes following steps:
Step S500: the information of real estate to be verified for having obtained verification result is extracted, the information of real estate to be verified of extraction is obtained
Corresponding artificial reinspection result；
It should be noted that the artificial reinspection result refers to, by modes such as artificial on-site inspections to the source of houses to be verified
Information is verified, and obtained result.Due to manually reviewing for by being accomplished manually, therefore in this step, it is only necessary to artificial
It reviews result to be obtained, specifically, can realize and artificial result of reviewing is obtained by by the modes such as being manually entered
?.In the concrete realization, artificial review can be by by manually carrying out core to each content in information of real estate to be verified one by one
It, specifically can be by inquiring official's data to realizing, the modes such as on-the-spot investigation, measurement realize verification.No matter it will be appreciated that
The verification result obtained in step S400 is true or false, and the artificial reinspection result may be true, it is also possible to be false.The present invention
For extracting the concrete mode of information of real estate to be verified with no restriction, specifically, can by the way of extracting in proportion, than
Such as: extracting 3% in the information of real estate to be verified for having obtained verification result, manually reviewed.
It will be appreciated that the present embodiment is conducive to improve the source of houses by the way that artificial the step of reviewing is arranged after step S400
The correctness of verification.Since typically, the quantity of information of real estate to be verified is more, it is difficult to manual verification is carried out one by one, therefore originally
Embodiment only reviews the information of real estate to be verified of extraction, is conducive to reduce cost of labor.
Step S600: when the artificial reinspection result and inconsistent corresponding verification result, according to the artificial reinspection
As a result trained information aggregate is updated with the characteristic information of the information of real estate to be verified.
It should be noted that manually review result with corresponding verification result is inconsistent specifically refers to the following two kinds situation:
Verification result is false and artificial to review result be true or verification result be true and artificial reinspection result is false.Further, when
When the artificial reinspection result and inconsistent corresponding verification result, after step S600, updated training can use
With information aggregate, the source of houses Logic Regression Models are regenerated, with the process that iterates in this way, realizes and the source of houses is returned
Return continuing to optimize for model.In the concrete realization, it is assumed that before step S300, the source of houses verification method further includes step
S210, step S220 and step S230 may return at step S230 after the step S600, to realize to the source of houses
Logic Regression Models carry out re -training.
In the concrete realization, it is realized due to manually reviewing generally by modes such as artificial on-the-spot investigations, it is with higher
Reliability, therefore when the artificial reinspection result and inconsistent corresponding verification result, result will can be manually reviewed as most
The true result of final acceptance inspection is supplied to the user for needing to inquire the source of houses.
In the present embodiment, by the way that artificial the step of reviewing is arranged, conducive to the correctness for improving source of houses verification.Due to usual
Speech, the quantity of information of real estate to be verified are more, it is difficult to carry out manual verification one by one, therefore the present embodiment is only to the room to be verified of extraction
Source information is reviewed, and is conducive to reduce cost of labor.Also, in the present embodiment, by according to the artificial reinspection result and institute
The characteristic information for stating information of real estate to be verified updates trained information aggregate, is conducive to carry out source of houses Logic Regression Models further
Optimization.
With reference to Fig. 5, Fig. 5 is the flow diagram of source of houses verification method fourth embodiment of the present invention.
Based on above-mentioned 3rd embodiment, the step S600 be can specifically include:
Step S610: when verification result be it is false and it is artificial to review result be true when, according to it is artificial review result and it is described to
The characteristic information for verifying information of real estate generates trained information of real estate, and the training of the generation is added into training with information of real estate
Use information aggregate；
It should be noted that the training is used with can store trained information of real estate, the training in information aggregate
Information of real estate can specifically include the information of real estate and classification data according to types such as history informations of real estate, utilize packet in this way
Include the training information aggregate of trained information of real estate, available source of houses Logic Regression Models.
It should be noted that the judging result of Logic Regression Models with for train the Logic Regression Models data from
The degree of dissipating is closely related.According to the difference of the specific source of houses Logic Regression Models of use, the dispersion degree of data is higher, usually
It will lead to information of real estate to be verified to be easier to be judged to very, for more special source of houses Logic Regression Models, data
Dispersion degree is higher, it is also possible to will lead to information of real estate to be verified and be easier to be judged to very.With regard to common source of houses logistic regression mould
For type, the dispersion degree of the data of training source of houses Logic Regression Models is higher, easier to be judged to information of real estate to be verified very,
And train the dispersion degree of the data of source of houses Logic Regression Models lower, it is easier that information of real estate to be verified is judged to vacation, this reality
Applying example is for above-mentioned common source of houses Logic Regression Models.
In this way, when verification result be it is false and it is artificial to review result be true when, added into trained information aggregate basis to
The training information of real estate that information of real estate generates is verified, usually can be conducive to improve the discrete of data in trained information aggregate
Degree uses source of houses Logic Regression Models to be conducive to reduce, and is false probability by information of real estate to be verified misjudgement.
Step S620: being fictitious time when verification result is true and artificial reinspection result, in trained information aggregate search with
The artificial reinspection result and the corresponding trained information of real estate of the information of real estate to be verified, delete the training room found
Source information.
It will be appreciated that be fictitious time when verification result is true and artificial reinspection result, it will be in trained information aggregate
Training corresponding with the artificial reinspection result and the information of real estate to be verified is deleted with information of real estate, can be realized in this way by
More discrete training is removed from training in information aggregate with information of real estate, to be conducive to reduce number in trained information aggregate
According to dispersion, and then be conducive to reduce and use source of houses Logic Regression Models, and information of real estate to be verified is misjudged as genuine probability.
It is worth noting that, can be realized the increase of trained information of real estate by step S610 in the present embodiment, passing through
Step S620 can be realized the reduction of trained information of real estate, and the two collective effect is conducive to realize trained information of real estate in number
Balance in amount.
In the present embodiment, when it is true that verification result, which is false and artificial reinspection result, added to training in information aggregate
According to the training information of real estate that information of real estate to be verified generates, it is conducive to reduce through source of houses Logic Regression Models, it will be to be verified
Information of real estate misjudgement is false probability.It is fictitious time when verification result is true and artificial reinspection result, it will be in trained information aggregate
In training corresponding with the artificial reinspection result and the information of real estate to be verified deleted with information of real estate, be conducive to reduce logical
Source of houses Logic Regression Models are crossed, information of real estate to be verified is misjudged as genuine probability.
With reference to Fig. 6, Fig. 6 is the flow diagram of the 5th embodiment of source of houses verification method of the present invention.
Based on above-mentioned 3rd embodiment, the step S500 be can specifically include:
Step S510: according to the content for each information of real estate to be verified for having obtained verification result, statistics has obtained verifying knot
The corresponding classification of each information of real estate to be verified of fruit；
In the concrete realization, obtained verification result each information of real estate to be verified may include source of houses location information and/
Or information carrys out source record.This step can specifically include: according to the source of houses for each information of real estate to be verified for having obtained verification result
Location information or information carry out source record, and statistics has obtained the corresponding classification of each information of real estate to be verified of verification result.
Step S520: the information of real estate to be verified to belong to a different category is extracted；
It should be noted that the purpose for extracting information of real estate to be verified is to review for artificial in this step.It is intelligible
It is, in the present embodiment, by being extracted to different classes of information of real estate to be verified, so that the information of real estate to be verified extracted
It is representative, so as to reduce it is artificial review workload while, conducive to the accuracy for improving source of houses verification.
Step S530: the artificial reinspection result of the information of real estate to be verified of extraction is obtained.
In the concrete realization, manually reviewing result can realize and obtain to be inputted by reinspection personnel through text.Really
So, it can also be clicked by mouse, the modes such as speech recognition, enable manually to review result and be acquired.
In the present embodiment, by being extracted to information of real estate category to be verified, so that the information of real estate to be verified tool extracted
It is representative, it can be while reducing artificial reinspection workload, conducive to the accuracy for improving source of houses verification.
With reference to Fig. 7, Fig. 7 is the flow diagram of the 5th embodiment of source of houses verification method of the present invention.
Based on above-mentioned first embodiment, the step S200 be can specifically include:
Step S210: according to the information of real estate to be verified, corresponding verifying reference information is searched；
It should be noted that the verifying reference information refers to, it can be directly as the reference information of verifying foundation.Citing
For, when information of real estate to be verified includes house-owner's information, the owner of house address can be inquired by housing bureau, will be looked into
The owner arrived is as verifying reference information；When information of real estate to be verified includes source of houses location information and home price information,
The home price information on periphery, and being averaged the home price information on the periphery found can be searched according to source of houses location information
Value is as verifying reference information；It, can be from the corresponding verifying reference of financial institution when information of real estate to be verified includes Financial Information
Information；When information of real estate to be verified includes insurance information, corresponding verifying reference information can be obtained from insurance institution.
Step S220: the information of real estate to be verified and the verifying reference information found；
It should be noted that in this step can by information of real estate to be verified partial content and verifying reference information into
Row compares, and the full content in information of real estate to be verified can also be compared with verifying reference information, can find
Verifying reference information subject to.
Step S230: when the information of real estate to be verified is consistent with the verifying reference information found, institute is extracted
State the characteristic information of information of real estate to be verified.
It will be appreciated that when the information of real estate to be verified and the inconsistent verifying reference information that finds, it can
It is false to directly determine verification result.For example, it when house-owner's information in information of real estate to be verified, is inquired with by housing bureau
When the owner of house address is inconsistent, so that it may determine that verification result is false.
In the concrete realization, when the information of real estate to be verified is consistent with the verifying reference information found, Ke Yi
Merely according to verifying reference information can not judge information of real estate to be verified it is true and false when, then extract the information of real estate to be verified
Characteristic information, and information of real estate to be verified is verified by source of houses Logic Regression Models, it in this way can be to avoid to all
Information of real estate to be verified passes through source of houses Logic Regression Models and is verified, and verifies to reduce to information of real estate to be verified
Calculation amount.
In the present embodiment, by the information of real estate to be verified and the verifying reference information unanimous circumstances found
Under, the characteristic information of the information of real estate to be verified is extracted, can pass through the source of houses to avoid to all informations of real estate to be verified
Logic Regression Models are verified, to reduce the calculation amount verified to information of real estate to be verified.
In addition, the embodiment of the present invention also proposes a kind of storage medium, source of houses verification program is stored on the storage medium,
The source of houses verification program realizes the step of source of houses verification method as described above when being executed by processor.
It is the structural block diagram of source of houses verification device first embodiment of the present invention referring to Fig. 8, Fig. 8.
As shown in figure 8, the source of houses verification device that the embodiment of the present invention proposes includes:
Module 100 is obtained, for obtaining information of real estate to be verified；
Extraction module 200, for extracting the characteristic information of the information of real estate to be verified；
The module 100 that obtains is also used to handle the characteristic information extracted by source of houses Logic Regression Models, obtains logic
Regression function value；
Comparison module 300, the logistic regression function value and preset threshold, according to comparison result obtain to it is described to
Verify the verification result of information of real estate.
The other embodiments or specific implementation of source of houses verification device of the present invention can refer to above-mentioned each method embodiment, this
Place repeats no more.
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, method, article or the system 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, method, article or system 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, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as read-only memory/random access memory, magnetic disk, CD), including some instructions are used so that a terminal device (can
To be mobile phone, computer, server, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of source of houses verification method, which is characterized in that the source of houses verification method the following steps are included:
Obtain information of real estate to be verified；
Extract the characteristic information of the information of real estate to be verified；
The characteristic information extracted is handled by source of houses Logic Regression Models, obtains logistic regression function value；
Compare the logistic regression function value and preset threshold, the information of real estate to be verified is tested according to comparison result acquisition
Demonstrate,prove result.
2. source of houses verification method as described in claim 1, which is characterized in that handle extraction by source of houses Logic Regression Models
Before the step of characteristic information, acquisition logistic regression function value, the source of houses verification method further include:
Obtain history information of real estate and corresponding judgement result information；
The characteristic information for extracting history information of real estate generates training according to the characteristic information of extraction and the judgement result information and uses
Information aggregate；
Trained Logic Regression Models are treated with information aggregate according to the training to be trained, and obtain the source of houses logistic regression mould
Type.
3. source of houses verification method as described in claim 1, which is characterized in that the logistic regression function value and default threshold
After the step of being worth, obtaining the verification result to the information of real estate to be verified according to comparison result, the source of houses verification method
Further include:
The information of real estate to be verified for having obtained verification result is extracted, the corresponding artificial reinspection of information of real estate to be verified of extraction is obtained
As a result；
When the artificial reinspection result and inconsistent corresponding verification result, according to the artificial reinspection result and described to be tested
The characteristic information for demonstrate,proving information of real estate updates trained information aggregate.
4. source of houses verification method as claimed in claim 3, which is characterized in that when the artificial reinspection result and corresponding verifying
As a result when inconsistent, trained information is updated according to the characteristic information of the artificial reinspection result and the information of real estate to be verified
The step of set, specifically includes:
When verification result be it is false and it is artificial to review result be true when, according to artificial result and the information of real estate to be verified reviewed
Characteristic information generates trained information of real estate, and the training of the generation is added into trained information aggregate with information of real estate；With/
Or,
It is fictitious time when verification result is true and artificial reinspection result, is searched and the artificial reinspection knot in trained information aggregate
Fruit and the corresponding trained information of real estate of the information of real estate to be verified, delete the training information of real estate found.
5. source of houses verification method as claimed in claim 3, which is characterized in that extract the source of houses to be verified for having obtained verification result
Information, specifically includes the step of obtaining the information of real estate to be verified corresponding artificial reinspection result of extraction:
According to the content for each information of real estate to be verified for having obtained verification result, statistics has obtained each room to be verified of verification result
The corresponding classification of source information；
Extract the information of real estate to be verified to belong to a different category；
Obtain the artificial reinspection result of the information of real estate to be verified extracted.
6. source of houses verification method as claimed in claim 5, which is characterized in that obtained each source of houses letter to be verified of verification result
Breath includes that source of houses location information and/or information carry out source record；
According to the content for each information of real estate to be verified for having obtained verification result, statistics has obtained each room to be verified of verification result
It the step of source information corresponding classification, specifically includes:
According to the source of houses location information for each information of real estate to be verified for having obtained verification result or information come source record, statistics is
Obtain the corresponding classification of each information of real estate to be verified of verification result.
7. source of houses verification method as described in claim 1, which is characterized in that extract the feature letter of the information of real estate to be verified
The step of breath, specifically includes:
According to the information of real estate to be verified, corresponding verifying reference information is searched；
Compare the information of real estate to be verified and the verifying reference information found；
When the information of real estate to be verified is consistent with the verifying reference information found, the source of houses letter to be verified is extracted
The characteristic information of breath.
8. a kind of source of houses verification device characterized by comprising
Module is obtained, for obtaining information of real estate to be verified；
Extraction module, for extracting the characteristic information of the information of real estate to be verified；
The module that obtains is also used to handle the characteristic information extracted by source of houses Logic Regression Models, obtains logistic regression function
Value；
Comparison module, the logistic regression function value and preset threshold are obtained according to comparison result to the room to be verified
The verification result of source information.
9. a kind of source of houses verification equipment, which is characterized in that the source of houses verification equipment includes: memory, processor and is stored in
On the memory and the source of houses verification program that can run on the processor, the source of houses verification program be arranged for carrying out as
Described in any one of claims 1 to 7 the step of source of houses verification method.
10. a kind of storage medium, which is characterized in that be stored with source of houses verification program, the source of houses verification on the storage medium
The step of source of houses verification method as described in any one of claim 1 to 7 is realized when program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910188708.7A CN110033284A (en) | 2019-03-13 | 2019-03-13 | Source of houses verification method, apparatus, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910188708.7A CN110033284A (en) | 2019-03-13 | 2019-03-13 | Source of houses verification method, apparatus, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110033284A true CN110033284A (en) | 2019-07-19 |
Family
ID=67235972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910188708.7A Pending CN110033284A (en) | 2019-03-13 | 2019-03-13 | Source of houses verification method, apparatus, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110033284A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111383032A (en) * | 2020-02-12 | 2020-07-07 | 北京城市网邻信息技术有限公司 | Method and device for detecting authenticity of house source information |
| CN111798251A (en) * | 2020-07-03 | 2020-10-20 | 北京字节跳动网络技术有限公司 | Verification method and device of house source data and electronic equipment |
| CN112257734A (en) * | 2019-11-15 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
| CN113409024A (en) * | 2021-07-02 | 2021-09-17 | 深圳市云房网络科技有限公司 | Method, system and computer storage medium for automatic verifying and auditing house source |
| CN113902457A (en) * | 2021-11-19 | 2022-01-07 | 北京房江湖科技有限公司 | Method and device for evaluating reliability of house source information, electronic equipment and storage medium |
| CN115311110A (en) * | 2022-09-29 | 2022-11-08 | 深圳市明源云科技有限公司 | House source processing method and device, terminal equipment and storage medium |
| CN115712662A (en) * | 2022-11-28 | 2023-02-24 | 贝壳找房(北京)科技有限公司 | Method, system, device and medium for verifying house source information |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952190A (en) * | 2017-03-22 | 2017-07-14 | 国信优易数据有限公司 | False source of houses typing Activity recognition and early warning system |
| CN107909516A (en) * | 2017-12-06 | 2018-04-13 | 链家网（北京）科技有限公司 | A kind of problem source of houses recognition methods and system |
| CN108628863A (en) * | 2017-03-15 | 2018-10-09 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
-
2019
- 2019-03-13 CN CN201910188708.7A patent/CN110033284A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108628863A (en) * | 2017-03-15 | 2018-10-09 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN106952190A (en) * | 2017-03-22 | 2017-07-14 | 国信优易数据有限公司 | False source of houses typing Activity recognition and early warning system |
| CN107909516A (en) * | 2017-12-06 | 2018-04-13 | 链家网（北京）科技有限公司 | A kind of problem source of houses recognition methods and system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112257734A (en) * | 2019-11-15 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
| CN111383032A (en) * | 2020-02-12 | 2020-07-07 | 北京城市网邻信息技术有限公司 | Method and device for detecting authenticity of house source information |
| 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 |
| CN111798251A (en) * | 2020-07-03 | 2020-10-20 | 北京字节跳动网络技术有限公司 | Verification method and device of house source data and electronic equipment |
| CN113409024A (en) * | 2021-07-02 | 2021-09-17 | 深圳市云房网络科技有限公司 | Method, system and computer storage medium for automatic verifying and auditing house source |
| CN113902457A (en) * | 2021-11-19 | 2022-01-07 | 北京房江湖科技有限公司 | Method and device for evaluating reliability of house source information, electronic equipment and storage medium |
| CN113902457B (en) * | 2021-11-19 | 2023-01-06 | 贝壳找房(北京)科技有限公司 | Method and device for evaluating reliability of house source information, electronic equipment and storage medium |
| CN115311110A (en) * | 2022-09-29 | 2022-11-08 | 深圳市明源云科技有限公司 | House source processing method and device, terminal equipment and storage medium |
| CN115712662A (en) * | 2022-11-28 | 2023-02-24 | 贝壳找房(北京)科技有限公司 | Method, system, device and medium for verifying house source information |
| CN115712662B (en) * | 2022-11-28 | 2023-07-28 | 贝壳找房(北京)科技有限公司 | Method, system, device and medium for verifying house source information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033284A (en) | Source of houses verification method, apparatus, equipment and storage medium | |
| CN107025509B (en) | Decision making system and method based on business model | |
| CN106096657B (en) | Based on machine learning come the method and system of prediction data audit target | |
| CN110349000A (en) | Method, apparatus and electronic equipment are determined based on the volume strategy that mentions of tenant group | |
| CN112348520A (en) | XGboost-based risk assessment method and device and electronic equipment | |
| WO2021174812A1 (en) | Data cleaning method and apparatus for profile, and medium and electronic device | |
| TW201539216A (en) | Document analysis system, document analysis method and document analysis program | |
| CN110688536A (en) | Label prediction method, device, equipment and storage medium | |
| CN110909970A (en) | Credit scoring method and device | |
| CN110415103A (en) | The method, apparatus and electronic equipment that tenant group mentions volume are carried out based on variable disturbance degree index | |
| CN110349007A (en) | The method, apparatus and electronic equipment that tenant group mentions volume are carried out based on variable discrimination index | |
| CN112671985A (en) | Agent quality inspection method, device, equipment and storage medium based on deep learning | |
| CN112948823A (en) | Data leakage risk assessment method | |
| CN108228567A (en) | For extracting the method and apparatus of the abbreviation of organization | |
| CN112328869A (en) | User loan willingness prediction method and device and computer system | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN113919432A (en) | Classification model construction method, data classification method and device | |
| CN112581271B (en) | Merchant transaction risk monitoring method, device, equipment and storage medium | |
| CN110569363A (en) | Decision flow component generation method and device, electronic equipment and storage medium | |
| CN114419631A (en) | Network management virtual system based on RPA | |
| CN111553685B (en) | Method, device, electronic equipment and storage medium for determining transaction routing channel | |
| CN109102396A (en) | A kind of user credit ranking method, computer equipment and readable medium | |
| CN107093018A (en) | Communication engineering project information method for visualizing and device based on health model | |
| CN115310091A (en) | Target security level identification method and device based on fusion model and electronic equipment | |
| CN112131354B (en) | Answer screening method and device, terminal equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190719 |