Real estate asset data management method based on Internet of Things

Abstract

The invention discloses a real estate asset data management method based on the Internet of Things, and particularly relates to the technical field of data management. Spatial data and attribute data are acquired, two key features of boundary geometric compactness and timestamp similarity are calculated, a risk assessment model is constructed, and intelligent analysis and risk identification are performed on a spatial attribute binding relationship; according to the model, a classifier is generated by training historical accurate binding samples, risk coefficients of each group of binding relations can be output, high-risk mismatching items are automatically marked, and verification and correction are realized in combination with a rule engine, so that the problem of mismatching caused by multi-source data fusion errors and lack of a verification mechanism in the prior art is effectively solved, and the accuracy of mismatching is improved. And the accuracy, the credibility and the management intelligence level of the real estate data are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a real estate asset data management method based on the Internet of Things. Background Art

[0002] Real estate asset data management refers to the systematic and standardized collection, organization, storage, updating, and application of data related to real estate (such as land and houses). Its core purpose is to achieve visualization, traceability, and efficient utilization of real estate assets throughout their lifecycle through information technology, thereby improving asset management efficiency, ensuring asset security, and providing accurate data support for decision-making.

[0003] The existing technology has the following shortcomings:

[0004] In the existing process of establishing digital models of real estate assets, when fusing multi-source data, mismatches between attribute information and spatial objects occur due to coordinate conversion errors, inconsistent numbering, or missing matching rules. The system lacks an effective logical verification mechanism, making it difficult to detect binding errors in a timely manner. This may lead to risks such as anomalies in property rights information, management decision-making errors, and legal disputes, seriously affecting the accuracy and credibility of asset data. Summary of the Invention

[0005] The purpose of the present invention is to provide a real estate asset data management method based on the Internet of Things to address the shortcomings of the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a real estate asset data management method based on the Internet of Things, comprising:

[0007] Obtain spatial data and attribute data of the real estate assets to be modeled;

[0008] Calculating the boundary geometric compactness of the spatial data, where the boundary geometric compactness is used to reflect the regularity of the boundary outline of the real estate;

[0009] Calculating the timestamp similarity between spatial data and attribute data, wherein the timestamp similarity is used to identify the degree of synchronization between data collection and update;

[0010] Based on the boundary geometry compactness and timestamp similarity, a risk assessment model for spatial attribute binding relationships is constructed, wherein the model is trained on accurate historical binding samples to generate a classifier for identifying potential binding mismatch risks;

[0011] Inputting the binding relationship between each set of spatial data and attribute data into the classifier and outputting the corresponding risk coefficient;

[0012] Binding relationships with risk factors exceeding the preset threshold are marked as high-risk mismatch items, and binding verification and correction are performed.

[0013] Preferably, the spatial data includes graphic boundary information, and the attribute data includes asset number, purpose, owner and data entry time information.

[0014] Preferably, the calculation method of the boundary geometric compactness is: suppose the boundary of the two-dimensional graph G is composed of the point set Composition, x i is the horizontal coordinate of the i-th boundary point; y i Represents the ordinate of the i-th boundary point; n represents the total number of points on the boundary of the figure. The least squares ellipse fitting algorithm is used to fit the ellipse to obtain the standard ellipse parameters: ellipse center: (x0, y0); major axis radius: a; minor axis radius: b; ellipse rotation angle: θ; the ellipse expression is: Where x′, y′ are the coordinates after rotation transformation; calculate the area A of the original figure; G , using the Shoelace formula for polygon area: Among them, (x n+1 ,y n+1 )=(x1,y1); calculate the area of ​​the fitted ellipse A E , the formula for the area of ​​an ellipse is: A E =πab; calculate the intersection area A of the original figure G and the ellipse E G∩E , and then normalize to get the boundary geometric compactness, the expression is: EFC is the boundary geometry compactness.

[0015] Preferably, the method for obtaining timestamp similarity is:

[0016] Extract the generation time from the spatial data and record it as T s ∈R; R is a real number set; extract the latest update time or storage time from the attribute data, denoted as T a ; Normalize the two timestamps to the absolute difference ΔT in days, the expression is: ΔT=|T s -T a |; Normalize the time difference to the range of [0,1] to calculate the timestamp similarity TSim, the expression is: Where: λ is the time decay coefficient, TSim∈(0,1].

[0017] Preferably, the construction of the risk assessment model includes: collecting spatial attribute binding samples that have been manually reviewed in the past, and constructing a data set containing binding correctness labels; calculating the boundary geometry compactness and timestamp similarity for each group of samples to form a training feature vector set; selecting a supervised learning algorithm, including logistic regression, random forest, support vector machine or neural network model, and training a classifier to identify binding mismatch risks; the result output by the classifier is the risk coefficient of the binding relationship, with a value range of [0,1], which is used to judge the accuracy of the binding.

[0018] Preferably, the binding verification and correction includes:

[0019] Binding relationships with a risk factor greater than or equal to the preset threshold are marked as high-risk and enter the correction process;

[0020] Retrieve unbound or low-risk attribute data within the spatial neighborhood to form a candidate set;

[0021] Calculate the modified score for each candidate relationship The expression is: Where: S ij Represents the spatial overlap ratio between graphic attributes; represents the normalized value of geometric compactness; ΔT ij Indicates the time difference between spatial data and attribute data; T max represents the normalized upper limit of the time difference; ω1, ω2, and ω3 represent weight coefficients.

[0022] Preferably, all candidate attribute data are scored according to the modified score Sort and input to the rule engine, if the highest scoring item The original binding relationship is automatically replaced; if all candidate scores are lower than the threshold η, the binding relationship is marked for manual review and processing.

[0023] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0024] 1. This invention introduces two key characteristic parameters: boundary geometry compactness and timestamp similarity. Combined with a supervised learning algorithm, this model constructs a risk assessment model, overcoming the bottleneck of traditional real estate data management, which lacks intelligent verification mechanisms. It effectively identifies binding mismatch risks between spatial and attribute data. Compared to traditional methods that rely on manual judgment or simple rule matching, this invention implements intelligent processing throughout the entire process, from data collection and risk assessment to automatic correction, significantly improving the accuracy and automation level of real estate digital models.

[0025] 2. This invention incorporates a rules engine and scoring mechanism to automatically rank high-risk binding relationships and automatically adjust candidate rankings. It also uses a multi-factor fusion scoring system to enable decisions about replacement or manual review, creating a closed-loop, self-optimizing data management system. This method offers excellent adaptability and scalability, applicable to a wide range of real estate asset data processing needs. It significantly enhances the system's data quality control capabilities, reduces manual operation and maintenance costs, and promotes the evolution of real estate asset management from static inventory management to dynamic, precise, and reliable intelligent management. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0027] Figure 1 This is a mind map of the method of the present invention. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] For examples, see Figure 1 As shown, the real estate asset data management method based on the Internet of Things described in this embodiment includes:

[0030] Obtain spatial data and attribute data of the real estate assets to be modeled;

[0031] Calculating the boundary geometric compactness of the spatial data, where the boundary geometric compactness is used to reflect the regularity of the boundary outline of the real estate;

[0032] Calculating the timestamp similarity between spatial data and attribute data, wherein the timestamp similarity is used to identify the degree of synchronization between data collection and update;

[0033] Based on the boundary geometry compactness and timestamp similarity, a risk assessment model for spatial attribute binding relationships is constructed, wherein the model is trained on accurate historical binding samples to generate a classifier for identifying potential binding mismatch risks;

[0034] Inputting the binding relationship between each set of spatial data and attribute data into the classifier and outputting the corresponding risk coefficient;

[0035] Binding relationships with risk factors exceeding the preset threshold are marked as high-risk mismatch items, and binding verification and correction are performed.

[0036] In this example, to address the difficulties in acquiring spatial and attribute data and inconsistent data sources in the early stages of real estate asset modeling, a high-precision, multi-source, automated data collection and fusion solution was designed. The details are as follows:

[0037] First, various types of IoT sensors are deployed at the real estate site to collect real estate spatial data. Specifically, they include:

[0038] Use a laser radar device to perform 3D point cloud scanning of real estate buildings to obtain complete 3D structural data. Use a point cloud contour extraction algorithm to extract the 2D boundary graphics of each building or plot and express it in vector form.

[0039] Combined with GNSS positioning terminals (such as RTK high-precision receivers), the boundary nodes of the graphics are spatially positioned to obtain precise longitude and latitude coordinates, and the collected data is uniformly converted to the Chinese Geodetic Coordinate System (CGCS2000) to ensure spatial consistency across different data sources.

[0040] For areas with severe building obstruction or GNSS signal interference, drones equipped with multi-angle cameras are used to perform low-altitude image acquisition tasks. Orthophotos are constructed through photogrammetry and image matching algorithms, and building boundary graphics are extracted to supplement areas with missing accuracy.

[0041] All spatially collected data is wirelessly uploaded to the data management platform via the 4G / 5G communication module or LoRa protocol, and is uniformly encapsulated into a GeoJSON structure through the platform format conversion module to establish a preliminary asset boundary layer.

[0042] Next, the real estate attribute data corresponding to the spatial data is obtained, and the method includes:

[0043] The system accesses the open data interface (such as RESTful API) of the real estate registration center and requests the corresponding real estate registration information based on the collected spatial graphic coordinate range or plot code, including asset number, owner name, use classification, registration time, etc.

[0044] For information that cannot be automatically obtained from the database, the system supports manual uploading of historical real estate paper archives, automatically parsing key field information through the OCR recognition module, and extracting structured data through regular expressions and machine learning models;

[0045] All attribute data are uniformly mapped to the asset field template set in the platform (such as: number, name, purpose, area, registration unit, entry time, etc.), and are initially associated with the spatial data through the asset unique identification code to establish a space-attribute binding relationship table.

[0046] Finally, to ensure data consistency and the accuracy of subsequent risk identification, the system records the original collection source, collection time, equipment number and processing log for each spatial attribute binding relationship for subsequent model training and verification traceability.

[0047] The collaborative acquisition solution of spatial data and attribute data provided by this embodiment can effectively improve the data accuracy and completeness in the initial stage of real estate asset modeling, laying a solid foundation for the subsequent establishment of accurate, dynamic and traceable digital asset archives.

[0048] Calculate the boundary geometric compactness of spatial data. The boundary geometric compactness is used to reflect the regularity of the real estate boundary outline. The calculation method of the boundary geometric compactness is:

[0049] Suppose the boundary of the two-dimensional graph G is composed of the point set It is composed to ensure a closed and ordered contour. i The horizontal coordinate (X-axis coordinate) of the i-th boundary point, usually in meters (m) or pixels; i Indicates the ordinate (Y-axis coordinate) of the i-th boundary point, the unit is the same as x i Same; n represents the total number of points on the boundary of the figure. Use the least squares ellipse fitting algorithm (such as the Fitzgibbon method) to fit the ellipse and obtain the standard ellipse parameters: ellipse center: (x0, y0); major axis radius: a; minor axis radius: b; ellipse rotation angle: θ; the ellipse expression is: Where x′, y′ are the coordinates after rotation transformation.

[0050] Calculate the area A of the original figure G , using the Shoelace formula for polygon area: Among them, (x n+1 ,y n+1 )=(x1,y1); calculate the area of ​​the fitted ellipse A E , the formula for the area of ​​an ellipse is: A E =πab; calculate the intersection area A of the original figure G and the ellipse E G∩E , and then normalize to get the boundary geometric compactness, the expression is: EFC is the boundary geometry compactness.

[0051] A higher geometric compactness of the boundary indicates that the boundary of a figure is closer to a regular shape, such as a circle or regular polygon. This generally indicates a more regular boundary outline, simple shapes with clear geometric relationships, and no significant indentations or irregular extensions. For example, circles and squares with a high degree of compactness often indicate a well-defined property plan or design.

[0052] Conversely, a lower geometrically compact boundary generally indicates a more complex boundary, with more indentations, bends, or irregular extensions. This indicates a less regular boundary outline, potentially due to historical changes, expansions, or irregular design. Such boundaries often exhibit greater variability, potentially impacting subsequent asset management and spatial analysis.

[0053] Calculate the timestamp similarity between spatial data and attribute data. The timestamp similarity is used to identify the degree of synchronization between data collection and update. The timestamp similarity is obtained as follows:

[0054] Extract the generation time (acquisition time, boundary graphic input time) from the spatial data and record it as T s ∈R; format: YYYY-MM-DD or Unix timestamp; R is a set of real numbers;

[0055] Extract the latest update time or storage time from the attribute data, and record it as T a ; Normalize the two timestamps to the absolute difference ΔT in days, the expression is: ΔT=|T s -T a |; The unit is day (hours / minutes can also be selected, depending on the actual business scenario);

[0056] To facilitate comparison, the time difference is normalized to the range of [0,1] to calculate the timestamp similarity TSim, which is expressed as: Where: λ is the time decay coefficient, which controls the sensitivity of time difference to similarity (for example, λ = 30 means that changes within 30 days have little impact); TSim∈(0,1], the closer the value is to 1, the more synchronized it is.

[0057] The greater the timestamp similarity between spatial data and attribute data, the closer the data collection and update times are, indicating a better synchronization of the two data's timeliness. This indicates a smaller time difference between spatial and attribute data updates, meaning that within the same time period, changes in spatial and attribute information are more consistent, reducing the risk of mismatches caused by data asynchrony. Consequently, the data is highly synchronized, demonstrating good reliability and consistency.

[0058] Conversely, when the timestamp similarity between spatial and attribute data is smaller, there is a significant discrepancy between their collection and update times, indicating a low degree of synchronization during the data collection and update process. In this case, spatial and attribute data may not be updated in a timely manner, resulting in significant differences in their timeliness and increasing the risk of mismatches caused by data asynchrony. Consequently, low data synchronization can affect the accuracy of subsequent analysis and decision-making.

[0059] To effectively identify potential mismatch risks in the binding process between real estate spatial data and attribute data, this embodiment provides a method for constructing a risk assessment model based on boundary geometry compactness and timestamp similarity, specifically including the following steps:

[0060] We collect sample data of spatial attribute bindings that have been manually reviewed and confirmed to be correct as training data. Each set of samples includes spatial boundary graphic data with known correct binding relationships and corresponding attribute data, as well as a label indicating whether the binding is incorrect (e.g., "matched correctly" or "matched incorrectly").

[0061] For each sample data, the boundary geometry compactness and timestamp similarity are calculated from the spatial graph;

[0062] The features of the above two categories are combined to form a feature vector set of training samples, and a training set (X, y) is constructed, where X is a two-dimensional or multi-dimensional vector composed of boundary geometric compactness and timestamp similarity, and y is the label of the binding relationship (1 indicates high-risk mismatch and 0 indicates correct binding).

[0063] Select and build an appropriate supervised learning model, such as:

[0064] Logistic regression model to output binding risk probability;

[0065] Random forest or support vector machine for nonlinear classification between multiple features;

[0066] Convolutional or fully connected neural network models for risk classification under large-scale data.

[0067] The model converges through the training process to obtain stable classification boundaries and prediction rules.

[0068] Each set of spatial attribute binding data currently in operation is fed into a trained classifier model. The model then outputs a risk coefficient for the binding relationship, which is used to determine whether there is a mismatch risk. If the risk coefficient is greater than or equal to a preset threshold, the binding relationship is marked as high risk; if the risk coefficient is less than the threshold, it is considered low risk or normal.

[0069] For binding relationships marked as high-risk, automatic corrections are performed in conjunction with the rule engine to improve overall data quality.

[0070] This approach enables intelligent identification of the accuracy of spatial and attribute bindings in real estate asset data, effectively preventing mismatches caused by data asynchrony or irregular graphs, and improving the system's intelligent management capabilities and data credibility. This model is both versatile and scalable, applicable to scenarios with diverse data sources and real estate types.

[0071] To improve the accuracy of binding real estate spatial data and attribute data and reduce manual verification costs, this embodiment proposes an automatic correction method that combines a rule engine with risk scoring results. This method achieves intelligent repair by scoring, determining, and ranking replacement candidates for high-risk binding relationships. The specific steps are as follows:

[0072] Input the binding relationship between each set of spatial data and attribute data into the risk assessment model to obtain its corresponding risk coefficient ρ ij , for the spatial data object G marked as high risk i , within a certain spatial neighborhood range D, retrieve all attribute data sets that have not been bound or whose binding relationship scores are lower than the threshold: represents the candidate attribute set, dist(G i ,A j ) represents the geographical distance or graphic overlap between the spatial object and the attribute data; τ alt Represents the maximum allowable risk threshold of the candidate binding relationship; for each set of candidate relationships (G i ,A j ), calculate its modified score It is defined by the formula: Where: S ij Represents the spatial overlap ratio between graphics and attributes (IoU, proximity, etc.); Indicates the normalized value of geometric compactness (the more regular, the smaller); ΔT ij Indicates the time difference between spatial data and attribute data (days); T max represents the normalized upper limit of the time difference; ω1, ω2, and ω3 represent weight coefficients, which must sum to 1. A higher score indicates a more credible binding relationship.

[0073] All candidate attribute data are scored Sorting is done and input into the rule engine. The rule engine contains the following decision logic:

[0074] If the highest rated item The original binding relationship will be automatically replaced; if all candidate scores are lower than the threshold η, the binding relationship will be marked as pending for manual verification; the scoring can be weighted in combination with priority rules (such as ownership agency priority, latest update time priority).

[0075] After the system completes the automatic correction: the corrected spatial attribute binding relationship is updated to the database; the original binding relationship, correction reason, candidate set scoring details and other information are retained; and a log is generated for auditing and subsequent model feedback learning.

[0076] Through the above method, the system can not only detect high-risk binding mismatch problems, but also realize automatic identification and intelligent correction based on comprehensive reasoning of space, time and shape logic, effectively improving the quality of real estate asset data and management efficiency.

[0077] The present invention provides a real estate asset data management method based on the Internet of Things. By deploying sensor equipment such as lidar, GNSS terminals and drones to obtain spatial boundary data, and combining real estate registration information with OCR recognition to extract attribute data, high-precision integration of spatial and attribute information is achieved. On this basis, the boundary geometry compactness and timestamp similarity are calculated, a risk assessment model is constructed, and a classifier is trained through a supervised learning algorithm to perform risk assessment on binding relationships. For high-risk binding relationships, automatic scoring and correction and replacement are performed in combination with a rule engine, forming a closed-loop management system covering data collection, risk identification and intelligent correction, effectively improving the integrity, accuracy and intelligence level of real estate data.

[0078] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0079] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0080] It should be understood that the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone, where A and B may be singular or plural. In addition, the character " / " herein generally indicates that the objects associated with each other are in an "or" relationship, but it may also indicate an "and / or" relationship, which can be understood by referring to the context. A person of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0081] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A real estate asset data management method based on the Internet of Things, characterized by: include: Obtain spatial data and attribute data of the real estate assets to be modeled; Calculating the boundary geometric compactness of the spatial data, where the boundary geometric compactness is used to reflect the regularity of the boundary outline of the real estate; Calculating the timestamp similarity between spatial data and attribute data, wherein the timestamp similarity is used to identify the degree of synchronization between data collection and update; Based on the boundary geometry compactness and timestamp similarity, a risk assessment model for spatial attribute binding relationships is constructed, wherein the model is trained on accurate historical binding samples to generate a classifier for identifying potential binding mismatch risks; Inputting the binding relationship between each set of spatial data and attribute data into the classifier and outputting the corresponding risk coefficient; Binding relationships with risk factors exceeding the preset threshold are marked as high-risk mismatch items, and binding verification and correction are performed.

2. The method for managing real estate asset data based on the Internet of Things according to claim 1, characterized in that: The spatial data includes graphic boundary information, and the attribute data includes asset number, purpose, owner and data entry time information.

3. The method for managing real estate asset data based on the Internet of Things according to claim 1, characterized in that: The calculation method of boundary geometry compactness is: suppose the boundary of the two-dimensional graph G is composed of the point set Composition, x i is the horizontal coordinate of the i-th boundary point; y i Represents the ordinate of the i-th boundary point; n represents the total number of points on the boundary of the figure. The least squares ellipse fitting algorithm is used to fit the ellipse to obtain the standard ellipse parameters: ellipse center: (x0, y0); major axis radius: a; minor axis radius: b; ellipse rotation angle: θ; the ellipse expression is: Where x′, y′ are the coordinates after rotation transformation; calculate the area A of the original figure; G , using the Shoelace formula for polygon area: Among them, (x n+1 ,y n+1 )=(x1,y1); calculate the area of ​​the fitted ellipse A E , the formula for the area of ​​an ellipse is: A E =πab; calculate the intersection area A of the original figure G and the ellipse E G∩E , and then normalize to get the boundary geometric compactness, the expression is: EFC is the boundary geometry compactness.

4. The method for managing real estate asset data based on the Internet of Things according to claim 3, characterized in that: The method for obtaining timestamp similarity is: Extract the generation time from the spatial data and record it as T s ∈R; R is a real number set; extract the latest update time or storage time from the attribute data, denoted as T a ; Normalize the two timestamps to the absolute difference ΔT in days, the expression is: ΔT=|T s -T a |; Normalize the time difference to the range of [0,1] to calculate the timestamp similarity TSim, the expression is: Where: λ is the time decay coefficient, TSim∈(0,1].

5. The method for managing real estate asset data based on the Internet of Things according to claim 4, characterized in that: The risk assessment model construction includes: collecting spatial attribute binding samples that have been manually reviewed in the past to construct a data set containing binding correctness labels; calculating the boundary geometry compactness and timestamp similarity of each set of samples to form a training feature vector set; selecting a supervised learning algorithm, including logistic regression, random forest, support vector machine or neural network model, to train a classifier for identifying binding mismatch risks; the classifier outputs a risk coefficient of the binding relationship with a value range of [0,1], which is used to judge the accuracy of the binding.

6. The method for managing real estate asset data based on the Internet of Things according to claim 5, characterized in that: The binding verification and correction includes: Binding relationships with a risk factor greater than or equal to the preset threshold are marked as high-risk and enter the correction process; Retrieve unbound or low-risk attribute data within the spatial neighborhood to form a candidate set; Calculate the modified score for each candidate relationship The expression is: Where: S ij Represents the spatial overlap ratio between graphic attributes; represents the normalized value of geometric compactness; ΔT ij Indicates the time difference between spatial data and attribute data; T max represents the normalized upper limit of the time difference; ω1, ω2, and ω3 represent weight coefficients.

7. The method for managing real estate asset data based on the Internet of Things according to claim 6, characterized in that: All candidate attribute data are scored according to the revised Sort and input to the rule engine, if the highest scoring item The original binding relationship is automatically replaced; if all candidate scores are lower than the threshold η, the binding relationship is marked for manual review and processing.

Images