CN107705145A - A kind of room rate assessment system - Google Patents
A kind of room rate assessment system Download PDFInfo
- Publication number
- CN107705145A CN107705145A CN201710785127.2A CN201710785127A CN107705145A CN 107705145 A CN107705145 A CN 107705145A CN 201710785127 A CN201710785127 A CN 201710785127A CN 107705145 A CN107705145 A CN 107705145A
- Authority
- CN
- China
- Prior art keywords
- data
- layer
- source
- room rate
- assessment system
- 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
- 238000013480 data collection Methods 0.000 claims abstract description 12
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 238000012937 correction Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 9
- 235000013399 edible fruits Nutrition 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 5
- 241000238413 Octopus Species 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000011161 development Methods 0.000 abstract description 4
- 230000010354 integration Effects 0.000 abstract description 3
- 238000013459 approach Methods 0.000 description 12
- 239000000284 extract Substances 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000003442 weekly effect Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 239000004575 stone Substances 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
- G06Q30/0283—Price estimation or determination
-
- 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)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Finance (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of room rate assessment system, and it includes source data layer, data collection layer, data analysis layer and data machined layer；Source data layer is used to provide multi-source data；Data collection layer is used to extract source data from source data layer；Data analysis layer is used for disk source data, transaction data and market price data after being cleaned to the source data of extraction；Data mart modeling layer is processed using cell average price Policy model to disk source data, transaction data and market price data, the average price of a certain building is obtained, return correction model using characteristic vector corrects to obtain the average price in a certain house according to the feature in each house progress data.The present invention has extraordinary open, integration and expansibility, while has the perspective of technology, meets industry prevalence development trend, disclosure satisfy that all demands of big data analysis.
Description
Technical field
The invention belongs to real estate technical field of internet application, and in particular to a kind of room rate assessment system.
Background technology
The theoretical method of house property appraisal had fully been verified that Market Comparison Approach was current in a very long time in past
Generally acknowledge maximally effective house property assessment models Construction Theory, but have higher threshold using Market Comparison Approach, be in particular in：The
One, it is necessary to collect a large amount of, normal real estate transaction data.That is, it is desirable to which it is quite big that evaluator grasps real-estate market
Scale data, even city have accumulated hundreds of thousands real estate transaction data, but once according to stricter
Standard is classified, and the space of each sample is still not big enough.If sample space is less than normal, then has confidence degree
Section is just very wide.If the distance between bound of confidential interval draws to open very much, criterion is just lost when room rate is discussed.
Second, necessarily require room rate relatively stable using Market Comparison Approach.In Market Comparison Approach, the room rate of realtor's estimation depends on
In their expections to marketplace trend.If real-estate market is more stable, then realtor can be on the basis of current room rate
It is upper to set room rate plus certain inflation rate.If market unsettled, room rate rises and drops suddenly and sharply, then using Market Comparison Approach
Difficulty it is just very big.In in the period of there is property-value bubble, it is possible to over-evaluate room rate, amplification real estate bubble using Market Comparison Approach
Foam.In this case, Market Comparison Approach has completely lost ample scope for abilities.Thus the theoretical model of Market Comparison Approach will be supported
Basic data is only established on recent real trade data, major defect be present.In other words, excessively scattered intermediary of China
Market, cause board lot according to being difficult to converge and be used immediately, so only must by transaction data design evaluation model
So three drawbacks be present：Coverage deficiency, poor in timeliness and accuracy are poor.
Traditional Market Comparison Approach valuation model too relies on the subjective experience of appraiser, and this not only causes rating result
It is unreliable, more likely trigger moral hazard, hinder the benign development of appraisal of real estate industry.Meanwhile Market Comparison Approach appraisal needs
Substantial amounts of humanity, society, economy, geodata are acquired, managed, analyzed and shown, traditional manual management mode
Obviously processing requirement of the house property appraisal to bulk information can not be met, valuation model is improved using new technological means, establish and estimate
Valency information system is to evaluate an inexorable trend of industry development.
The content of the invention
In order to solve above mentioned problem existing for prior art, the invention provides a kind of room rate assessment system.
The technical solution adopted in the present invention is：A kind of room rate assessment system includes source data layer, data collection layer, data
Process layer and data machined layer；The source data layer is used to provide multi-source data；The data collection layer is used for from the source number
Source data is extracted according to layer；The data analysis layer be used for the disk source data after being cleaned to the source data of extraction,
Transaction data and market price data；The data mart modeling layer using cell average price Policy model to disk source data, transaction data and
Market price data are processed, and obtain the average price of a certain building, and correction model is returned according to each house using characteristic vector
Feature carries out data and corrects to obtain the average price in a certain house.
Further, the sale at reduced prices number that the multi-source data includes the disk visitor logical sale at reduced prices date, the source of houses changes the valency date, disk visitor is logical
Sold at reduced prices data and third party transaction data according to, Q rooms ERP transaction data, third party.
Further, the data collection layer using sale at reduced prices data logical to disk visitor batch processing framework Spring Batch and
Q rooms ERP transaction data is acquired, sold at reduced prices by the way of octopus and LocoySpider combination to third party data and the
Tripartite transaction data are acquired.
Further, the detailed process that the data processing number of plies is cleaned to the source data of extraction is：
1) data reliability rank is set；To market price, true sale data, have official commission book cell offer valency, have
The confidence levels of official commission books and newspapers disk valency and third party's offer valency are arranged as according to order from high to low：Market price can
Reliability>The confidence level of true sale data>There is the confidence level of official commission book cell offer valency>Without official commission books and newspapers disk valency
Confidence level>The confidence level of third party's offer valency；
2) (the offer valency-average price of cell transaction in the recent period)/transaction average price in the reasonable data for obtaining step 1)>10%
Data markers are dirty data；
3) the monovalent and minimum unit price of disk source highest is set for each city, rational data area is limited, by step 2)
Data markers in obtained reasonable data outside the data area are dirty data；
4) reasonable data obtained for step 3), operation personnel care for according to system operation flag data to the corresponding purchase of property
Ask and examined, data mode is re-flagged；The abnormal data for having follow-up to record is re-flagged；
5) reasonable data obtained for step 4), when data are all concentrated in a kind of data source, gradient is taken to cluster
Method, with the 5% of each city average price as data gradient, data are further cleaned.
Further, the data mart modeling layer is processed to disk source data, transaction data and market price data, and use is small
The process for the average price that area's average price Policy model obtains a certain building is：
Using gradient comparing method judge disk source data, transaction data and market price data whether setting gradient scope
It is interior, if in gradient scope, the number of data in gradient scope is counted, a certain building is calculated using the method for average
Average price；Otherwise, the gradient clustering method of use is handled data again, until data are in gradient scope.
Further, the data mart modeling layer uses multiple linear regression model construction feature vector regression correction model,
The characteristic vector of structure returns correction model：
Q=a0+∑aiZi+ ε,
In formula, Q represents the assessment unit price of certain specific set second-hand house, a0The average price of building, a where representing certain set second-hand houseiTable
Show the feature in the construction characteristic vector of second-hand house, ZiRepresent adjustment ratio corresponding to each single item feature in the characteristic vector of second-hand house
Example, ε represent other influences factor, and it is determined by traffic characteristic, construction characteristic and neighbourhood's environment, and traffic characteristic includes public bus network
And subway station；Construction characteristic includes construction area, place floor, total floor, direction, finishing, supporting and building age；Neighbourhood's ring
It is supporting that border includes life；Feature a in the characteristic vector of second-hand houseiIncluding age of dwellings, house type, floor, direction, finishing and supporting.
Further, standard interface layer is additionally provided with the room rate assessment system, applications end passes through the mark
Standardization interface layer 5 obtains the average price in a certain house that the data mart modeling layer obtains.
Further, authentication dispatch layer is additionally provided with the room rate assessment system, the authentication dispatch layer is arranged on institute
State between data mart modeling layer and standard interface layer.
Further, Distribution GIS and building dictionary Back ground Information are additionally provided with the room rate assessment system
Storehouse, the cloud source of houses big data platform that Q rooms net is built obtain the geography information in Distribution GIS, the room rate by API
Assessment system is assessed to obtain the room rate in any space by the geography information in building dictionary basic database and GIS.
Further, school district management information bank is additionally provided with the room rate assessment system, the cloud source of houses that Q rooms net is built is big
Data platform is combined with school district management information bank, and the room rate assessment system is assessed to obtain the room of the counterpart cell of each school
Valency.
Due to using above technical scheme, beneficial effects of the present invention are：The present invention is with data of offerring, transaction data and city
Field valence mumber is foundation stone according to multiparty data is waited, theoretical based on Market Comparison Approach, assistant's opinion supplemented by characteristic vector analytic approach, with reference to
GIS technology, build the intelligent room rate assessment system of specific rule.The problem of for coverage deficiency：13 O2O of Q Fang Wang groups
City can obtain the true house property information for sale of in the market more than 65%, and flat price for sale represents Vehicles Collected from Market valency
Lattice, house property data to be transacted are laid in reference to transaction data+colleague, finally cover close to 100% can sale resource pricing data.
For poor in timeliness problem, Q rooms net group internal treats the management system regulation of sale resource pricing information, weekly follow-up
Once, guaranteed price unusual fluctuation is in the response frequency of assessment system.The problem of for accuracy difference：Level is done to data reliability
Division, self mechanism is added, and individual difference is adjusted by the method for method for feature analysis more science, rather than with master
The index factor for conjesturing and finding out and being had a great influence to room rate is seen, then these indexs are carried out with multiple linear regression equations and room rate
Fitting, finally accomplishes a room monovalence.
The present invention has extraordinary open, integration and expansibility, while has the perspective of technology, meets
Industry prevalence development trend；It uses distributed storage, Distributed Calculation, cluster High Availabitity, heterogeneous data source to extract, streaming meter
The field such as calculation, Data cache technology maturation front-end technology, it disclosure satisfy that all demands of big data analysis.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described.It is clear that drawings in the following description are only this hair
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of Organization Chart for room rate assessment system that one embodiment of the invention provides.
In figure：1- source data layers；2- data collection layers；3- data analysis layers；4- data mart modeling layers；5- standard interfaces
Layer；6- authenticates dispatch layer；7- application ends.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, technical scheme will be carried out below
Detailed description.Obviously, described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art are resulting on the premise of creative work is not made to be owned
Other embodiment, belong to the scope that the present invention is protected.
As shown in figure 1, the invention provides a kind of room rate assessment system, it includes source data layer 1, data collection layer 2, number
According to process layer 3 and data machined layer 4.Source data layer 1 is used to provide multi-source data, and these data include disk visitor logical sale at reduced prices day
Phase, the source of houses change valency date, the transaction data that disk visitor is led to, third party sale at reduced prices data and third party transaction data etc..Data collection layer 2
For extracting source data from source data layer 1.Data analysis layer 3 is used to clean the source data of extraction, filters out those not
Satisfactory data, disk source data, transaction data and market price data after being cleaned.Wherein, undesirable number
According to the data for mainly including incomplete data, the data of mistake and repetition.Data mart modeling layer 4 uses cell average price Policy model
Disk source data, transaction data and market price data are processed, obtain the average price of a certain building, is returned and rectified using characteristic vector
Positive model carries out data according to the feature in each house and corrects to obtain the average price in a certain house.
In above-described embodiment, logical to disk visitor batch processing framework Spring Batch sale at reduced prices data and Q rooms ERP friendship are used
Easy data are acquired.Batch processing framework Spring Batch are monitored execution to task configuration, are completed with reference to scheduling system
The extraction work of whole multi-data source.
Batch processing framework Spring Batch are configured by simple task, just can be realized using considerably less manpower more
Access, process monitoring and the result informing mechanism of data source, these characteristics are due to that Spring Batch are provided and can largely weighed
Component, include implementation procedure daily record, tracking, affairs, Mission Operations statistics, task restart, skip, repeat and resource pipe
Reason.For big data quantity and high performance batch processing task, SpringBatch is also provided that Premium Features and characteristic to prop up
Hold, such as sectoring function, remote functionality.In a word, simple, complicated and big data quantity can be supported by Spring Batch
Batch processing job.
Data of being sold at reduced prices using the mode that octopus and LocoySpider combine to third party and third party transaction data are carried out
Collection.
Octopus collector is a simple and practical collector, multiple functional, simple to operate, without writing rule.It is carried
The cloud collection of confession, acquisition tasks can also be run even if shutdown on Cloud Server.
LocoySpider is a professional internet data crawl, processing, analysis and excavates software, its can flexibly,
The data message of distribution at random on webpage is promptly captured, and by a series of analyzing and processing, accurately excavates required data,
The most frequently used is exactly to gather the online resources such as the word, picture, data of some websites.Its interface is more complete, can use PHP
Or C# develops the extension of any function.
In above-described embodiment, the decimation rule that data collection layer 2 extracts source data is：Set according to city and extract data source
Object, data source object and frequency are configured.For example, can set in nearest X days, there are the data of follow-up necessary to price
Reach more than Samsung comprising certificate of entrustment, broker's star, extract the frequency 1 times a week, to enable short message prompting.
The detailed process that data analysis layer 3 is cleaned to the source data of extraction is：
1) data reliability rank is set；To market price, true sale data, have official commission book cell offer valency, have
The confidence levels of official commission books and newspapers disk valency and third party's offer valency are arranged as according to order from high to low：Market price can
Reliability>The confidence level of true sale data>There is the confidence level of official commission book cell offer valency>Without official commission books and newspapers disk valency
Confidence level>The confidence level of third party's offer valency.
2) (the offer valency-average price of cell transaction in the recent period)/transaction average price in the reasonable data for obtaining step 1)>10%
Data markers are dirty data.
3) the monovalent and minimum unit price of disk source highest is set for each city, rational data area is limited, by step 2)
Data markers in obtained reasonable data outside the data area are dirty data.For example, in the Pan Yuan extraction processes of Shenzhen, will
Offer valency/settlement price<8000 and the valency of offerring/settlement price>150000 are labeled as dirty data.
4) reasonable data obtained for step 3), operation personnel care for according to system operation flag data to the corresponding purchase of property
Ask and examined, data mode is re-flagged；The abnormal data for having follow-up to record is re-flagged.
5) reasonable data obtained for step 4), when data are all concentrated in a kind of data source, gradient is taken to cluster
Method, with the 5% of each city average price as data gradient, data are further cleaned.For example, Shenzhen average price 50,000, existing
Having in a cell has 10 Pan Yuan selling, price is 25000 respectively, 32000,38000,39000,39100,39500,
60000、80000、120000、84000；50000*5%=2500 is so found out into positive and negative 2500 model as a data gradient
The most data of the interior data amount check included are enclosed, and are reasonable data by the data markers in the range of the data positive and negative 2500, will
Other data markers are dirty data.
In above-described embodiment, the data after the processing of data analysis layer 3 include disk source data, transaction data and market valence mumber
According to.Data mart modeling layer 4 obtains the average price of a certain building using cell average price Policy model, and its detailed process is：
Using gradient comparing method judge disk source data, transaction data and market price data whether setting gradient scope
It is interior, if in gradient scope, the number of data in gradient scope is counted, a certain building is calculated using the method for average
Average price；Otherwise, data are handled again using the gradient clustering method of step 5), until data are in gradient scope.
For example, it is assumed that Shenzhen city average price is 50000 Yuan/㎡, gradient scope is 2500 yuan；
Disk source data average price=P, transaction data average price=T, market price average price=M, P>T>M, (P-M)≤2500, P are present
8 data P1~P8, there are 2 data T1 in T and T2, M have 1 data M1,
The then average price of cell=(P1+P2+P3+P4+P5+P6+P7+P8+T1+T2+M1)/(8+2+1).
If P1 is obtained according to gradient comparing method and the datas of P6 two do not meet data admittable regulation, as dirty data, then
The average price of cell=(P2+P3+P4+P5+P7+P8+T1+T2+M1)/(6+2+1).
In above-described embodiment, data mart modeling layer assesses valency according to the data reliability level calculation of setting.
If market price, valency=market price+appraisal rule adjustment item is assessed；
Otherwise, if settlement price and offer valency, then valency=(settlement price+offer valency)/2+ appraisal rule adjustment items are assessed；
Otherwise, if settlement price is without offer valency, then valency=settlement price+appraisal rule adjustment item is assessed；
Otherwise, if valency no deal valency of offerring, then valency=offer valency+appraisal rule adjustment item is assessed；
Otherwise, if without offer valency no deal valency, assessment valency=can not assess.
Specifically, returned using multiple linear regression model construction feature vector regression correction model, the characteristic vector of structure
The correction model is returned to be：
Q=a0+∑aiZi+ ε,
In formula, Q represents the assessment unit price of certain specific set second-hand house, a0The average price of building, a where representing certain set second-hand houseiTable
Show the feature in the construction characteristic vector of second-hand house, ZiRepresent adjustment ratio corresponding to each single item feature in the characteristic vector of second-hand house
Example, ε represent other influences factor, and it is determined by traffic characteristic, construction characteristic and neighbourhood's environment.Wherein, traffic characteristic includes public affairs
Intersection road and subway station；Construction characteristic includes construction area, place floor, total floor, direction, finishing, supporting and building age；
It is supporting that neighbourhood's environment includes life.Feature a in the characteristic vector of second-hand houseiIncluding age of dwellings, house type, floor, direction, finishing and
It is supporting etc..
Table 1 gives the feature a in the characteristic vector of second-hand houseiIt is corresponding with each single item feature in the characteristic vector of second-hand house
Adjustment ratio ZiBetween corresponding relation.
Feature a in the characteristic vector of the second-hand house of table 1iCorresponding adjustment ratio ZiMapping table
Embodiment：To ensure the reference value of data, offer valency average price and Q rooms net transaction average price are calculated weekly, fetch area
Between have in nearly 15 days follow-up price offer data and the transaction data of nearly 1 month；Using in room rate assessment system of the present invention
4 pairs of disk source data of data mart modeling layer, transaction data and market price data are processed, and obtain the average price of building, binding characteristic to
Quantity algorithm, the average price in certain house is obtained, its detailed process is：
1) user evaluates, and if there is market price, then assesses valency=market price+appraisal rule adjustment item, wherein, appraisal rule
Then adjust item=(QF-F) * FC+ (QO-O) * OC+ (QS-S) * AC.
2) disk source price list is inquired about, judges that the affiliated building transaction average price in nearly moon house and offer average price whether there is.
If transaction average price and offer average price are all present, the assessment valency in the house is calculated using following assessment valency formula,
And the assessment valency to being calculated is presented.
Assessment valency=(TP+OF)/2+ (QF-F) * FC+ (QO-O) * OC+ (QS-S) * AC.
In formula, TP represents transaction average price, same disk this month Q room net N bar transaction data is taken, if N>=6, then the date is taken in N
6 newest datas are averaged；If N<6, then take whole month data to be averaged；If this month, the cell was merchandised without Q rooms net
Data, then standard price do not calculate transaction average price, using offer average price as reference.
OF represents offer average price, takes this week offer valency average price.
MF represents market average price.
QF represents the number of plies where inquiry room floor.
F represents benchmark floor, benchmark floor=total floor/2.
O represents benchmark direction, benchmark direction value=5；South-north direction value=10, the Southern Dynasties are worth=8 to value=9, southeast direction,
Southwest direction value=7, east-west direction value=6, east direction value=5, northeast direction value=4, west direction value=3, northwest direction value
=2, the Northern Dynasties to value=1.
QS represents area value where inquiry room.
S represents reference area, reference area=2；A1=(0~60 square meter)=3, A2=(60~110 square meter)=2, A3
=(more than 110 square meters)=1.
AC represents area coefficient, area coefficient=feature vector, XAc%* cell average prices.
FC represents floor beams index, floor beams index=feature vector, XFC%* cell average prices.
OC is represented towards coefficient, towards coefficient=feature vector, XOC%* cell average prices.
If the affiliated building transaction average price in house of the nearly moon is not present, determine whether that offer average price whether there is.Such as
Fruit is present, then the assessment valency in the house is calculated using following assessment valency formula, and the assessment valency to being calculated is presented.Such as
Fruit is not present, then can not be evaluated.
Assessment valency=OF+ (QF-F) * FC+ (QO-O) * OC+ (QS-S) * AC.
If the affiliated building offer average price in house of the nearly moon is not present, determine whether that transaction average price whether there is.Such as
Fruit is present, then the assessment valency in the house is calculated using following assessment valency formula, and the assessment valency to being calculated is presented.Such as
Fruit is not present, then can not be evaluated.
Assessment valency=TP+ (QF-F) * FC+ (QO-O) * OC+ (QS-S) * AC.
In above-described embodiment, standard interface layer 5 is additionally provided with room rate assessment system of the present invention.Applications end 7 is logical
Cross the average price that standard interface layer 5 obtains a certain house that data mart modeling layer 4 obtains.Made the rounds of the wards valency including Q rooms net at applications end 7
Channel, Q rooms net fetched data channel, the reference of disk visitor's way system price specifications, the support of new media dispatch data, financial air control reference
Data target, the appraisal of user's house property and real estate market confidence index etc..
In above-described embodiment, authentication dispatch layer is additionally provided with room rate assessment system of the present invention, authentication dispatch layer is arranged on
Between data mart modeling layer 4 and standard interface layer 5.
Authentication dispatch layer is provided with city switchgear distribution, calculates frequency configuration, channel mandate, Urban Strategy configuration and channel
Strategy configuration.Wherein, city switchgear distribution is used for the switch for configuring some city, if the source data in a city is through undue
Analysis, more than 50% building estimation can be covered, can be switched by opening this city, realize the extraction of whole data,
The functions such as cleaning, calculating, result storage, interface interchange.The frequency is calculated to be configured to extract calculating week for the configuration of each city
Phase, such as：For Shenzhen, extract a data weekly, on every Fridays 0 morning start to calculate.Channel mandate is used to configure channel calling
Data-interface scope, such as：Building room rate is only provided, school district, subway and single room rate are not provided and assess authority.Urban Strategy is matched somebody with somebody
Put for configure city make the rounds of the wards valency application level, source data extract scope and extract the frequency.Such as：The Hangzhou valency degree of accuracy of making the rounds of the wards is commented
Estimate and extract scope (thering is follow-up to change valency action for 15 days) for B levels, disk source data, transaction data takes nearly 15 days, and third party's data take
Full dose.Channel strategy is configured to configure channel calling level privileges, calls scope, calls the frequency.
In above-described embodiment, Distribution GIS and building dictionary base are additionally provided with room rate assessment system of the present invention
Plinth information bank.The cloud source of houses big data platform that Q rooms net is built includes the coordinate of all cells, traffic station point coordinates information.With reference to
The API (Application Programming Interface, application programming interface) that Baidu opens, believed using geography
GIS technology is ceased, can be to draw the house property average price information in any range., can be to geography in the case of coverage is complete
In the range of all rooms evaluated, in conjunction with GIS provide flexible division spacial ability, can be to the room rate in any space
Make equal Data-Statistics.
The outstanding advantage of GIS-Geographic Information System (GIS) technology is that its powerful spatial data, attribute data processing energy
Power and visualization capability；The integrated management of spatial information and attribute information can be realized；It can not only inquire about, retrieve data, but also
Can be formed as needed with other Professional Models or mathematical modeling an analysis during an analytical model for application is carried out, processing,
Evaluation and support decision-making, therefore utilize GIS data management, space querying, spatial analysis, visualization and other Professional Models
Integration capability improves appraisal of real estate model, establishes the room rate assessment system of a GIS platform based on flexible division space.
In above-described embodiment, it can be deduced that the average price of each cell, by building school district management information bank, with reference to the cloud source of houses
Building modeling information management module in big data platform, two parts information is associated according to national publicity content, so
Can the pricing information of the counterpart cell of each school is collected with equal Data-Statistics, establish what is converted from school district to house property
Information channel.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art can readily occur in change or replacement in presently disclosed technical scope, all should
It is included within the scope of the present invention.Therefore, protection scope of the present invention should using the scope of the claims as
It is accurate.
Claims (10)
1. a kind of room rate assessment system, it is characterised in that it includes source data layer, data collection layer, data analysis layer and data
Machined layer；The source data layer is used to provide multi-source data；The data collection layer is used to extract source number from the source data layer
According to；The data analysis layer is used for disk source data, transaction data and city after being cleaned to the source data of extraction
Field valence mumber evidence；The data mart modeling layer is entered using cell average price Policy model to disk source data, transaction data and market price data
Row processing, obtains the average price of a certain building, and return correction model using characteristic vector carries out data according to the feature in each house
Correction obtains the average price in a certain house.
2. a kind of room rate assessment system as claimed in claim 1, it is characterised in that the multi-source data is put including what disk visitor was led to
Disk date, the source of houses change valency date, the sale at reduced prices data that disk visitor is led to, Q rooms ERP transaction data, third party's sale at reduced prices data and third party
Transaction data.
3. a kind of room rate assessment system as claimed in claim 1, it is characterised in that the data collection layer uses batch processing frame
Sale at reduced prices data logical to disk visitor frame Spring Batch and Q rooms ERP transaction data are acquired, and are adopted using octopus and train
The mode of storage combination is acquired to third party's sale at reduced prices data and third party transaction data.
4. a kind of room rate assessment system as described in claim 1 or 2 or 3, it is characterised in that the data processing number of plies is to taking out
The detailed process that the source data taken is cleaned is：
1) data reliability rank is set；To market price, true sale data, have official commission book cell offer valency, have it is formal
The confidence levels of certificate of entrustment offer valency and third party's offer valency are arranged as according to order from high to low：The confidence level of market price
>The confidence level of true sale data>There is the confidence level of official commission book cell offer valency>Without the credible of official commission books and newspapers disk valency
Degree>The confidence level of third party's offer valency；
2) (the offer valency-average price of cell transaction in the recent period)/transaction average price in the reasonable data for obtaining step 1)>10% data
Labeled as dirty data；
3) the monovalent and minimum unit price of disk source highest is set for each city, limits rational data area, step 2) is obtained
Reasonable data in data markers outside the data area be dirty data；
4) reasonable data obtained for step 3), operation personnel enter according to system operation flag data to corresponding purchase of property consultant
Row is examined, and data mode is re-flagged；The abnormal data for having follow-up to record is re-flagged；
5) reasonable data obtained for step 4), when data are all concentrated in a kind of data source, gradient clustering method is taken,
With the 5% of each city average price as data gradient, data are further cleaned.
5. a kind of room rate assessment system as described in claim 1 or 2 or 3, it is characterised in that the data mart modeling layer is to Pan Yuan
Data, transaction data and market price data are processed, and the mistake of the average price of a certain building is obtained using cell average price Policy model
Cheng Wei：
Disk source data, transaction data and market price data are judged whether in the gradient scope of setting using gradient comparing method, such as
Fruit then counts the number of data in gradient scope in gradient scope, and the average price of a certain building is calculated using the method for average；
Otherwise, the gradient clustering method of use is handled data again, until data are in gradient scope.
6. a kind of room rate assessment system as described in claim 1 or 2 or 3, it is characterised in that the data mart modeling layer uses more
First linear regression model (LRM) construction feature vector regression correction model, the characteristic vector of structure return correction model and are：
Q=a0+∑aiZi+ ε,
In formula, Q represents the assessment unit price of certain specific set second-hand house, a0The average price of building, a where representing certain set second-hand houseiRepresent two
Feature in the construction characteristic vector in hand room, ZiRepresent adjustment ratio, ε corresponding to each single item feature in the characteristic vector of second-hand house
Other influences factor is represented, it is determined by traffic characteristic, neighbourhood's environment, and traffic characteristic includes public bus network and subway station；Building
Feature includes construction area, place floor, total floor, direction, finishing, supporting and building age；Neighbourhood's environment is matched somebody with somebody including life
Set；Feature a in the characteristic vector of second-hand houseiIncluding age of dwellings, house type, floor, direction, finishing and supporting.
7. a kind of room rate assessment system as described in claim 1 or 2 or 3, it is characterised in that in the room rate assessment system also
It is provided with standard interface layer, applications end obtains certain that the data mart modeling layer obtains by the standard interface layer 5
The average price in one house.
8. a kind of room rate assessment system as described in claim 1 or 2 or 3, it is characterised in that in the room rate assessment system also
Authentication dispatch layer is provided with, the authentication dispatch layer is arranged between the data mart modeling layer and standard interface layer.
9. a kind of room rate assessment system as described in claim 1 or 2 or 3, it is characterised in that in the room rate assessment system also
Distribution GIS and building dictionary basic database are provided with, the cloud source of houses big data platform that Q rooms net is built passes through API
The geography information in Distribution GIS is obtained, the room rate assessment system passes through in building dictionary basic database and GIS
Geography information assess to obtain the room rate in any space.
10. a kind of room rate assessment system as described in claim 1 or 2 or 3, it is characterised in that in the room rate assessment system
School district management information bank is additionally provided with, the cloud source of houses big data platform that Q rooms net is built is combined with school district management information bank, the room
Valency assessment system is assessed to obtain the room rate of the counterpart cell of each school.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710785127.2A CN107705145A (en) | 2017-09-01 | 2017-09-01 | A kind of room rate assessment system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710785127.2A CN107705145A (en) | 2017-09-01 | 2017-09-01 | A kind of room rate assessment system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107705145A true CN107705145A (en) | 2018-02-16 |
Family
ID=61171930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710785127.2A Pending CN107705145A (en) | 2017-09-01 | 2017-09-01 | A kind of room rate assessment system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107705145A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921734A (en) * | 2018-07-18 | 2018-11-30 | 北京航空航天大学 | One real estate information visualization system based on multi-source heterogeneous data |
| CN110097271A (en) * | 2019-04-23 | 2019-08-06 | 杭州中立房地产土地评估规划咨询有限公司 | A kind of Real Estate Appraisal system |
| CN111275489A (en) * | 2020-01-20 | 2020-06-12 | 河南城建学院 | Real estate big data calculation processing method and system |
| TWI739372B (en) * | 2020-04-07 | 2021-09-11 | 中華誠信資產管理顧問股份有限公司 | Real estate comparative price geographic information evaluation method and system |
| CN113988930A (en) * | 2021-10-29 | 2022-01-28 | 重庆汇集源科技有限公司 | Artificial intelligent valuation system for commercial real estate |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101969475A (en) * | 2010-11-15 | 2011-02-09 | 张军 | Business data controllable distribution and fusion application system based on cloud computing |
| CN103607469A (en) * | 2013-11-28 | 2014-02-26 | 东莞中国科学院云计算产业技术创新与育成中心 | Cloud platform for achieving distributed isomerous data sharing and data sharing method thereof |
| CN105321131A (en) * | 2015-11-06 | 2016-02-10 | 厦门均达网络科技有限公司 | Real estate value evaluation system and evaluation method |
| CN106095953A (en) * | 2016-06-13 | 2016-11-09 | 西安数驰信息科技有限公司 | A kind of real estate data integration method based on GIS |
| CN106445986A (en) * | 2016-05-26 | 2017-02-22 | 成都好房通科技股份有限公司 | Method and system used for realizing second-hand housing transaction information industry networking |
-
2017
- 2017-09-01 CN CN201710785127.2A patent/CN107705145A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101969475A (en) * | 2010-11-15 | 2011-02-09 | 张军 | Business data controllable distribution and fusion application system based on cloud computing |
| CN103607469A (en) * | 2013-11-28 | 2014-02-26 | 东莞中国科学院云计算产业技术创新与育成中心 | Cloud platform for achieving distributed isomerous data sharing and data sharing method thereof |
| CN105321131A (en) * | 2015-11-06 | 2016-02-10 | 厦门均达网络科技有限公司 | Real estate value evaluation system and evaluation method |
| CN106445986A (en) * | 2016-05-26 | 2017-02-22 | 成都好房通科技股份有限公司 | Method and system used for realizing second-hand housing transaction information industry networking |
| CN106095953A (en) * | 2016-06-13 | 2016-11-09 | 西安数驰信息科技有限公司 | A kind of real estate data integration method based on GIS |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921734A (en) * | 2018-07-18 | 2018-11-30 | 北京航空航天大学 | One real estate information visualization system based on multi-source heterogeneous data |
| CN110097271A (en) * | 2019-04-23 | 2019-08-06 | 杭州中立房地产土地评估规划咨询有限公司 | A kind of Real Estate Appraisal system |
| CN111275489A (en) * | 2020-01-20 | 2020-06-12 | 河南城建学院 | Real estate big data calculation processing method and system |
| TWI739372B (en) * | 2020-04-07 | 2021-09-11 | 中華誠信資產管理顧問股份有限公司 | Real estate comparative price geographic information evaluation method and system |
| CN113988930A (en) * | 2021-10-29 | 2022-01-28 | 重庆汇集源科技有限公司 | Artificial intelligent valuation system for commercial real estate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107705145A (en) | A kind of room rate assessment system | |
| Bielecki et al. | Impact of the lockdown during the COVID-19 pandemic on electricity use by residential users | |
| Ready et al. | The amenity and disamenity impacts of agriculture: estimates from a hedonic pricing model | |
| Tu et al. | Industrial land use efficiency under government intervention: Evidence from Hangzhou, China | |
| Wu et al. | Impact of urban green space on residential housing prices: Case study in Shenzhen | |
| Alrawi et al. | High-resolution household load profiling and evaluation of rooftop PV systems in selected houses in Qatar | |
| KR101167653B1 (en) | Real estate development business destination positioning system using web-gis and control method thereof | |
| CN105190674A (en) | A method of tracking and reporting energy performance for businesses | |
| JP5414562B2 (en) | Information processing apparatus and information processing system | |
| CN105917337A (en) | Improving designing and installation quoting for solar energy systems | |
| CN106203773A (en) | A kind of method and device of automatic management employee | |
| CN106651277A (en) | Regional logistics information-based network transmission system and data analysis method | |
| JP2002279025A (en) | Method and program for preparing collection/exchange working plan of liquefied petroleum gas cylinder and recording medium | |
| Taminiau et al. | City‐scale urban sustainability: Spatiotemporal mapping of distributed solar power for New York City | |
| CN107679827A (en) | Towards the management platform of ordinarily resident | |
| JP2003022314A (en) | Method, device and program for estimating real estate price function | |
| Ravallion et al. | Breaking up the collective farm: welfare outcomes of Vietnam's massive land privatization | |
| KR102293468B1 (en) | System for providing security-enhanced map based realestate information service | |
| CN106803192A (en) | A kind of supporting impact evaluation method of the environment and surrounding of real estate | |
| JP2013161293A (en) | System, method, and program for providing real estate evaluation information | |
| Ghavidelfar et al. | Evaluating the determinants of high-rise apartment water demand through integration of water consumption, land use and demographic data | |
| Walker et al. | Measuring the performance of social housing organisations in England and the Netherlands: A policy review and research agenda | |
| Sohn | Watering cities: spatial analysis of urban water use in the Southeastern United States | |
| Ghavidelfar et al. | Evaluating spatial and seasonal determinants of residential water demand across different housing types through data integration | |
| TW201935371A (en) | Automatic valuation system for real estate capable of effectively responding to fluctuations in house prices and providing objective valuation results immediately |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180216 |
|
| RJ01 | Rejection of invention patent application after publication |