CN111222921A - Real estate valuation method and system based on integrated thought - Google Patents
Real estate valuation method and system based on integrated thought Download PDFInfo
- Publication number
- CN111222921A CN111222921A CN202010019713.8A CN202010019713A CN111222921A CN 111222921 A CN111222921 A CN 111222921A CN 202010019713 A CN202010019713 A CN 202010019713A CN 111222921 A CN111222921 A CN 111222921A
- Authority
- CN
- China
- Prior art keywords
- price
- cases
- cell
- case
- similar
- 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 129
- 238000011156 evaluation Methods 0.000 claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 238000012937 correction Methods 0.000 claims description 147
- 238000001914 filtration Methods 0.000 claims description 48
- 238000012216 screening Methods 0.000 claims description 37
- 238000009499 grossing Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
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
The invention relates to a real estate valuation method and a system based on an integrated thought, the method integrates a direct method, an indirect method and a proximity method, combines mass historical case data to evaluate the value of a real estate to be estimated, and is implemented specifically as follows: selecting a direct method or an indirect method to calculate the value of the property according to whether the property to be estimated has special factors; if the evaluation result of the direct method or the indirect method is empty, carrying out house property value evaluation calculation according to the proximity method; and if the evaluation result of the direct method or the indirect method is not empty, the evaluation result is used as the value of the property to be evaluated. Meanwhile, the invention discloses a real estate valuation system which comprises a receiving module, an obtaining module, a parameter configuration module, a valuation module and a display module.
Description
Technical Field
The invention relates to a real estate valuation method and a real estate valuation system based on an integrated thought.
Background
At present, the property valuation is mainly carried out by professional evaluators according to personal experience, on one hand, the method has evaluation differences due to different experiences and preferences of the evaluators, and on the other hand, the method needs the evaluators to carefully select reference cases, so that the defects of time and labor waste exist.
Secondly, some selected influence factors in the existing intelligent house property evaluation methods are too complicated to be popularized to each owner, and some evaluation methods depend on case data too much, so that evaluation cannot be performed under the condition of insufficient cases.
Disclosure of Invention
In view of the above problems, it is an object of the present invention to provide a method for real estate valuation based on an integrated thought, and it is another object of the present invention to provide a real estate valuation system based on an integrated thought.
The first technical scheme adopted by the invention for solving the technical problems is as follows:
a real estate valuation method based on integrated thought, comprising:
step 1, acquiring property attribute information input by a user;
step 2, selecting a direct method or an indirect method to evaluate and calculate the value of the property according to whether the property to be evaluated has special factors;
step 3, judging whether the evaluation is finished or not according to the evaluation and the result of the direct method or the indirect method;
step 4, if the evaluation result of the direct method or the indirect method is not empty, the real estate evaluation is finished;
and 5, if the evaluation result of the direct method or the indirect method is empty, evaluating and calculating the property value according to the proximity method.
The property attribute information comprises a property address, a building area, a living room type, a total floor, a building age, an orientation, a house type structure and special factors;
the special factors include:
building king, subway, street, lake, school house, basement, garden with air, semi-underground house and the like;
further, the calculating the value of the property to be estimated according to the direct method includes:
step 1, screening a case with the maximum similarity based on a case screening rule;
step 2, time correction and deal-with-hang-card ratio correction are carried out on the screened similar cases;
and 3, calculating the value of the property to be estimated by using a mean value and peak value algorithm.
Wherein, the case screening rule comprises:
step 1, screening a listing case for a certain time in a cell;
and 2, performing matching screening according to the house type, the room type, the area, the total floor, the house type structure, the orientation, the construction age, special factors and the like.
The time correction includes:
case price x (1+ exponential growth rate) ^ (number of days from case time point to calculation time point/number of days from case time point to exponential termination time point);
the deal-to-hand card-hanging ratio correction comprises the following steps:
listing case price x deal listing ratio
The peak algorithm comprises the following steps:
step 1, carrying out interval discretization on the screened case price;
step 2, counting the case frequency of each interval;
step 3, judging the peak value condition according to the frequency distribution: unimodal, multimodal, unimodal;
step 4, if the distribution is a single peak, performing quantile point calculation according to the highest and lowest prices of the peak sections;
step 5, if the distribution is multi-peak, performing the site calculation according to the maximum number of the five cases, the maximum price and the minimum price of the peak;
and 6, if the distribution is non-peak, performing arithmetic mean calculation according to the case price of the section with the most frequency.
Further, calculating the value of the property to be estimated according to an indirect method, comprising:
step 1, generating a cell standard house according to case data;
step 2, generating a reference price of the standard house of the cell according to a direct method;
step 3, auditing the reference price of the standard house of the cell;
step 4, screening similar standard rooms according to the property of the property to be estimated;
and 5, performing time correction, public correction and special correction on the reference price of the screened standard house according to the property of the house to be estimated.
Wherein the generating of the cell standard room comprises;
step 1, selecting case time participating in calculation;
step 2, screening the type of the living room and the characteristics of the general building generation standard room according to the case data;
step 3, based on the cases, dividing area segments and counting the number of the cases in a segmented manner;
and 4, reserving a standard room according to the number of cases of different area sections.
Wherein, the reference price to standard room is examined and verified, including:
step 1, judging whether a reference price generated according to a direct method is 0;
step 2, if the generated reference price is 0, calculating the reference price of the standard house according to the attribute price model;
step 3, judging whether to adjust the price according to the number of case sources if the generated reference price is not 0;
step 4, if the generated reference price is from a plurality of case sources, adjusting the price according to a weight algorithm;
step 5, if the generated reference price is from a case source, judging whether the reference price is abnormal;
and 6, if the reference price is from one source and is abnormal, calculating the reference price according to the price comparison relation model.
Wherein, the calculating the reference price of the standard house according to the attribute price model comprises the following steps:
step 1, performing attribute discretization processing on case data of a month;
step 2, carrying out grouping statistics on the digits according to the discretized attributes to generate attribute basic prices;
step 3, performing multiple linear regression according to the attribute price data to obtain attribute regression coefficients;
step 4, dividing the regression coefficient of each attribute by a constant term to obtain a correction coefficient of each attribute;
step 5, multiplying the attribute basic price by each attribute correction coefficient to obtain a correction price;
step 6, multiplying the corrected price by the consignment listing ratio to obtain the reference price of the standard house;
wherein the weighting algorithm comprises:
step 1, judging whether the price difference ratio of at least two sources is within 10%;
step 2, if the conditions are met, carrying out weighted average according to the source weight;
and 3, if the condition is not met, continuing to use the original price without price adjustment.
Wherein the calculating the reference price according to the price comparison relation model comprises:
step 1, calculating a correlation coefficient between standard rooms according to prices of the standard rooms in past six months;
step 2, classifying the standard rooms according to the correlation coefficients;
step 3, calculating the ratio of prices of the standard rooms in the same class at each stage, and taking the average of the ratios as the final price ratio of the standard rooms;
and 4, calculating the reference price of the new first period of the standard house according to the price ratio.
Further, calculating the value of the property to be estimated according to a proximity method, including;
step 1, estimating values according to similar cases in a region;
step 2, estimating values according to similar cases in administrative areas;
step 3, estimating values according to similar cases in the city;
and 4, evaluating the case according to the sea-election filter area.
Wherein, the estimating according to the similar cases in the area comprises:
judging whether the cell has the cell average price of the past six months;
if the average price of the cells of six months exists, estimating values according to similar cases of completely similar cells;
if the average price of the cells of nearly six months is lost, estimating the value according to the similar cases of the incompletely similar cells;
and if the average price of the cells does not exist in nearly six months, carrying out estimation on similar cases in the filtering area according to a quartile filtering method.
Wherein, the estimating according to the similar case of the completely similar cell comprises:
step 1, acquiring the cell average price of each cell in a district of nearly six months;
step 2, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
and 5, carrying out weighted average on the corrected cases according to the source weight.
The trend similarity is a correlation coefficient of the average price of the past six months of the two cells;
the price similarity is the closeness of the average price of the past six months of the two cells;
the case similarity is the proportion of the same characteristic values of the two samples;
the time correction is to correct the past price level to the current month according to the trend;
the public correction is to correct the price according to a public correction coefficient and an attribute value;
wherein, according to the similar case estimation value according to the incomplete similar cell, the method comprises the following steps:
step 1, acquiring the cell average price of each cell in a district of nearly six months;
step 2, calculating the average price difference ratio of each month of each cell and the cell where the house property to be estimated is located, and locking similar cells with the price difference ratio within 5%;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
and 5, carrying out weighted average on the corrected cases according to the source weight.
The average price difference ratio is the ratio of the average price difference of two cells in the same month;
the case similarity is the same as above, and is not described herein again;
the time correction and the public correction are the same as above, and are not described again;
wherein, similar cases in the filtering area are evaluated according to a quartile filtering method, including;
step 1, calculating the case similarity between all cases in a parcel and a real estate to be estimated;
step 2, screening similar cases according to a threshold value;
step 3, time correction and public correction are carried out on the screened similar cases
Step 4, reserving 50% of cases in the middle according to a quartile filtering method;
and 5, carrying out weighted average on the corrected cases according to the source weight.
The case similarity is the same as above, and is not described herein again;
the time correction and the public correction are the same as above, and are not described again;
the quartile filtering method comprises the following steps:
step 1, calculating a first quartile and a third quartile;
and 2, screening cases with case prices more than or equal to the first quartile and less than or equal to the third quartile.
The quartile is a set of values at 25% and 75% of the positions after data sorting, and is calculated as follows:
position of the first quartile: (n + 1). times.0.25
Position of the third quartile: (n + 1). times.0.75
Wherein, the estimating according to similar cases in administrative districts comprises the following steps:
judging whether the cell has the cell average price of the past six months;
if the average price of the cells of six months exists, estimating values according to similar cases of completely similar cells;
if the average price of the cells of nearly six months is lost, estimating the value according to the similar cases of the incompletely similar cells;
if the average price of the district does not exist in nearly six months, filtering similar cases in the administrative district according to a quartile filtering method to estimate the value
Wherein, the estimating according to the similar case of the completely similar cell comprises:
step 1, acquiring the average price of each cell in other districts in an administrative district, wherein the average price of each cell is nearly six months;
step 2, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
and 5, carrying out weighted average on the corrected cases according to the source weight.
The trend similarity, the price similarity, the case similarity, the time correction and the public correction are the same as above, and are not repeated here;
wherein the similar case estimation according to the incomplete similar cell comprises:
step 1, acquiring the average price of each cell in other districts in an administrative district, wherein the average price of each cell is nearly six months;
step 2, calculating the average price difference ratio of each month of each cell and the cell where the house property to be estimated is located, and locking similar cells with the price difference ratio within 5%;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
and 5, carrying out weighted average on the corrected cases according to the source weight.
The average price-price difference ratio, case similarity, time correction and public correction are the same as above, and are not described again here;
wherein, similar cases in the administrative region are filtered according to a quartile filtering method for evaluation, including;
step 1, calculating the case similarity between all cases of other districts in the administrative district and the house property to be estimated;
step 2, screening similar cases according to a threshold value;
step 3, time correction and public correction are carried out on the screened similar cases
Step 4, reserving 50% of cases in the middle according to a quartile filtering method;
and 5, carrying out weighted average on the corrected cases according to the source weight.
The case similarity, time correction, public correction and quartile filtering method are the same as above, and are not described herein again;
wherein, the estimating according to similar cases in city comprises:
judging whether the cell has the cell average price of the past six months;
if the cell average price of six months exists and similar cases exist, estimating values according to the similar cases of the completely similar cells;
if the cell average price of six months does not have similar cases, correcting the evaluation value according to the cell average price;
wherein, the estimating according to the similar case of the completely similar cell comprises:
step 1, acquiring the average price of each cell in other districts in an administrative district, wherein the average price of each cell is nearly six months;
step 2, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
and 5, carrying out weighted average on the corrected cases according to the source weight.
The trend similarity, the price similarity, the case similarity, the time correction and the public correction are the same as above, and are not repeated here;
wherein, the correcting the estimated value according to the cell average price comprises the following steps:
step 1, predicting average price of the current-month cell according to a one-time exponential smoothing method;
and 2, carrying out public correction and special correction on the average price of the current-month cell.
The calculation formula of the first exponential smoothing method is as follows:
F(t)＝alpha*X(t-1)+(1-alpha)*F(t-1)
wherein, alpha is a smoothing coefficient, F (t-1) is a predicted value of a t-1 period, F (t) is a predicted value of the t period, and X (t-1) is a true value of the t-1 period;
the public correction is the same as above, and is not described again here;
the special correction is to multiply a special correction coefficient according to a special factor;
wherein, the estimating according to the case of the sea film selecting area comprises the following steps:
step 1, judging whether the case data of the cell in about three months is more than 10;
step 2, if the number of the cases in the neighborhood of three months is more than 10, filtering the cases in the neighborhood of three months according to a quartile filtering method to estimate values;
step 3, if the number of the cases in the region is less than or equal to 10, estimating the value according to the cases in the same area section;
step 4, if no case exists in the cell in about March, judging whether more than 10 cases exist in the cell in about March;
step 5, if the number of the cases in the near-March area is more than 10, filtering the cases in the near-March area for evaluation according to a quartile filtering method;
step 6, if the number of the cases in the similar March area is less than or equal to 10, estimating according to the cases in the same area section;
and 7, if no case exists in the district in March, correcting the valuation according to the average price of the administrative district or the city.
The quartile filtering method is the same as above, and is not described herein again;
the estimating according to the case rooms of the same area segment comprises the following steps:
step 1, screening cases in the same area segment with a real estate to be estimated;
step 2, time correction and public correction are carried out on the screened cases;
and 3, carrying out weighted average on the cases according to the source weight.
The correcting of the estimated value according to the average price of the administrative district or the city comprises the following steps:
step 1, forecasting the average price of the administrative region or the city in the current month according to a one-time exponential smoothing method;
and 2, carrying out public correction and special correction on the average price of the administrative region or the city in the current month.
The second technical scheme adopted by the invention for solving the technical problems is as follows:
an integrated idea based property valuation system, comprising:
the receiving module is used for receiving the attribute information of the property to be estimated, which is sent by the user terminal;
the acquisition module is used for acquiring case data and property average price information according to the property of the property to be estimated;
the parameter configuration module is used for configuring parameter information related in the management model;
the valuation module is used for calculating the value of the property to be estimated according to the case data and the property average price information;
the display module is used for displaying the house property evaluation result information and the reference information;
wherein the obtaining module is further configured to:
acquiring longitude and latitude information of the parcel and administrative district according to the house address;
the parameter configuration module is further configured to:
screening and calculating parameters and relevant correction coefficients and other information by the configuration case;
the display module is further configured to:
displaying the geographical position information of the real estate;
the property attribute information includes:
house address, building area, floor information, building age, room type, house type structure, orientation, special factors and the like;
the property case information includes:
house address, building area, floor information, building age, room type, house type structure, orientation, special factors, listing time and other characteristics;
the property average price information comprises:
information such as time, city name, administrative district name, district average price, administrative district average price, city average price and the like
The parameter information includes:
case screening parameters, case calculation parameters, film area management parameters, correction system parameters and the like;
the reference information includes:
reference case, cell details, cell average price, administrative district average price, city average price and the like.
Compared with the prior art, the invention has the beneficial effects that: the invention integrates the advantages of the direct method, the indirect method and the proximity method, supplements each other, and makes the real estate assessment more intelligent, scientific and objective. Meanwhile, the defect that the existing assessment method excessively depends on case data is overcome, and very important application value is provided for house property assessment. The method is based on the latest case data, combines the average price of the residential area, the administrative area and the city for trend correction, provides a more accurate reference case for real estate valuation, avoids the influence of subjective factors, and reflects the current market situation more objectively and truly.
Drawings
FIG. 1 is a flow chart of a property valuation method based on an integrated idea of the present invention;
FIG. 2 is a flow chart of the present invention for real estate valuation based on the direct method;
FIG. 3 is a flow chart of the indirect-based property valuation process of the present invention;
FIG. 4 is a flow chart of the proximity-based property valuation process of the present invention;
fig. 5 is a structural framework diagram of the property valuation system based on the integrated idea of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a real estate valuation method based on an integrated thought, and the method comprises the following concrete implementation steps with reference to fig. 1-5:
s1, acquiring property attribute information input by a user;
s2, selecting a direct method or an indirect method to evaluate the value of the property according to whether the property to be evaluated has special factors;
s3, judging whether the evaluation is finished according to the evaluation and the result of the direct method or the indirect method;
s4, if the evaluation result of the direct method or the indirect method is not empty, the property evaluation is finished;
s5, if the evaluation result of the direct method or the indirect method is empty, carrying out house property value evaluation according to the proximity method;
in S1, property attribute information input by the user may be acquired through a website or an API interface;
wherein the property attribute information includes:
house address, building area, room type, total floor, building year, orientation, house type structure and special factors;
in S2, selecting a direct method or an indirect method to evaluate the value of the property according to whether the property to be evaluated has special factors, and specifically implementing the method as follows:
s2.1, obtaining values of special house property factors;
s2.2, if the property special factor to be estimated is not null, estimating the property value according to an indirect method;
s2.3, if the special attribute factors of the house to be estimated are null, evaluating the value of the house property according to the direct method;
the special factors include:
building king, subway, street, lake, school house, basement, garden with air, semi-underground house and the like;
in S2.3, the value of the property to be estimated is calculated according to the direct method, with reference to fig. 2, the specific implementation steps are as follows:
s2.3.1, screening the case with the maximum case similarity based on the case screening rule;
s2.3.2, correcting time and cross-listing ratio of the screened similar cases;
s2.3.3, calculating the value of the property to be estimated by using a mean value and peak value algorithm;
the case screening rule is specifically implemented as follows:
s01, screening a listing case for a certain time in the cell;
s02, matching and screening according to the house type, the living room type, the area, the total floor, the house type structure, the orientation, the construction age, special factors and the like;
the time correction and the deal-to-deal listing ratio correction are specifically implemented as follows:
time correction: case price x (1+ exponential growth rate) ^ (number of days from case time point to calculation time point/number of days from case time point to exponential termination time point);
correcting the card-handing ratio: listing case price x deal listing ratio
The peak value algorithm is implemented as follows:
s01, carrying out interval discretization on the screened case prices;
s02, counting the case frequency of each section;
s03, judging the peak condition according to the frequency distribution: unimodal, multimodal, unimodal;
s04, if the distribution is a single peak, calculating the quantile point according to the highest and lowest prices of the peak section;
s05, if the distribution is multi-peak, performing the site calculation according to the maximum number of the five cases, the maximum price and the minimum price of the peak;
s06, if the distribution is no peak, carrying out arithmetic mean calculation according to the case price of the section with the most frequency;
in S2.3, the value of the property to be estimated is calculated according to an indirect method, which is specifically implemented as follows with reference to fig. 3:
s2.3.1, generating a cell standard house according to the case data;
s2.3.2, generating a reference price of the standard cell according to the direct method;
s2.3.3, auditing the reference price of the standard house of the cell;
s2.3.4, screening similar standard rooms according to the property of the property to be estimated;
s2.3.5, performing time correction, public correction and special correction on the reference price of the screened standard house according to the property of the house to be estimated;
wherein, the generation of the cell standard house is implemented specifically as follows;
s01, selecting case time participating in calculation;
s02, screening the types of living rooms and the characteristics of the general floors to generate standard rooms according to the case data;
s03, dividing area segments based on the cases, and counting the number of the cases in a segmented manner;
s04, reserving a standard room according to the number of cases of different area sections;
wherein, the reference price of the standard house is audited, and the specific implementation is as follows:
s01, judging whether the reference price generated by the direct method is 0;
s02, if the generated reference price is 0, calculating the reference price of the standard house according to the attribute price model;
s03, if the generated reference price is not 0, judging whether to adjust the price according to the number of case sources;
s04, if the generated reference price is from a plurality of case sources, carrying out price adjustment according to a weight algorithm;
s05, if the generated reference price is from a case source, judging whether the reference price is abnormal;
s06, if the reference price is from one source and is abnormal, calculating the reference price according to the price comparison relation model;
the standard price of the standard house is calculated according to the attribute price model, and the method is implemented specifically as follows:
s01, performing attribute discretization processing on the case data of the last month;
s02, performing grouping statistics on the digits according to the discretized attributes to generate attribute basic prices;
s03, performing multiple linear regression according to the attribute price data to obtain attribute regression coefficients;
s04, dividing the attribute regression coefficient by a constant term to obtain an attribute correction coefficient;
s05, obtaining a corrected price by multiplying the attribute basic price by each attribute correction coefficient;
s06, multiplying the corrected price by the cross-hang plate ratio to obtain the reference price of the standard house;
the weighting algorithm is specifically implemented as follows:
s01, judging whether the price difference ratio of at least two sources is within 10%;
s02, if the condition is met, carrying out weighted average according to the source weight;
s03, if the condition is not met, continuing to use the original price without price adjustment;
wherein the calculating the reference price according to the price comparison relation model comprises:
s01, calculating a correlation coefficient between the standard rooms according to the prices of the standard rooms in the past six months;
s02, classifying the standard rooms according to the correlation coefficients;
s03, calculating the ratio of prices of the standard rooms in the same class at each stage, and taking the average of the ratios as the final price ratio of the standard rooms;
s04, calculating the reference price of the standard house in the new period according to the price ratio;
in the step S5, the value of the property to be estimated is calculated according to the proximity method, and the calculation is specifically implemented;
s5.1, estimating values according to similar cases in the areas;
s5.2, estimating values according to similar cases in administrative areas;
s5.3, estimating values according to similar cases in the city;
and S5.4, case evaluation is conducted according to the sea election filter area.
Wherein, the estimation according to the similar cases in the area is implemented as follows:
s5.1.1, judging whether the cell has the cell average price of the past six months;
s5.1.2, if there is a cell average price of six months, then carrying out estimation according to the similar case of the completely similar cell;
s5.1.3, if the average price of the cells in about six months is missing, estimating according to the similar cases of the incompletely similar cells;
s5.1.4, if there is no average price in the cell in about six months, then estimating the value according to the similar cases in the filtering area of the quartile filtering method;
wherein, the estimation is performed according to the similar case of the completely similar cell, and the specific implementation is as follows:
s01, acquiring the cell average price of each cell in the parcel in about six months;
s02, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
s03, locking similar cases in similar cells according to case similarity;
s04, carrying out time correction and public correction on the similar cases;
and S05, carrying out weighted average on the corrected cases according to the source weight.
The trend similarity is a correlation coefficient of the average price of the past six months of the two cells;
the price similarity is the closeness of the average price of the past six months of the two cells;
the case similarity is the proportion of the same characteristic values of the two samples;
the time correction is to correct the past price level to the current month according to the trend;
the public correction is to correct the price according to a public correction coefficient and an attribute value;
wherein, according to the similar case estimation value of the incomplete similar cell, the specific implementation is as follows:
s01, acquiring the cell average price of each cell in the parcel in about six months;
s02, calculating the average price difference ratio of each month of each cell and the cell where the real estate to be estimated is located, and locking similar cells with the price difference ratio within 5%;
s03, locking similar cases in similar cells according to case similarity;
s04, carrying out time correction and public correction on the similar cases;
and S05, carrying out weighted average on the corrected cases according to the source weight.
The average price difference ratio is the ratio of the average price difference of two cells in the same month;
the case similarity is the same as above, and is not described herein again;
the time correction and the public correction are the same as above, and are not described again;
wherein, similar cases in the filtering area are evaluated according to a quartile filtering method, and the method is specifically implemented as follows;
s01, calculating the similarity of all cases in the area and the cases of the property to be estimated;
s02, screening similar cases according to a threshold value;
s03, time correction and public correction are carried out on the similar cases which are screened
S04, reserving 50% of cases in the middle according to a quartile filtering method;
and S05, carrying out weighted average on the corrected cases according to the source weight.
The case similarity is the same as above, and is not described herein again;
the time correction and the public correction are the same as above, and are not described again;
the quartile filtering method is specifically implemented as follows:
s01, calculating a first quartile and a third quartile;
s02, screening cases with case prices more than or equal to the first quartile and less than or equal to the third quartile;
the quartile is a set of values at 25% and 75% of the positions after data sorting, and is calculated as follows:
position of the first quartile: (n + 1). times.0.25
Position of the third quartile: (n + 1). times.0.75
According to similar case evaluation in administrative districts, the method is specifically implemented as follows:
s5.2.1, judging whether the cell has the cell average price of the past six months;
s5.2.2, if there is a cell average price of six months, then carrying out estimation according to the similar case of the completely similar cell;
s5.2.3, if the average price of the cells in about six months is missing, estimating according to the similar cases of the incompletely similar cells;
s5.2.4, if no district average price exists in nearly six months, filtering similar cases in the administrative district according to a quartile filtering method to estimate the value;
wherein, the estimation is performed according to the similar case of the completely similar cell, and the specific implementation is as follows:
s01, acquiring the average price of the cells in the administrative district in about six months in each of the other districts;
s02, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
s03, locking similar cases in similar cells according to case similarity;
s04, carrying out time correction and public correction on the similar cases;
and S05, carrying out weighted average on the corrected cases according to the source weight.
The trend similarity, the price similarity, the case similarity, the time correction and the public correction are the same as above, and are not repeated here;
wherein, according to the similar case estimation value according to the incomplete similar cell, the specific implementation is as follows:
s01, acquiring the average price of the cells in the administrative district in about six months in each of the other districts;
s02, calculating the average price difference ratio of each month of each cell and the cell where the real estate to be estimated is located, and locking similar cells with the price difference ratio within 5%;
s03, locking similar cases in similar cells according to case similarity;
s04, carrying out time correction and public correction on the similar cases;
and S05, carrying out weighted average on the corrected cases according to the source weight.
The average price-price difference ratio, case similarity, time correction and public correction are the same as above, and are not described again here;
wherein, similar cases in the administrative region are filtered according to a quartile filtering method for evaluation, and the method is specifically implemented as follows;
s01, calculating the similarity of all cases of other districts in the administrative district and the cases of the property to be estimated;
s02, screening similar cases according to a threshold value;
s03, time correction and public correction are carried out on the similar cases which are screened
S04, reserving 50% of cases in the middle according to a quartile filtering method;
and S05, carrying out weighted average on the corrected cases according to the source weight.
The case similarity, time correction, public correction and quartile filtering method are the same as above, and are not described herein again;
wherein, the estimating according to similar cases in the city is implemented as follows:
s5.3.1, judging whether the cell has a cell average price of the past six months;
s5.3.2, if the average price of the cell of six months exists and similar cases exist, carrying out estimation according to the similar cases of the completely similar cell;
s5.3.3, if there is a six-month cell average price but there is no similar case, correcting the estimation value according to the cell average price;
wherein, the estimation is performed according to the similar case of the completely similar cell, and the specific implementation is as follows:
s01, acquiring the average price of the cells in the administrative district in about six months in each of the other districts;
s02, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
s03, locking similar cases in similar cells according to case similarity;
s04, carrying out time correction and public correction on the similar cases;
and S05, carrying out weighted average on the corrected cases according to the source weight.
The trend similarity, the price similarity, the case similarity, the time correction and the public correction are the same as above, and are not repeated here;
wherein, the correcting the estimated value according to the cell average price is implemented as follows:
s01, predicting the average price of the current-month cell according to a one-time exponential smoothing method;
s02, carrying out public correction and special correction on the average price of the current month cell;
the calculation formula of the first exponential smoothing method is as follows:
F(t)＝alpha*X(t-1)+(1-alpha)*F(t-1)
wherein, alpha is a smoothing coefficient, F (t-1) is a predicted value of a t-1 period, F (t) is a predicted value of the t period, and X (t-1) is a true value of the t-1 period;
the public correction is the same as above, and is not described again here;
the special correction is to multiply a special correction coefficient according to a special factor;
wherein, the estimating according to the case of the sea film selecting area is implemented as follows:
s5.4.1, judging whether the case data of the cell in about three months is more than 10;
s5.4.2, if the number of cases in the neighborhood is more than 10, filtering the cases in the neighborhood for three months according to a quartile filtering method to estimate the value;
s5.4.3, if the number of cases in the region is less than or equal to 10, carrying out estimation according to the cases in the same area segment;
s5.4.4, if there are no cases in the region, judging whether there are more than 10 cases in the region;
s5.4.5, if the number of the cases in the near-March area is more than 10, filtering the cases in the near-March area for evaluation according to a quartile filtering method;
s5.4.6, if the number of the cases in the near March area is less than or equal to 10, carrying out estimation according to the cases in the same area segment;
s5.4.7, if there is no case in the district, correcting the valuation according to the average price of the administrative district or the city;
the quartile filtering method is the same as above, and is not described herein again; step (ii) of
The estimation is carried out according to the cases of the same area segment, and the specific implementation is as follows:
s01, screening cases in the same area segment with the property to be estimated;
s02, carrying out time correction and public correction on the screened cases;
and S03, carrying out weighted average on the cases according to the source weight.
The correcting of the estimated value according to the average price of the administrative district or the city comprises the following steps:
s01, forecasting the average price of the administrative district or the city in the current month according to a one-time exponential smoothing method;
and S02, carrying out public correction and special correction on the average price of the current administrative district or city.
The present invention is not limited to the embodiments described above, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are included in the scope defined by the claims of the present application.
Claims (5)
1. A real estate valuation method based on integrated thought, comprising:
step 1, acquiring property attribute information input by a user;
step 2, selecting a direct method or an indirect method to evaluate and calculate the value of the property according to whether the property to be evaluated has special factors;
step 3, judging whether the evaluation is finished or not according to the evaluation and the result of the direct method or the indirect method;
step 4, if the evaluation result of the direct method or the indirect method is not empty, the real estate evaluation is finished;
step 5, if the evaluation result of the direct method or the indirect method is empty, carrying out house property value evaluation calculation according to the proximity method;
the property attribute information comprises a property address, a building area, a living room type, a total floor, a building age, an orientation, a house type structure and special factors;
the special factors include:
building king, subway, street, lake, school house, basement, garden with air, semi-underground house and the like.
2. The method of claim 1, wherein calculating the value of the property to be estimated according to direct methods comprises:
step 1, screening a case with the maximum similarity based on a case screening rule;
step 2, time correction and deal-with-hang-card ratio correction are carried out on the screened similar cases;
step 3, calculating the value of the property to be estimated by using a mean value and peak value algorithm;
wherein, the case screening rule comprises:
step 1, screening a listing case for a certain time in a cell;
step 2, matching and screening according to the house type, the room type, the area, the total floor, the house type structure, the orientation, the construction age, special factors and the like;
the time correction includes:
case price x (1+ exponential growth rate) ^ (number of days from case time point to calculation time point/number of days from case time point to exponential termination time point);
the deal-to-hand card-hanging ratio correction comprises the following steps:
the price of the card-hanging case is multiplied by the card-hanging ratio of the deal;
the peak algorithm comprises the following steps:
step 1, carrying out interval discretization on the screened case price;
step 2, counting the case frequency of each interval;
step 3, judging the peak value condition according to the frequency distribution: unimodal, multimodal, unimodal;
step 4, if the distribution is a single peak, performing quantile point calculation according to the highest and lowest prices of the peak sections;
step 5, if the distribution is multi-peak, performing the site calculation according to the maximum number of the five cases, the maximum price and the minimum price of the peak;
and 6, if the distribution is non-peak, performing arithmetic mean calculation according to the case price of the section with the most frequency.
3. The method of claim 1, wherein calculating the value of the property to be estimated according to an indirect method comprises:
step 1, generating a cell standard house according to case data;
step 2, generating a reference price of the standard house of the cell according to a direct method;
step 3, auditing the reference price of the standard house of the cell;
step 4, screening similar standard rooms according to the property of the property to be estimated;
step 5, performing time correction, public correction and special correction on the reference price of the screened standard house according to the property of the house to be estimated;
wherein the generating of the cell standard room comprises;
step 1, selecting case time participating in calculation;
step 2, screening the type of the living room and the characteristics of the general building generation standard room according to the case data;
step 3, based on the cases, dividing area segments and counting the number of the cases in a segmented manner;
step 4, reserving a standard room according to the number of cases of different area sections;
wherein, the reference price to standard room is examined and verified, including:
step 1, judging whether a reference price generated according to a direct method is 0;
step 2, if the generated reference price is 0, calculating the reference price of the standard house according to the attribute price model;
step 3, judging whether to adjust the price according to the number of case sources if the generated reference price is not 0;
step 4, if the generated reference price is from a plurality of case sources, adjusting the price according to a weight algorithm;
step 5, if the generated reference price is from a case source, judging whether the reference price is abnormal;
step 6, if the reference price is from one source and is abnormal, calculating the reference price according to the price comparison relation model;
wherein, the calculating the reference price of the standard house according to the attribute price model comprises the following steps:
step 1, performing attribute discretization processing on case data of a month;
step 2, carrying out grouping statistics on the digits according to the discretized attributes to generate attribute basic prices;
step 3, performing multiple linear regression according to the attribute price data to obtain attribute regression coefficients;
step 4, dividing the regression coefficient of each attribute by a constant term to obtain a correction coefficient of each attribute;
step 5, multiplying the attribute basic price by each attribute correction coefficient to obtain a correction price;
step 6, multiplying the corrected price by the consignment listing ratio to obtain the reference price of the standard house;
wherein the weighting algorithm comprises:
step 1, judging whether the price difference ratio of at least two sources is within 10%;
step 2, if the conditions are met, carrying out weighted average according to the source weight;
step 3, if the condition is not met, continuing to use the original price without price adjustment;
wherein the calculating the reference price according to the price comparison relation model comprises:
step 1, calculating a correlation coefficient between standard rooms according to prices of the standard rooms in past six months;
step 2, classifying the standard rooms according to the correlation coefficients;
step 3, calculating the ratio of prices of the standard rooms in the same class at each stage, and taking the average of the ratios as the final price ratio of the standard rooms;
and 4, calculating the reference price of the new first period of the standard house according to the price ratio.
4. The method of claim 1, wherein said calculating a value of a property to be estimated according to a proximity method comprises;
step 1, estimating values according to similar cases in a region;
step 2, estimating values according to similar cases in administrative areas;
step 3, estimating values according to similar cases in the city;
step 4, evaluating the case value according to the sea-election filter area;
wherein, the estimating according to the similar cases in the area comprises:
judging whether the cell has the cell average price of the past six months;
if the average price of the cells of six months exists, estimating values according to similar cases of completely similar cells;
if the average price of the cells of nearly six months is lost, estimating the value according to the similar cases of the incompletely similar cells;
if the average price of the cells does not exist in nearly six months, carrying out valuation on similar cases in the filtering area according to a quartile filtering method;
wherein, the estimating according to the similar case of the completely similar cell comprises:
step 1, acquiring the cell average price of each cell in a district of nearly six months;
step 2, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
step 5, carrying out weighted average on the corrected cases according to the source weight;
the trend similarity is a correlation coefficient of the average price of the past six months of the two cells;
the price similarity is the closeness of the average price of the past six months of the two cells;
the case similarity is the proportion of the same characteristic values of the two samples;
the time correction is to correct the past price level to the current month according to the trend;
the public correction is to correct the price according to a public correction coefficient and an attribute value;
wherein, according to the similar case estimation value according to the incomplete similar cell, the method comprises the following steps:
step 1, acquiring the cell average price of each cell in a district of nearly six months;
step 2, calculating the average price difference ratio of each month of each cell and the cell where the house property to be estimated is located, and locking similar cells with the price difference ratio within 5%;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
step 5, carrying out weighted average on the corrected cases according to the source weight;
the average price difference ratio is the ratio of the average price difference of two cells in the same month;
the case similarity is the same as above, and is not described herein again;
the time correction and the public correction are the same as above, and are not described again;
wherein, similar cases in the filtering area are evaluated according to a quartile filtering method, including;
step 1, calculating the case similarity between all cases in a parcel and a real estate to be estimated;
step 2, screening similar cases according to a threshold value;
step 3, time correction and public correction are carried out on the screened similar cases;
step 4, reserving 50% of cases in the middle according to a quartile filtering method;
step 5, carrying out weighted average on the corrected cases according to the source weight;
the case similarity is the same as above, and is not described herein again;
the time correction and the public correction are the same as above, and are not described again;
the quartile filtering method comprises the following steps:
step 1, calculating a first quartile and a third quartile;
step 2, screening cases with case prices more than or equal to the first quartile and less than or equal to the third quartile;
the quartile is a set of values at 25% and 75% of the positions after data sorting, and is calculated as follows:
position of the first quartile: (n + 1). times.0.25
Position of the third quartile: (n + 1). times.0.75
Wherein, the estimating according to similar cases in administrative districts comprises the following steps:
judging whether the cell has the cell average price of the past six months;
if the average price of the cells of six months exists, estimating values according to similar cases of completely similar cells;
if the average price of the cells of nearly six months is lost, estimating the value according to the similar cases of the incompletely similar cells;
if the average price of the district does not exist in nearly six months, filtering similar cases in the administrative district according to a quartile filtering method to estimate the value;
wherein, the estimating according to the similar case of the completely similar cell comprises:
step 1, acquiring the average price of each cell in other districts in an administrative district, wherein the average price of each cell is nearly six months;
step 2, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
step 5, carrying out weighted average on the corrected cases according to the source weight;
the trend similarity, the price similarity, the case similarity, the time correction and the public correction are the same as above, and are not repeated here;
wherein the similar case estimation according to the incomplete similar cell comprises:
step 1, acquiring the average price of each cell in other districts in an administrative district, wherein the average price of each cell is nearly six months;
step 2, calculating the average price difference ratio of each month of each cell and the cell where the house property to be estimated is located, and locking similar cells with the price difference ratio within 5%;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
step 5, carrying out weighted average on the corrected cases according to the source weight;
the average price-price difference ratio, case similarity, time correction and public correction are the same as above, and are not described again here;
wherein, similar cases in the administrative region are filtered according to a quartile filtering method for evaluation, including;
step 1, calculating the case similarity between all cases of other districts in the administrative district and the house property to be estimated;
step 2, screening similar cases according to a threshold value;
step 3, time correction and public correction are carried out on the screened similar cases
Step 4, reserving 50% of cases in the middle according to a quartile filtering method;
step 5, carrying out weighted average on the corrected cases according to the source weight;
the case similarity, time correction, public correction and quartile filtering method are the same as above, and are not described herein again;
wherein, the estimating according to similar cases in city comprises:
judging whether the cell has the cell average price of the past six months;
if the cell average price of six months exists and similar cases exist, estimating values according to the similar cases of the completely similar cells;
if the cell average price of six months does not have similar cases, correcting the evaluation value according to the cell average price;
wherein, the estimating according to the similar case of the completely similar cell comprises:
step 1, acquiring the average price of each cell in other districts in an administrative district, wherein the average price of each cell is nearly six months;
step 2, calculating the trend similarity and the price similarity of each cell and the cell where the house property to be estimated is located, and locking the similar cells;
step 3, locking similar cases in similar cells according to case similarity;
step 4, time correction and public correction are carried out on the similar cases;
step 5, carrying out weighted average on the corrected cases according to the source weight;
the trend similarity, the price similarity, the case similarity, the time correction and the public correction are the same as above, and are not repeated here;
wherein, the correcting the estimated value according to the cell average price comprises the following steps:
step 1, predicting average price of the current-month cell according to a one-time exponential smoothing method;
step 2, carrying out public correction and special correction on the average price of the current month cell;
the calculation formula of the first exponential smoothing method is as follows:
F(t)＝alpha*X(t-1)+(1-alpha)*F(t-1)
wherein, alpha is a smoothing coefficient, F (t-1) is a predicted value of a t-1 period, F (t) is a predicted value of the t period, and X (t-1) is a true value of the t-1 period;
the public correction is the same as above, and is not described again here;
the special correction is to multiply a special correction coefficient according to a special factor;
wherein, the estimating according to the case of the sea film selecting area comprises the following steps:
step 1, judging whether the case data of the cell in about three months is more than 10;
step 2, if the number of the cases in the neighborhood of three months is more than 10, filtering the cases in the neighborhood of three months according to a quartile filtering method to estimate values;
step 3, if the number of the cases in the region is less than or equal to 10, estimating the value according to the cases in the same area section;
step 4, if no case exists in the cell in about March, judging whether more than 10 cases exist in the cell in about March;
step 5, if the number of the cases in the near-March area is more than 10, filtering the cases in the near-March area for evaluation according to a quartile filtering method;
step 6, if the number of the cases in the similar March area is less than or equal to 10, estimating according to the cases in the same area section;
step 7, if no case exists in the district in March, correcting the valuation according to the average price of the administrative district or the city;
the quartile filtering method is the same as above, and is not described herein again;
the estimating according to the case rooms of the same area segment comprises the following steps:
step 1, screening cases in the same area segment with a real estate to be estimated;
step 2, time correction and public correction are carried out on the screened cases;
and 3, carrying out weighted average on the cases according to the source weight.
The correcting of the estimated value according to the average price of the administrative district or the city comprises the following steps:
step 1, forecasting the average price of the administrative region or the city in the current month according to a one-time exponential smoothing method;
and 2, carrying out public correction and special correction on the average price of the administrative region or the city in the current month.
5. An integrated idea based property valuation system, comprising:
the receiving module is used for receiving the attribute information of the property to be estimated, which is sent by the user terminal;
the acquisition module is used for acquiring case data and property average price information according to the property of the property to be estimated;
the parameter configuration module is used for configuring parameter information related in the management model;
the valuation module is used for calculating the value of the property to be estimated according to the case data and the property average price information;
the display module is used for displaying the house property evaluation result information and the reference information;
wherein the obtaining module is further configured to:
acquiring longitude and latitude information of the parcel and administrative district according to the house address;
the parameter configuration module is further configured to:
screening and calculating parameters and relevant correction coefficients and other information by the configuration case;
the display module is further configured to:
displaying the geographical position information of the real estate;
the property attribute information includes:
house address, building area, floor information, building age, room type, house type structure, orientation, special factors and the like;
the property case information includes:
house address, building area, floor information, building age, room type, house type structure, orientation, special factors, listing time and other characteristics;
the property average price information comprises:
information such as time, city name, administrative district name, district average price, administrative district average price, city average price and the like;
the parameter information includes:
case screening parameters, case calculation parameters, film area management parameters, correction system parameters and the like;
the reference information includes:
reference case, cell details, cell average price, administrative district average price, city average price and the like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010019713.8A CN111222921A (en) | 2020-01-08 | 2020-01-08 | Real estate valuation method and system based on integrated thought |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010019713.8A CN111222921A (en) | 2020-01-08 | 2020-01-08 | Real estate valuation method and system based on integrated thought |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111222921A true CN111222921A (en) | 2020-06-02 |
Family
ID=70832244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010019713.8A Pending CN111222921A (en) | 2020-01-08 | 2020-01-08 | Real estate valuation method and system based on integrated thought |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222921A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738831A (en) * | 2020-06-19 | 2020-10-02 | 中国建设银行股份有限公司 | Service processing method, device and system |
| CN113988641A (en) * | 2021-10-29 | 2022-01-28 | 重庆汇集源科技有限公司 | Automatic valuation system for residential real estate |
-
2020
- 2020-01-08 CN CN202010019713.8A patent/CN111222921A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738831A (en) * | 2020-06-19 | 2020-10-02 | 中国建设银行股份有限公司 | Service processing method, device and system |
| CN113988641A (en) * | 2021-10-29 | 2022-01-28 | 重庆汇集源科技有限公司 | Automatic valuation system for residential real estate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rozenfeld et al. | The area and population of cities: New insights from a different perspective on cities | |
| US20140164260A1 (en) | Systems and methods for selecting comparable real estate properties | |
| CN111222921A (en) | Real estate valuation method and system based on integrated thought | |
| CN108416630A (en) | A kind of determination method and device of target audience | |
| US11093982B1 (en) | Determine regional rate of return on home improvements | |
| CN116502755A (en) | System and method for industrial development prediction by constructing industrial map by adopting big data | |
| EP2427863A1 (en) | System for generating a housing price index | |
| CN110633401A (en) | Prediction model of store data and establishment method thereof | |
| TW201514902A (en) | Integrated computing valuation system on information of real value registry on real estate and method thereof | |
| CN108647189B (en) | Method and device for identifying user crowd attributes | |
| CN110717668A (en) | Tourist attraction internet influence assessment and attraction automatic management scheduling method | |
| Detweiler et al. | Computer-assisted real estate appraisal: A tool for the practicing appraiser | |
| Rossini et al. | Automated valuation model accuracy: some empirical testing | |
| CN115146990A (en) | Urban vitality quantitative evaluation method integrating multi-source geographic big data | |
| Kettani et al. | PariTOP: A goal programming-based software for real estate assessment | |
| CN115018318A (en) | Method and system for predicting and analyzing risk of social area | |
| CN112926794A (en) | Bank loan information prediction method and device | |
| CN112884317A (en) | Water-saving city evaluation method, system, equipment and storage medium thereof | |
| Ahmadzade | Model for forecasting passenger of airport | |
| US20230260035A1 (en) | System and method for analyzing, evaluating and ranking properties using artificial intelligence | |
| CN116756439B (en) | Address selection method, device, server and computer readable storage medium | |
| Maat | Simulating discharges and forecasting floods using a conceptual rainfall-runoff model for the Bolivian Mamoré basin | |
| CN116307909A (en) | Non-genetic village environment monitoring management platform | |
| CN111143656B (en) | Method for adjusting event attribute and related device | |
| CN112488749A (en) | Business district information evaluation method |
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 |