CN117010933A - Real estate market feature evaluation method based on model - Google Patents
Real estate market feature evaluation method based on model Download PDFInfo
- Publication number
- CN117010933A CN117010933A CN202310959963.3A CN202310959963A CN117010933A CN 117010933 A CN117010933 A CN 117010933A CN 202310959963 A CN202310959963 A CN 202310959963A CN 117010933 A CN117010933 A CN 117010933A
- Authority
- CN
- China
- Prior art keywords
- property
- market
- feature
- data
- score
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000000605 extraction Methods 0.000 claims abstract description 44
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 238000007405 data analysis Methods 0.000 claims description 26
- 238000013179 statistical model Methods 0.000 claims description 15
- 238000000611 regression analysis Methods 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 26
- 238000004458 analytical method Methods 0.000 abstract description 11
- 238000011160 research Methods 0.000 abstract description 9
- 230000000875 corresponding effect Effects 0.000 description 59
- 238000001514 detection method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 238000013316 zoning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Abstract
The application relates to a model-based real estate market feature evaluation method, and relates to the technical field of real estate data research. The method comprises the following steps: acquiring property attribute data corresponding to a target area; obtaining at least two property market feature variables corresponding to the target area; determining a property market feature index corresponding to the target area based on the property market feature variable; determining a property market feature score based on the property market feature index; and evaluating the property market characteristics based on the property market characteristic scores. In the process of evaluating the characteristics of the property market, property attribute data are constructed through property space data, property transaction data and property POI data associated with property conditions, multidimensional characteristic extraction is carried out from the property attribute data through a characteristic extraction process and a property market characteristic index generation process, and the property market characteristics are reflected in a score form. Through multidimensional data sources and multi-level feature analysis, the accuracy of prediction and monitoring of the characteristics of the house property market is improved.
Description
Technical Field
The application relates to the technical field of real estate data research, in particular to a method for monitoring and predicting real estate market characteristics.
Background
The property market feature is used to represent features associated with property sales. Optionally, it includes at least one of real-time house price, house type, house price trend, house price expectations.
In the related art, research on spatial distribution rules of features of a property market such as a property price in academia can be categorized into two categories: the spatial distribution pattern of the characteristics of the house property market is researched by utilizing spatial analysis and geostatistical analysis of GIS; the other is to quantitatively analyze each factor affecting the price of the house by establishing a characteristic price model. When the property market features are realized as the property price, the research method of the property price space diversity mode is mainly divided into a metering economy method and a GIS space analysis method, wherein the former is mainly a plurality of linear regression and cluster analysis, and the latter adopts K-type estimation method, kriging interpolation method, exploratory space analysis (ESDA) technology and the like, and the related geographic information system software is combined to analyze the price space diversity mode. In recent years, research on spatial diversity of real estate prices has tended to be diversified on a spatial scale, and the scale of analysis has been developed from national and provincial levels to regional and city-county levels.
However, the research mode of the real estate price space rule in the related technology cannot introduce the change condition of the historical real estate market characteristics of the target area as a reference, and after the characteristic model is established, the condition of inaccurate monitoring and evaluation of the real estate market characteristics often occurs.
Disclosure of Invention
The application relates to a model-based real estate market feature evaluation method, which can improve the accuracy of monitoring and evaluating real estate market features. The method is applied to the computer equipment, and comprises the following steps:
acquiring property attribute data corresponding to a target area in a target time period, wherein the property attribute data comprises property space data, property transaction data and property information point POI data, the property space data is data generated based on the space position of a property, the property transaction data is data generated based on the transaction activity of the property, and the property POI data is data generated based on the living activity of a property holder;
inputting property attribute data into a feature extraction model, and outputting to obtain at least two property market feature variables corresponding to a target area, wherein the feature extraction model comprises at least two feature extraction sub-models, and the types of the feature extraction sub-models comprise at least one of a chart statistical model and a space data analysis model;
determining a property market feature index corresponding to the target area based on the property market feature variable;
determining a property market feature score based on the property market feature index, wherein the property market feature score is used for quantitatively evaluating the quality of the property market feature;
and evaluating the property market characteristics based on the property market characteristic scores.
In an alternative embodiment, acquiring property attribute data corresponding to a target area within a target time period includes:
acquiring a property area map corresponding to a target area, wherein property information and area geographic information are displayed on the property area map of the target area in a superimposed manner;
performing monitoring grid superposition processing on the real estate area map to generate monitoring grid data corresponding to the real estate area map;
establishing a geographic coordinate system corresponding to a real estate area map based on the area geographic information;
determining a house code of a house property in the target area based on the house property information;
based on the monitoring grid, the real estate space data and real estate transaction data corresponding to the target area are generated by combining a geographic coordinate system and a house code.
In an alternative embodiment, acquiring property attribute data corresponding to a target area within a target time period includes:
establishing interest point entry data, wherein the interest point entry data comprises an interest point name field, an interest point category field, an interest point address field, an interest point longitude and latitude field, a province field where the interest point is located, a city field where the interest point is located, a region field where the interest point is located and an eight-bit coding field where the interest point is located;
and matching the interest point entry data with a real estate area map overlapped with the monitoring grid, and generating real estate POI data corresponding to the target area.
In an alternative embodiment, the feature extraction sub-model is a graph statistical model;
inputting the property attribute data into a feature extraction model, and outputting to obtain at least two property market feature variables corresponding to the target area, wherein the feature extraction model comprises the following steps:
determining a property attribute data chart corresponding to the property attribute data, wherein the property attribute data chart is a picture material recorded with the property attribute data;
inputting a property attribute data chart into a chart statistical model;
extracting rules corresponding to the property attribute data graph matching characteristics through a graph statistical model;
and extracting and outputting the property market feature variable based on the feature extraction rule through the chart statistical model.
In an alternative embodiment, the feature extraction sub-model is a spatial data analysis model;
inputting the property attribute data into a feature extraction model, and outputting to obtain at least two property market feature variables corresponding to the target area, wherein the feature extraction model comprises the following steps:
inputting property attribute data into a space data analysis model;
extracting spatial information in property attribute data through a spatial data analysis model, wherein the spatial information is used for representing the geospatial attribute of a target area;
determining a spatial distribution mode corresponding to the target area based on the spatial information through a spatial data analysis model;
determining a property market feature distribution mode based on the spatial distribution mode through a spatial data analysis model;
and outputting the property market feature variable corresponding to the target area based on the property market feature distribution mode through the space data analysis model.
In an alternative embodiment, the property market feature index corresponds to a property market feature index feature value and a property market feature significance value;
determining a property market feature indicator corresponding to the target area based on the property market feature variable, comprising:
generating at least two property market feature variable points based on at least two property market feature variables, wherein the property market feature variable points have a position association relationship with geographic positions in a target area;
extracting characteristic values of at least two property market characteristic variable points based on resources corresponding to property allocation in a target area to obtain property market characteristic index characteristic values corresponding to the property market characteristic variable points, wherein the property market characteristic index characteristic values comprise at least one of characteristic factor values and characteristic statistical distance values;
carrying out regression analysis on at least two property market feature variable points to obtain properties corresponding to the property market feature variable points;
and determining the property market feature index based on the property market feature index feature value and the property market feature significance value.
In an alternative embodiment, the regression analysis includes a least squares OLS based regression analysis and a geographically weighted regression GWR based regression analysis.
In an alternative embodiment, the property market feature score includes a market volume forecast score and a market price forecast score;
determining a property market feature score based on the property market feature index, comprising:
determining a market-volume-prediction-score sub-item corresponding to the market-volume-prediction score and a market-volume-prediction-score sub-item weight corresponding to the market-volume-prediction-score sub-item;
determining a market-volume prediction score based on the market-volume prediction score sub-term and the market-volume prediction score sub-term weight;
determining a market price prediction score sub-item corresponding to the market price prediction score and a market price prediction score sub-item weight corresponding to the market price prediction score sub-item;
determining a market price prediction score based on the market price prediction score sub-term and the market price prediction score sub-term weight;
based on the market-volume prediction score and the market-volume prediction score, a property market feature score is determined.
In an alternative embodiment, evaluating the property market feature based on the property market feature score includes:
determining at least two property market feature score gears;
based on the property market feature score gear, the property market feature score is correspondingly determined, and the property market feature evaluation result corresponding to the property market feature score is used for evaluating the property market feature.
The technical scheme provided by the application has the beneficial effects that at least:
in the process of evaluating the characteristics of the property market, property attribute data are constructed through property space data, property transaction data and property POI data associated with property conditions, multidimensional characteristic extraction is carried out from the property attribute data through a characteristic extraction process and a property market characteristic index generation process, and the property market characteristics are reflected in a score form. Through multidimensional data sources and multi-level feature analysis, the accuracy of prediction and monitoring of the characteristics of the house property market is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic flow chart of a model-based property market feature evaluation method according to an exemplary embodiment of the present application.
FIG. 2 illustrates a flow chart of another model-based property market feature evaluation method provided by an exemplary embodiment of the present application.
Fig. 3 is a schematic diagram of a superposition manner of a detection grid according to an exemplary embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
First, terms involved in the embodiments of the present application will be explained:
besides being influenced by economic and social factors, the urban house price has a more and more intimate relationship with the space geographic position, the space positions of the houses are different, and obvious differences of the prices also occur. The residential district which meets the conditions of close distance to the urban central area, good surrounding public transportation conditions, high school quality in the school district, good surrounding medical and health conditions, good environmental quality conditions and the like has higher price. Such a phenomenon that the prices are significantly different due to different spatial locations of the residences is called spatial differentiation of the residences, i.e., the residences are significantly differentiated in a certain direction in spatial distribution, including spatial distribution regularity, spatial division, spatial autocorrelation, etc. The research considers that the core influencing factors of the price space difference of the urban houses are the construction grade and the level of the district, and the price influencing factors of different types of residential markets are different; the main driving forces are the location direction of specific residential types and grades, space aggregation of specific income classes, space difference of public object investment, urban living land expansion and urban updating. Therefore, the influence factors of the house price and the spatial difference of the house price are suitable for research by using methods of space-time big data analysis measurement, simulation deduction, data mining and the like pointed out by technical schematics. The application provides a method for evaluating the characteristics of a house property market based on a model.
Fig. 1 shows a schematic flow chart of a model-based property market feature evaluation method according to an exemplary embodiment of the present application, and the method is applied to a computer device for explanation, and includes:
and step 101, acquiring property attribute data corresponding to the target area in the target time period.
The method shown in the embodiment of the application is executed by computer equipment, and optionally, the computer equipment has the functions of data acquisition and data analysis. The computer device may be implemented as a physical or virtual terminal such as a personal computer, virtual machine, cell phone, etc. The embodiment of the application is not limited to the specific type of the computer equipment.
In the embodiment of the application, the target time period is a time period for evaluating the characteristics of the property market, and the final output property market characteristic evaluation result of the embodiment of the application is the comprehensive condition evaluation result of all properties in the target area aiming at the target time period.
In the embodiment of the application, the property attribute data comprises property space data, property transaction data and property information point POI data, wherein the property space data is data generated based on the space position of the property, the property transaction data is data generated based on the transaction activity of the property, and the property POI data is data generated based on the living activity of the property holder. POIs generally refer to point class data generated based on user interests in internet electronic maps, and in a geographic information system, the POIs characterize target points through four kinds of information including names, categories, coordinates and classifications. . The embodiment of the application does not limit the specific source and actual representation form of the property attribute data. In one example, property attribute data may be data transmitted from a particular network interface into a computer device. And the computer equipment acquires the real-time monitoring of the real-time property information website to acquire real-time property information data in the target time period.
And 102, inputting the property attribute data into a feature extraction model, and outputting to obtain at least two property market feature variables corresponding to the target area.
In the embodiment of the application, the feature extraction model can be an artificial intelligent model based on machine learning or a mathematical analysis model, and the embodiment of the application does not limit the specific form of the feature extraction model.
In the embodiment of the application, after the property attribute data is input into the feature extraction model, the computer equipment obtains at least two property market feature variables. The property market feature variables may be implemented in the form of feature vectors, or the property market feature variables may be implemented in the form of values. The property market feature variables are used to characterize at least one aspect of the property market feature. In one example, when the property market feature is a vacation, the property market feature variable may be used to represent at least one of a growing trend of the property price, a degree of association of the property price with the location, and a price average of the property price in the target area.
And step 103, determining a property market feature index corresponding to the target area based on the property market feature variable.
And 104, determining the property market feature scores based on the property market feature indexes.
In the embodiment of the application, the property market feature score is used for quantitatively evaluating the advantages and disadvantages of the property market feature. Alternatively, the higher the property market feature score, the more excellent the state of the property market feature within the target area is indicated. In one example, the property market feature is a property price, the full score of the property market feature score is 3 points, and the property market feature score is 2.66 points, which indicates that the property price is stable and is responsible for the running state of the market.
Alternatively, in other embodiments of the application, the property market feature score corresponds to one property market feature index of a property market feature, in which case the property market feature indicates the status of the property market feature in a single dimension. In one example, the property market feature is implemented as a property price, which corresponds to two property market feature indicators, a market volume and a market price, respectively. In this case, two property market feature indexes of the market volume and the market price correspond to property market feature scores, respectively. For this example, the property market feature score for the market volume is 0.32 points and the property market feature score for the market price is 1.05 points.
And step 105, evaluating the property market characteristics based on the property market characteristic scores.
The process corresponds to step 104, and the computer device outputs the evaluation result. Alternatively, the computer device directly outputs the score as a reference for evaluating the property market characteristics. In another example, the computer device performs field matching based on a property market feature evaluation rule, generating a description field for a property market feature status.
In summary, in the method provided by the embodiment of the application, in the process of evaluating the characteristics of the property market, property attribute data is constructed by property space data, property transaction data and property POI data associated with property conditions, and multidimensional characteristic extraction is performed from the property attribute data by a characteristic extraction process and a property market characteristic index generation process, and the property market characteristics are reflected in a score form. Through multidimensional data sources and multi-level feature analysis, the accuracy of prediction and monitoring of the characteristics of the house property market is improved.
FIG. 2 is a flow chart of another model-based property market feature evaluation method according to an exemplary embodiment of the present application, and the method is applied to a computer device for illustration, and includes:
step 201, acquiring a property area map corresponding to a target area.
Steps 201 to 207 show the acquisition process of property attribute data of different kinds. In the embodiment of the application, different kinds of property data are obtained by combining the related data in the target area with the property market index spatialization technology, so that a property area map corresponding to the target area is generated in the process of acquiring the data. In the embodiment of the application, the real estate information and the regional geographic information are displayed on the regional map of the target region in a superimposed manner. The map of the real estate area can be a map containing two-dimensional geographic information or a map containing three-dimensional geographic information, and the embodiment of the application does not limit the actual implementation form of the map of the real estate area.
Optionally, the property information is used to characterize the disposition of the property. In one example, the property information includes at least one of a trade condition of the property, a current property condition of the property, a completion time of the property, a time when the current property person holds the property, and a sales condition of the property.
Optionally, the regional geographic information includes historical information corresponding to the target region and political and economic condition related information, and the specific content of the regional geographic information is not limited.
And 202, performing monitoring grid superposition processing on the real estate area map to generate monitoring grid data corresponding to the real estate area map.
In the embodiment of the application, map data corresponding to a map of a property area is determined by drawing and overlaying data of the detection grid for facilitating subsequent analysis. Referring to fig. 3, on a property area map 310, grid lines 320 are superimposed in both lateral and longitudinal directions. After the grid line superposition processing, the computer device may perform subsequent data processing based on the monitor grid data generated by superposition, in which case the A, B, C, D, E five-place position divided by division as a standard will be further divided by the grid line 320.
Step 203, establishing a geographic coordinate system corresponding to the real estate area map based on the area geographic information.
This process is a process of determining a geographic coordinate system based on the elevation information shown in step 201. The purpose of establishing a geographic coordinate system is to correlate property information with geographic locations for subsequent data generation and chart simulation.
Step 204, determining a house code of the property in the target area based on the property information.
In an embodiment of the application, the data corresponding to the property references the house code mechanism. The house code is also called as "house registration basic unit code", and is a code programmed by the registration institution according to the regulations and corresponding to the house registration basic unit one by one. The house code is a generic term for house codes and household codes, and all houses should be the encoding object. House codes are uniformly coded by special departments. And generating codes representing the house by adopting a completion time method, a coordinate method, a zoning method, a framing method and the like according to the space position of the horizontal projection surface of the house. The house code is applied to the fields of house property mapping, rights and interests registering, house property transaction and the like, and has uniqueness, scientificity and applicability.
In the embodiment of the application, the house code generation is based on house code generation standard, and consists of 26-bit characters, wherein the first 25 bits are body codes, and the last bit is check codes. The left-right arrangement is 9-bit administrative division codes, 12-bit building numbers, 4-bit user numbers and 1-bit digital check codes. The administrative division codes are generated based on village and town (street) level administrative division regions to which the centroid of the house building belongs; the number of the building adopts a framing method, and the division of the diagram is according to the specification of GB/T17986.1 of the house property measurement Specification; the family number and the check code are generated by a house property mapping system and have no absolute relation with the spatial position of the building.
Step 205, based on the monitoring grid, combining the geographic coordinate system and the house code, generating the house property space data and the house property transaction data corresponding to the target area.
In the embodiment of the application, the property space data and the property transaction data are extracted from a property area map of the superposition detection grid based on the house codes. In the embodiment of the application, the monitoring grid plays a role in positioning.
In step 206, point of interest entry data is created.
In the embodiment of the application, corresponding to actual conditions, the interest point entry data comprises an interest point name field, an interest point category field, an interest point address field, an interest point longitude and latitude field, an interest point province field, an interest point city field, an interest point region field and an interest point eight-bit coding field. Optionally, the data source of the point of interest entry data is the internet.
Step 207, matching the interest point entry data with the real estate area map overlapped with the monitoring grid, and generating real estate POI data corresponding to the target area.
In some embodiments of the present application, for practical situations, it is necessary to perform a point expanding based on latitude and longitude coordinates on information related to property POI data directly from a source, and match the point expanding with a detection grid through operations such as projection, coordinate transformation, space calibration, and the like, so as to finally obtain property POI data corresponding to a target area.
And step 208, determining a property attribute data chart corresponding to the property attribute data.
After the property attribute is acquired, steps 208 to 216 show the generation manner of the property market feature variable, wherein the types of the corresponding feature extraction sub-models include the chart statistical model and the space data analysis model, steps 208 to 211 show the process of extracting the property market feature variable based on the chart statistical model, and steps 212 to 216 show the process of extracting the property market feature variable based on the space data analysis model.
Optionally, the property attribute data chart is a picture material in which property attribute data is recorded. Alternatively, the photo material may be implemented as a read detection report for the target area, or as read macroscopic data statistics for the target area.
Step 209, inputting the property attribute data chart into a chart statistical model.
Step 210, extracting rules corresponding to the property attribute data graph matching characteristics through a graph statistical model.
In the embodiment of the application, the carrier of the property attribute data chart is usually realized as a macroscopic report, and the characteristic of macroscopic description and coarse granularity of data analysis is realized, so that the characteristic extraction rule is matched through the chart statistical model to carry out deep characteristic extraction. In one example, the graph matching feature extraction rules include a traversal search extraction rule that extracts data in a property attribute icon, extracts commodity house month supply data, commodity house month achievement data, second-hand house month achievement data in a statistical graph, and extracts commodity house month supply data, commodity house month achievement data, second-hand house month achievement data, stock house transaction ranking data, commodity house transaction ranking data, and commodity house residential partition achievement situation data in a statistical table. The application does not limit the extraction rule of the graph matching characteristics.
Step 211, extracting and outputting the property market feature variable based on the feature extraction rule through the feature extraction model.
The process is the output process of the characteristic variable of the real estate market.
And step 212, inputting the property attribute data into a spatial data analysis model.
The process is a data input process.
And step 213, extracting spatial information in the property attribute data through a spatial data analysis model, wherein the spatial information is used for representing the geospatial attribute of the target area.
Alternatively, studies have shown that the distribution of geographic objects in space has a certain regularity. In the case of cities, the urban density in plain areas is higher than in hilly and mountainous areas, affected by the terrain. Some identical attributes of different geographic objects have a certain rule in space, and observation data of the attributes have potential interdependencies or are clustered or dispersed, which is called spatial autocorrelation.
Step 214, determining a spatial distribution pattern corresponding to the target area based on the spatial information through the spatial data analysis model.
In this case, a high/low clustering tool is configured in the spatial data analysis model to make determination of a spatial distribution pattern corresponding to the target region.
Step 215, determining a property market feature distribution pattern based on the spatial distribution pattern by the spatial data analysis model.
Corresponding to the content of step 214, the spatial data analysis model will perform one-step extraction and determine the association of the property market feature with space. In one example, the property market feature is implemented as a price of a house, based on steps 214-215, where spatially observing the house deal occurs will find that the house deal event occurs at locations that are not randomly distributed, nor distributed throughout, but centrally in several areas of the city. And the regional home prices in which these home transactions occur in a centralized manner are also high. In this case, based on the property market feature distribution pattern, the transaction hotspots of the property transaction, and the spatial distribution of the property prices can be deduced.
And step 216, outputting the property market feature variable corresponding to the target area based on the property market feature distribution mode through the space data analysis model.
The process is the analysis process of the characteristic variable of the real estate market.
At step 217, at least two property market feature variable points are generated based on the at least two property market feature variables.
In the embodiment of the application, the position association relation exists between the property market characteristic variable points and the geographic positions in the target area. Thus, the branch property feature variable point is implemented in a form based on the existence of a map of the property region, and the variable point contains at least one feature factor, and features the property market feature from at least one dimension.
And step 218, extracting characteristic values of at least two characteristic variable points of the property market based on resources corresponding to property allocation in the target area, and obtaining characteristic values of characteristic indexes of the property market corresponding to the characteristic variable points of the property market.
In the embodiment of the application, the characteristic value of the characteristic index of the real estate market comprises at least one of a characteristic factor value and a characteristic statistical distance value.
In one example, the property market feature is implemented as a property price, and at this time, the property price corresponds to a plurality of types of feature factors and feature factors, and the quantization conditions are as shown in table 1 below:
table 1: characteristic factor and characteristic factor
Optionally, the feature statistical distance is a distance used by a feature factor of the corresponding periphery of the target statistics. In the embodiment of the application, the feature statistical distance corresponding to the feature variable points of the property market can be determined based on the space concept.
And 219, carrying out regression analysis on at least two property market feature variable points to obtain property market feature significance values corresponding to the property market feature variable points.
In the embodiment of the application, the regression analysis comprises the regression analysis based on OLS and the regression analysis based on GWR. Optionally, the value of the characteristic significant value of the property market can be determined by means of regression analysis statistics, wherein the value of the characteristic significant value of the property market is another part for evaluating the characteristic index of the property market.
And 220, determining the property market feature index based on the property market feature index feature value and the property market feature significance value.
The process is the output process of the property market characteristic index. Optionally, a property market feature index is associated with the assessment process, the property market feature being characterized in quantified form from at least one dimension.
Step 221, determining a market-volume-prediction-score sub-item corresponding to the market-volume-prediction-score and a market-volume-prediction-score sub-item weight corresponding to the market-volume-prediction-score sub-item.
In the embodiment of the application, the property market characteristic score comprises a market quantity predictive score and a market price predictive score.
Step 222, determining the market-size prediction score based on the market-size prediction score sub-term and the market-size prediction score sub-term weight.
Step 223, determining a market price prediction score sub-item corresponding to the market price prediction score and a market price prediction score sub-item weight corresponding to the market price prediction score sub-item.
Step 224, determining the market price prediction score based on the market price prediction score sub-term and the market price prediction score sub-term weight.
Step 225, determining a property market feature score based on the market volume prediction score and the market volume prediction score.
In the embodiment of the application, the specification of the index system is performed by taking the property market feature as an example of the price of the house.
In this case, the index system includes three major sub-items of land yielding, value demand and house price, and there are eleven predictive sub-items of a new house operating area same-ratio speed-up, a near 3-month house land supply area/a front 12-month house land supply area sum, a commercial house supply area/a front 12-month commercial house supply area sum, a commercial house sales area/a front 12-month commercial house sales area sum, a second-hand house sales area/a front 12-month second-hand house sales area sum, a commercial house removal period, a commercial house sales average price ratio speed-up, a second-hand house sales average price ratio speed-up, and a second-hand house sales average price ratio speed-up, respectively, corresponding to the three major sub-items.
In this case, the weights are given in two dimensions of the market volume and the market price, respectively, and the results of the index weights are shown in table 2 below:
table 2: evaluation index weighting condition schematic table
Under the condition, after the critical value ranges and the specific values of different indexes are determined, two values of the market quantity comprehensive score and the market price comprehensive score can be finally obtained.
At least two property market feature score gears are determined 226.
In one example, 7 property market feature score gears can be established if the establishment is as shown in Table 3 below:
table 3 real estate market characteristics score gear table
In the table, x is the actual value of the index, z x Is the standard value of the index when taking the value x, and x1 to x6 are interval critical values, and the interval critical values are determined by computer equipment based on rules.
Step 227, determining a property market feature evaluation result corresponding to the property market feature score based on the property market feature score gear and the corresponding property market feature score.
The process is the process of finally determining the property market characteristic evaluation result.
In combination with the foregoing embodiment, the property market feature evaluation result is used to evaluate the property market feature.
In summary, in the method provided by the embodiment of the application, in the process of evaluating the characteristics of the property market, property attribute data is constructed by property space data, property transaction data and property POI data associated with property conditions, and multidimensional characteristic extraction is performed from the property attribute data by a characteristic extraction process and a property market characteristic index generation process, and the property market characteristics are reflected in a score form. Through multidimensional data sources and multi-level feature analysis, the accuracy of prediction and monitoring of the characteristics of the house property market is improved.
According to the method provided by the embodiment of the application, the residential characteristic price model can be well constructed by utilizing POI and commodity house residential transaction data and combining the characteristic statistical distance. The interpretation degree of the model on the price is also possible to be improved, and factors of building characteristics, including planning information such as building volume rate, greening rate, building density and the like, are needed to be enriched in later research. The variable significance summary data provided by the exploratory regression tool can well show the degree of influence of the characteristic factors on the price of each region, and give positive and negative influence and stability.
The foregoing description of the preferred embodiments of the present application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements within the spirit and principles of the present application.
Claims (9)
1. A method for evaluating characteristics of a property market based on a model, wherein the method is applied to a computer device, and comprises:
acquiring property attribute data corresponding to a target area in a target time period, wherein the property attribute data comprises property space data, property transaction data and property information point POI data, the property space data is data generated based on a space position of a property, the property transaction data is data generated based on a transaction activity of the property, and the property POI data is data generated based on a living activity of a property holder;
inputting the property attribute data into the feature extraction model, and outputting to obtain at least two property market feature variables corresponding to the target area, wherein the feature extraction model comprises at least two feature extraction sub-models, and the types of the feature extraction sub-models comprise at least one of a chart statistical model and a space data analysis model;
determining a property market feature index corresponding to the target area based on the property market feature variable;
determining a property market feature score based on the property market feature index, wherein the property market feature score is used for quantitatively evaluating the quality of the property market feature;
and evaluating the property market characteristics based on the property market characteristic scores.
2. The method of claim 1, wherein the acquiring property attribute data corresponding to the target area for the target period of time comprises:
acquiring a property area map corresponding to the target area, wherein the property area map is overlapped with property information and area geographic information on the area map of the target area;
performing monitoring grid superposition processing on the real estate area map to generate monitoring grid data corresponding to the real estate area map;
establishing a geographic coordinate system corresponding to the real estate area map based on the area geographic information;
determining a house code of a house property in the target area based on the house property information;
and generating the real estate space data and the real estate transaction data corresponding to the target area by combining the geographic coordinate system and the house code based on the monitoring grid.
3. The method according to claim 2, wherein the acquiring property attribute data corresponding to the target area within the target period of time includes:
establishing interest point entry data, wherein the interest point entry data comprises an interest point name field, an interest point category field, an interest point address field, an interest point longitude and latitude field, a province field where the interest point is located, a city field where the interest point is located, a region field where the interest point is located and an eight-bit coding field where the interest point is located;
and matching the interest point entry data with the real estate area map overlapped with the monitoring grid to generate real estate POI data corresponding to the target area.
4. A method according to claim 3, wherein the feature extraction sub-model is a graph statistical model;
inputting the property attribute data into the feature extraction model, and outputting to obtain at least two property market feature variables corresponding to the target area, wherein the feature extraction model comprises the following steps:
determining a property attribute data chart corresponding to the property attribute data, wherein the property attribute data chart is a picture material recorded with the property attribute data;
inputting the property attribute data chart into the chart statistical model;
through the chart statistical model, a chart matching feature extraction rule corresponding to the property attribute data is adopted;
and extracting and outputting the property market feature variable based on the feature extraction rule through the chart statistical model.
5. A method according to claim 3, wherein the feature extraction sub-model is a spatial data analysis model;
inputting the property attribute data into the feature extraction model, and outputting to obtain at least two property market feature variables corresponding to the target area, wherein the feature extraction model comprises the following steps:
inputting the property attribute data into the spatial data analysis model;
extracting spatial information in the property attribute data through the spatial data analysis model, wherein the spatial information is used for representing the geographic spatial attribute of the target area;
determining a spatial distribution mode corresponding to the target area based on the spatial information through the spatial data analysis model;
determining, by the spatial data analysis model, the property market feature distribution pattern based on the spatial distribution pattern;
and outputting the property market feature variable corresponding to the target area based on the property market feature distribution mode through the space data analysis model.
6. A method according to claim 3, wherein the property market feature indicator corresponds to a property market feature indicator feature value and a property market feature significance value;
the determining the property market feature index corresponding to the target area based on the property market feature variable comprises the following steps:
generating at least two property market feature variable points based on at least two property market feature variables, wherein the property market feature variable points have a position association relationship with geographic positions in a target area;
extracting characteristic values of at least two property market characteristic variable points based on resources corresponding to the property configuration in the target area to obtain property market characteristic index characteristic values corresponding to the property market characteristic variable points, wherein the property market characteristic index characteristic values comprise at least one of characteristic factor values and characteristic statistical distance values;
carrying out regression analysis on at least two property market feature variable points to obtain property market feature significance values corresponding to the property market feature variable points;
and determining the property market feature index based on the property market feature index feature value and the property market feature significance value.
7. The method of claim 6, wherein the regression analysis comprises a least squares OLS based regression analysis and a geographically weighted regression GWR based regression analysis.
8. The method of claim 3, wherein the property market feature score comprises a market volume predictive score and a market price predictive score;
the determining the property market feature score based on the property market feature index includes:
determining a market-volume-prediction-score sub-item corresponding to the market-volume-prediction-score and a market-volume-prediction-score sub-item weight corresponding to the market-volume-prediction-score sub-item;
determining the market-volume prediction score based on the market-volume prediction score sub-item and the market-volume prediction score sub-item weight;
determining a market price prediction score sub-item corresponding to the market price prediction score and a market price prediction score sub-item weight corresponding to the market price prediction score sub-item;
determining the market price prediction score based on the market price prediction score sub-term and the market price prediction score sub-term weight;
the real estate market feature score is determined based on the market volume predictive score and the market volume predictive score.
9. The method of claim 8, wherein evaluating the property market feature based on the property market feature score comprises:
determining at least two property market feature score gears;
and determining a property market feature evaluation result corresponding to the property market feature score based on the property market feature score gear, wherein the property market feature evaluation result is used for evaluating the property market feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310959963.3A CN117010933A (en) | 2023-08-01 | 2023-08-01 | Real estate market feature evaluation method based on model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310959963.3A CN117010933A (en) | 2023-08-01 | 2023-08-01 | Real estate market feature evaluation method based on model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117010933A true CN117010933A (en) | 2023-11-07 |
Family
ID=88570502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310959963.3A Pending CN117010933A (en) | 2023-08-01 | 2023-08-01 | Real estate market feature evaluation method based on model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117010933A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117539920A (en) * | 2024-01-04 | 2024-02-09 | 上海途里信息科技有限公司 | Data query method and system based on real estate transaction multidimensional data |
-
2023
- 2023-08-01 CN CN202310959963.3A patent/CN117010933A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117539920A (en) * | 2024-01-04 | 2024-02-09 | 上海途里信息科技有限公司 | Data query method and system based on real estate transaction multidimensional data |
| CN117539920B (en) * | 2024-01-04 | 2024-04-05 | 上海途里信息科技有限公司 | Data query method and system based on real estate transaction multidimensional data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Unwin | Geographical information systems and the problem of'error and uncertainty' | |
| Lovett et al. | Improving benefit transfer demand functions: a GIS approach | |
| Shang et al. | Estimating building-scale population using multi-source spatial data | |
| CN111401692B (en) | Method for measuring urban space function compactness | |
| CN112819319A (en) | Method for measuring correlation between city vitality and spatial social characteristics and application | |
| Akinyemi | A conceptual poverty mapping data model | |
| CN113360587B (en) | Land surveying and mapping equipment and method based on GIS technology | |
| CN112508332B (en) | Gradual rural settlement renovation partitioning method considering multidimensional characteristics | |
| CN117010933A (en) | Real estate market feature evaluation method based on model | |
| CN116451931A (en) | Data processing method for public service facility site selection administrative management decision | |
| Stylianidis et al. | A GIS for urban sustainability indicators in spatial planning | |
| de Smet et al. | Characterising the morphology of suburban settlements: A method based on a semi-automatic classification of building clusters | |
| CN114398951A (en) | Land use change driving factor mining method based on random forest and crowd-sourced geographic information | |
| CN110716998A (en) | Method for spatializing fine-scale population data | |
| CN112381332A (en) | Population spatial distribution prediction method based on settlement object | |
| Mubea et al. | Spatial effects of varying model coefficients in urban growth modeling in Nairobi, Kenya | |
| Liu et al. | An integrated method used to value recreation land–a case study of Sweden | |
| Kim et al. | How the pattern recognition ability of deep learning enhances housing price estimation | |
| CN114282934A (en) | Urban low-income crowd distribution prediction method and system based on mobile phone signaling data and storage medium | |
| CN111861257A (en) | Method and device for identifying hollow village based on power data thermodynamic diagram | |
| CN111506879A (en) | Population spatialization measuring and calculating method and device based on multi-source perception data | |
| Li et al. | Characterizing urban spatial structure through built form typologies: A new framework using clustering ensembles | |
| Balakrishnan | Heterogeneity within Indian cities: Methods for empirical analysis | |
| CN111581318B (en) | Shared bicycle riding purpose inference method and device and storage medium | |
| Daams | Rethinking the economic valuation of natural land: Spatial analyses of how deeply people value nature in rural areas and in cities |
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 |