CN114723338A - Resource data evaluation method and device and computer equipment - Google Patents
Resource data evaluation method and device and computer equipment Download PDFInfo
- Publication number
- CN114723338A CN114723338A CN202210548659.5A CN202210548659A CN114723338A CN 114723338 A CN114723338 A CN 114723338A CN 202210548659 A CN202210548659 A CN 202210548659A CN 114723338 A CN114723338 A CN 114723338A
- Authority
- CN
- China
- Prior art keywords
- sample
- target
- evaluation object
- resource data
- data
- 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
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Abstract
The application relates to a resource data evaluation method, a resource data evaluation device, a computer device, a storage medium and a computer program product, which can be applied to the field of big data, or financial technology or other related fields. The method comprises the following steps: acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model; and calculating the predicted resource data of the target evaluation object according to the target space characteristic, the target city network distance characteristic and the geographical weighted regression model of the target evaluation object. By adopting the method, the resource data of the target evaluation object is estimated by utilizing the geographic regression weighting model, the calculation is carried out from multiple aspects of space characteristics and distance characteristics, the resource data can be comprehensively predicted, and therefore the accurate resource data of each target evaluation object can be determined.
Description
Technical Field
The present application relates to the field of big data technologies, and in particular, to a method and an apparatus for evaluating resource data, and a computer device.
Background
In the conventional technology, for the evaluation of an evaluation object, estimation is mainly performed from a location where the evaluation object is located and recent transaction resource data, the evaluation object may be an object such as a house, but a geographic location is only one of factors influencing the resource data, and the recent transaction resource data can only dynamically reflect a change of a demand condition of a market for the evaluation object, but cannot reflect fluctuation of the resource data of the evaluation object. Therefore, the evaluation of the resource data of the evaluation object by the above method is relatively simple, which results in inaccurate evaluation of the resource data.
Disclosure of Invention
In view of the above, it is necessary to provide an evaluation method, an apparatus, a computer device, a computer readable storage medium and a computer program product for resource data that can be accurately evaluated.
In a first aspect, a method for evaluating resource data is provided. The method comprises the following steps:
acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the initial geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object.
In one embodiment, the method further comprises:
collecting a sample data set of a sample evaluation object;
and calculating a space characteristic influence coefficient and an urban network distance characteristic influence coefficient in the initial geographical weighted regression model according to the sample resource data, the sample space characteristic, the sample urban network distance characteristic and a pre-established initial geographical weighted regression model of the sample evaluation object to obtain a trained geographical weighted regression model.
In one embodiment, the method further comprises:
acquiring spatial characteristics and interest point data of a plurality of evaluation objects in a target area, wherein the interest point data comprises identification information, address information, coordinate information and category information;
acquiring road vector data of a target area in a vector data map, wherein the road vector data comprises road type information and road position information;
and calculating urban network distance characteristics corresponding to each evaluation object according to the spatial characteristics of the evaluation objects in the target area, the interest point data and the road vector data, and generating an urban network model corresponding to the target area.
In one embodiment, the acquiring a sample dataset of sample evaluation objects comprises:
obtaining sample space characteristics and sample urban network distance characteristics of the sample evaluation object in the urban network model;
determining sample identification information of the sample evaluation object according to the sample evaluation object;
and determining sample resource data corresponding to the sample identification information in an incidence relation table of preset identification and reference resource data according to the sample identification information.
In one embodiment, the method further comprises:
if the sample identification information is not inquired in the incidence relation table of the preset identification and the reference resource data, obtaining an average value of transaction resource data of the area where the sample evaluation object is located in a preset time range, and taking the average value as the sample resource data corresponding to the sample identification information.
In one embodiment, the calculating the spatial feature influence coefficients and the city network distance feature influence coefficients in the initial geographical weighted regression model includes:
calculating a spatial feature influence coefficient in the initial geographical weighted regression model through a preset Gaussian kernel function algorithm;
and calculating the urban network distance characteristic influence coefficient in the initial geographical weighted regression model through a preset local weighted least square algorithm.
In one embodiment, the method further comprises:
acquiring target resource data of the target evaluation object;
determining a target screening range according to the predicted resource data;
and under the condition that the target resource data exceeds the target screening range, generating risk prompt information corresponding to the target evaluation object, and outputting the risk prompt information.
In a second aspect, the present application further provides an apparatus for evaluating resource data. The device comprises:
the acquisition module is used for acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
the calculation module is used for calculating the predicted resource data of the target evaluation object according to the target space characteristic, the target city network distance characteristic and the geographical weighted regression model of the target evaluation object; the initial geographical weighting regression model is obtained by training the initial geographical weighting regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample space characteristics and sample urban network distance characteristics of the sample evaluation object.
In one embodiment, the apparatus further comprises:
the acquisition module is used for acquiring a sample data set of a sample evaluation object;
and the coefficient calculation module is used for calculating a spatial characteristic influence coefficient and an urban network distance characteristic influence coefficient in the initial geographical weighted regression model according to the sample resource data, the sample spatial characteristic, the sample urban network distance characteristic and a pre-established initial geographical weighted regression model of the sample evaluation object to obtain the trained geographical weighted regression model.
In one embodiment, the apparatus further comprises:
the data acquisition module is used for acquiring spatial characteristics and interest point data of a plurality of evaluation objects in a target area, wherein the interest point data comprises identification information, address information, coordinate information and category information;
the road vector data acquisition module is used for acquiring road vector data of a target area in a vector data map, wherein the road vector data comprises road type information and road position information;
and the generating module is used for calculating the urban network distance characteristics corresponding to each evaluation object according to the spatial characteristics of the evaluation objects in the target area, the interest point data and the road vector data, and generating an urban network model corresponding to the target area.
In one embodiment, the acquisition module is specifically configured to:
obtaining sample space characteristics and sample urban network distance characteristics of the sample evaluation object in the urban network model;
determining sample identification information of the sample evaluation object according to the sample evaluation object;
and determining sample resource data corresponding to the sample identification information in an incidence relation table of preset identification and reference resource data according to the sample identification information.
In one embodiment, the apparatus further comprises:
and the query module is used for acquiring the average value of the transaction resource data of the area where the sample evaluation object is located in a preset time range if the sample identification information is not queried in the association relation table of the preset identification and the reference resource data, and taking the average value as the sample resource data corresponding to the sample identification information.
In one embodiment, the coefficient calculation module is specifically configured to:
calculating a spatial feature influence coefficient in the initial geographical weighted regression model through a preset Gaussian kernel function algorithm;
and calculating the urban network distance characteristic influence coefficient in the initial geographical weighted regression model through a preset local weighted least square algorithm.
In one embodiment, the apparatus further comprises:
the risk evaluation module is used for acquiring target resource data of the target evaluation object;
the target screening range determining module is used for determining a target screening range according to the predicted resource data;
and the risk prompt information generation module is used for generating risk prompt information corresponding to the target evaluation object and outputting the risk prompt information under the condition that the target resource data exceeds the target screening range.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the initial geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the initial geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the initial geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object.
The method, the device, the computer equipment, the storage medium and the computer program product for evaluating the resource data comprise the following steps: acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model; calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample space characteristics and sample urban network distance characteristics of the sample evaluation object. By adopting the method, the resource data of the target evaluation object is estimated by utilizing the geographic regression weighting model, the calculation is carried out from multiple aspects of space characteristics and distance characteristics, the resource data can be comprehensively predicted, and therefore the accurate resource data of each target evaluation object can be determined.
Drawings
FIG. 1 is a flow diagram illustrating a method for evaluating resource data according to one embodiment;
FIG. 2 is a schematic flow chart diagram illustrating the model training steps in one embodiment;
FIG. 3 is a schematic flow chart diagram illustrating the steps for generating a model of a metropolitan network in one embodiment;
FIG. 4 is a schematic flow chart of the sample resource data determination step in one embodiment;
FIG. 5 is a flowchart illustrating the impact coefficient determining step in one embodiment;
FIG. 6 is a schematic flow chart of the risk assessment steps in one embodiment;
FIG. 7 is a block diagram showing an arrangement for evaluating resource data according to an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, as shown in fig. 1, a resource data evaluation method is provided, and this embodiment is exemplified by applying the method to a terminal, it is to be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and is implemented by interaction between the terminal and the server, where the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device and the like, and the server can be realized by an independent server or a server cluster formed by a plurality of servers. In this embodiment, the resource data evaluation method includes the following steps:
and 102, acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model.
The city network model may be a city network model of the target area, for example, a city network model of a city, a city network model corresponding to a B area of the city a, or a city network model corresponding to a C street in the B area of the city a.
Specifically, the target evaluation object may be an object of resource data to be evaluated, for example, an object such as a house property, and the target spatial feature may be a geographic location feature of the target evaluation object, for example, a longitude and latitude feature, and the like; the target urban network distance feature may be a distribution feature of the target evaluation object in the urban network of the target area, and may include the number of each type of target object in the first area and a distance of each closest type of target object, the first area may be a circular area with the target evaluation object as a center and a radius as a first distance, and the first distance may be one kilometer, three kilometers, five kilometers, and the like.
In this way, the terminal determines the longitude and latitude characteristics of the target evaluation object, the number of various types of target objects in the first area corresponding to the target evaluation object and the distance between the various types of target objects closest to the target evaluation object through a preset urban network model in the target area, the number of various types of target objects in the 1km area of the target evaluation object and the distance between the various types of target objects closest to the target evaluation object, wherein the various types of target objects can be markets, schools, subway stations, bus stations, primary schools, universities and the like. The terminal may specifically be as shown in table 1 through a city network model:
TABLE 1
And 104, calculating the predicted resource data of the target evaluation object according to the target space characteristic, the target city network distance characteristic and the geographical weighted regression model of the target evaluation object.
The geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, the sample evaluation object data set includes sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object, and the resource data may represent the value of each evaluation object, for example, in the case that the evaluation object is a property, the resource data may be the price of the property.
Specifically, the terminal trains the initial geographical weighted regression model through the sample resource data, the sample spatial features and the sample urban network distance features of the sample evaluation object, so that the influence parameters corresponding to the sample spatial features and the influence parameters corresponding to the urban network distance features can be determined, and the trained geographical weighted regression model is obtained. Therefore, the terminal can input the target space characteristics and the target city network distance characteristics of the target evaluation object into the trained geographical weighted regression model to obtain the output result of the geographical weighted regression model and obtain the predicted resource data of the target evaluation object.
The method for evaluating resource data includes: acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model; calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the initial geographical weighting regression model is obtained by training the initial geographical weighting regression model based on a sample data set of a sample evaluation object, and the sample evaluation object data set comprises sample resource data, sample space characteristics and sample city network distance characteristics of the sample evaluation object. By adopting the method, the resource data of the target evaluation object is estimated by utilizing the geographic regression weighting model, the calculation is carried out from multiple aspects of space characteristics and distance characteristics, the resource data can be comprehensively predicted, and therefore the accurate resource data of each target evaluation object can be determined.
In one embodiment, as shown in fig. 2, the method for evaluating resource data further includes:
step 202, a sample data set of a sample evaluation object is collected.
Specifically, the sample evaluation object may be a sample home POI (Point of Interest), which may be Point class data in an internet electronic map, for example, the category of each POI may include a home, a municipal and public service facility (e.g., administration, hospital, kindergarten of middle and primary schools, park and square, library museum, scenic spot, etc.), a business (e.g., mall, commercial street, etc.), a transportation node (subway station, bus station, etc.). Therefore, the terminal can acquire a sample data set of one or more sample evaluation objects in the target object, and mainly acquires sample resource data, sample space characteristics and sample urban network distance characteristics of the sample evaluation objects of each sample evaluation object to form the sample data set.
And 204, calculating a space characteristic influence coefficient and an urban network distance characteristic influence coefficient in the initial geographical weighted regression model according to the sample resource data, the sample space characteristics, the sample urban network distance characteristics and the pre-established initial geographical weighted regression model of the sample evaluation object to obtain the trained geographical weighted regression model.
Specifically, the pre-established initial geo-weighted regression model may be as follows:
wherein i can be the ith evaluation object (e.g., the ith POI), can be the ith sample evaluation object, j can be the jth city network distance feature, betaj(ui,vi) (j-0, 1,2, …, p) may be a preset spatial geographical location function, XijMay be the feature value, Y, corresponding to the jth city network distance feature of the ith POIiResource data for the ith POI, ∈iMay be a predetermined constant term, (u)i，vi) There may be p urban network distance features in total, which may be spatial features, i.e., latitude and longitude, of the ith evaluation object.
In this way, the terminal can substitute the sample resource data, the sample spatial characteristics and the sample urban network distance characteristics corresponding to the multiple sample evaluation objects into the geographical weighted regression model through the pre-established geographical weighted regression model, and respectively calculate the influence coefficients corresponding to the spatial characteristics and the influence coefficients corresponding to the urban network distance characteristics.
In one embodiment, as shown in fig. 3, the method for evaluating resource data further includes:
step 302, obtaining the spatial characteristics and the interest point data of a plurality of evaluation objects in the target area.
The point of interest data comprises identification information, address information, coordinate information and category information.
In particular, the target area may be an area determined according to an actual application scenario, for example, a C street. The terminal may obtain spatial features and interest points of a plurality of POIs (points of interest) in a target area in an open source API (Application Programming Interface), where the open source API may be an internet electronic map such as a Baidu map, the POIs in the target area may be a plurality of evaluation objects in the target area, the interest points may be identification information (such as name information) of the evaluation objects, address information (for example, in the case where the evaluation object is a property, the address information may be seat and floor information of the property), coordinate information, and category information, where the category information may include a residence, a municipal and public service facility, a business, a transportation node, and the like, the residence may include a civil residence and a commercial residence, and the municipal and public service facility may include an administrative department, a hospital, a primary and secondary school kindergarten, a public park, a public service facility, a public service department, a park, a public service node, and public service facility, Library museums, scenic spots, etc., the business may comprise a mall or mall, etc., and the traffic nodes may comprise subway stations, bus stations, etc.
And step 304, collecting road vector data of the target area in the vector data map.
The road vector data includes road type information and road position information.
In particular, the vector data Map may be Open source vector data (Open Street Map), which may comprise urban roads of a plurality of road classes, which may be, for example, highways, grade roads, expressways. The terminal may extract type information of each road within the target area and position information of each road in the vector data map.
Step 306, calculating city network distance characteristics corresponding to each evaluation object according to the space characteristics, the interest point data and the road vector data of the evaluation objects in the target area, and generating a city network model corresponding to the target area.
Specifically, the terminal may process the road vector data in the target area through Geographic Information System (GIS) software, and the specific processing steps may include selection, extraction, clipping, and network generation of the road vector data. The terminal may also perform processing in data analysis software (e.g., Python, R, Matlab), and the specific processing procedure may be: carrying out attribute coding and assignment on point-shaped and linear vector data to be constructed; based on administrative districts, selecting a city range in which a network model is required to be constructed, namely determining a target area, and performing mask cutting and vector data extraction in the target area; and for each POI data connection nearest neighbor road linear data, constructing an urban network model by taking the POI as a network node (node).
In one embodiment, as shown in fig. 4, the specific process of "acquiring a sample data set of a sample evaluation object" includes:
step 402, obtaining sample space characteristics and sample urban network distance characteristics of a sample evaluation object in the urban network model.
Specifically, the terminal determines, in the urban network model, sample spatial features of one or more sample evaluation objects (for example, longitude and latitude of the sample evaluation objects), and sample urban network distance features of the sample evaluation objects, where the sample urban network distance features may include a plurality of features, for example, the number of malls in the first area, the number of schools in the first area, the number of subway stations in the first area, the number of bus shows in the first area, the distance of the nearest mall, the distance of the nearest school, the distance of the nearest subway station, and the distance of the nearest bus station, the first area may be a circular area defined by taking the position of the sample evaluation object as a center and the first distance as a radius, and the first distance may be one kilometer, three kilometers, five kilometers, and so on.
In step 404, sample identification information of the sample evaluation object is determined according to the sample evaluation object.
Specifically, the terminal determines the sample identification information of the sample evaluation object (sample POI point), i.e., the name information of the sample evaluation object.
And step 406, determining sample resource data corresponding to the sample identification information in an association relation table of the preset identification and the reference resource data according to the sample identification information.
Specifically, the preset association relationship table between the identifier and the reference resource data may be a correspondence relationship between each evaluation object and resource data of each evaluation object in a target area determined by the terminal according to an actual application scenario. And the terminal inquires reference resource data corresponding to the sample identification information in an association relation table of preset identification and reference resource data based on the sample identification information, and takes the reference resource data as sample resource data of the sample evaluation object.
In one embodiment, the method for evaluating resource data further comprises:
and if the sample identification information is not inquired in the incidence relation table of the preset identification and the reference resource data, acquiring the average value of the transaction resource data of the area where the sample evaluation object is located in the preset time range, and taking the average value as the sample resource data corresponding to the sample identification information.
Specifically, the terminal queries sample resource data corresponding to the sample identification information in an association relationship table between a preset identification and reference resource data based on the sample identification information, and if sample resource data corresponding to the sample identification information is not queried, the terminal may obtain transaction resource data of an area where the sample evaluation object is located within a preset time range based on the sample identification information, calculate a mean value of the sample evaluation object according to the preset time range, and use the mean value as the sample resource data corresponding to the sample identification information, that is, the sample resource data of the sample evaluation object.
In an example, the sample evaluation object may be a property at the sample POI point, the sample identification information of the sample evaluation object may be the home name information of the property, the sample resource data of the sample evaluation object may be the price data of the property, and the association table of the preset identification and the reference resource data may be obtained by associating each sample evaluation object and the price data corresponding to each sample evaluation object. In this way, the terminal can create a new price field at the sample POI point and associate the price field with the price data of the property. For a target area where a guide price of a property has been published, the guide price of the property may be associated with a POI point where the property is located. For a city without published guiding prices, the terminal can select the average price of the house transaction unit prices in the last year as the unit price of the sample house, and the average price is associated with the POI point where the house is located.
In one embodiment, as shown in fig. 5, the specific process of step 204 "calculating the spatial feature influence coefficients and the city network distance feature influence coefficients in the initial geographic weighted regression model" includes:
step 502, calculating a spatial characteristic influence coefficient in the initial geographical weighted regression model through a preset Gaussian kernel function algorithm.
And step 504, calculating an urban network distance characteristic influence coefficient in the initial geographical weighted regression model through a preset local weighted least square algorithm.
Specifically, the terminal may obtain a sample spatial feature of the sample evaluation object, which may be latitude and longitude (u) of a given geographic location, and at least one urban network distance feature0，v0) The terminal can use local weighted least square algorithm to influence the coefficient beta corresponding to the distance characteristics of the j city networksj(u0,v0) The calculation is performed such that (j ═ 0,1,2, …, p) can be represented by the following formula:
wherein, wi(u0,v0) Is at a geographic location (u)0,v0) The spatial weight of (a). Order to
β(u0,v0)＝(β0(u0,v0),β1(u0,v0),…,βp(u0,v0))T
Then beta (u)0,v0) In (u)0,v0) At a local least squares estimate of
Wherein the content of the first and second substances,
X＝(X0,X1,…,Xp),Xj＝(x1j,x2j,…xnj)T
Y＝(Y1,Y2,…,Yn)T
W(u0,v0)＝Diag(w1(u0,v0),w2(u0,v0),…,wn(u0,v0))
for the influence coefficient corresponding to the sample spatial feature, the terminal may perform calculation through a preset gaussian kernel function algorithm, so that the terminal may select a gaussian kernel function from the spatial weighting kernel functions, and may specifically calculate through the following formula:
wherein h is the window width, dijIs (u)j,vj) To (u)i,vi) So that the window width h can be selected by cross-validation
In this way, the terminal can calculate the optimal window width by the following formula:
in one embodiment, as shown in fig. 6, the method for evaluating resource data further includes:
step 602, target resource data of a target evaluation object is obtained.
Specifically, the target evaluation object may be an object determined by the terminal according to an actual application scenario, and the terminal may obtain target resource data corresponding to the target evaluation object together, where the target resource data may be resource data to be detected or resource data to be determined, and the target resource data may be estimated by a third party organization for the target evaluation object.
Step 604, determining a target screening range according to the predicted resource data.
Specifically, the terminal may determine the predicted resource data Y of the target evaluation object by the method of the above embodiment, so that the terminal may perform calculation according to the predicted resource data and a preset floating threshold to obtain a target screening range, for example, the preset floating threshold may be 0.2 times of the predicted resource data, so that the target screening range may be [0.8Y, 1.2Y ].
And 606, generating risk prompt information corresponding to the target evaluation object under the condition that the target resource data exceeds the target screening range, and outputting the risk prompt information.
Specifically, the terminal may determine the target resource data of the target evaluation object according to the target screening range of the target evaluation object. If the target resource data of the target evaluation object is within the target screening range, the terminal can determine that the target resource data of the target evaluation object has no risk. If the target resource data of the target evaluation object is not in the target screening range, the terminal can determine that the target resource data of the target evaluation object has a risk, and thus, the terminal can generate risk prompt information.
In an example, the mode of the terminal outputting the risk prompting information may be through a preset display device, or may be through wireless communication to send to a mobile terminal corresponding to the target evaluation object.
In one embodiment, the sample urban network distance features include a total number of mated objects of each target type within the first area to which the sample evaluation object belongs and a shortest distance between the sample evaluation object and the mated objects for each target type.
In an alternative example, the terminal may consider more dimensional features when needing to perform more accurate evaluation on the resource data of the evaluation object, for example, the more dimensional features may include a floor feature, a volume rate feature, a construction year feature, and the like of the evaluation object.
The invention provides a resource data evaluation method and also provides a geographical weighted regression model based on vector network data, and a terminal can evaluate the resource data of an evaluation object with an unknown point through the geographical weighted regression model, so that a powerful grapple can be provided for credit workers to judge the resource data of the evaluation object (such as a house property and the like), bad account risks can be avoided, and illegal transactions can be pre-warned. Specifically, the terminal constructs an urban network model through data corresponding to each vector point in the target area and road linear data, estimates a plurality of evaluation objects included in an unknown area of undetermined resource data based on a geographic weighted regression model, and takes the resource allocation condition and the geographic position of urban public service facilities and commercial facilities as spatial weight factors influencing the distribution of the resource data, so that the problem that only the spatial location attribute is taken as a single influence factor, the spatial and resource attribute performances are combined more in line with the practical situation, and the distribution of the resource data of each evaluation object in the target area can be evaluated more accurately is avoided.
It should be understood that, although the steps in the flowcharts related to the embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides an evaluation apparatus for resource data, which is used for implementing the above-mentioned evaluation method for resource data. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the method, so that specific limitations in the embodiment of the device for evaluating one or more resource data provided below can be referred to the limitations of the method for evaluating resource data in the foregoing, and details are not described herein again.
In one embodiment, as shown in fig. 7, there is provided an apparatus 700 for evaluating resource data, including:
an obtaining module 701, configured to obtain, in a preset urban network model, a target space feature and a target urban network distance feature of a target evaluation object;
a calculating module 702, configured to calculate predicted resource data of the target evaluation object according to a target space feature, a target city network distance feature, and a geographic weighted regression model of the target evaluation object; the initial geographical weighting regression model is obtained by training the initial geographical weighting regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample space characteristics and sample urban network distance characteristics of the sample evaluation object.
In one embodiment, the apparatus 700 for evaluating resource data further includes:
the acquisition module is used for acquiring a sample data set of a sample evaluation object;
and the coefficient calculation module is used for calculating a spatial characteristic influence coefficient and an urban network distance characteristic influence coefficient in the initial geographical weighted regression model according to the sample resource data, the sample spatial characteristic, the sample urban network distance characteristic and a pre-established initial geographical weighted regression model of the sample evaluation object to obtain the trained geographical weighted regression model.
In one embodiment, the apparatus 700 for evaluating resource data further includes:
the data acquisition module is used for acquiring spatial characteristics and interest point data of a plurality of evaluation objects in a target area, wherein the interest point data comprises identification information, address information, coordinate information and category information;
the road vector data acquisition module is used for acquiring road vector data of a target area in a vector data map, wherein the road vector data comprises road type information and road position information;
and the generating module is used for calculating urban network distance characteristics corresponding to each evaluation object according to the spatial characteristics of the evaluation objects in the target area, the interest point data and the road vector data, and generating an urban network model corresponding to the target area.
In one embodiment, the acquisition module in the resource data evaluation apparatus 700 is specifically configured to:
obtaining sample space characteristics and sample urban network distance characteristics of the sample evaluation object in the urban network model;
determining sample identification information of the sample evaluation object according to the sample evaluation object;
and determining sample resource data corresponding to the sample identification information in an incidence relation table of preset identification and reference resource data according to the sample identification information.
In one embodiment, the apparatus 700 for evaluating resource data further includes:
and the query module is used for acquiring the average value of the transaction resource data of the area where the sample evaluation object is located in a preset time range if the sample identification information is not queried in the association relation table of the preset identification and the reference resource data, and taking the average value as the sample resource data corresponding to the sample identification information.
In one embodiment, the coefficient calculating module in the apparatus for evaluating resource data 700 is specifically configured to:
calculating a spatial feature influence coefficient in the initial geographical weighted regression model through a preset Gaussian kernel function algorithm;
and calculating the urban network distance characteristic influence coefficient in the initial geographical weighted regression model through a preset local weighted least square algorithm.
In one embodiment, the apparatus 700 for evaluating resource data further includes:
the risk evaluation module is used for acquiring target resource data of the target evaluation object;
the target screening range determining module is used for determining a target screening range according to the predicted resource data;
and the risk prompt information generation module is used for generating risk prompt information corresponding to the target evaluation object and outputting the risk prompt information under the condition that the target resource data exceeds the target screening range.
The respective modules in the above-described resource data evaluation device may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing relevant data of the evaluation object. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of evaluating resource data.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program implementing the steps in the method embodiments described below:
acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
calculating predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographic weighted regression model of the target evaluation object; the initial geographical weighting regression model is obtained by training the initial geographical weighting regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample space characteristics and sample urban network distance characteristics of the sample evaluation object.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method embodiments described below. :
acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the initial geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It should be noted that the method and apparatus of the embodiments of the present disclosure may be applied to the field of big data technology, the field of financial technology, or other related fields, and the method and apparatus of the embodiments of the present disclosure are not limited to the application field.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (11)
1. A method for evaluating resource data, the method comprising:
acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
calculating the predicted resource data of the target evaluation object according to the target space characteristics, the target city network distance characteristics and the geographical weighted regression model of the target evaluation object; the initial geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object.
2. The method of claim 1, further comprising:
collecting a sample data set of a sample evaluation object;
and calculating a space characteristic influence coefficient and an urban network distance characteristic influence coefficient in the initial geographical weighted regression model according to the sample resource data, the sample space characteristic, the sample urban network distance characteristic and a pre-established initial geographical weighted regression model of the sample evaluation object to obtain a trained geographical weighted regression model.
3. The method of claim 1, further comprising:
acquiring spatial characteristics and interest point data of a plurality of evaluation objects in a target area, wherein the interest point data comprises identification information, address information, coordinate information and category information;
acquiring road vector data of a target area in a vector data map, wherein the road vector data comprises road type information and road position information;
and calculating urban network distance characteristics corresponding to each evaluation object according to the spatial characteristics of the evaluation objects in the target area, the interest point data and the road vector data, and generating an urban network model corresponding to the target area.
4. The method of claim 3, wherein said acquiring a sample dataset of sample assessment objects comprises:
in the urban network model, acquiring sample space characteristics and sample urban network distance characteristics of the sample evaluation object;
determining sample identification information of the sample evaluation object according to the sample evaluation object;
and determining sample resource data corresponding to the sample identification information in an incidence relation table of preset identification and reference resource data according to the sample identification information.
5. The method of claim 4, further comprising:
if the sample identification information is not inquired in the incidence relation table of the preset identification and the reference resource data, obtaining an average value of transaction resource data of the area where the sample evaluation object is located in a preset time range, and taking the average value as the sample resource data corresponding to the sample identification information.
6. The method of claim 2, wherein the calculating spatial feature impact coefficients and city network distance feature impact coefficients in the initial geo-weighted regression model comprises:
calculating a spatial feature influence coefficient in the initial geographical weighted regression model through a preset Gaussian kernel function algorithm;
and calculating the urban network distance characteristic influence coefficient in the initial geographic weighted regression model through a preset local weighted least square algorithm.
7. The method of claim 1, further comprising:
acquiring target resource data of the target evaluation object;
determining a target screening range according to the predicted resource data;
and under the condition that the target resource data exceeds the target screening range, generating risk prompt information corresponding to the target evaluation object, and outputting the risk prompt information.
8. An apparatus for evaluating resource data, the apparatus comprising:
the acquisition module is used for acquiring target space characteristics and target urban network distance characteristics of a target evaluation object in a preset urban network model;
the calculation module is used for calculating the predicted resource data of the target evaluation object according to the target space characteristic, the target city network distance characteristic and the geographical weighted regression model of the target evaluation object; the initial geographical weighted regression model is obtained by training the initial geographical weighted regression model based on a sample data set of a sample evaluation object, wherein the sample evaluation object data set comprises sample resource data, sample spatial features and sample urban network distance features of the sample evaluation object.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
11. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210548659.5A CN114723338A (en) | 2022-05-20 | 2022-05-20 | Resource data evaluation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210548659.5A CN114723338A (en) | 2022-05-20 | 2022-05-20 | Resource data evaluation method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114723338A true CN114723338A (en) | 2022-07-08 |
Family
ID=82230823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210548659.5A Pending CN114723338A (en) | 2022-05-20 | 2022-05-20 | Resource data evaluation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114723338A (en) |
-
2022
- 2022-05-20 CN CN202210548659.5A patent/CN114723338A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016150407A1 (en) | Address resolution data-based construction land type rapid identification method | |
| US20150363700A1 (en) | Discovering Functional Groups of an Area | |
| Valente et al. | Apartment rent prediction using spatial modeling | |
| CN110659433B (en) | Method, device and equipment for POI value evaluation and computer storage medium | |
| CN109949063B (en) | Address determination method and device, electronic equipment and readable storage medium | |
| WO2021203728A1 (en) | Site selection method and apparatus for service development area, and computer device and medium | |
| CN110503485B (en) | Geographical region classification method and device, electronic equipment and storage medium | |
| Xu et al. | Simulating multiple urban land use changes by integrating transportation accessibility and a vector-based cellular automata: a case study on city of Toronto | |
| Pulugurtha et al. | Modeling annual average daily traffic with integrated spatial data from multiple network buffer bandwidths | |
| Jayasekare et al. | The price of a view: Estimating the impact of view on house prices | |
| KR20170121974A (en) | Device and method for providing building value maps | |
| CN114548811B (en) | Airport reachability detection method and device, electronic equipment and storage medium | |
| Gao et al. | Improving the accuracy of extant gridded population maps using multisource map fusion | |
| KR101835789B1 (en) | Method and device for determining future real estate based on number of future customrers coming into store | |
| Islam et al. | A GIS-based approach to explore the factors contributing towards Urban residential land development and re-development (LDR): a case of Rajshahi City Corporation area | |
| Mane et al. | Influence of proximal land use and network characteristics on link travel time | |
| Bajat et al. | Spatial hedonic modeling of housing prices using auxiliary maps | |
| Taima et al. | The relation between block size and building shape | |
| WO2020031296A1 (en) | Map data processing device | |
| CN108647189B (en) | Method and device for identifying user crowd attributes | |
| Ismail | Hedonic modelling of housing markets using geographical information system (gis) and spatial statistic:; a case study of glasgow, scotland | |
| CN114723338A (en) | Resource data evaluation method and device and computer equipment | |
| Zhang et al. | Influence of POI accessibility on temporal–spatial differentiation of housing prices: A case study of Hangzhou, China | |
| Chen et al. | Large-scale urban building function mapping by integrating multi-source web-based geospatial data | |
| Zhuwaki et al. | Network accessibility study to evaluate the extent of public transport coverage in the harare metropolitan area |
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 |