Geographic object value evaluation method and device

Abstract

The invention discloses a geographic object value evaluation method and device, and the method comprises the steps: obtaining the attribute data of a to-be-evaluated geographic object, and determining a first result of the to-be-evaluated geographic object according to the attribute data; obtaining historical trading prices of all the similar geographic objects and calculating a second result of statistical values of all the historical trading prices; obtaining historical transaction prices of other geographic objects in the region where the to-be-evaluated geographic object is located at different times, and determining a predicted value of an evaluation result of the current region as a third result according to a fitting curve determined by a relation between the historical transaction prices and the time; calculating the ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve, and taking the ratio as a trend change coefficient; and adjusting the first result by using the missing degree of the similar geographic object as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount to obtain a value evaluation result of the to-be-evaluated geographic object.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for evaluating the value of a geographic object. Background Art

[0002] The valuation of geographic objects (such as real estate) refers to the assessment of the resource data required for the transfer of ownership of geographic objects. It is a key technology for realizing asset digitization. The accuracy of geographic object valuation is of great significance to geographic object transactions and is also an important prerequisite for the digitization of asset transactions.

[0003] At present, when evaluating the value of geographic objects, one way is to rely on manual calculation to evaluate the value of geographic objects. Manual calculation valuation not only has a long cycle and high cost, but also has large evaluation differences due to different appraisers' experience and preferences. The other way is to use the geographic object valuation model to estimate the value of geographic objects. The value of geographic objects is estimated in digital form. Although it can improve the accuracy of the evaluation compared with manual calculation, when using the existing geographic object valuation model to evaluate the value of geographic objects, it is necessary to collect a large amount of disordered related data, and the collected data will vary from user to user. This causes this method to not only occupy a large amount of computing resources and be time-consuming and labor-intensive, but also there will be large differences between the valuation results of geographic objects and the actual transaction results, and between the usage results of different users, resulting in the geographic object transaction cycle being too long or unable to be completed.

[0004] Therefore, how to improve the efficiency of geographic object value assessment while reducing computing resources is an urgent problem that needs to be solved. Summary of the invention

[0005] The embodiment of the present application provides a geographic object value assessment method to improve the efficiency of geographic object value assessment while reducing computing resources.

[0006] The embodiment of the present application provides a method for evaluating the value of a geographic object, including: determining a geographic object to be evaluated; obtaining attribute data of the geographic object to be evaluated, and determining a preliminary value evaluation result of the geographic object to be evaluated based on the attribute data as a first result; determining at least one similar geographic object to the geographic object to be evaluated, obtaining historical transaction prices of all similar geographic objects, and calculating statistical values ​​of all historical transaction prices as a second result of similarity prediction; obtaining historical transaction prices of other geographic objects in the area where the geographic object to be evaluated is located at different times, determining a predicted value of the current evaluation result of the area based on a fitting curve determined by the relationship between the historical transaction prices and time as a third result, and calculating a ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as a trend change coefficient; determining the missing degree of the similar geographic object based on the number of similar geographic objects to the geographic object to be evaluated and the number of transaction objects in the area where the geographic object to be evaluated is located; using the missing degree as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount, adjusting the first result to obtain a value evaluation result of the geographic object to be evaluated.

[0007] Optionally, the calculation of the statistical values ​​of all historical transaction prices includes: A similarity characterizing the degree of association between each similar geographic object and the geographic object to be evaluated is determined, and a statistical value of all historical transaction prices is calculated by weighted averaging all historical transaction prices using the similarity as a weight.

[0008] Optionally, the calculation of the statistical values ​​of all historical transaction prices includes: The statistical value of all historical transaction prices is calculated by taking the arithmetic average of all historical transaction prices or taking the median of all historical transaction prices.

[0009] Optionally, the similar geographical objects are determined using predefined rules; wherein the predefined rules at least include: Taking all or part of other geographical objects in the set area to which the geographical object to be evaluated belongs as similar geographical objects; Other geographical objects in the set area to which the geographical object to be evaluated belongs and / or in the adjacent set area having the same or similar area as the geographical object to be evaluated are regarded as similar geographical objects; Other geographical objects in the set area to which the geographical object to be evaluated belongs and / or in the adjacent set area having the same or similar floor as the geographical object to be evaluated are regarded as similar geographical objects; Other geographical objects in the set area to which the geographical object to be evaluated belongs that are in the same building or adjacent to the geographical object to be evaluated are regarded as similar geographical objects.

[0010] Optionally, determining similar geographical objects to the geographical object to be evaluated by clustering method includes: Determine other geographical objects in the area where the geographical object to be evaluated is located or in an adjacent area of ​​the area; Acquire attribute data of the other geographic objects; Clustering the other geographic objects according to the attribute data and using the attribute categories as clustering features; Determine geographical objects similar to the geographical object to be evaluated from different clusters.

[0011] Optionally, determining geographical objects similar to the geographical object to be evaluated from different clusters includes: Determine the similarity between other geographic objects in different clusters and the geographic object to be evaluated, Other geographical objects whose similarity exceeds a set threshold are regarded as similar geographical objects to the geographical object to be evaluated.

[0012] Optionally, the similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: According to the attribute data of the geographic object to be evaluated, a vector representation of the attribute data is obtained as a first vector; Obtaining a vector representation of attribute data of any other geographic object as a second vector; The cosine similarity between the first vector and the second vector is calculated as the similarity between the other geographic object and the geographic object to be evaluated.

[0013] Optionally, the similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: Determine the geographical distance between the geographical object to be evaluated and any other geographical object according to the geographical location information of the geographical object to be evaluated and the geographical location information of any other geographical object; The geographical distance is used as the similarity between the other geographical object and the geographical object to be evaluated.

[0014] Optionally, the similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: Convert the house type of the geographic object to be evaluated into a numerical feature representation as a third vector; Convert the house type data of any other geographic object into a numerical feature representation as a second vector; The cosine similarity between the third vector and the fourth vector is calculated as the similarity between the other geographic object and the geographic object to be evaluated.

[0015] Optionally, the similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: Normalize the areas of other geographic objects; The normalized result is used as the similarity between other geographic objects and the geographic object to be evaluated.

[0016] Optionally, also include: Obtain the category data of the geographic object to be evaluated and the city data to which it belongs; Determining, according to the category data and the attribute data, an evaluation result of the to-be-evaluated geographic object as a first additional result; Determine, according to the city data and the attribute data, an evaluation result of the to-be-evaluated geographic object as a second additional result; The value assessment result is integrated with the first additional result and the second additional result to obtain a total assessment result of the geographic object to be assessed.

[0017] Optionally, after obtaining the value assessment result or the overall evaluation result of the geographic object to be assessed, it also includes: The value assessment result or the total assessment result of the geographic object to be assessed is revised using a dynamic revision strategy, including: Determine the favorable or unfavorable factors that may affect the value assessment of the geographical object to be assessed; Determine the impact of the positive or negative event on the current value assessment as a correction factor; The correction coefficient is used to correct the value assessment result or the overall assessment result of the geographical object to be assessed.

[0018] The embodiment of the present application also provides a geographic object value assessment device, including: a determination unit, used to determine the geographic object to be assessed; a first result assessment unit, used to obtain attribute data of the geographic object to be assessed, and determine the preliminary value assessment result of the geographic object to be assessed according to the attribute data as a first result; a second result acquisition unit, used to determine at least one similar geographic object to the geographic object to be assessed, obtain the historical transaction prices of all similar geographic objects, and calculate the statistical value of all historical transaction prices as a second result of similar prediction; a trend change coefficient determination unit, used to obtain the historical transaction prices of other geographic objects in the area where the geographic object to be assessed is located at different times, and determine the preliminary value assessment result of the geographic object to be assessed according to the attribute data as a first result; a second result acquisition unit, used to determine at least one similar geographic object to the geographic object to be assessed, obtain the historical transaction prices of all similar geographic objects, and calculate the statistical value of all historical transaction prices as a second result of similar prediction; A fitting curve determined by the relationship between historical transaction prices and time is used to determine the predicted value of the current evaluation result of the area as the third result, and the ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve is calculated as the trend change coefficient; a missing degree determination unit is used to determine the missing degree of the similar geographical object according to the number of similar geographical objects to the geographical object to be evaluated and the number of transaction objects in the area where the geographical object to be evaluated is located; a value assessment result determination unit is used to use the missing degree as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount to adjust the first result to obtain the value assessment result of the geographical object to be evaluated.

[0019] The present application also provides an electronic device, which includes a processor and a memory; a computer program is stored in the memory, and the processor executes the above method after running the computer program.

[0020] The present application also provides a computer storage medium, wherein the computer storage medium stores a computer program, and after the computer program is run by a processor, the above method is executed.

[0021] Compared with the prior art, the embodiments of the present application have the following advantages: The embodiment of the present application provides a method for evaluating the value of a geographic object, including: determining a geographic object to be evaluated; obtaining attribute data of the geographic object to be evaluated, and determining a preliminary value evaluation result of the geographic object to be evaluated based on the attribute data as a first result; determining at least one similar geographic object to the geographic object to be evaluated, obtaining historical transaction prices of all similar geographic objects, and calculating statistical values ​​of all historical transaction prices as a second result of similarity prediction; obtaining historical transaction prices of other geographic objects in the area where the geographic object to be evaluated is located at different times, determining a predicted value of the current evaluation result of the area based on a fitting curve determined by the relationship between the historical transaction prices and time as a third result, and calculating a ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as a trend change coefficient; determining the missing degree of the similar geographic object based on the number of similar geographic objects to the geographic object to be evaluated and the number of transaction objects in the area where the geographic object to be evaluated is located; using the missing degree as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount, adjusting the first result to obtain a value evaluation result of the geographic object to be evaluated.

[0022] The geographic object value assessment method described in the embodiment of the present application comprehensively considers the impact of the preliminary value assessment result determined based on the attribute data of the geographic object to be assessed, the statistical value of the historical transaction prices of all similar geographic objects similar to the geographic object to be assessed, the predicted value of the current assessment result of the area determined by the fitting curve determined by the relationship between the historical transaction prices and time of other geographic objects in the area where the geographic object to be assessed is located at different times, the trend change coefficient determined by the ratio of the predicted value to the historical transaction price corresponding to the previous time unit on the fitting curve, and the missing degree of similar geographic objects on the value assessment result of the geographic object to be assessed, when obtaining the value assessment result of the geographic object to be assessed, thereby improving the accuracy of the value assessment of the geographic object to be assessed, and the data required for the assessment calculation are ordered and determined, which reduces the consumption of computing resources, improves the efficiency of the assessment calculation and the stability of the calculation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the first application scenario of a geographic object value assessment method provided in the first embodiment of the present application.

[0024] Figure 2 It is a schematic diagram of a second application scenario of a geographic object value assessment method provided in the first embodiment of the present application.

[0025] Figure 3 It is a flowchart of a method for assessing the value of a geographic object provided in the first embodiment of the present application.

[0026] Figure 4It is a schematic diagram of a fitting curve in a geographic object value assessment method provided in the first embodiment of the present application.

[0027] Figure 5 It is a schematic diagram of a geographic object value assessment device provided in the second embodiment of the present application.

[0028] Figure 6 This is a schematic diagram of an electronic device provided in the third embodiment of the present application. DETAILED DESCRIPTION

[0029] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0030] First, in order to enable those skilled in the art to better understand the present application, the following describes in detail the specific application scenarios of the embodiments of the present application based on a geographic object data processing method provided by the present application. Before describing in detail the specific application scenarios of the embodiments of the present application, the background of the solution is first described.

[0031] The valuation of geographic objects (such as real estate) refers to the evaluation of resource data required for the transfer of ownership of geographic objects. It is a key technology for the digitization of assets. The accuracy of the valuation of geographic objects is of great significance to the transaction of geographic objects and is also an important prerequisite for the digitization of asset transactions. At present, when evaluating the value of geographic objects, one is to rely on manual calculation to evaluate the value of geographic objects. Manual valuation is not only long and costly, but also has large evaluation differences due to the experience and preferences of appraisers. The other is to use the geographic object valuation model to estimate the value of geographic objects and use digital form to estimate the value of geographic objects. Although it can improve the accuracy of the evaluation compared with manual calculation, when using the existing geographic object valuation model to evaluate the value of geographic objects, it is necessary to collect a large amount of disordered related data, and the collected data will vary from user to user. This results in the method not only occupying a large amount of computing resources, time-consuming and labor-intensive, but also there will be large differences between the valuation results of geographic objects and the actual transaction results, and between the results of use of different users, resulting in the situation that the transaction cycle of geographic objects is too long or the transaction cannot be completed. Therefore, how to improve the efficiency of geographic object value evaluation while reducing computing resources is an urgent problem to be solved.

[0032] Based on this, an embodiment of the present application provides a method for evaluating the value of a geographic object. When obtaining the value evaluation result of the geographic object to be evaluated, the method comprehensively considers the preliminary value evaluation result determined based on the attribute data of the geographic object to be evaluated, the statistical value of the historical transaction prices of all similar geographic objects similar to the geographic object to be evaluated, the predicted value of the current evaluation result of the area determined by the fitting curve determined by the relationship between the historical transaction prices and time of other geographic objects in the area where the geographic object to be evaluated is located at different times, the trend change coefficient determined by the ratio of the predicted value to the historical transaction price corresponding to the previous time unit on the fitting curve, and the influence of the missing degree of similar geographic objects on the value evaluation result of the geographic object to be evaluated, thereby improving the accuracy of the value evaluation of the geographic object to be evaluated. Moreover, the data required for the evaluation calculation is ordered and definite, which reduces the consumption of computing resources, improves the efficiency of the evaluation calculation and the stability of the calculation results.

[0033] The following is an explanation of the technical terms involved in the embodiments of the present application: Robustness: refers to the stability and adaptability of a system, model, or method in the face of uncertainty, disturbance, or change. A robust system is able to maintain its performance under different conditions without being affected by external factors. Robustness can be applied to many fields, including engineering, statistics, computer science, artificial intelligence, etc.

[0034] Unsupervised learning: is a paradigm of machine learning that differs from supervised learning in that it does not use labeled data. In unsupervised learning, the algorithm learns from unlabeled data, trying to discover patterns or structures within the data. Common tasks of unsupervised learning include clustering, dimensionality reduction, and anomaly detection.

[0035] Time series: A data set that records a series of observations in chronological order. These observations can be any measurable variable, such as stock prices, temperature changes, website visits, etc. Time series analysis has a wide range of applications in many fields, including but not limited to economics, finance, meteorology, engineering, and social sciences.

[0036] The following combination Figure 1-Figure 2 The application scenarios of the geographic object value assessment method provided in the embodiments of the present application are described in detail.

[0037] See also Figure 1 , Figure 1It is a schematic diagram of the first application scenario of a method for evaluating the value of a geographic object provided by the first embodiment of the present application. In the embodiment of the present application, the geographical object to be evaluated is described as a house source as an example, and the value of the house source is evaluated. First, the attribute data of the house source is obtained. The attribute data can specifically be the information of the community where the house source is located, such as the number of buildings in the community, the construction age of the community, and the greening of the community; then, the house source information is obtained, such as the floor where the house source is located, the area of ​​the house source, and the historical transaction prices of other houses in the community; finally, the geographical information of the house source needs to be obtained, such as the zoning information to which the house source belongs, whether there are supporting facilities such as subways, parks, and schools around the house source, etc. Based on the attribute data of the above-mentioned house source, the preliminary value evaluation result of the house source is obtained through the preset regression model, that is, the first result. Then, the clustering information is obtained through the clustering model, and similar houses with similar attribute data to the house source to be evaluated are obtained, and the historical transaction prices of all similar houses are further obtained, and the statistical values ​​of all historical transaction prices are calculated as the second result of similar prediction. And according to the number of similar properties and the number of sold properties in the area where the property to be evaluated is located, the missing degree of similar properties is determined. Then, based on the price of the residential area, the price of the business district, the price of the district and the price of the city where the property is located, the trend change coefficient of the property is obtained based on the time series model. Finally, the missing degree is used as the adjustment coefficient, and the product of the second result and the trend change coefficient is used as the adjustment amount to adjust the first result, and finally the value evaluation result of the property is obtained.

[0038] In specific implementation, the first additional result of the house to be evaluated can be obtained according to the category data and attribute data of the house to be evaluated, and the second additional result of the house to be evaluated can be obtained according to the city data and attribute data of the house to be evaluated. Finally, the value assessment result is integrated with the first additional result and the second additional result to obtain the total assessment result of the house to be evaluated. Figure 2 , Figure 2It is a schematic diagram of the second application scenario of a geographic object value assessment method provided by the first embodiment of the present application. In the embodiment of the present application, the geographic objects can be classified, for example, the type of the geographic object can be a residence, an apartment, a villa, or a garage. The city to which the geographic object belongs can also be classified, for example, whether the geographic object is in a first-tier city or a second-tier city, in the East China region or the Northwest region, etc. It should be noted that each type corresponds to a sub-model, and by inputting the above-mentioned different types of attribute data into the corresponding sub-model, the additional assessment results of the geographic object to be assessed can be obtained, and the total assessment results of the housing source can be obtained according to the value assessment results and the additional assessment results. Of course, during the specific implementation, the total assessment results of the housing source can also be corrected. For example, in the case of sudden market fluctuations, the degree of influence of market fluctuations on the value assessment results is determined as a correction coefficient. The correction coefficient can be used to correct the above-mentioned value assessment results or the total assessment results, so that the final estimated results of the housing source are more accurate.

[0039] The method for evaluating the value of geographic objects described in the embodiment of the present application mainly includes three parts, the attribute layer, the model layer and the strategy layer. The attribute layer is the basis, and can subdivide the housing sources according to multiple dimensions such as residential attributes and geographical location in order to select a suitable valuation model. Then, different types of housing sources are routed to the most suitable main and sub-models to improve the accuracy and efficiency of the valuation. Among them, residential attributes include construction year, area, room type, floor, etc. These attributes can reflect the basic situation of the housing source and are important factors in evaluating the value of real estate. Geographical location mainly takes into account the block, division, or even city where the housing source is located, which has a significant impact on housing prices, such as areas with convenient transportation, commercial and prosperous areas, etc. The model layer is the core part, which consists of a valuation main model and multiple sub-models. As the core model, the valuation main model integrates multiple key factors, such as historical transactions, similar housing sources, market trends, etc., with the aim of providing a preliminary and comprehensive valuation reference. The sub-model carefully considers the unique attributes of a specific type of housing source. In a complex real estate market, a single model is difficult to adapt to all situations. Therefore, multiple sub-models are customized according to different residential attributes and geographical locations. Modeling. For example, the apartment sub-model may take into account the special properties of apartments, while the city sub-model focuses more on the city level to which the property belongs. Although each sub-model may be similar in structure, it will have significant differences in the treatment of specific factors to ensure that its predictions for specific property types are more accurate. The strategy layer is mainly responsible for the final processing of the model results and is responsible for further correction of the valuation results output by the model layer to ensure the robustness and flexibility of the system. The valuation results output by the model may be affected by various non-standard factors in actual applications, such as sudden market fluctuations. The strategy layer handles these sudden factors in a variety of ways (such as weighted averaging, smoothing, etc.) to ensure the stability of the valuation results, thereby enhancing robustness. When encountering emergencies, such as the addition or reduction of supporting facilities around a property, the strategy layer can quickly adjust the corresponding parameters or adopt emergency strategies to promptly correct the valuation results. This rapid response mechanism ensures that the valuation system can adapt to the dynamically changing market environment and improves flexibility.

[0040] The above is the full process analysis of the geographic object value assessment method described in the embodiment of the present application. The geographic object value assessment method described in the embodiment of the present application includes: determining the geographic object to be assessed; obtaining the attribute data of the geographic object to be assessed, and determining the preliminary value assessment result of the geographic object to be assessed according to the attribute data as the first result; determining at least one similar geographic object to the geographic object to be assessed, obtaining the historical transaction prices of all similar geographic objects, and calculating the statistical values ​​of all historical transaction prices as the second result of similar prediction; obtaining the historical transaction prices of other geographic objects in the area where the geographic object to be assessed is located at different times, and determining the predicted value of the current assessment result of the area according to the fitting curve determined by the relationship between the historical transaction prices and time as the third result, and calculating the ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as the trend change coefficient; determining the missing degree of the similar geographic object according to the number of similar geographic objects to the geographic object to be assessed and the number of transaction objects in the area where the geographic object to be assessed is located; using the missing degree as the adjustment coefficient, and the product of the second result and the trend change coefficient as the adjustment amount, adjusting the first result to obtain the value assessment result of the geographic object to be assessed.

[0041] The geographic object value assessment method described in the embodiment of the present application comprehensively considers the impact of the preliminary value assessment result determined based on the attribute data of the geographic object to be assessed, the statistical value of the historical transaction prices of all similar geographic objects similar to the geographic object to be assessed, the predicted value of the current assessment result of the area determined by the fitting curve determined by the relationship between the historical transaction prices and time of other geographic objects in the area where the geographic object to be assessed is located at different times, the trend change coefficient determined by the ratio of the predicted value to the historical transaction price corresponding to the previous time unit on the fitting curve, and the missing degree of similar geographic objects on the value assessment result of the geographic object to be assessed, when obtaining the value assessment result of the geographic object to be assessed, thereby improving the accuracy of the value assessment of the geographic object to be assessed, and the data required for the assessment calculation are ordered and determined, which reduces the consumption of computing resources, improves the efficiency of the assessment calculation and the stability of the calculation results.

[0042] The present application is described in detail below through multiple embodiments and drawings. First embodiment

[0043] The first embodiment of the present application provides a method for evaluating the value of a geographic object. Figure 3 The method for assessing the value of the geographic object is explained in detail.

[0044] Step S301: Determine the geographic object to be evaluated.

[0045] This step is used to determine the geographic object to be evaluated. Taking the geographic object as a house as an example, the geographic object can be a house, an apartment, a villa, a house, etc. The geographic object to be evaluated refers to the geographic object whose value needs to be evaluated.

[0046] Step S302: obtaining attribute data of the geographic object to be evaluated, and determining a preliminary value evaluation result of the geographic object to be evaluated according to the attribute data as a first result.

[0047] This step is used to obtain the attribute data of the geographic object to be evaluated, and determine the preliminary value evaluation result of the geographic object to be evaluated according to the attribute data as the first result.

[0048] In the embodiment of the present application, the attribute data includes the feature data of the geographic object, the set area data to which the geographic object belongs, the geographic information of the geographic object, and the surrounding ancillary information data. The geographic information of the geographic object is the relationship information between the geographic object to be evaluated and the surrounding associated geographic objects, and the surrounding associated geographic objects are geographic objects whose distance from the geographic object to be evaluated is within a first preset distance range and have an associated influence on the users in the geographic object to be evaluated; the surrounding ancillary information data is the relationship data between the area where the geographic object to be evaluated is located and the neighboring area, and the neighboring area is an area whose distance from the area where the geographic object to be evaluated is within a second preset distance range.

[0049] The characteristic data of the geographic object can be the numerical information of the geographic object, or the text information of the geographic object. In the embodiment of the present application, the geographic object to be evaluated is the geographic object of the value to be evaluated. The description is made by taking the geographic object to be evaluated as a house source as an example. The geographic object can be various types of houses, such as commercial houses, houses, apartments, villas, houses, garages, warehouses, etc. The numerical information can specifically be the relevant attribute information of the house source and the community where the house source is located. The house source information can specifically include the building year, area, floor, hall, room, bathroom, orientation and other information of the house source. The information of the community where the house source is located can specifically include the greening rate of the community, the plot ratio (Plot Ratio / Floor Area Ratio / Volume Fraction, which refers to the ratio of the total ground building area to the net land area of ​​a community, also known as the gross density of the building area) and water, electricity and fuel costs and other information. The text information mainly includes the description information of the house source, and the description information of the house source can be information such as the house source introduction, community introduction, surrounding facilities, and traffic conditions.

[0050] It should be noted that the building year, area, floor and room type of the house can directly reflect the basic situation of the house and is an important factor in evaluating the value of the house. Whether the supporting facilities around the community are complete, whether the transportation around the community is convenient, and whether the community is in a prosperous commercial area are all important factors affecting the valuation results of the house.

[0051] The set area to which the geographic object belongs refers to the community where the geographic object to be evaluated (such as real estate) is located, or a sub-district of the community. For example, some houses belong to District 1, District 2, or East District, South District, etc. The set area data to which the geographic object belongs refers to the characteristic data of the community where the geographic object to be evaluated is located, or the characteristic data of a sub-district of the community. The characteristic data of the community where the geographic object is located can also include quantifiable numerical information and descriptive text information. The set area data to which the geographic object belongs can refer to the data of the community where the house is located. The community refers to a large residential area with a relatively independent living environment in a certain area of ​​the city, and is equipped with a complete set of living service facilities.

[0052] The geographic information of the geographic object can refer to the information of the house source and the surrounding subway stations, hospitals, etc., or the convenience information of the supporting entities to the house source obtained by calculation. In the embodiment of the present application, the surrounding associated geographic object is a geographic object whose distance from the geographical object to be evaluated is within the first preset distance range and has an associated influence on the user in the geographical object to be evaluated. The surrounding associated geographic object can be specifically the supporting entity information, and the supporting entity information refers to the surrounding geographical factors that have a significant impact on the value of the property, such as schools, subways, hospitals, parks, supermarkets, shopping malls or other important entities. In the specific implementation, the entity list can be pre-set to determine the influence of the entities in the entity list on the house source, or the house source data and the entity data can be input into the preset model, and the influence of the entity on the house source can be predicted by the model, and then it is determined whether the entity is an associated entity of the house source. It should be noted that the surrounding associated geographic object refers to the surrounding associated geographic object of the house source, and the surrounding associated geographic object of the house source can be an entity outside the community where the house source is located, or an entity inside the community where the house source is located, such as convenience stores and schools inside the community, convenience stores and fast food restaurants in commercial buildings, etc. The surrounding area refers not only to the outside of the community or the outside of the commercial building, but also to the inside of the community or the inside of the commercial building. The surrounding auxiliary information data may specifically be the relationship data between the community where the geographic object to be evaluated is located and its surrounding neighboring communities.

[0053] In the embodiment of the present application, the preliminary value assessment result of the geographic object to be assessed can be determined according to the attribute data as the first result. When determining the preliminary value assessment result of the geographic object to be assessed according to the attribute data, the feature data of the geographic object, the set area data to which the geographic object belongs, the geographic information of the geographic object and the surrounding ancillary information data are input into a preset geographic object value assessment model to determine the preliminary value assessment result of the geographic object to be assessed, i.e., the first result. .

[0054] The geographic object value assessment model is a regression model obtained through training, and the geographic object value assessment model is trained in the following manner: determine sample data of a geographic object set data composed of multiple geographic objects that have completed value assessment, the sample data includes feature data samples of the geographic objects in the geographic object set data, data samples of the set areas to which the geographic objects belong, geographic information samples of the geographic objects, data samples of surrounding ancillary information, and actual result samples of the value assessment of the geographic objects in the geographic object set data; take the feature data samples of each of the geographic objects, the data samples of the set areas to which the geographic objects belong, the geographic information samples of each of the geographic objects, the data samples of the surrounding ancillary information, and each of the actual result samples as a group of training sample pairs, and the training sample pairs are used to train the geographic object value assessment model; determine An initial geographic object value assessment model; inputting feature data samples of geographic objects, data samples of set areas to which geographic objects belong, geographic information samples of geographic objects, and data samples of surrounding ancillary information into the initial geographic object value assessment model to determine the initial value assessment result of the geographic object; if the loss data between the initial value assessment result and the actual result sample meets the acceptable loss condition, the initial geographic object value assessment model is determined as the geographic object value assessment model; otherwise, adjusting the model parameters in the initial geographic object value assessment model until the value assessment result obtained by adjusting the model parameters of the geographic object value assessment model and the loss data between the actual result sample meet the acceptable loss condition, and the geographic object value assessment model after adjusting the model parameters is determined as the geographic object value assessment model.

[0055] The above is a training method for the geographic object value assessment model. When it is implemented, the LightGMB regression model method can also be used for model training based on the sample data of the house. LightGBM is a fast, distributed, high-performance gradient boosting framework based on the decision tree algorithm. It is mainly used for sorting, classification, regression and many other machine learning tasks. The main advantages of LightGBM include faster training speed, higher efficiency, lower memory usage and higher accuracy. In order to improve the model's ability to fit abnormal data, the loss function can be trained using Huber Loss, that is,

[0056] in, For actual results, To estimate the results, = , is a hyperparameter that determines the point at which the loss function changes from square error to absolute error.

[0057] The above is a process of determining the preliminary value assessment result of the geographic object to be assessed based on the attribute data of the geographic object to be assessed as the first result. The following describes the process of determining at least one similar geographic object to the geographic object to be assessed, obtaining the historical transaction prices of all similar geographic objects, and calculating the statistical values ​​of all historical transaction prices as the second result of similar prediction.

[0058] Step S303: determining at least one similar geographic object to the geographic object to be evaluated, obtaining historical transaction prices of all similar geographic objects, and calculating statistical values ​​of all historical transaction prices as a second result of similarity prediction.

[0059] This step is used to determine similar geographic objects to the geographic object to be evaluated. Similar geographic objects refer to geographic objects with similar feature data to the geographic object to be evaluated. Obtaining the historical transaction prices of all similar geographic objects and calculating the statistical values ​​of all historical transaction prices can significantly improve the accuracy and reliability of the value estimation results of the geographic object to be evaluated.

[0060] In the field of house price estimation, it is very important to accurately estimate the price of a house. In order to improve the accuracy of the prediction, a variety of methods can be used to refer to the characteristics of similar houses to obtain the estimated value of similar houses. One method is to determine the similar geographical objects using predefined rules; wherein the predefined rules at least include: taking all or part of other geographical objects in the set area to which the geographical object to be evaluated belongs as similar geographical objects; taking other geographical objects with the same or similar area as the geographical object to be evaluated in the set area and / or adjacent set area to which the geographical object to be evaluated belongs as similar geographical objects; taking other geographical objects with the same or similar floor as the geographical object to be evaluated in the set area and / or adjacent set area to which the geographical object to be evaluated belongs as similar geographical objects; taking other geographical objects with the same or adjacent building as the geographical object to be evaluated in the set area to which the geographical object to be evaluated belongs as similar geographical objects. For example, houses in the same community: the houses in the community usually have little difference in geographical location and environment. Therefore, it is preferred to compare houses in the same community as similar houses. Properties with similar areas: Classify properties by area, usually choose properties with similar areas to the target property, such as properties within ±10%. Properties with similar floors: The height of the floor will affect the price of the property, so choose properties with similar floors to the target property for comparison, such as properties within ±2 floors. Properties with similar buildings: In the same community, the prices of different buildings may also vary. By choosing properties in the same or similar buildings, the error of the estimated results can be further reduced.

[0061] One is to determine similar geographical objects to the geographical object to be evaluated by clustering method, specifically including: determining other geographical objects in the area where the geographical object to be evaluated is located or in the adjacent area of ​​the area; obtaining attribute data of the other geographical objects; clustering the other geographical objects according to the attribute data and the attribute category as clustering features; and determining similar geographical objects to the geographical object to be evaluated from different clusters. Determining similar geographical objects to the geographical object to be evaluated from different clusters includes: determining the similarity between other geographical objects in different clusters and the geographical object to be evaluated, and taking other geographical objects whose similarity exceeds a set threshold as similar geographical objects to the geographical object to be evaluated.

[0062] The clustering method uses unsupervised learning technology in data mining to group properties according to multiple dimensions, and then analyze similar groups to estimate prices. Unsupervised clustering is performed based on geographic location, historical performance price, property layout, etc., and similar property information is found through multi-way recall. The main process is as follows: 1) Feature selection: To perform clustering, you first need to select appropriate features, such as geographic location (latitude and longitude coordinates), historical transaction prices, property layout (such as number of rooms, area), etc. 2) Data standardization: In order to ensure the relative influence between different features, the data can be standardized so that each feature is at the same level. 3) Select clustering algorithm: Use clustering algorithms such as K-means and DBSCAN to cluster property data, and the properties in each category have a high similarity. 4) Multi-way recall: Clustering is performed from multiple angles (geographic location, price, layout). Each clustering method can find similar properties, and then more accurate property information is obtained by comprehensively evaluating similar properties from different angles.

[0063] Another way is to use a preset model to encode the feature data of the geographic object to obtain the encoded feature vector; cluster the feature vector based on the preset clustering conditions to obtain a set of similar geographic objects. Specifically, a deep learning model is used to learn high-level features of the house through unsupervised or semi-supervised methods, and then cluster and similarly match according to the learned representations. The main process is as follows: 1) Data preparation: The data includes text features (house description), numerical features (area, price, etc.) and image features (house pictures). 2) Model selection: Use a deep learning model such as Autoencoder or Variational Autoencoder (VAE) for unsupervised learning to learn high-level features from the data. 3) Representation learning: Use the model to represent the house features and map the house data to a high-dimensional feature space. At this time, each house has a higher-dimensional feature representation. 4) Clustering of similar houses: Clustering is performed in the high-dimensional feature space so that similar houses are aggregated into one category. Through these similar house information, the price of the house to be evaluated is estimated. 5) Model optimization: Semi-supervised learning methods can be used to train the model using a portion of data with known labels to improve the model’s representation capabilities.

[0064] In a specific implementation, the similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: according to the attribute data of the geographical object to be evaluated, a vector representation of the attribute data is obtained as a first vector A; a vector representation of the attribute data of any other geographical object is obtained as a second vector B; and the cosine similarity between the first vector and the second vector is calculated as the similarity between the other geographical object and the geographical object to be evaluated. ,Right now

[0065] When determining the similarity based on the location of the geographical object, the similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: based on the geographical location information of the geographical object to be evaluated ( ) and any other geographic object's geographic location information ( ), determine the geographical distance between the geographical object to be evaluated and the other geographical object; and use the geographical distance as the similarity between the other geographical object and the geographical object to be evaluated. ) can be the latitude and longitude data of the geographic object to be evaluated. The geographic distance is Euclidean distance or Manhattan distance. The geographic distance is used to measure the location similarity between other geographic objects and the geographic object to be evaluated. ,Right now

[0066] When determining the similarity based on the room type of the geographical object, the similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: first, the room type of the geographical object to be evaluated is converted into a numerical feature representation as a third vector ; Convert the house type data of any other geographic object into a numerical feature representation as the fourth vector ; For example, the house type of the geographical object to be evaluated is two bedrooms, one living room, one kitchen, one bathroom, facing south, etc. In the specific implementation, two bedrooms, one living room, one kitchen, one bathroom, facing south can be converted into corresponding numerical features for representation, and each vector representation data is obtained. These vector representation data are spliced ​​to obtain the high-dimensional vector of the overall house type. Of course, two bedrooms, one living room, one kitchen, and one bathroom can also be directly represented by vectors ( ) indicates that the vector ( Then, the cosine similarity between the third vector and the fourth vector is calculated as the similarity between the other geographic object and the geographic object to be evaluated. ,Right now

[0067] When determining similarity based on the area of ​​a geographic object, the similarity between the other geographic objects and the geographic object to be evaluated is calculated by: normalizing the area of ​​the other geographic objects; and using the normalized result as the similarity between the other geographic objects and the geographic object to be evaluated. For example, after normalizing the area of ​​the geographic object to be evaluated and the other geographic objects, the absolute value of the normalized result is subtracted, and the area similarity is calculated. The closer the result is to zero, the closer the house areas are, and the higher the similarity of the houses. The normalization method for the area is as follows:

[0068] It should be noted that the above method uses the attribute data, location information, room type, and area between geographic objects to determine the similarity. You can also combine multiple feature similarities and use the weighted average method to obtain the final house similarity. , in specific implementation, you can choose the corresponding similarity calculation method according to actual needs. The following is the comprehensive similarity The calculation method of is the location similarity, is the weight of position similarity, is the room type similarity, is the weight of room type similarity, is the area similarity, is the weight of area similarity, Through model training, we can get:

[0069] The above is the process of obtaining the similarity between other geographical objects and the geographical object to be evaluated and the set of similar geographical objects. In specific implementation, a suitable method or a combination of several methods can be selected according to actual needs to obtain a set of similar geographical objects to improve the accuracy of housing price prediction. By combining the results of multiple methods for comprehensive evaluation, the accuracy and reliability of price estimation can be significantly improved. After determining at least one similar geographical object to the geographical object to be evaluated, the historical transaction prices of all similar geographical objects are obtained, and the statistical value of all historical transaction prices is calculated as the second result of similarity prediction. The statistical value of all historical transaction prices is calculated, including: determining the similarity that characterizes the degree of association between each similar geographical object and the geographical object to be evaluated, and using the similarity as a weight to perform a weighted average on all historical transaction prices to calculate the statistical value of all historical transaction prices. The statistical value of all historical transaction prices is calculated, including: determining the similarity that characterizes the degree of association between each similar geographical object and the geographical object to be evaluated, and using the similarity as a weight to perform a weighted average on all historical transaction prices to calculate the statistical value of all historical transaction prices.

[0070] Get a collection of similar geographic objects Then, further obtain the similarity data between each similar geographical object in the similar geographical object set and the geographical object to be evaluated , It may refer to any one of the multiple single similarities obtained by the above calculation, or it may refer to the comprehensive similarity calculated above, as well as the historical transaction price of each similar geographic object in the similar geographic object set. Based on the similarity data between each of the similar geographic objects and the geographic object to be evaluated and the historical transaction price of each similar geographic object , using the similarity as a weight to perform a weighted average on all historical transaction prices to calculate the statistical value of all historical transaction prices ,Right now

[0071] in, is similarity data. In actual calculation, if the similarity is calculated based on position similarity, then the similarity According to the above If the similarity is calculated based on the room type similarity, then the similarity According to the above If the similarity is calculated based on the comprehensive similarity, then the similarity According to the above If the similarity is calculated based on area or price similarity, then the similarity Correspondingly, the values ​​are taken according to the above-mentioned area similarity or price similarity. is the historical transaction price of similar properties. is a collection of similar properties. Finally, the statistical value of all historical transaction prices is calculated by taking the arithmetic average of all historical transaction prices or taking the median of all historical transaction prices.

[0072] Step S304: Obtain the historical transaction prices of other geographical objects in the area where the geographical object to be evaluated is located at different times, determine the predicted value of the current evaluation result of the area as the third result based on the fitting curve determined by the relationship between the historical transaction prices and time, and calculate the ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as the trend change coefficient.

[0073] When obtaining the trend change coefficient, specifically, first obtain the historical transaction prices of other geographical objects in the area where the geographical object to be evaluated is located at different times, wherein the area where the geographical object to be evaluated is located may be within a preset cell range, may be a joint area of ​​surrounding cells, may be an area within a preset distance range centered on the geographical object to be evaluated, may be the district information to which the geographical object to be evaluated belongs, or may be the city to which the geographical object to be evaluated belongs. The specific implementation may be set according to actual needs. After obtaining the historical transaction prices of other geographical objects in the area where the geographical object to be evaluated is located at different times, the predicted value of the current evaluation result of the area may be determined based on the fitting curve determined based on the relationship between the historical transaction prices and time, as the third result, i.e. .

[0074] In specific implementation, the housing prices in different regions can be aggregated according to the monthly dimension, and the time series of regional, monthly, and average price dimensions can be constructed to obtain the housing price trend data of the region. Figure 4 , Figure 4 It is a schematic diagram of a fitting curve in a geographic object value assessment method provided in the first embodiment of the present application. According to the fitting curve, the housing price trend in the region can be obtained. For example, based on the historical transaction data (such as the average price) before January 2024, the estimated housing price data for March 2024 and April 2024 can be predicted ( Figure 4 It should be noted that the Prophet model is used in the embodiment of the present application. The basic principle of Prophet is to decompose the time series into trend terms, seasonal terms and holiday terms, and use the additive model for prediction on this basis. Specifically, it is assumed that the time series consists of the following three parts: trend term : Describes the long-term trend of the time series and is fitted using a piecewise linear model with autoregression terms and seasonal terms; the seasonal term : Describes the periodic changes of time series and uses Fourier series to fit; holiday term : Describes abnormal events in time series (such as holidays, etc.), using custom binary variables to represent; : Error term: represents the changes that the model fails to capture, usually assumed to be normally distributed. Add the trend term, seasonal term, and holiday term to get the forecast value of the time series Right now

[0075] In specific implementation, in order to obtain the trend change coefficient , in determining the predicted value of the current assessment results for the area Then, obtain the historical transaction price corresponding to the previous time unit (such as the previous month) on the fitting curve. , trend change coefficient For the third result The historical transaction price corresponding to the previous time unit on the fitting curve The ratio of

[0076] It should be noted that the previous time unit on the fitting curve is determined according to the time unit adopted when the fitting curve is determined based on the relationship between historical transaction prices and time. For example, if the time unit adopted when the fitting curve is determined is year, the previous time unit is the previous year; if the time unit adopted when the fitting curve is determined is month, the previous time unit is the previous month; if the time unit adopted when the fitting curve is determined is quarter, the previous time unit is the previous quarter.

[0077] Step S305: Determine the missing degree of the similar geographical object according to the number of similar geographical objects to the geographical object to be evaluated and the number of transaction objects in the area where the geographical object to be evaluated is located.

[0078] This step is used to determine the missing degree of similar geographic objects.

[0079] When determining the missing degree data of similar geographic objects, first obtain the number of similar geographic objects of the geographic object to be evaluated and the number of transaction objects in the area where the geographic object to be evaluated is located, then obtain the difference between the number of similar geographic objects of the geographic object to be evaluated and the number of transaction objects in the area where the geographic object to be evaluated is located, and finally obtain the ratio of the difference to the number of transaction objects in the area where the geographic object to be evaluated is located as the missing degree of the similar geographic object. For example, if the number of similar geographic objects of the geographic object to be evaluated is 15 and the number of transaction objects in the area where the geographic object to be evaluated is 20, then the missing degree is 15. for:

[0080] It should be noted that if the number of similar geographic objects to the geographic object to be evaluated is 30, and the number of transaction objects in the area where the geographic object to be evaluated is 20, since the number of similar geographic objects to the geographic object to be evaluated exceeds the number of transaction objects in the area where the geographic object to be evaluated is located, the missing degree If the number of transaction objects in the area where the geographic object to be evaluated is located is 0, the missing degree is 1.

[0081] Step S306: using the missing degree as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount, adjusting the first result to obtain a value assessment result of the geographic object to be assessed.

[0082] This step is used to obtain the value assessment result of the geographic object to be assessed. The value assessment result combines the preliminary value assessment result of the geographic object to be assessed, the second result of similar prediction, the trend change coefficient and the missing degree of similar geographic objects, so that the final value assessment result is more accurate.

[0083] In an embodiment of the present application, the missing degree is used as an adjustment coefficient, and the product of the second result and the trend change coefficient is used as an adjustment amount to adjust the first result to obtain a value assessment result of the geographic object to be assessed, including: obtaining a negative missing degree corresponding to the first result based on the full value corresponding to the missing degree and the missing degree; using the negative missing degree as the weight of the first result and the missing degree as the weight of the second result to obtain weighted sum data of the first result and the second result; using the trend change coefficient as adjustment factor data of the weighted sum data, using the trend change coefficient to adjust the weighted sum data, and obtaining the value assessment result of the geographic object to be assessed.

[0084] It should be noted that according to the first result , Second result and trend change coefficient , obtain the value assessment results of the geographic object to be assessed Specifically, when determining the missing degree of similar geographic objects After that, assuming The range is 0-1, then the first result The corresponding negative missing degree is 1- , the negative missing degree 1- As the first result The weight of As the second result The weight of With the second result The weighted sum of data, and then the trend change coefficient As an adjustment factor for the weighted sum data, use the trend change coefficient Adjust the weighted sum data to obtain the value assessment results of the geographic object to be assessed ,Right now

[0085] It should be noted that when the missing When it approaches 0, the estimated result of the house will tend to be the first result. , when the missing When it tends to 1, the estimated housing results tend to be the second result. That is, when the number of transaction objects in the area where the geographic object to be evaluated is located is relatively abundant, the results obtained by the geographic object value evaluation model can be used; when the number of transaction objects in the area where the geographic object to be evaluated is relatively sparse, the transaction results of similar geographic objects can be referred to.

[0086] The above is the process of obtaining the value evaluation result of the geographic object to be evaluated through the single house source prediction module, the similar house source price prediction module, and the housing price trend estimation module. Among them, in the similar house source price prediction module, the clustering information part mainly provides similar house sources and similar community information for new houses and sparsely traded communities to increase the robustness of the overall model. In specific implementation, the first additional result of the house to be evaluated can also be obtained according to the category data and attribute data of the house to be evaluated, and the second additional result of the house to be evaluated can be obtained according to the city data and attribute data of the house to be evaluated. Finally, the value evaluation result is merged with the first additional result and the second additional result to obtain the total evaluation result of the house to be evaluated, so that the final house value estimation result is more accurate. Specifically, the category data of the geographic object to be evaluated and the city data to which it belongs are obtained; according to the category data and the attribute data, the evaluation result of the geographic object to be evaluated is determined as the first additional result; according to the city data and the attribute data, the evaluation result of the geographic object to be evaluated is determined as the second additional result; the value evaluation result is merged with the first additional result and the second additional result to obtain the total evaluation result of the geographic object to be evaluated.

[0087] Determining the evaluation result of the to-be-evaluated geographic object as the first additional result based on the category data and the attribute data includes: determining the category data to obtain a submodel; and determining the evaluation result of the to-be-evaluated geographic object as the first additional result based on the category data to obtain the submodel and the attribute data. Determining the evaluation result of the to-be-evaluated geographic object as the second additional result based on the city data and the attribute data includes: determining the city data to obtain a submodel; and determining the evaluation result of the to-be-evaluated geographic object as the second additional result based on the city data to obtain the submodel and the attribute data.

[0088] It should be noted that the category data of the geographic object to be evaluated can represent the type of the geographic object to be evaluated, such as residence, apartment, villa, house, etc. For example, if the type of the geographic object to be evaluated is an apartment, considering the special attributes of the apartment type, the apartment sub-model can be selected, and the apartment value evaluation sub-model is constructed based on the historical transaction records of the apartment through the attribute data such as the apartment's geographical location, apartment area, number of rooms, construction year, supporting facilities, rental price, water, electricity and property fees. The training method of the apartment value evaluation sub-model is similar to the training method of the above-mentioned geographic object value evaluation model. Please refer to the training method of the above-mentioned geographic object value evaluation model, which will not be described in detail here.

[0089] The above is a training method for the apartment value assessment sub-model. When it is implemented, it can also be trained using the GBDT model based on the sample data of the apartment. ‌GBDT model (Gradient Boosting Decision Tree) is a reinforcement learning algorithm that is commonly used for regression and classification problems. It improves the accuracy of the model by combining multiple weak learners (usually decision trees) into a strong learner. ‌GBDT model mainly builds decision trees step by step in an iterative manner. Each construction attempts to correct the error of the previous model. The basic process is as follows: 1. Initial model: First, use a simple model (usually the average value) to initialize the prediction. For regression problems, the initial output is the mean of the target value of the training data. 2. Calculate the residual: Use the current model to predict the training data and calculate the error (residual) of each sample. The residual is the difference between the true value and the predicted value. 3. Build a new tree: Build a new decision tree based on the residual. The new tree aims to minimize the loss function of the current model. Specifically, it will fit the residual calculated in the previous step. 4. Update the model: Add the predictions of the new tree to the predictions of the current model. Usually, a learning rate (shrinkage) is used to control the impact of each tree on the final prediction. 5. Iteration: Repeat steps 2 to 4 until the preset number of trees is reached or the residual does not change significantly.

[0090] In the specific implementation, in addition to the apartment value assessment sub-model, a villa value assessment sub-model and a garage value assessment sub-model can also be constructed. For the villa value assessment sub-model, considering the special attributes of the villa type, a separate model can be constructed for the villa type of housing, taking into account the villa's address location, villa area, total floors, number of rooms, architectural style, construction year, volume ratio, property fees and other data, and the villa value assessment sub-model is constructed based on the villa's historical transaction records. For the training of the villa value assessment sub-model, the training method of the above-mentioned apartment value assessment sub-model can also be used for training, or the GBDT model can be used for training. For the garage value assessment sub-model, the garage value assessment sub-model can separately estimate the value of the parking space for the housing source that contains the parking space, and comprehensively consider the information such as the price of the community to which the parking space belongs, the size of the parking space, the type of parking space, and the rent, and estimate the value of the parking space.

[0091] It should be noted that the city data to which the geographic object to be evaluated belongs can be obtained through the city sub-model and the regional sub-model. For the city sub-model, taking into account the different levels of development of cities, for example, the second-hand housing transactions in first-tier cities are more active and the unit price is higher, and the second-hand housing transactions in third- and fourth-tier cities are sparse and the unit price is lower, group modeling is performed based on the development level of the city to construct the city sub-model. The training method of the city sub-model is similar to that of the above sub-model and will not be described in detail here. For the regional sub-model, considering the different levels of development in different regions, for example, the liquidity of housing in eastern cities is higher than that in western cities. Based on the national address division, regional sub-models are constructed separately according to different regions. The training method of the regional sub-model is similar to that of the above sub-model and will not be described in detail here.

[0092] It should be noted that the geographic object value assessment model is the core model as the main valuation model. The main valuation model integrates multiple key factors, such as historical transactions, similar properties, market trends, etc. Its purpose is to provide a preliminary and comprehensive valuation reference. The sub-model carefully considers the unique attributes of a specific type of property. In a complex real estate market, a single model is difficult to adapt to all situations. Therefore, multiple sub-models are customized according to different residential properties and geographical locations. For example, the apartment value assessment sub-model may take into account the special attributes of the apartment, while the city sub-model pays more attention to the city level to which the property belongs. Although each sub-model may be similar in structure, there will be significant differences in the treatment of specific factors to ensure that its predictions for specific types of properties are more accurate.

[0093] In an embodiment of the present application, the value assessment result is integrated with the first additional result and the second additional result to obtain a total assessment result of the geographic object to be assessed, including: obtaining a first weight of the value assessment result; obtaining a second weight of the first additional result and the second additional result; and obtaining a total assessment result of the geographic object to be assessed based on the value assessment result, the first weight, the first additional result, the second additional result, and the second weight.

[0094] In specific implementation, the value assessment result can be the main result, and the first additional result and the second additional result can be used as auxiliary results. And auxiliary results , obtain the overall evaluation result of the geographic object to be evaluated When the LR model is used based on the type of house and the city it belongs to, different weights are learned for different sub-models based on the training data, and the final model prediction results are obtained through weighted methods. The first weight , auxiliary results The second weight , get the main result and the auxiliary results The weighted sum data is used as the total evaluation result of the geographic object to be evaluated. ,Right now

[0095] It should be noted that according to the main results And auxiliary results , obtain the overall evaluation result of the geographic object to be evaluated hour, , the auxiliary result can be multiple auxiliary results The sum of .

[0096] The above is the overall process of obtaining the overall evaluation result of the geographic object to be evaluated. In specific implementation, after obtaining the value evaluation result or the overall evaluation result of the geographic object to be evaluated, it also includes: using a dynamic correction strategy to correct the value evaluation result or the overall evaluation result of the geographic object to be evaluated, including: determining favorable or unfavorable events that affect the value evaluation of the geographic object to be evaluated; determining the degree of influence of the favorable or unfavorable event on the current value evaluation as a correction coefficient; and using the correction coefficient to correct the value evaluation result or the overall evaluation result of the geographic object to be evaluated.

[0097] It should be noted that after obtaining the total evaluation result of the geographic object to be evaluated, the value evaluation result or the total evaluation result of the geographic object to be evaluated will be corrected. Specifically, the favorable or unfavorable events that affect the value evaluation of the geographic object to be evaluated are first determined, and then the degree of influence of the favorable or unfavorable events on the current value evaluation is determined as a correction coefficient. Finally, the value evaluation result or the total evaluation result of the geographic object to be evaluated is corrected using the correction coefficient. For example, the supporting facilities around the geographical location of the geographic object are temporarily increased or reduced; it can also be determined based on the characteristic data of the demand side of the geographic object itself, such as the number of houses already owned by the house buyer. The above situations will have an impact on the valuation results of the housing source. Through the correction coefficient, the valuation results of the housing source can better adapt to the dynamically changing market environment.

[0098] The above is a full description of the method for evaluating the value of geographic objects described in the embodiment of the present application. On the one hand, the method solves the limited similar house source identification ability in the prior art. Most of the existing real estate valuation models rely only on the historical transaction data of the community to evaluate the value of the property, ignoring the comprehensive analysis of similar houses and similar communities, resulting in obvious defects in the generalization performance of the model. For example, even if different communities are geographically close, their housing prices may also be significantly different due to differences in building quality, supporting facilities and other factors. Therefore, relying solely on the data of a single community for valuation may ignore these important external factors. On the one hand, the method solves the problem that it is difficult to adapt to the rapidly changing market dynamics in the prior art. The real estate market price is affected by a variety of complex factors, such as supply and demand, which are usually difficult to predict and change rapidly. However, many existing valuation models are built based on static data and cannot reflect the latest market dynamics in a timely manner. Especially in the case of large market fluctuations, there may be a large deviation between the valuation results and the actual price. On the other hand, this method solves the problem of insufficient consideration of geographical heterogeneity. There may be huge differences in housing prices between different cities or even different regions in the same city. If the general valuation model does not fully take into account the geographical heterogeneity, it may cause large errors in the valuation results. For example, the housing prices in the city center may be very different from those in the suburbs, and some existing models cannot accurately capture this regional difference, thereby affecting the accuracy of the valuation. In contrast, the geographic object data processing method described in the embodiment of the present application comprehensively considers a single house source, similar houses and market trends. The model is not only based on the house source information in a single community, but also incorporates the historical transaction data of similar houses and similar communities, so as to enhance the robustness and accuracy of the model. In addition, by analyzing the characteristics of housing price fluctuations in different regions, the model can learn and capture the changing trend of housing prices, thereby improving the ability to predict future market trends.

[0099] The method for evaluating the value of a geographic object described in the embodiment of the present application includes: determining a geographic object to be evaluated; obtaining attribute data of the geographic object to be evaluated, and determining a preliminary value evaluation result of the geographic object to be evaluated based on the attribute data as a first result; determining at least one similar geographic object to the geographic object to be evaluated, obtaining historical transaction prices of all similar geographic objects, and calculating statistical values ​​of all historical transaction prices as a second result of similar prediction; obtaining historical transaction prices of other geographic objects in the area where the geographic object to be evaluated is located at different times, determining a predicted value of the current evaluation result of the area based on a fitting curve determined by the relationship between the historical transaction prices and time as a third result, and calculating a ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as a trend change coefficient; determining the missing degree of the similar geographic object based on the number of similar geographic objects to the geographic object to be evaluated and the number of transaction objects in the area where the geographic object to be evaluated is located; using the missing degree as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount, adjusting the first result to obtain a value evaluation result of the geographic object to be evaluated.

[0100] The geographic object value assessment method described in the embodiment of the present application comprehensively considers the impact of the preliminary value assessment result determined based on the attribute data of the geographic object to be assessed, the statistical value of the historical transaction prices of all similar geographic objects similar to the geographic object to be assessed, the predicted value of the current assessment result of the area determined by the fitting curve determined by the relationship between the historical transaction prices and time of other geographic objects in the area where the geographic object to be assessed is located at different times, the trend change coefficient determined by the ratio of the predicted value to the historical transaction price corresponding to the previous time unit on the fitting curve, and the missing degree of similar geographic objects on the value assessment result of the geographic object to be assessed, when obtaining the value assessment result of the geographic object to be assessed, thereby improving the accuracy of the value assessment of the geographic object to be assessed, and the data required for the assessment calculation are ordered and determined, which reduces the consumption of computing resources, improves the efficiency of the assessment calculation and the stability of the calculation results. Second embodiment

[0101] In the above-mentioned first embodiment, a geographic object value assessment method is provided. Correspondingly, the second embodiment of the present application provides a geographic object value assessment device. Since the device embodiment is basically similar to the first method embodiment, the description is relatively simple. For relevant parts, please refer to the partial description of the method embodiment. The device embodiment described below is only illustrative.

[0102] Please refer to Figure 5 , which is a schematic diagram of a geographic object value assessment device provided in the second embodiment of the present application.

[0103] The geographic object value assessment device 500 comprises: A determination unit 501 is used to determine a geographic object to be evaluated; A first result evaluation unit 502 is used to obtain attribute data of the geographic object to be evaluated, and determine a preliminary value evaluation result of the geographic object to be evaluated according to the attribute data as a first result; The second result obtaining unit 503 is used to determine at least one similar geographic object to the geographic object to be evaluated, obtain the historical transaction prices of all similar geographic objects, and calculate the statistical values ​​of all historical transaction prices as the second result of the similarity prediction; The trend change coefficient determination unit 504 is used to obtain the historical transaction prices of other geographical objects in the area where the geographical object to be evaluated is located at different times, determine the predicted value of the current evaluation result of the area as the third result based on the fitting curve determined by the relationship between the historical transaction prices and time, and calculate the ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as the trend change coefficient; A missing degree determining unit 505 is used to determine the missing degree of the similar geographical object according to the number of similar geographical objects of the geographical object to be evaluated and the number of transaction objects in the area where the geographical object to be evaluated is located; The value assessment result determination unit 506 is used to use the missing degree as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount to adjust the first result to obtain the value assessment result of the geographic object to be assessed. Third embodiment

[0104] Corresponding to the above method embodiment of the present application, the third embodiment of the present application further provides an electronic device. Figure 6 As shown, Figure 6 This is a schematic diagram of an electronic device provided in the third embodiment of the present application. The electronic device includes: at least one processor 601, at least one communication interface 602, at least one memory 603 and at least one communication bus 604; optionally, the communication interface 602 may be an interface of a communication module, such as an interface of a GSM module; the processor 601 may be a processor CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. The memory 603 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Among them, the memory 603 stores a program, and the processor 601 calls the program stored in the memory 603 to execute the method provided in the above embodiment of the present application. Fourth embodiment

[0105] Corresponding to the above method of the present application, the fourth embodiment of the present application further provides a computer storage medium. The computer storage medium stores a computer program, which is executed by a processor to execute the method provided in the above embodiment of the present application.

[0106] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0108] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0109] 1. Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0110] 2. Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0111] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described in this article within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0112] 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 used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

Claims

1. A method for assessing the value of a geographic object, characterized in that: include: Identify the geographic objects to be assessed; Obtaining attribute data of the geographic object to be evaluated, and determining a preliminary value evaluation result of the geographic object to be evaluated according to the attribute data as a first result; Determine at least one similar geographic object to the geographic object to be evaluated, obtain historical transaction prices of all similar geographic objects, and calculate statistical values ​​of all historical transaction prices as a second result of similarity prediction; Obtaining historical transaction prices of other geographical objects in the area where the geographical object to be evaluated is located at different times, determining a predicted value of the current evaluation result of the area according to a fitting curve determined by the relationship between the historical transaction prices and time as a third result, and calculating a ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as a trend change coefficient; Determining the missing degree of the similar geographical object according to the number of similar geographical objects to the geographical object to be evaluated and the number of transaction objects in the area where the geographical object to be evaluated is located; The missing degree is used as an adjustment coefficient, and the product of the second result and the trend change coefficient is used as an adjustment amount to adjust the first result to obtain a value assessment result of the geographic object to be assessed.

2. The method for assessing the value of a geographic object according to claim 1, characterized in that: The statistical values ​​of all historical transaction prices are calculated, including: A similarity characterizing the degree of association between each similar geographic object and the geographic object to be evaluated is determined, and a statistical value of all historical transaction prices is calculated by weighted averaging all historical transaction prices using the similarity as a weight.

3. The method for assessing the value of a geographic object according to claim 1, characterized in that: The statistical values ​​of all historical transaction prices are calculated, including: The statistical value of all historical transaction prices is calculated by taking the arithmetic average of all historical transaction prices or taking the median of all historical transaction prices.

4. The method for assessing the value of a geographic object according to any one of claims 1 to 3, characterized in that: Determine the similar geographic objects using predefined rules; wherein the predefined rules at least include: Taking all or part of other geographical objects in the set area to which the geographical object to be evaluated belongs as similar geographical objects; Other geographical objects in the set area to which the geographical object to be evaluated belongs and / or in the adjacent set area having the same or similar area as the geographical object to be evaluated are regarded as similar geographical objects; Other geographical objects in the set area to which the geographical object to be evaluated belongs and / or in the adjacent set area having the same or similar floor as the geographical object to be evaluated are regarded as similar geographical objects; Other geographical objects in the set area to which the geographical object to be evaluated belongs that are in the same building or adjacent to the geographical object to be evaluated are regarded as similar geographical objects.

5. The method for assessing the value of a geographic object according to any one of claims 1 to 3, characterized in that: Determining similar geographical objects to the geographical object to be evaluated by clustering method includes: Determine other geographical objects in the area where the geographical object to be evaluated is located or in an adjacent area of ​​the area; Acquire attribute data of the other geographic objects; Clustering the other geographic objects according to the attribute data and using the attribute categories as clustering features; Determine geographical objects similar to the geographical object to be evaluated from different clusters.

6. The method for assessing the value of a geographic object according to claim 5, characterized in that: The determining of geographical objects similar to the geographical object to be evaluated from different clusters includes: Determine the similarity between other geographic objects in different clusters and the geographic object to be evaluated, Other geographical objects whose similarity exceeds a set threshold are regarded as similar geographical objects to the geographical object to be evaluated.

7. The method for assessing the value of a geographic object according to claim 6, characterized in that: The similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: According to the attribute data of the geographic object to be evaluated, a vector representation of the attribute data is obtained as a first vector; Obtaining a vector representation of attribute data of any other geographic object as a second vector; The cosine similarity between the first vector and the second vector is calculated as the similarity between the other geographic object and the geographic object to be evaluated.

8. The method for assessing the value of a geographic object according to claim 6, characterized in that: The similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: Determine the geographical distance between the geographical object to be evaluated and any other geographical object according to the geographical location information of the geographical object to be evaluated and the geographical location information of any other geographical object; The geographical distance is used as the similarity between the other geographical object and the geographical object to be evaluated.

9. The method for assessing the value of a geographic object according to claim 6, characterized in that: The similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: Convert the house type of the geographic object to be evaluated into a numerical feature representation as a third vector; Convert the house type data of any other geographic object into a numerical feature representation as a second vector; The cosine similarity between the third vector and the fourth vector is calculated as the similarity between the other geographic object and the geographic object to be evaluated.

10. The method for assessing the value of a geographic object according to claim 6, characterized in that: The similarity between the other geographical objects and the geographical object to be evaluated is calculated in the following manner: Normalize the areas of other geographic objects; The normalized result is used as the similarity between other geographic objects and the geographic object to be evaluated.

11. The method for assessing the value of a geographic object according to claim 1, characterized in that: Also includes: Obtain the category data of the geographic object to be evaluated and the city data to which it belongs; Determining, according to the category data and the attribute data, an evaluation result of the to-be-evaluated geographic object as a first additional result; Determine, according to the city data and the attribute data, an evaluation result of the to-be-evaluated geographic object as a second additional result; The value assessment result is integrated with the first additional result and the second additional result to obtain a total assessment result of the geographic object to be assessed.

12. The method for assessing the value of a geographic object according to claim 1 or 11, characterized in that: After obtaining the value assessment results or the overall evaluation results of the geographic object to be assessed, it also includes: The value assessment result or the total assessment result of the geographic object to be assessed is revised using a dynamic revision strategy, including: Determine the favorable or unfavorable factors that may affect the value assessment of the geographical object to be assessed; Determine the impact of the positive or negative event on the current value assessment as a correction factor; The correction coefficient is used to correct the value assessment result or the overall assessment result of the geographical object to be assessed.

13. A device for evaluating the value of a geographical object, characterized in that: include: A determination unit, used for determining a geographic object to be evaluated; A first result evaluation unit, configured to obtain attribute data of the geographic object to be evaluated, and determine a preliminary value evaluation result of the geographic object to be evaluated according to the attribute data as a first result; A second result obtaining unit, configured to determine at least one similar geographical object to the geographical object to be evaluated, obtain historical transaction prices of all similar geographical objects, and calculate statistical values ​​of all historical transaction prices as a second result of similarity prediction; a trend change coefficient determination unit, used to obtain historical transaction prices of other geographical objects in the area where the geographical object to be evaluated is located at different times, determine the predicted value of the current evaluation result of the area as the third result according to a fitting curve determined by the relationship between the historical transaction prices and time, and calculate the ratio of the third result to the historical transaction price corresponding to the previous time unit on the fitting curve as the trend change coefficient; A missing degree determining unit, configured to determine the missing degree of the similar geographical object according to the number of similar geographical objects to the geographical object to be evaluated and the number of transaction objects in the area where the geographical object to be evaluated is located; The value assessment result determination unit is used to use the missing degree as an adjustment coefficient and the product of the second result and the trend change coefficient as an adjustment amount to adjust the first result to obtain the value assessment result of the geographic object to be assessed.

14. An electronic device, characterized in that: The electronic device comprises a processor and a memory; The memory stores a computer program, and after the processor runs the computer program, the method according to any one of claims 1 to 12 is executed.

15. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and after the computer program is run by the processor, the method according to any one of claims 1 to 12 is executed.

Images