WO2018188509A1

WO2018188509A1 - Estate information processing method and apparatus, computer device and storage medium

Info

Publication number: WO2018188509A1
Application number: PCT/CN2018/081878
Authority: WO
Inventors: 王健宗; 黄章成; 吴天博; 肖京
Original assignee: 平安科技（深圳）有限公司
Priority date: 2017-04-11
Filing date: 2018-04-04
Publication date: 2018-10-18
Also published as: CN107798636A

Abstract

Proposed is an estate information processing method, comprising: acquiring a target geographical position corresponding to estate information to be estimated; by taking the target geographical position as a centre, searching, in an estate database, for information about the K estates closest to the target geographical position, wherein K is a positive integer greater than 0; and according to estate price information in the information about the K closest estates, calculating estate price information corresponding to the target geographical position by using an argmin function.

Description

Real estate information processing method, device, computer equipment and storage medium

This application claims the priority of the Chinese Patent Application filed on April 11, 2017, the Chinese Patent Office, Application No. 2017102472301, entitled "Real Estate Information Processing Method, Apparatus, Computer Equipment, and Storage Media", the entire contents of which are incorporated by reference. Combined in this application.

Technical field

The present application relates to the field of computer processing, and in particular, to a real estate information processing method, device, computer device and storage medium.

Background technique

With the development of the economy, the real estate finance industry has prospered, and residential real estate dominates all real estate assets. Correct evaluation of residential real estate value is of great significance to the development and investment of real estate finance. However, the current housing price assessment needs to rely on more information, such as the construction period, land use price, construction cost, etc., and because of the different ages of construction, the land use price, construction cost and other factors are not easy to collect and difficult to reconcile. The resulting price assessment is cumbersome and time consuming.

Summary of the invention

According to various embodiments of the present application, a method, an apparatus, a computer device, and a storage medium for processing real estate information are provided.

A method for processing real estate information, comprising:

Obtaining the target geographic location corresponding to the real estate information to be evaluated;

Centering on the target geographic location, searching for K property information closest to the target geographic location from the real estate database, wherein K is a positive integer greater than 0;

According to the real estate price information in the latest K real estate information, the argmin function is used to calculate the real estate price information corresponding to the target geographical location.

A real estate information processing device, comprising:

An obtaining module, configured to obtain a target geographic location corresponding to the real estate information to be evaluated;

a search module, configured to search, from the real estate database, the K real estate information closest to the target geographic location, where K is a positive integer greater than 0;

The calculating module is configured to calculate, according to the real estate price information in the latest K real estate information, an argmin function to calculate real estate price information corresponding to the target geographic location.

A computer device comprising a memory and one or more processors having stored therein computer readable instructions, the computer readable instructions being executed by the one or more processors such that the one or more The processors perform the following steps:

One or more non-transitory computer readable storage media storing computer executable instructions, when executed by one or more processors, cause the one or more processors to perform the following steps:

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below. Other features, objects, and advantages of the invention will be apparent from the description and appended claims.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. Other drawings may also be obtained from those of ordinary skill in the art in light of the inventive work.

FIG. 1 is an application scenario diagram of a real estate information processing method according to one or more embodiments.

2 is a block diagram of a terminal in accordance with one or more embodiments.

3 is a block diagram of a server in accordance with one or more embodiments.

4 is a flow chart of a method of processing a property information in accordance with one or more embodiments.

FIG. 5 is a flow chart of a method for processing real estate information in another embodiment.

6 is a flow chart of a method for processing real estate information in still another embodiment.

7 is a flow chart of a method for determining the credibility of a property price evaluation model under different K values according to one or more embodiments, and determining a K value corresponding to the property price evaluation model according to the calculated credibility.

FIG. 8 is a block diagram of a real estate information processing apparatus in accordance with one or more embodiments.

Figure 9 is a block diagram of a real estate information processing apparatus in another embodiment.

Figure 10 is a block diagram of a real estate information processing apparatus in still another embodiment.

11 is a block diagram of a determination module in accordance with one or more embodiments.

detailed description

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

The real estate information processing method provided by the application can be applied to the application scenario as shown in FIG. 1 . The terminal 102 communicates with the server 104 over a network. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablets, and portable wearable devices, and the server 104 can be implemented with a stand-alone server or a server cluster composed of a plurality of servers. First, the terminal 102 sends the target geographic location corresponding to the real estate information to be evaluated to the server 104. After the server 104 obtains the target geographic location corresponding to the real estate information to be evaluated, the terminal 104 searches for the target geographic location and searches from the real estate database. The K real estate information of the target geographical location, wherein K is a positive integer greater than 0; and calculating the real estate price corresponding to the target geographical location by using the argmin function according to the real estate price information in the latest K real estate information information.

As shown in FIG. 2, in some embodiments, the internal structure of terminal 102 is as shown in FIG. 2, including a processor, memory, network interface, display screen, and input device connected by a system bus. The processor of the terminal is used to provide computing and control capabilities to support the operation of the entire terminal. The memory of the terminal includes a non-transitory computer readable storage medium, an internal memory. The non-transitory computer readable storage medium of terminal 102 can store an operating system and computer readable instructions that, when executed, can cause the processor to perform a real estate information processing method. The network interface is used to connect to the network for communication. The display screen of the terminal 102 may be a liquid crystal display or an electronic ink display screen. The input device may be a touch layer covered on the display screen, or may be a button, a trackball or a touchpad provided on the outer casing of the electronic device, or may be An external keyboard, trackpad, or mouse. The terminal can be a tablet, a laptop, a desktop computer, or the like. It will be understood by those skilled in the art that the structure shown in FIG. 2 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific terminal may include a ratio. More or fewer components are shown in the figures, or some components are combined, or have different component arrangements.

As shown in FIG. 3, in some embodiments, the internal structure of server 104 is as shown in FIG. 3, including a processor, memory, and network interface connected by a system bus. The server's processor is used to provide computing and control capabilities that support the operation of the entire server. The memory of the server includes a non-transitory computer readable storage medium, an internal memory. The non-volatile storage medium can store operating system and computer readable instructions. When the computer readable instructions are executed, the processor can be caused to execute a real estate information processing method. The server's network interface is used to communicate with external servers or terminals over a network connection. Those skilled in the art can understand that the structure shown in FIG. 3 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the server to which the solution of the present application is applied. The specific server may include a ratio. More or fewer components are shown in the figures, or some components are combined, or have different component arrangements.

As shown in FIG. 4, in some embodiments, a real estate information processing method is proposed, which can be applied to a terminal or a server, and specifically includes the following steps:

Step 302: Obtain a target geographic location corresponding to the real estate information to be evaluated.

In one embodiment, the target geographic location refers to the location of the real estate information to be evaluated, and the target geographic location is represented by a latitude and longitude value. As the average transaction price of some real estates (that is, the average transaction price per unit area) is not directly available, it is necessary to estimate the real estate transaction prices that cannot be directly obtained, and the average transaction price is the geographical location of the real estate. The position is closely related, wherein the average transaction price refers to the average transaction price per unit area, that is, the average transaction price per square meter. Therefore, in order to be able to evaluate the average transaction price of the real estate corresponding to the average transaction price, it is necessary to obtain the target geographical location corresponding to the real estate information to be evaluated. The target geographical location of the real estate is fixed and can be obtained by traditional positioning technology. The latitude and longitude information of the property.

Step 304: Searching for K pieces of real estate information closest to the target geographical location from the real estate database centered on the target geographic location, where K is a positive integer greater than 0.

In one embodiment, after obtaining the target geographic location, the K real estate information closest to the target geographic location is searched from the real estate database centering on the target geographic location. Each property information in the real estate database includes the geographical location information of the real estate and the price information of the real estate. The price information of the real estate refers to the average price per square meter of the real estate. Among them, the value of K can be a fixed value set in advance, for example, K=5 can be set, then the corresponding is to find the 5 real estate information closest to the target geographical location from the real estate database. There are various methods for finding the latest K property information. In some embodiments, the distance between the target geographic location and the geographic location corresponding to each property in the real estate database is first calculated, and the calculated distance is as short to long. In order of the order, pick out the top K real estate information with the shortest distance, where K is a positive integer greater than zero.

In another embodiment, the real estate information in the real estate database is represented in the form of a node on the map according to the geographical location information of each real estate, and then the target geographic location is taken as the center, and the radius is scanned and acquired on the map. The K nodes with the closest geographical location, in some embodiments, are scanned by near and far radius scanning until the K property information closest to the target geographic location is obtained. In other embodiments, the radius of the scan may be set in advance (for example, radius = 500 m), and then all the real estate information in the radius is obtained, and the quantity of the acquired real estate information is taken as the value of K.

Step 306: Calculate the real estate price information corresponding to the target geographical location according to the real estate price information in the latest K real estate information by using the argmin function.

In one embodiment, the real estate information includes real estate location information and real estate price information. Among them, the real estate price information refers to the average transaction price per unit area, that is, the price per square meter of real estate. It should be noted that the price information of the real estate in this article refers to the transaction price per unit area. After obtaining the K property information closest to the target geographical location, the real estate price information corresponding to the target geographical location is calculated according to the real estate price information in the K real estate information. The specific calculation method can be calculated by the argmin function, and the argmin function represents the value of the argument when the function value is minimized. For example, if the target geographic location coordinates are (x', y'), the nearest K property information of the found distance (x', y') is {(p ₁ , x ₁ , y ₁ ), (p ₂ , x ₂ , y ₂ ) ... (p _k , x _k , y _k )}, where p _i represents the real estate price information, x _i , y _i represents the geographical location information of the real estate, x _i represents the longitude data, and y _i represents the latitude data. Among them, the subscript i is used to represent different real estates, then the real estate price information corresponding to the target geographical location satisfies the formula:

That is, when the function takes a small value, the value of p' is the calculated real estate price information corresponding to the target geographic location.

In one embodiment, by obtaining the target geographic location corresponding to the real estate information to be evaluated, and searching for the K real estate information closest to the target geographical location from the real estate database, and based on the nearest K The real estate price information in the real estate information uses the argmin function to calculate the real estate price information corresponding to the target geographical location. Compared with the traditional method, the method does not need any historical data that is old, may have been lost, and is difficult to collect. It only needs to know the geographical location of the real estate information to be evaluated, and can predict the corresponding real estate according to the geographical location information. The price is simple and convenient, and the method only needs to collect the geographical location information of the easily acquired real estate and the corresponding property price information, saving time and effort.

As shown in FIG. 5, in some embodiments, before the step of obtaining the target geographic location corresponding to the real estate information to be evaluated, the method further includes:

Step 400: Collect all the real estate information that can be obtained, and the real estate information includes the geographical location information of the real estate and the real estate price information.

In one embodiment, in order to be able to evaluate the unknown price information of a certain real estate, it is first necessary to obtain the real estate price information of the real estate, so as to facilitate the construction of the real estate database. Collect all the real estate information that can be obtained. The real estate information includes the geographical location information of the real estate and the real estate price information. The real estate price information here refers to the average transaction price of the real estate, that is, the transaction price per unit area. The price information of the real estate can be obtained by collecting past transaction data. Since the geographical location of the real estate is fixed, the corresponding geographical location information can obtain the corresponding latitude and longitude information through the traditional positioning technology.

In step 401, the geographical location information of the collected real estate and the price information of the corresponding real estate are correspondingly stored, and the real estate database is constructed.

In one embodiment, after collecting the geographical location information of the known real estate and the price information of the real estate, the geographical location information of the collected real estate and the corresponding price information are correspondingly stored, and the real estate database is constructed. In some embodiments, in order to facilitate subsequent quick search, each real estate information may be represented in the form of coordinate nodes on the map according to the geographical location information of the real estate, and each node represents a real estate information, including latitude and longitude information and price information. Build a real estate database displayed in the form of a map.

In one embodiment, it is only necessary to collect the geographical location information and the corresponding price information of the easily acquired real estate, and it is not necessary to obtain the real-time real estate data, and it is not necessary to obtain other data that is not easily obtained, for example, The population density information, etc., the method determines the corresponding price information based on the invisible relationship between the value of each real estate and the surrounding real estate, which is simple and convenient, and the accuracy is relatively high because the data does not depend on uncertain factors.

In some embodiments, the collected real estate geographic location information and the corresponding real estate price information are correspondingly stored, and the step 401 of constructing the real estate database includes: according to the geographical location information of the real estate, each real estate information is in the form of a node on the map. Said to build a real estate database displayed in the form of a map. Step 404 includes: taking the target geographic location as the center, acquiring K nodes closest to the target geographic location on the map by near and far scanning, and K is a positive integer greater than 0.

In one embodiment, in order to facilitate the search for the real estate information that is relatively close to the target geographical location, after obtaining the known real estate information, the real estate information is mapped on the map according to the geographical location information of the real estate (ie, the longitude and latitude information). The coordinates are displayed in a way to build a real estate database displayed in the form of a map. Each node displayed on the map represents a property information, and can visually display the distance between the properties. After obtaining the target geographical location of the real estate information to be evaluated, the target geographical location is displayed on the map, and the known real estate information is also displayed on the map. Then, based on the target geographic location, K nodes closest to the target geographic location are acquired on the map by near and far circumferential scanning. Specifically, it may be set to scan at a fixed radius centering on the target geographic location, wherein when less than K nodes are found by scanning a circle with a fixed radius, the length of the radius is sequentially increased, and scanning is continued until the acquisition is performed. To the K nodes closest to the target geographic location, K is a pre-set positive integer greater than zero.

As shown in FIG. 6, in some embodiments, before the step of obtaining the target geographic location corresponding to the real estate information to be evaluated, the method includes:

In step 408, a nearest neighbor algorithm is used to establish a property price evaluation model.

In one of the embodiments, firstly, in order to evaluate the unknown property price information, a K-Nearest Neighbor (KNN) algorithm is used to establish a property price evaluation model, and the model needs to be trained to determine the corresponding Parameter K value. Among them, the KNN algorithm is a theoretically mature method and one of the relatively simple machine learning algorithms. The idea of this method is: if a sample is the most similar in the feature space (ie, the closest in the feature space) Most of the samples belong to a certain category, and the sample also belongs to this category. In the KNN algorithm, the selected neighbors are all objects that have been correctly classified. The method determines the category to which the sample to be classified belongs according to the category of the nearest neighbor or samples. Therefore, using the nearest neighbor algorithm to establish a property price evaluation model is relatively simple, but it has a scientific theoretical basis and can accurately predict the corresponding property price information.

Step 410: Calculate the credibility of the property price evaluation model under different K values, and determine the K value corresponding to the property price evaluation model according to the calculated credibility.

In one of the embodiments, after the nearest neighbor algorithm is used to establish the property price evaluation model, the most important thing is to train the value of the parameter K, that is, it is most suitable to determine the neighboring points. Among them, the training set used in the training of the above-mentioned property price evaluation model is the real estate information of the known property price information that has been obtained, that is, the real estate information in the real estate database. The most appropriate K value is determined by calculating the credibility of the property evaluation model at different K values.

Specifically, in order to determine the parameter K of the property price evaluation model, K is assigned different values, and then the estimated price of the real estate corresponding to each node is calculated under different K values. After obtaining the estimated price of the real estate corresponding to each node under different K values, the real value of the real estate price corresponding to each node is obtained from the real estate database, and then according to the estimated value of the real estate price of each node and the corresponding The true value of the real estate price of each node calculates the credibility corresponding to the property price evaluation model under different K values. The greater the credibility, the more accurate the forecasting of the property price evaluation model is, so the corresponding credibility is the largest. The K value is taken as the determined K value. Among them, the calculation of credibility depends on the deviation and absolute deviation between the calculated real value of each point and the estimated value.

As shown in FIG. 7 , in some embodiments, the credibility of the property price evaluation model under different K values is separately calculated, and the step 310 of determining the K value corresponding to the property price evaluation model according to the calculated credibility includes:

Step 410A, traverse each node in the real estate database under different K values, and obtain K nodes closest to each node from the real estate database, and calculate each according to the real estate price information corresponding to the nearest K nodes. The estimated price of the real estate corresponding to a node, where K is a positive integer greater than zero.

In one of the embodiments, in order to determine the parameter K of the property price evaluation model, K is assigned different values, and then the estimated price of the real estate corresponding to each node is calculated under different K values. Specifically, after assigning K to a specific value, traverse each node in the real estate database, and obtain K nodes closest to each node from the real estate database, according to the latest price of the nearest K nodes. The information uses the argmin function to calculate the estimated price of the real estate corresponding to each node, where the value given to K is a positive integer greater than zero. In order to obtain the appropriate K value more accurately, in the case of K=1, 2, 3...n, calculate the estimated price of the real estate corresponding to each node in the real estate database.

Step 410B: Calculate the credibility of the property price evaluation model under different K values according to the estimated value of the real estate price of each node and the corresponding real value of the real estate price.

In one embodiment, after obtaining the estimated price of the real estate corresponding to each node under different K values, the real value of the real estate price corresponding to each node is respectively obtained from the real estate database, and then according to each node The estimated value of the real estate price and the corresponding real value of the real estate price of each node calculate the credibility corresponding to the property price evaluation model under different K values. Among them, the calculation of credibility depends on the deviation and absolute deviation between the calculated real value of each point and the estimated value. Calculate the mean and variance of the deviations of all nodes and the mean and variance of the absolute deviations according to the deviation and absolute deviation between the real value and the estimated value of each point of the real estate price. The credibility of the property price evaluation model under different K values is determined according to the calculated mean and variance of the deviations of all nodes and the mean and variance of the absolute deviations. Among them, the mean and variance of the deviation of all nodes and the mean and variance of the absolute deviation are the smaller the value, the higher the corresponding credibility. Specifically, after calculating the true value and the estimated value of each node, the mean and variance of the deviations of all nodes are calculated, and the calculation formula is as follows:

Where N represents the number of all nodes, p _i and

Represents the true value of each property and the estimated value calculated using the above property valuation model.

After calculating the absolute difference between the true value and the estimated value of each node, the formula for calculating the mean and variance of the absolute difference of the deviation is as follows:

In some embodiments, it is also necessary to calculate a probability that the absolute difference between the true value and the estimated value of each node is greater than a given value τ, and the specific formula is as follows:

among them,

According to the above indicators, the credibility of the property price evaluation model under different K values is calculated. The smaller the better, the smaller the various indicators obtained above, the greater the corresponding credibility. In some embodiments, first, the mean of the calculated deviations, the smaller the mean is, the smaller the degree of offset is. In the case where the mean is equivalent, the lower the variance, the smaller the error of the evaluation. Therefore, the weights of the mean and the variance can be set in advance. Generally, the weight of the mean is relatively large, and the weight of the variance is relatively small. After calculating the mean and variance, the error value calculated by the weighted summation, the error value is inversely related to the credibility, that is, the smaller the error value, the greater the credibility. Subsequently, the appropriate K value is determined by comparing the magnitude of the credibility as a parameter of the above-mentioned property evaluation model.

In step 410C, the K value corresponding to the property price evaluation model is determined according to the calculated credibility of the property price evaluation model under different K values.

In one of the embodiments, the higher the credibility of the calculated property price evaluation model, the more accurate the land price evaluation model is used to evaluate the property price. Therefore, the K value corresponding to the maximum credibility is selected as the parameter K of the property evaluation model.

It should be understood that although the various steps in the flowcharts of FIGS. 4 through 7 are sequentially displayed as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Except as explicitly stated herein, the execution of these steps is not strictly limited, and the steps may be performed in other orders. Moreover, at least some of the steps in Figures 4 to 7 may comprise a plurality of sub-steps or stages, which are not necessarily performed at the same time, but may be performed at different times, these sub-steps or stages The order of execution is not necessarily performed sequentially, but may be performed alternately or alternately with at least a portion of other steps or sub-steps or stages of other steps.

As shown in FIG. 8, in some embodiments, a real estate information processing apparatus is proposed, the apparatus comprising:

The obtaining module 802 is configured to obtain a target geographic location corresponding to the real estate information to be evaluated.

The searching module 804 is configured to search, from the real estate database, the K real estate information closest to the target geographic location, where the target location is 804, where K is a positive integer greater than 0.

The calculating module 806 is configured to calculate, according to the real estate price information in the latest K real estate information, an argmin function to calculate real estate price information corresponding to the target geographic location.

As shown in FIG. 9, in some embodiments, the foregoing real estate information processing apparatus further includes:

The collecting module 800 is configured to collect all the real estate information that can be obtained, and the real estate information includes real estate geographic location information and real estate price information.

The storage module 801 is configured to store the collected geographical location information of the real estate and the corresponding real estate price information to construct a real estate database.

In some embodiments, the collection module 800 is further configured to represent each real estate information in the form of a node on the map according to the geographical location information of the real estate, and construct a real estate database displayed in a map form. The searching module 804 is further configured to acquire K nodes closest to the target geographic location in the near and far scanning manner on the map centered on the target geographic location, where K is a positive integer greater than 0. .

As shown in FIG. 10, in some embodiments, the foregoing real estate information processing apparatus further includes:

The module 808 is configured to establish a property price evaluation model by using a nearest neighbor algorithm.

The determining module 810 is configured to separately calculate the credibility of the property price evaluation model under different K values, and determine the K value corresponding to the property price evaluation model according to the calculated credibility.

As shown in FIG. 11, in some embodiments, the determining module 810 includes:

The estimated value calculation module 810A is configured to traverse each node in the real estate database under different K values, and obtain K nodes closest to each node from the real estate database, according to the latest The real estate price information corresponding to the K nodes calculates the estimated price of the real estate corresponding to each node, where K is a positive integer greater than zero.

The credibility calculation module 810B is configured to calculate the credibility of the corresponding property price evaluation model according to the real value of the real estate price of each node and the corresponding estimated value of the real estate price.

The K value determining module 810C is configured to determine a K value corresponding to the property price evaluation model according to the calculated credibility of the property price evaluation model under different K values.

Each module in the above-mentioned real estate information processing apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The network interface may be an Ethernet card or a wireless network card. The above modules may be embedded in the hardware in the processor or in the memory in the server, or may be stored in the memory in the server, so that the processor calls the corresponding operations of the above modules. The processor can be a central processing unit (CPU), a microprocessor, a microcontroller, or the like.

The above-described real estate information processing apparatus can be implemented in the form of a computer readable instruction which can be run on a terminal or server as shown in FIG. 2 or 3.

The embodiment of the present application provides a computer device. The internal structure of the computer device may correspond to the structure shown in FIG. 2 or 3, that is, the computer device may be a server or a terminal, and the device includes a series of storage on the memory. The computer readable instructions, when the computer readable instructions are executed by the processor, can implement the real estate information processing method proposed by the embodiments of the present application. Embodiments of the present application propose a computer device including a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor executing the computer The readable instruction implements the following steps: obtaining a target geographic location corresponding to the real estate information to be evaluated; and searching for the K real estate information closest to the target geographical location from the real estate database centering on the target geographic location, wherein K It is a positive integer greater than 0; the real estate price information corresponding to the target geographic location is calculated according to the real estate price information in the latest K real estate information by using the argmin function.

In some embodiments, one or more non-transitory computer readable storage media storing computer-executable instructions are provided, which when executed by one or more processors, cause the one or The plurality of processors perform the following steps: obtaining the target geographic location corresponding to the real estate information to be evaluated; and searching for the K real estate information closest to the target geographical location from the real estate database centering on the target geographic location, wherein K It is a positive integer greater than 0; the real estate price information corresponding to the target geographic location is calculated according to the real estate price information in the latest K real estate information by using the argmin function.

A person skilled in the art can understand that all or part of the process of implementing the above embodiment method can be completed by a computer program to instruct related hardware, and the computer program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The technical features of the above-described embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be considered as the scope of this manual.

The above-mentioned embodiments are merely illustrative of several embodiments of the present application, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the present application. Therefore, the scope of the invention should be determined by the appended claims.

Claims

A method for processing real estate information, comprising:

Obtaining the target geographic location corresponding to the real estate information to be evaluated;

Centering on the target geographic location, searching for K property information closest to the target geographic location from the real estate database, wherein K is a positive integer greater than 0;

According to the real estate price information in the latest K real estate information, the argmin function is used to calculate the real estate price information corresponding to the target geographical location.
The method according to claim 1, further comprising: before acquiring the target geographic location corresponding to the real estate information to be evaluated, further comprising:

Collect all the real estate information that can be obtained, and the real estate information includes the geographical location information of the real estate and the real estate price information;

The geographical location information of the collected real estate and the corresponding real estate price information are stored correspondingly, and the real estate database is constructed.
The method according to claim 2, wherein the collected geographical location information of the real estate and the corresponding real estate price information are correspondingly stored, and the real estate database is constructed, including:

According to the geographical location information of the real estate, each real estate information is represented in the form of a node on the map, and a real estate database displayed in the form of a map is constructed;

And searching, by the target geographic location, the K real estate information closest to the target geographic location from the real estate database, wherein the step of K being a positive integer greater than 0 includes:

Centering on the target geographic location, K nodes closest to the target geographic location are acquired on the map by near and far scanning, and K is a positive integer greater than zero.
The method according to claim 2, further comprising: before the obtaining the target geographic location corresponding to the real estate information to be evaluated,

Establishing a property price evaluation model using the nearest neighbor algorithm; and

The credibility of the property price evaluation model under different K values is calculated separately, and the K value corresponding to the property price evaluation model is determined according to the calculated credibility.
The method according to claim 4, wherein the calculating the credibility of the property price evaluation model under different K values, and determining the K value corresponding to the property price evaluation model according to the calculated credibility includes :

Navigating each node in the real estate database under different K values, and obtaining K nodes closest to each node from the real estate database, according to the real estate price information corresponding to the nearest K nodes Calculate the estimated price of the real estate corresponding to each node, where K is a positive integer greater than 0;

Calculating the credibility of the corresponding property price evaluation model according to the actual value of the real estate price of each node and the corresponding estimated value of the real estate price; and

The K value corresponding to the property price evaluation model is determined according to the calculated credibility of the property price evaluation model under different K values.
A real estate information processing device, comprising:

An obtaining module, configured to obtain a target geographic location corresponding to the real estate information to be evaluated;

a search module, configured to search, from the real estate database, the K real estate information closest to the target geographic location, where K is a positive integer greater than 0;

The calculating module is configured to calculate, according to the real estate price information in the latest K real estate information, an argmin function to calculate real estate price information corresponding to the target geographic location.
The device according to claim 6, wherein the device further comprises:

The collection module is configured to collect all the real estate information that can be obtained, and the real estate information includes the geographical location information of the real estate and the real estate price information;

The storage module is configured to store the collected geographical location information of the real estate and the corresponding real estate price information to construct a real estate database.
The device according to claim 7, wherein the collection module is further configured to display each real estate information in the form of a node on a map according to the geographical location information of the real estate, and construct a real estate database displayed in a map form;

The searching module is further configured to acquire K nodes closest to the target geographic location in the near and far scanning manner on the map centered on the target geographic location, where K is a positive integer greater than 0.
The device according to claim 6, wherein the device further comprises:

Establishing a module for establishing a property price evaluation model using a nearest neighbor algorithm; and

The determining module is configured to separately calculate the credibility of the property price evaluation model under different K values, and determine the K value corresponding to the property price evaluation model according to the calculated credibility.
The apparatus according to claim 9, wherein the determining module comprises:

An estimated value calculation module, configured to traverse each node in the real estate database under different K values, and obtain K nodes closest to each node from the real estate database, according to the nearest K The real estate price information corresponding to each node calculates the estimated price of the real estate corresponding to each node, where K is a positive integer greater than 0;

The credibility calculation module is configured to calculate the credibility of the corresponding property price evaluation model according to the real value of the real estate price of each node and the corresponding estimated value of the real estate price; and

The K value determining module is configured to determine a K value corresponding to the property price evaluation model according to the calculated credibility of the property price evaluation model under different K values.
A computer device comprising a memory and one or more processors, the memory storing computer readable instructions, the computer readable instructions being executed by the one or more processors such that the one or more The processors perform the following steps:

Obtaining the target geographic location corresponding to the real estate information to be evaluated;

Centering on the target geographic location, searching for K property information closest to the target geographic location from the real estate database, wherein K is a positive integer greater than 0;

According to the real estate price information in the latest K real estate information, the argmin function is used to calculate the real estate price information corresponding to the target geographical location.
The computer device according to claim 11, wherein the processor is further configured to perform the following steps before acquiring the target geographic location corresponding to the real estate information to be evaluated:

Collect all the real estate information that can be obtained, and the real estate information includes the geographical location information of the real estate and the real estate price information;

The geographical location information of the collected real estate and the corresponding real estate price information are stored correspondingly, and the real estate database is constructed.
The computer device according to claim 12, wherein the collected geographical location information of the real estate and the corresponding real estate price information are correspondingly stored, and the real estate database is constructed, including:

According to the geographical location information of the real estate, each real estate information is represented in the form of a node on the map, and a real estate database displayed in the form of a map is constructed;

And searching, by the target geographic location, the K real estate information closest to the target geographic location from the real estate database, wherein the step of K being a positive integer greater than 0 includes:

Centering on the target geographic location, K nodes closest to the target geographic location are acquired on the map by near and far scanning, and K is a positive integer greater than zero.
The computer device according to claim 12, wherein the processor is further configured to perform the following steps before the obtaining the target geographic location corresponding to the real estate information to be evaluated:

Establishing a property price evaluation model using the nearest neighbor algorithm; and

The credibility of the property price evaluation model under different K values is calculated separately, and the K value corresponding to the property price evaluation model is determined according to the calculated credibility.
The computer device according to claim 14, wherein the calculating the credibility of the property price evaluation model under different K values, and determining the K value corresponding to the property price evaluation model according to the calculated credibility include:

Navigating each node in the real estate database under different K values, and obtaining K nodes closest to each node from the real estate database, according to the real estate price information corresponding to the nearest K nodes Calculate the estimated price of the real estate corresponding to each node, where K is a positive integer greater than 0;

Calculating the credibility of the corresponding property price evaluation model according to the real value of the real estate price of each node and the corresponding estimated value of the real estate price; and determining the credibility of the property price evaluation model under different K values according to the calculation The K value corresponding to the property price evaluation model.
One or more non-transitory computer readable storage media storing computer executable instructions, when executed by one or more processors, cause the one or more processors to perform the following steps:

Obtaining the target geographic location corresponding to the real estate information to be evaluated;

Centering on the target geographic location, searching for K property information closest to the target geographic location from the real estate database, wherein K is a positive integer greater than 0;

According to the real estate price information in the latest K real estate information, the argmin function is used to calculate the real estate price information corresponding to the target geographical location.
The storage medium according to claim 16, wherein the processor is further configured to perform the following steps before acquiring the target geographic location corresponding to the real estate information to be evaluated:

Collect all the real estate information that can be obtained, and the real estate information includes the geographical location information of the real estate and the real estate price information;

The geographical location information of the collected real estate and the corresponding real estate price information are stored correspondingly, and the real estate database is constructed.
The storage medium according to claim 17, wherein the collected real estate geographic location information and the corresponding real estate price information are correspondingly stored, and the real estate database is constructed, including:

According to the geographical location information of the real estate, each real estate information is represented in the form of a node on the map, and a real estate database displayed in the form of a map is constructed;

And searching, by the target geographic location, the K real estate information closest to the target geographic location from the real estate database, wherein the step of K being a positive integer greater than 0 includes:

Centering on the target geographic location, K nodes closest to the target geographic location are acquired on the map by near and far scanning, and K is a positive integer greater than zero.
The storage medium according to claim 17, wherein the processor is further configured to perform the following steps before the obtaining the target geographic location corresponding to the real estate information to be evaluated:

Establishing a property price evaluation model using the nearest neighbor algorithm; and

The credibility of the property price evaluation model under different K values is calculated separately, and the K value corresponding to the property price evaluation model is determined according to the calculated credibility.
The storage medium according to claim 19, wherein the calculating the credibility of the property price evaluation model under different K values, and determining the K value corresponding to the property price evaluation model according to the calculated credibility include:

Navigating each node in the real estate database under different K values, and obtaining K nodes closest to each node from the real estate database, according to the real estate price information corresponding to the nearest K nodes Calculate the estimated price of the real estate corresponding to each node, where K is a positive integer greater than 0;

Calculating the credibility of the corresponding property price evaluation model according to the actual value of the real estate price of each node and the corresponding estimated value of the real estate price; and

The K value corresponding to the property price evaluation model is determined according to the calculated credibility of the property price evaluation model under different K values.