CN109544410A - Cell source of houses value parameter estimation method and device - Google Patents
Cell source of houses value parameter estimation method and device Download PDFInfo
- Publication number
- CN109544410A CN109544410A CN201811290362.3A CN201811290362A CN109544410A CN 109544410 A CN109544410 A CN 109544410A CN 201811290362 A CN201811290362 A CN 201811290362A CN 109544410 A CN109544410 A CN 109544410A
- Authority
- CN
- China
- Prior art keywords
- cell
- houses
- source
- target
- index
- 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 40
- 238000013528 artificial neural network Methods 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims description 110
- 230000000153 supplemental effect Effects 0.000 claims description 44
- 238000012360 testing method Methods 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 28
- 238000003064 k means clustering Methods 0.000 claims description 10
- 241000208340 Araliaceae Species 0.000 claims description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 4
- 235000008434 ginseng Nutrition 0.000 claims description 4
- 210000004027 cell Anatomy 0.000 claims 120
- 210000005056 cell body Anatomy 0.000 claims 1
- 238000010801 machine learning Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 230000013011 mating Effects 0.000 description 3
- 210000004218 nerve net Anatomy 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0278—Product appraisal
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves machine learning and field of neural networks, for handling cell source of houses data, and in particular to a kind of cell source of houses value parameter estimation method, device, computer equipment and storage medium.Method includes: to obtain every cell index of Target cell；It is inputted default cell similarity model, obtains the cell appraisal index of Target cell；Index is evaluated according to the cell of Target cell in default cell set and searches the corresponding similar cell of Target cell；Obtain the cell source of houses average value parameter of similar cell, the source of houses average value parameter of Target cell is estimated, the source of houses average value parameter of Target cell is obtained, the appraisal parameter of the target source of houses is obtained, the assessed value parameter of the target source of houses is obtained by default half parameter quantile regression.The application does not need the valuation of appraiser without necessarily referring to the transaction data of the source of houses of house type identical as the target source of houses yet, can estimate the value parameter of the target source of houses, the result of appraisal is more objective and accurate.
Description
Technical field
This application involves field of information processing, more particularly to a kind of cell source of houses value parameter estimation method and dress
It sets.
Background technique
With the development of economy with the propulsion of urbanization, people's lives level also constantly promoted.In city, cell
Refer to based on residence building and is formed equipped with commercial network, culture and education, amusement, greening, public and communal facility etc.
Resident living area of certain scale.The main body of cell is resident's building, and a cell generally comprises several residents and lives
Room, community resident house are the focuses of present investment in property.
Tradition uses market sample appraisal method to cell house property valuation: appraiser rule of thumb selects similar to target house
Several houses of house type, then artificially judge determining for target house according to the listed price in similar house or concluded price
Valence, but since the effect of the valuation methods is determined by the experience of appraiser completely, but the data of appraiser's prospecting may be not enough
Specifically, it is contemplated that factor may be not comprehensive enough, judge whether two houses belong to similar house also without specific standard,
Determine to be not allowed so as to cause similar house, then leads to the misjudgment to target source of houses room rate.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of cell source of houses value parameter estimation method, device,
Computer equipment and storage medium.
A kind of cell source of houses value parameter estimation method, which comprises
Obtain every cell index of Target cell；
The Target cell every cell index corresponding with Target cell is inputted into default cell similarity model, is obtained
The cell of Target cell evaluates index, and the default cell similarity model is to carry the training of cell source of houses average value parameter
Cell is obtained as training data；
Index is evaluated according to the cell of Target cell in default cell set and searches the corresponding similar cell of Target cell, institute
State the cell appraisal index that default cell set includes default cell；
The cell source of houses average value parameter for obtaining the similar cell found, according to the cell of the similar cell
The source of houses average value parameter of source of houses average value parameters on target cell is estimated, the source of houses flat fare of Target cell is obtained
Value parameter；
Obtain the target source of houses each appraisal influence factor, according to the prediction average value parameter of the Target cell source of houses with
And each appraisal influence factor of the target source of houses, estimate that the value of the target source of houses is joined by presetting half parameter quantile regression
Number, the default half parameter quantile regression are based on each appraisal influence factor and the prediction average value parameter to institute
The influence for stating the value parameter of the target source of houses is established.
The every cell index for obtaining Target cell includes: in one of the embodiments,
Obtain the cell information of Target cell；
According to the cell information of the Target cell, every cell index of Target cell is obtained.
It is described by the Target cell every cell index input corresponding with Target cell in one of the embodiments,
Cell similarity model is preset, before the cell appraisal index for obtaining Target cell, further includes:
Obtain every cell index of the training cell for carrying cell source of houses average value parameter and training cell；
Classified according to every cell index of training cell to the trained cell by K-means clustering,
Obtain training cell class；
Training dataset and test data set are determined according to training cell class；
Training dataset is inputted into initial BP neural network, initial BP neural network is instructed by training dataset
Practice；
It is tested by the initial BP neural network that test data set completes training；
When test passes through, the initial BP neural network that training is completed is as default cell similarity model；
It is obstructed out-of-date when testing, the initial BP neural network is updated according to test result, it will be updated described initial
BP neural network is re-used as initial BP neural network, returns training dataset inputting initial BP neural network, pass through training
The operation that data set is trained initial BP neural network.
It is described in one of the embodiments, that index lookup phase is evaluated according to the cell of Target cell in default cell set
Like cell, before the cell source of houses average value parameter for obtaining the similar cell, further includes:
Obtain the range information of each cell and Target cell；
Default cell is determined according to the range information of each cell and the Target cell；
Obtain every cell index of the default cell；
The default cell every cell index corresponding with default cell is inputted into default cell similarity model, is obtained
Default cell set.
It is described in one of the embodiments, that index lookup mesh is evaluated according to the cell of Target cell in default cell set
The corresponding similar cell of cell is marked, the default cell set includes that the cell appraisal index of default cell specifically includes:
The cell appraisal index that cell is preset in default cell set is obtained, by the cell appraisal index of default cell in target
Default cell in the preset range of the cell appraisal index of cell is as similar cell.
The half parameter quantile regression is specifically as follows in one of the embodiments:
Y=X β+g (T)+ε
Wherein Y is target source of houses estimated price, and X is the factor for influencing the appraisal of the target source of houses, the source of houses including Target cell
Argument section in the appraisal influence factor of average price and the target source of houses, β are regression coefficient, and g (T) is in appraisal influence factor
Nonparametric part, ε are random error.
The cell source of houses average value parameter for obtaining the similar cell is specifically wrapped in one of the embodiments,
It includes:
Obtain each market average value supplemental characteristic of the similar cell source of houses；
When the market average value supplemental characteristic is greater than preset quantity threshold value, the market average value parameter is removed
Maxima and minima in data, using the average value of other market average value supplemental characteristics as the cell room of similar cell
Source average value parameter obtains each market when the market average value supplemental characteristic is less than or equal to preset quantity threshold value
The confidence level of average value supplemental characteristic, using the highest market average value supplemental characteristic of confidence level as the cell of similar cell
Source of houses average value parameter.
A kind of cell source of houses average price parameter estimation apparatus, described device include:
Cell index selection module, for obtaining every cell index of Target cell；
Index computing module is evaluated, for the Target cell every cell index input corresponding with Target cell is pre-
If cell similarity model, the cell appraisal index of Target cell is obtained, the default cell similarity model is to carry cell
The training cell of source of houses average value parameter is obtained as training data；
Similar cell search module searches target for evaluating index according to the cell of Target cell in default cell set
The corresponding similar cell of cell, the default cell set include that the cell of default cell evaluates index；
Source of houses average price computing module, for obtaining the cell source of houses average value parameter of the similar cell found,
Estimated according to the source of houses average value parameter of the cell source of houses average value parameters on target cell of the similar cell, is obtained
Obtain the source of houses average value parameter of Target cell；
One room monovalence estimation module, for obtaining each appraisal influence factor of the target source of houses, according to the Target cell room
Each appraisal influence factor of the prediction average value parameter in source and the target source of houses is by presetting half parameter quantile regression mould
Type estimates the value parameter of the target source of houses, and the default half parameter quantile regression is based on each appraisal influence factor and institute
Influence of the prediction average value parameter to the value parameter of the target source of houses is stated to establish.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Obtain every cell index of Target cell；
The Target cell every cell index corresponding with Target cell is inputted into default cell similarity model, is obtained
The cell of Target cell evaluates index, and the default cell similarity model is to carry the training of cell source of houses average value parameter
Cell is obtained as training data；
Index is evaluated according to the cell of Target cell in default cell set and searches the corresponding similar cell of Target cell, institute
State the cell appraisal index that default cell set includes default cell；
The cell source of houses average value parameter for obtaining the similar cell found, according to the cell of the similar cell
The source of houses average value parameter of source of houses average value parameters on target cell is estimated, the source of houses flat fare of Target cell is obtained
Value parameter；
Obtain the target source of houses each appraisal influence factor, according to the prediction average value parameter of the Target cell source of houses with
And each appraisal influence factor of the target source of houses, estimate that the value of the target source of houses is joined by presetting half parameter quantile regression
Number, the default half parameter quantile regression are based on each appraisal influence factor and the prediction average value parameter to institute
The influence for stating the value parameter of the target source of houses is established.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain every cell index of Target cell；
The Target cell every cell index corresponding with Target cell is inputted into default cell similarity model, is obtained
The cell of Target cell evaluates index, and the default cell similarity model is to carry the training of cell source of houses average value parameter
Cell is obtained as training data；
Index is evaluated according to the cell of Target cell in default cell set and searches the corresponding similar cell of Target cell, institute
State the cell appraisal index that default cell set includes default cell；
The cell source of houses average value parameter for obtaining the similar cell found, according to the cell of the similar cell
The source of houses average value parameter of source of houses average value parameters on target cell is estimated, the source of houses flat fare of Target cell is obtained
Value parameter；
Obtain the target source of houses each appraisal influence factor, according to the prediction average value parameter of the Target cell source of houses with
And each appraisal influence factor of the target source of houses, estimate that the value of the target source of houses is joined by presetting half parameter quantile regression
Number, the default half parameter quantile regression are based on each appraisal influence factor and the prediction average value parameter to institute
The influence for stating the value parameter of the target source of houses is established.
Above-mentioned cell source of houses value parameter estimation method, device, computer equipment and storage medium, first acquisition target
Cell and every cell index；And the every cell information for the Target cell that post analysis obtains, it is combined by cell information pre-
If cell similarity model Target cell is analyzed, obtain Target cell cell appraisal index, then according to cell
Evaluate index and search similar cell, the source of houses average price of Target cell is estimated by the source of houses average price of similar cell.Pass through
The source of houses average price of each similar cell of preset comprehensive estimates the source of houses price of Target cell, then obtains estimating for the target source of houses
Valence parameter, according to the appraisal parameter of the average value parameter of the Target cell source of houses and the target source of houses by presetting half parameter quartile
Regression model obtains the assessed value parameter of the target source of houses.The application is by default half parameter quantile regression to the target source of houses
Price estimated, without necessarily referring to the transaction data of the source of houses of house type identical as the target source of houses, do not need appraiser's yet
Valuation can estimate the value parameter of the target source of houses that the factor of consideration is specific and comprehensive, the more objective standard of the result of appraisal
Really.
Detailed description of the invention
Fig. 1 is the flow diagram of cell source of houses value parameter estimation method in one embodiment；
Fig. 2 is the flow diagram of cell source of houses value parameter estimation method in one embodiment；
Fig. 3 is the flow diagram of cell source of houses value parameter estimation method in one embodiment；
Fig. 4 is the flow diagram of cell source of houses value parameter estimation method in one embodiment；
Fig. 5 is the structural block diagram that cell source of houses value parameter estimates estimation device in one embodiment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
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.
Cell source of houses value parameter estimation method provided by the present application, estimates for the average price to the cell source of houses, tool
Body can realize that computer program can load by cell source of houses average price estimation method of the computer program to the application
In in terminal, terminal can be, but not limited to be various personal computers, laptop, smart phone, tablet computer.
As shown in Figure 1, the cell source of houses value parameter estimation method of the application in one of the embodiments, comprising:
S200 obtains every cell index of Target cell.
Target cell refers to the target of appraisal, can be estimated by average price of this method to the Target cell source of houses
Meter.Cell index specifically can with the rigid index of items of cell, can the type according to locating for index classify to index, specifically
It may include that cell location, cell information, the cell time limit, cell class, cell environment, cell safety coefficient, cell are mating etc.
Multiple types, and under each type then include every cell index, for example, including: cell location under cell location, locating for cell
Loop wire；It include: that cell amount, the total building number of cell, the total unit number of cell, cell occupied area, cell go into operation under cell information
Time, cell time of completion etc..Include: under cell class cell belong under high-grade cell/middle-grade cell/low grade cell which kind of,
Developer's scoring of the group rental room accounting, cell of cell, the scoring of the property price of cell, the property of cell etc.；Under cell environment
Including plot ratio, green percentage, added value equipment etc.；Include: security protection measure under " cell safety coefficient ", whether closes cell, is small
Area's security personnel's scoring etc.；Cell is mating to be specifically included: residential parking space saturation, whether human and vehicle shunting, water and electricity supply heating, education set
It applies, means of transportation, recreational facilities etc., wherein cell index can be indicated specifically with parametric form, such as can be to environment classification
Under cell coefficient plot ratio and green percentage be expressed as the parameters of percents, under cell safety coefficient whether closing is small
Area can indicate that 0 indicates not close cell, and 1 indicates closing cell with 0 and 1 parameter.
The every cell index for calculating the Target cell of source of houses average value is obtained first.
The Target cell every cell index corresponding with Target cell is inputted default cell similarity mould by S400
Type obtains the cell appraisal index of Target cell, and the default cell similarity model is to carry cell source of houses average value ginseng
Several training cells is obtained as training data.
Cell appraisal index specifically refers to can be used for based on what above-mentioned every cell index comprehensive was handled to defeated
Enter the index that the value parameter of cell is estimated, cell appraisal index specifically can be to above-mentioned cell location, cell information,
The scoring for all types of cell indexs such as the cell time limit, cell class, cell environment, cell safety coefficient, cell be mating, Ke Yigen
Obtain the TOP SCORES of the classification according to every cell index under the classification, such as can be with cell amount, the total building number of cell, small
The scoring of many kinds of parameters such as the total unit number of Qu, cell occupied area, cell on-stream time, cell time of completion acquisition cell information
Etc..And according to the cell of the cell index selection cell of input evaluate index work can by cell similarity model come
It realizes.Every cell index of every cell index of Target cell and default cell is inputted into cell similarity model
To determine that the cell of Target cell evaluates index by cell similarity model.Default cell similarity model refers to trained completion
Cell similarity model.Cell similarity model is specifically based on BP neural network realization in one of the embodiments,.
The Target cell every cell index input corresponding with Target cell preset after obtaining cell index small
Area's similarity model obtains the cell appraisal index of Target cell.
S600 is corresponding similar small according to the cell of Target cell appraisal index lookup Target cell in default cell set
Area, the default cell set include that the cell of default cell evaluates index
Default cell refers to the cell of several known cell source of houses average value parameters, presets in cell set comprising several
Cell similar with Target cell and several and Target cell dissmilarity cell.Each default cell is small in default cell set
Area's appraisal index obtains in advance.It searches and refers to after obtaining the cell appraisal index of Target cell, in default cell set
The every cell appraisal index of interior lookup cell similar with Target cell, and as the similar cell of Target cell.
After obtaining every appraisal index of Target cell, it can be estimated in default cell set according to the cell of Target cell
Valence index searches the corresponding similar cell of Target cell.
S800 obtains the cell source of houses average value parameter of the similar cell found, according to the similar cell
The source of houses average value parameter of cell source of houses average value parameters on target cell estimated, obtain the source of houses of Target cell
Average value parameter.
Average value parameter refers to the design parameter for describing cell source of houses average value, can by average value parameter
To embody the specific value of the cell source of houses.
After determining the similar cell of Target cell, the cell source of houses average value of the available similar cell is joined
Number, is then estimated according to the source of houses average value parameter of the cell source of houses average value parameters on target cell of similar cell
Pass through, determines the source of houses average value parameter of Target cell.
S900 obtains each appraisal influence factor of the target source of houses, according to the prediction average value parameter of the Target cell source of houses
And each appraisal influence factor of the target source of houses, estimate that the value of the target source of houses is joined by presetting half parameter quantile regression
Number presets value of the half parameter quantile regression based on each appraisal influence factor and the prediction average value parameters on target source of houses
The influence of parameter is established.
The appraisal parameter of the target source of houses specifically refer to may include building information where the target source of houses, the target source of houses room
Room position, layout structure, daylighting and area etc. factors.Half parameter quantile regression is specifically as follows:
Y=X β+g (T)+ε
Wherein Y is target source of houses estimated price, and X is the factor for influencing the appraisal of the target source of houses, the source of houses including Target cell
Argument section in the appraisal influence factor of average price and the target source of houses, β are regression coefficient, and g (T) is in appraisal influence factor
Nonparametric part, ε are random error.
Obtain the Target cell source of houses prediction average value parameter after, obtain the target source of houses each appraisal influence because
Element, and the value parameter of the target source of houses is calculated by presetting half parameter quantile regression.Compared with traditional mean regression,
Half parameter quantile regression can depict the situation under the conditions of given independent variable on each quantile of response variable comprehensively.Due to room
The mean regression of source data is unsatisfactory for the normal distribution of error term, and quantile regression is not limited by error term distribution, can be more
Accurately predict as a result, and have explanatory well, carried out so as to accurately value parameter to the target source of houses
Estimation.
In one of the embodiments, before the appraisal affecting parameters for obtaining the target source of houses, we can be according to influence
The condition of the value parameter of the target source of houses, i.e. influence of each variable to source of houses value parameter in half parameter quantile regression,
Establish half parameter quantile regression.Each variable specifically includes the second level factor under the level-one factor and the level-one factor, wherein
In one embodiment, the level-one factor specifically includes the position Lou Dong, construction quality, building capacity, building corollary equipment, house position
It sets, the Multiple factors such as layout structure, daylighting situation and floor space, and the position Lou Dong under the level-one factor includes traffic
The second levels factor such as convenience and ornamental value includes the second levels factors such as purposes, function, exterior wall and service life, building under construction quality
It include that longitudinal capacity, lateral capacity, overall carrying population, structural bearing population, structure universality, overall space are general under capacity
Adaptive and exterior space etc..Also have under building corollary equipment, house location etc. level-one factor corresponding each second level because
Son.Foundation is specifically included by the process of half parameter quantile regression: each variable is determined, then by kernel function according to above-mentioned
Each variable carrys out double of parameter quantile regression and is estimated, can be marked in one of the embodiments, by nonparametric AIC
Standard selects suitable bandwidth, then selects general gaussian kernel function, passes through double of parameter point in Local Polynomial linear approach
Position regression model is estimated, available half parameter quantile regression is obtained.
Above-mentioned cell source of houses value parameter estimation method, first acquisition Target cell and every cell index；Then divide
The every cell information for analysing the Target cell obtained combines preset cell similarity model to Target cell by cell information
It is analyzed, obtains the cell appraisal index of Target cell, index is then evaluated according to cell and searches similar cell, by similar
The source of houses average price of cell estimates the source of houses average price of Target cell.Pass through the source of houses average price pair of each similar cell of preset comprehensive
The source of houses price of Target cell is estimated, the appraisal parameter of the target source of houses is then obtained, according to being averaged for the Target cell source of houses
The appraisal parameter of value parameter and the target source of houses obtains the estimation valence of the target source of houses by default half parameter quantile regression
Value parameter.The application estimates the price of the target source of houses by default half parameter quantile regression, without necessarily referring to
The transaction data of the source of houses of the identical house type of the target source of houses, does not need the valuation of appraiser yet, can join to the value of the target source of houses
Number is estimated that the factor of consideration is specific and comprehensive, and the result of appraisal is more objective and accurate.
As shown in Fig. 2, S200 is specifically included in one of the embodiments:
S210 obtains the cell information of Target cell.
S230 obtains Target cell every cell index corresponding with default cell according to the cell information of Target cell.
Cell information refers to the specific data of items of cell, has specifically included the number of digitized data and non-digitalization
According to.The cell information of Target cell available first, then determined according to actual conditions, that is, cell information of each cell with
The corresponding every cell index of each cell.By obtaining cell information, then the cell information comprising text information is converted to
The cell index of digital representation, it is more convenient easy-to-use.
As shown in figure 3, in one of the embodiments, before S400, further includes:
S310, the every cell for obtaining the training cell for carrying cell source of houses average value parameter and training cell refer to
Mark.
S330 carries out the trained cell according to every cell index of training cell by K-means clustering
Classification obtains training cell class.
S350 determines training dataset and test data set according to training cell class.
Training dataset is inputted initial BP neural network by S370, by training dataset to initial BP neural network into
Row training.
S380 is tested by the initial BP neural network that test data set completes training,
S392, when test passes through, the initial BP neural network that training is completed is as default cell similarity model；
It is obstructed out-of-date when testing, S394 is entered step, the initial BP neural network is updated according to test result, is then returned
Return step S310.
K-means clustering is one of unsupervised learning clustering algorithm, and input is the data set of no label, output
Be each test sample in k different clusters and data set classification.Cluster is also sometimes referred to as unsupervised segmentation.It is logical
Preliminary classification can be carried out for training cell by crossing K-means clustering.BP neural network is that one kind is inversely passed according to error
The multilayer feedforward neural network for broadcasting algorithm training is current most widely used neural network.
When being trained to cell similarity model, unsupervised K-means clustering can be first passed through according to survey
Training cell is carried out preliminary classification by the every cell index for trying cell, and sorted cell is then divided into training set and is surveyed
Examination collection, is trained initial BP neural network by the data of training set, by test set to the BP nerve net after training
Network is tested, and the cell similarity model that can be used for obtaining cell appraisal index according to the cell index of input is obtained.It is logical
The training and test of crossing model can effectively improve the validity of model judgement, improve Target cell average value parameter Estimation
Validity.
As shown in figure 4, in one of the embodiments, before S600, further includes:
S520 obtains the range information of each cell and Target cell.
S540 determines default cell according to the range information of each cell and the Target cell.
S560 obtains every cell index of the default cell.
The default cell every cell index corresponding with default cell is inputted default cell similarity mould by S580
Type obtains default cell set.
Such as it can be centered on Target cell, so being selected as default cell from the cell in 1.5km in Target cell.
Range information is mainly the quantity for determining default cell, and it is default cell that cell in 1.5km is chosen when cell density is sufficiently high,
When cell density is too low, can choose be cell in 2km from Target cell range is default cell.Secondly, locating for cell
Position being affected for cell price similar cell can be carried out just first by the consistent words to positional factor
Step screening reduces and screens default number of cells, while by choosing default cell according to distance, can sufficiently improve resulting
The validity of the prediction average price of the Target cell source of houses.The cell index of each default cell is then obtained, and by default
The cell index of each default cell is converted cell appraisal index by cell similarity model, and is estimated according to the cell after conversion
Valence index generates default cell set.
Step S600 is specifically included in one of the embodiments:
The cell appraisal index that cell is preset in default cell set is obtained, by the cell appraisal index of default cell in target
Default cell in the preset range of the cell appraisal index of cell is as similar cell.
Target cell can be searched by each default cell in the default cell set of comparison and the appraisal index of Target cell
Similar cell.When the appraisal index that some presets cell all falls within every appraisal index of corresponding default cell
In preset range.This can then be preset to cell as the default cell of Target cell.By appraisal index can preset it is small
The similar cell of multiple Target cells is searched in area's collection, method is simple and fast, can be improved and calculates Target cell source of houses flat fare
The rate of value parameter.
S800 is specifically included in one of the embodiments:
Obtain each market average value supplemental characteristic of the similar cell source of houses.When market, average value supplemental characteristic is greater than
When preset quantity threshold value, the maxima and minima in market average value supplemental characteristic is removed, by other market average values
Cell source of houses average value parameter of the average value of supplemental characteristic as similar cell, when market, average value supplemental characteristic is less than
Or when being equal to preset quantity threshold value, the confidence level of each market average value supplemental characteristic is obtained, the highest market of confidence level is put down
Equal cell source of houses average value parameter of the value parameter data as similar cell.
Before the average value parameter for calculating the Target cell source of houses by similar cell, it is also necessary to calculate similar cell room
The average value parameter in source.The source of houses average value parameter for the similar cell that specific available each channel provides, channel tool
Body may include each mechanism, letting agency and letting agency website.When the data volume that channel provides is enough, canal is removed
Road provides peak and minimum in data, then joins the mean value of remaining data as the average value of the Target cell source of houses
Number.If the data volume that channel provides is not enough, wherein most believable data being averaged as the Target cell source of houses is chosen
Value parameter.By calculating the average value parameter of the similar cell source of houses, average value that can effectively to the Target cell source of houses
Parameter is estimated.
The cell source of houses value parameter estimation method of the application in one of the embodiments, comprising: obtain Target cell
Cell information；According to the cell information of the Target cell, every cell index of Target cell is obtained.It obtains and carries cell
The training cell of source of houses average value parameter and every cell index of training cell.By K-means clustering according to
Every cell index of training cell classifies to the trained cell, obtains training cell class.It is true according to training cell class
Determine training dataset and test data set.Training dataset is inputted into initial BP neural network, by training dataset to first
Beginning BP neural network is trained.It is tested by the initial BP neural network that test data set completes training.Work as test
By when, will training complete initial BP neural network as default cell similarity model.It is obstructed out-of-date when testing, according to survey
Test result updates the initial BP neural network, and the updated initial BP neural network is re-used as initial BP nerve net
Network returns training dataset inputting initial BP neural network, is trained by training dataset to initial BP neural network
Operation.The Target cell every cell index corresponding with Target cell is inputted into default cell similarity model, is obtained
The cell of Target cell evaluates index.Obtain the range information of each cell and Target cell.It is small according to each cell and the target
The distance in area determines default cell.Obtain every cell index of the default cell.By the default cell and default cell
Corresponding items cell index inputs default cell similarity model, obtains default cell set.It obtains and is preset in default cell set
The cell of cell evaluates index, and the cell appraisal index of default cell is evaluated to the preset range of index in the cell of Target cell
Interior default cell is as similar cell.Obtain each market average value supplemental characteristic of the similar cell source of houses；When the city
When average value supplemental characteristic is greater than preset quantity threshold value, remove maximum value in the market average value supplemental characteristic with
Minimum value, using the average value of other market average value supplemental characteristics as the cell source of houses average value parameter of similar cell,
When the market average value supplemental characteristic is less than or equal to preset quantity threshold value, each market average value supplemental characteristic is obtained
Confidence level, using the highest market average value supplemental characteristic of confidence level as similar cell cell source of houses average value join
Number.Each appraisal influence factor for obtaining the target source of houses, according to the prediction average value parameter of the Target cell source of houses and institute
Each appraisal influence factor for stating the target source of houses estimates the value parameter of the target source of houses by presetting half parameter quantile regression.
The cell source of houses price parameter estimation method of the application passes through computer software reality in one of the embodiments,
Existing, user wishes to inquire the price of certain set source of houses in some newly-built community, prepares to buy house.When he is to including the application
The computer software input of cell source of houses value parameter estimation method wishes after inquiring the title of the cell of average price that the software is first
Determine Target cell (i.e. the cell of user's input)；Then obtain every cell index of Target cell；Then by these cells
And cell index corresponding with cell inputs preset cell similarity model, the every cell appraisal for obtaining Target cell refers to
Mark will be then to have the cell of average value parameter to regard default cell in range in 1.5km away from Target cell distance, will preset
The cell index of cell inputs preset cell similarity model, obtains the cell appraisal index of each default cell, and by these
Default cell is classified as default cell set, and the similar cell of Target cell is then searched in default cell set, then passes through market
The average value parameter of each similar cell provided estimates the average value parameter of Target cell.Finally obtain the target source of houses
Each appraisal influence factor, according to each appraisal of the prediction average value parameter of the Target cell source of houses and the target source of houses influence because
Element estimates the value parameter of the target source of houses by presetting half parameter quantile regression.Then the predictive value of the target source of houses is joined
Number is shown to user, for reference.
It should be understood that although each step in the flow chart of Fig. 1-4 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 1-4
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
As shown in figure 5, the application also provides a kind of cell source of houses value parameter estimation device, device includes:
Cell index selection module 200, for obtaining every cell index of Target cell；
Index computing module 400 is evaluated, for the Target cell every cell index corresponding with Target cell is defeated
Enter default cell similarity model, obtains the cell appraisal index of Target cell, the default cell similarity model is to carry
The training cell of cell source of houses average value parameter is obtained as training data；
Similar cell search module 600 is searched for evaluating index according to the cell of Target cell in default cell set
The corresponding similar cell of Target cell, the default cell set include that the cell of default cell evaluates index；
Source of houses average price computing module 800, the cell source of houses average value for obtaining the similar cell found are joined
Number, is estimated according to the source of houses average value parameter of the cell source of houses average value parameters on target cell of the similar cell
Meter, obtains the source of houses average value parameter of Target cell；
One room monovalence estimation module 900, for obtaining each appraisal influence factor of the target source of houses, according to the Target cell
Each appraisal influence factor of the prediction average value parameter of the source of houses and the target source of houses, by presetting half parameter quantile regression
Model estimates the value parameter of the target source of houses, the default half parameter quantile regression be based on each appraisal influence factor and
Influence of the prediction average value parameter to the value parameter of the target source of houses is established.
Cell index selection module is specifically used for obtaining the cell information of Target cell in one of the embodiments,；Root
According to the cell information of the Target cell, every cell index of Target cell is obtained.
In one of the embodiments, further include model training module, carries cell source of houses average value ginseng for obtaining
Every cell index of several training cell and training cell；By K-means clustering according to the items of training cell
Cell index classifies to the trained cell, obtains training cell class；According to training cell class determine training dataset with
And test data set；Training dataset is inputted into initial BP neural network, by training dataset to initial BP neural network into
Row training；It is tested by the initial BP neural network that test data set completes training；It is when test passes through, training is complete
At initial BP neural network as default cell similarity model；It is obstructed out-of-date when testing, updated according to test result described in
Initial BP neural network returns training dataset inputting initial BP neural network, by training dataset to initial BP nerve
The operation that network is trained.
Further include in one of the embodiments, default cell setup module be used to obtain each cell and Target cell away from
From information；Default cell is determined at a distance from the Target cell according to each cell；Obtain every cell of the default cell
Index；The default cell every cell index corresponding with default cell is inputted into default cell similarity model, is obtained pre-
If cell set.
Similar determination module 400, which is specifically used for obtaining in default cell set, in one of the embodiments, presets cell
Cell evaluates index, and the cell appraisal index of default cell is pre- in the preset range of the cell appraisal index of Target cell
If cell is as similar cell.
Source of houses average price computing module 800 is specifically used for obtaining each of the similar cell source of houses in one of the embodiments,
Market average value supplemental characteristic；When the market average value supplemental characteristic is greater than preset quantity threshold value, the city is removed
Maxima and minima in the average value supplemental characteristic of field, using the average value of other market average value supplemental characteristics as phase
Like the cell source of houses average value parameter of cell, when the market average value supplemental characteristic is less than or equal to preset quantity threshold value
When, obtain the confidence level of each market average value supplemental characteristic, using the highest market average value supplemental characteristic of confidence level as
The cell source of houses average value parameter of similar cell.
Specific restriction about cell source of houses value parameter estimation device may refer to be worth above for the cell source of houses
The restriction of method for parameter estimation, details are not described herein.Modules in above-mentioned cell source of houses value parameter estimation device can be complete
Portion or part are realized by software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of calculating
In processor in machine equipment, it can also be stored in a software form in the memory in computer equipment, in order to processor
It calls and executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 6.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment 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 and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of cell source of houses value parameter estimation method.The display screen of the computer equipment can be liquid crystal display or electronics
Ink display screen, the input unit of the computer equipment can be the touch layer covered on display screen, are also possible to computer and set
Key, trace ball or the Trackpad being arranged on standby shell, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
Obtain every cell index of Target cell；
The Target cell every cell index corresponding with Target cell is inputted into default cell similarity model, is obtained
The cell of Target cell evaluates index, and the default cell similarity model is to carry the training of cell source of houses average value parameter
Cell is obtained as training data；
Index is evaluated according to the cell of Target cell in default cell set and searches the corresponding similar cell of Target cell, institute
State the cell appraisal index that default cell set includes default cell；
The cell source of houses average value parameter for obtaining the similar cell found, according to the cell of the similar cell
The source of houses average value parameter of source of houses average value parameters on target cell is estimated, the source of houses flat fare of Target cell is obtained
Value parameter；
Obtain the target source of houses each appraisal influence factor, according to the prediction average value parameter of the Target cell source of houses with
And each appraisal influence factor of the target source of houses estimates that the value of the target source of houses is joined by presetting half parameter quantile regression
Number, the default half parameter quantile regression are based on each appraisal influence factor and the prediction average value parameter to institute
The influence for stating the value parameter of the target source of houses is established.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains the small of Target cell
Area's information；According to the cell information of the Target cell, every cell index of Target cell is obtained
In one embodiment, acquisition is also performed the steps of when processor executes computer program carries the cell source of houses
The training cell of average value parameter and every cell index of training cell；By K-means clustering according to training
Every cell index of cell classifies to the trained cell, obtains training cell class；Instruction is determined according to training cell class
Practice data set and test data set；Training dataset is inputted into initial BP neural network, by training dataset to initial BP
Neural network is trained；It is tested by the initial BP neural network that test data set completes training；When test passes through
When, the initial BP neural network that training is completed is as default cell similarity model；It is obstructed out-of-date when testing, it is tied according to test
Fruit updates the initial BP neural network, and the updated initial BP neural network is re-used as initial BP neural network,
It returns and training dataset is inputted into initial BP neural network, the behaviour that initial BP neural network is trained by training dataset
Make.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains each cell and target
The range information of cell；Default cell is determined according to the range information of each cell and the Target cell；Obtain it is described preset it is small
Every cell index in area；The default cell every cell index corresponding with default cell is inputted into default cell similarity
Model obtains default cell set.
In one embodiment, it is also performed the steps of when processor executes computer program in the default cell set of acquisition
The cell of default cell evaluates index, and the cell appraisal index of default cell is evaluated the default of index in the cell of Target cell
Default cell in range is as similar cell.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains the similar cell source of houses
Each market average value supplemental characteristic；When the market average value supplemental characteristic is greater than preset quantity threshold value, removal
Maxima and minima in the market average value supplemental characteristic, by the average value of other market average value supplemental characteristics
As the cell source of houses average value parameter of similar cell, when the market average value supplemental characteristic is less than or equal to present count
When measuring threshold value, the confidence level of each market average value supplemental characteristic is obtained, by the highest market average value parameter number of confidence level
According to the cell source of houses average value parameter as similar cell.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain every cell index of Target cell；
The Target cell every cell index corresponding with Target cell is inputted into default cell similarity model, is obtained
The cell of Target cell evaluates index, and the default cell similarity model is to carry the training of cell source of houses average value parameter
Cell is obtained as training data；
Index is evaluated according to the cell of Target cell in default cell set and searches the corresponding similar cell of Target cell, institute
State the cell appraisal index that default cell set includes default cell；
The cell source of houses average value parameter for obtaining the similar cell found, according to the cell of the similar cell
The source of houses average value parameter of source of houses average value parameters on target cell is estimated, the source of houses flat fare of Target cell is obtained
Value parameter；
Obtain the target source of houses each appraisal influence factor, according to the prediction average value parameter of the Target cell source of houses with
And each appraisal influence factor of the target source of houses estimates that the value of the target source of houses is joined by presetting half parameter quantile regression
Number, the default half parameter quantile regression are based on each appraisal influence factor and the prediction average value parameter to institute
The influence for stating the value parameter of the target source of houses is established.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains Target cell
Cell information；According to the cell information of the Target cell, every cell index of Target cell is obtained.
In one embodiment, acquisition is also performed the steps of when computer program is executed by processor carries cell room
The training cell of source average value parameter and every cell index of training cell；By K-means clustering according to instruction
The every cell index for practicing cell classifies to the trained cell, obtains training cell class；It is determined according to training cell class
Training dataset and test data set；Training dataset is inputted into initial BP neural network, by training dataset to initial
BP neural network is trained；It is tested by the initial BP neural network that test data set completes training；When test is logical
Out-of-date, the initial BP neural network that training is completed is as default cell similarity model；It is obstructed out-of-date when testing, according to test
As a result the initial BP neural network is updated, the updated initial BP neural network is re-used as initial BP nerve net
Network returns training dataset inputting initial BP neural network, is trained by training dataset to initial BP neural network
Operation.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains each cell and mesh
Mark the range information of cell；Default cell is determined according to the range information of each cell and the Target cell；It obtains described default
Every cell index of cell；It is similar that the default cell every cell index corresponding with default cell is inputted into default cell
Model is spent, default cell set is obtained.
In one embodiment, acquisition default cell set is also performed the steps of when computer program is executed by processor
The cell of interior default cell evaluates index, and the cell appraisal index of default cell is evaluated the pre- of index in the cell of Target cell
If the default cell in range is as similar cell.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains similar cell room
Each market average value supplemental characteristic in source；When the market average value supplemental characteristic is greater than preset quantity threshold value, go
Except the maxima and minima in the market average value supplemental characteristic, by being averaged for other market average value supplemental characteristics
It is worth the cell source of houses average value parameter as similar cell, is preset when the market average value supplemental characteristic is less than or equal to
When amount threshold, the confidence level of each market average value supplemental characteristic is obtained, by the highest market average value parameter of confidence level
Cell source of houses average value parameter of the data as similar cell.
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
Instruct relevant hardware to complete by computer program, computer program to can be stored in a non-volatile computer readable
It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen
Please provided by any reference used in each embodiment to memory, storage, database or other media, may each comprise
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, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), 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..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Above embodiments only express the several embodiments of the application, and the description thereof is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for those of ordinary skill in the art,
Under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection scope of the application.
Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of cell source of houses value parameter estimation method, which comprises
Obtain every cell index of Target cell；
The Target cell every cell index corresponding with Target cell is inputted into default cell similarity model, obtains target
The cell of cell evaluates index, and the default cell similarity model is to carry the training cell of cell source of houses average value parameter
It is obtained as training data；
Index is evaluated according to the cell of Target cell in default cell set and searches the corresponding similar cell of Target cell, it is described pre-
If cell set includes that the cell of default cell evaluates index；
The cell source of houses average value parameter for obtaining the similar cell found, according to the cell source of houses of the similar cell
The source of houses average value parameter of average value parameters on target cell is estimated, the source of houses average value ginseng of Target cell is obtained
Number；
Each appraisal influence factor for obtaining the target source of houses, according to the prediction average value parameter of the Target cell source of houses and institute
Each appraisal influence factor for stating the target source of houses estimates the value parameter of the target source of houses by presetting half parameter quantile regression,
The default half parameter quantile regression is based on each appraisal influence factor with the prediction average value parameter to described
The influence of the value parameter of the target source of houses is established.
2. the method according to claim 1, wherein the every cell index for obtaining Target cell includes:
Obtain the cell information of Target cell；
According to the cell information of the Target cell, every cell index of Target cell is obtained.
3. the method according to claim 1, wherein described that the Target cell is corresponding with Target cell each
Item cell index inputs default cell similarity model, before the cell appraisal index for obtaining Target cell, further includes:
Obtain every cell index of the training cell for carrying cell source of houses average value parameter and training cell；
Classified according to every cell index of training cell to the trained cell by K-means clustering, is obtained
Training cell class；
Training dataset and test data set are determined according to training cell class；
Training dataset is inputted into initial BP neural network, initial BP neural network is trained by training dataset；
It is tested by the initial BP neural network that test data set completes training；
When test passes through, the initial BP neural network that training is completed is as default cell similarity model；
It is obstructed out-of-date when testing, the initial BP neural network is updated according to test result, by the updated initial BP mind
It is re-used as initial BP neural network through network, returns and training dataset is inputted into initial BP neural network, pass through training data
Collect the operation being trained to initial BP neural network.
4. the method according to claim 1, wherein described presetting the cell in cell set according to Target cell
Evaluate index and search similar cell, before the cell source of houses average value parameter for obtaining the similar cell, further includes:
Obtain the range information of each cell and Target cell；
Default cell is determined according to the range information of each cell and the Target cell；
Obtain every cell index of the default cell；
The default cell every cell index corresponding with default cell is inputted into default cell similarity model, is preset
Cell set.
5. the method according to claim 1, wherein described presetting the cell in cell set according to Target cell
Evaluate index and search the corresponding similar cell of Target cell, the default cell set includes the cell appraisal index tool of default cell
Body includes:
The cell appraisal index that cell is preset in default cell set is obtained, by the cell appraisal index of default cell in Target cell
Cell appraisal index preset range in default cell as similar cell.
6. the method according to claim 1, wherein the half parameter quantile regression is specifically as follows:
Y=X β+g (T)+ε
Wherein Y is target source of houses estimated price, and X is the factor for influencing the appraisal of the target source of houses, the source of houses average price including Target cell
And the argument section in the appraisal influence factor of the target source of houses, β are regression coefficient, g (T) is the non-ginseng evaluated in influence factor
Number part, ε is random error.
7. the method according to claim 1, wherein the cell source of houses flat fare for obtaining the similar cell
Value parameter specifically includes:
Obtain each market average value supplemental characteristic of the similar cell source of houses；
When the market average value supplemental characteristic is greater than preset quantity threshold value, the market average value supplemental characteristic is removed
In maxima and minima, put down the average value of other market average value supplemental characteristics as the cell source of houses of similar cell
It is average to obtain each market when the market average value supplemental characteristic is less than or equal to preset quantity threshold value for equal value parameter
The confidence level of value parameter data, using the highest market average value supplemental characteristic of confidence level as the cell source of houses of similar cell
Average value parameter.
8. a kind of cell source of houses average price parameter estimation apparatus, which is characterized in that described device includes:
Cell index selection module, for obtaining every cell index of Target cell；
Evaluate index computing module, it is small for presetting the Target cell every cell index input corresponding with Target cell
Area's similarity model obtains the cell appraisal index of Target cell, and the default cell similarity model is to carry the cell source of houses
The training cell of average value parameter is obtained as training data；
Similar cell search module searches Target cell for evaluating index according to the cell of Target cell in default cell set
Corresponding similar cell, the default cell set include that the cell of default cell evaluates index；
Source of houses average price computing module, for obtaining the cell source of houses average value parameter of the similar cell found, according to
The source of houses average value parameter of the cell source of houses average value parameters on target cell of the similar cell is estimated, mesh is obtained
Mark the source of houses average value parameter of cell；
One room monovalence estimation module, for obtaining each appraisal influence factor of the target source of houses, according to the Target cell source of houses
Each appraisal influence factor of prediction average value parameter and the target source of houses is estimated by default half parameter quantile regression
Count the value parameter of the target source of houses, the default half parameter quantile regression be based on each appraisal influence factor with it is described pre-
Influence of the average value parameter to the value parameter of the target source of houses is surveyed to establish.
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 (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290362.3A CN109544410A (en) | 2018-10-31 | 2018-10-31 | Cell source of houses value parameter estimation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290362.3A CN109544410A (en) | 2018-10-31 | 2018-10-31 | Cell source of houses value parameter estimation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109544410A true CN109544410A (en) | 2019-03-29 |
Family
ID=65846317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811290362.3A Pending CN109544410A (en) | 2018-10-31 | 2018-10-31 | Cell source of houses value parameter estimation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109544410A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619089A (en) * | 2019-05-31 | 2019-12-27 | 北京无限光场科技有限公司 | Information retrieval method and device |
| CN111523614A (en) * | 2020-05-09 | 2020-08-11 | 上海添玑网络服务有限公司 | Cell similarity judgment method and device |
-
2018
- 2018-10-31 CN CN201811290362.3A patent/CN109544410A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619089A (en) * | 2019-05-31 | 2019-12-27 | 北京无限光场科技有限公司 | Information retrieval method and device |
| CN111523614A (en) * | 2020-05-09 | 2020-08-11 | 上海添玑网络服务有限公司 | Cell similarity judgment method and device |
| CN111523614B (en) * | 2020-05-09 | 2023-12-19 | 上海添玑网络服务有限公司 | Cell similarity judging method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | Review of urban building energy modeling (UBEM) approaches, methods and tools using qualitative and quantitative analysis | |
| CN110070713B (en) | Traffic flow prediction method based on bidirectional nested LSTM neural network | |
| Sun et al. | Using Bayesian deep learning to capture uncertainty for residential net load forecasting | |
| CN111104981B (en) | Hydrological prediction precision evaluation method and system based on machine learning | |
| WO2017143921A1 (en) | Multi-sampling model training method and device | |
| CN109242140A (en) | A kind of traffic flow forecasting method based on LSTM_Attention network | |
| CN105740991A (en) | Climate change prediction method and system for fitting various climate modes based on modified BP neural network | |
| CN107690660A (en) | Image-recognizing method and device | |
| CN109615280A (en) | Employee's data processing method, device, computer equipment and storage medium | |
| CN107798615A (en) | Declaration form renews charge difficulty Forecasting Methodology and device | |
| CN111612640A (en) | Data-driven vehicle insurance fraud identification method | |
| CN110377846A (en) | Social networks method for digging, device, storage medium and computer equipment | |
| CN109544410A (en) | Cell source of houses value parameter estimation method and device | |
| CN114418175A (en) | Personnel management method and device, electronic equipment and storage medium | |
| CN109583940A (en) | Cell source of houses value parameter estimation method and device | |
| Cuellar et al. | Assessing the accuracy of sensitivity analysis: an application for a cellular automata model of Bogota’s urban wetland changes | |
| CN109920489A (en) | It is a kind of that model and method for building up are hydrocracked based on Lasso-CCF-CNN | |
| CN117436653A (en) | Prediction model construction method and prediction method for travel demands of network about vehicles | |
| CN105224801A (en) | A kind of multiple-factor reservoir reservoir inflow short-time forecast evaluation method | |
| Noor et al. | Prediction map of rainfall classification using random forest and inverse distance weighted (IDW) | |
| CN109544214A (en) | Cell source of houses average value method for parameter estimation and device | |
| Lu et al. | Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions | |
| CN115796030A (en) | Traffic flow prediction method based on graph convolution | |
| Swietek et al. | Visual Capital: Evaluating building-level visual landscape quality at scale | |
| CN109559157A (en) | Cell source of houses value parameter estimation method and device |
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 |
Application publication date: 20190329 |
|
| WD01 | Invention patent application deemed withdrawn after publication |