CN118195320A - Real estate registration information sharing management system and method based on big data technology - Google Patents
Real estate registration information sharing management system and method based on big data technology Download PDFInfo
- Publication number
- CN118195320A CN118195320A CN202410401522.6A CN202410401522A CN118195320A CN 118195320 A CN118195320 A CN 118195320A CN 202410401522 A CN202410401522 A CN 202410401522A CN 118195320 A CN118195320 A CN 118195320A
- Authority
- CN
- China
- Prior art keywords
- real estate
- estate registration
- registration information
- matrix
- full
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title abstract description 10
- 239000013598 vector Substances 0.000 claims description 112
- 239000011159 matrix material Substances 0.000 claims description 99
- 238000007726 management method Methods 0.000 claims description 53
- 238000012502 risk assessment Methods 0.000 claims description 29
- 238000007621 cluster analysis Methods 0.000 claims description 26
- 238000010606 normalization Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 20
- 238000009826 distribution Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000010354 integration Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012954 risk control Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of intelligent management, and particularly discloses a real estate registration information sharing management system and method based on a big data technology. Thus, the sharing of the real estate registration information can be ensured to be safer and more efficient, so that the utilization efficiency and the value of the real estate registration information are improved.
Description
Technical Field
The application relates to the technical field of intelligent management, in particular to a real estate registration information sharing management system and method based on big data technology.
Background
Real estate registration is an important administrative task, and the main purpose of the real estate registration is to protect legal rights of real estate rights, maintain social and economic orders and promote social and economic development. However, real estate registration information management faces a great challenge due to the large volume, large types, and frequent updating of real estate registration information.
Conventional real estate registration information management systems generally employ database technology for information storage and management, but this approach has the following problems: firstly, the information inquiry efficiency is low, and the requirement of large-scale and complex information inquiry cannot be met; secondly, the information sharing is difficult, the information exchange and sharing among different departments and different areas are difficult, and the effective integration of information resources cannot be realized; and thirdly, the risk control capability is weak, and effective risk assessment and early warning are difficult to carry out on a large amount of real estate registration information.
With the rapid development of information technology, big data technology is increasingly widely applied to various industries. In the field of real estate registration, the conventional information management method cannot meet the requirements of the modern society. Therefore, a real estate registration information sharing management system and method based on big data technology is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a real estate registration information sharing management system and method based on big data technology, which adopts artificial intelligence technology based on deep learning to perform semantic understanding and joint cluster analysis on a set of real estate registration information so as to capture the whole sample domain semantic association characteristics of the real estate registration information and mine potential risk factors in the set of real estate registration information, thereby realizing risk assessment of the real estate registration information and further performing open authority setting according to a risk assessment result. Thus, the sharing of the real estate registration information can be ensured to be safer and more efficient, so that the utilization efficiency and the value of the real estate registration information are improved.
Accordingly, according to an aspect of the present application, there is provided a real estate registration information sharing management system based on big data technology, comprising:
The real estate registration information acquisition module is used for acquiring a set of real estate registration information;
the real estate registration information semantic coding module is used for carrying out semantic coding on the set of real estate registration information to obtain a set of real estate registration information semantic coding feature vectors;
The joint cluster analysis module is used for inputting the set of the real estate registration information semantic coding feature vectors into a joint cluster analysis network to obtain a real estate registration full-sample domain association feature matrix;
The risk judging module is used for determining a risk assessment result of the real estate registration information based on the real estate registration full-sample domain association feature matrix;
And the permission setting module is used for opening a data acquisition interface for acquiring the set of real estate registration information and setting open permissions for the risk assessment result.
In the real estate registration information sharing management system based on big data technology, the real estate registration information semantic coding module includes: the data preprocessing unit is used for carrying out data cleaning, format conversion and data integration on each real estate registration information in the set of real estate registration information to obtain a set of preprocessed real estate registration information; the semantic coding unit is used for carrying out semantic coding on each piece of preprocessed real estate registration information in the preprocessed real estate registration information set to obtain a set of semantic coding feature vectors of the real estate registration information.
In the real estate registration information sharing management system based on big data technology, the semantic coding unit is configured to: and passing each piece of preprocessed real estate registration information in the preprocessed real estate registration information set through a real estate information semantic encoder based on a transducer model to obtain the real estate registration information semantic encoding feature vector set.
In the real estate registration information sharing management system based on big data technology, the joint cluster analysis module comprises: an adjacency association unit, configured to construct an adjacency matrix and a degree matrix of the set of real estate registration information semantic coding feature vectors, where feature values of each position on a non-diagonal line in the adjacency matrix are weights between nodes between every two real estate registration information semantic coding feature vectors in the set of real estate registration information semantic coding feature vectors, and feature values of each position on a diagonal line in the degree matrix are sums of weights between nodes between each real estate registration information semantic coding feature vector and all other real estate registration information semantic coding feature vectors; the Laplace matrix calculation unit is used for carrying out element pair phase subtraction and difference processing on the degree matrix and the adjacent matrix to obtain a Laplace matrix; the normalization unit is used for carrying out symmetrical normalization processing on the Laplace matrix to obtain a normalized Laplace matrix; the characteristic value decomposition unit is used for arranging the characteristic values of the normalized Laplace matrix from large to small, taking the first K characteristic values, and decomposing the normalized Laplace matrix based on the first K characteristic values to obtain K real estate registration full-sample domain associated characteristic vectors, wherein K is the number of the real estate registration information semantic coding characteristic vectors; and the standardized processing unit is used for respectively carrying out standardized processing on the K real estate registration full-sample domain association feature vectors and then carrying out two-dimensional arrangement to obtain the real estate registration full-sample domain association feature matrix.
In the real estate registration information sharing management system based on big data technology, the adjacency association unit is configured to: constructing an adjacency matrix and a degree matrix of the set of real estate registration information semantically encoded feature vectors in an adjacency correlation formula; wherein, the adjacent association formula is: ; wherein/> Is the/>, of the set of real estate registration information semantically encoded feature vectorsSemantic coding feature vector of real estate registration information,/>Is/>Semantic coding feature vector of real estate registration information,/>For the/>Semantic coding feature vectors of personal real estate registration information and the/>Standard deviation between semantically encoded feature vectors of individual real estate registration information,/>Representing the square of the 2-norm of the feature vector,/>Representing element pair bit minus difference processing,/>Representing natural exponential function operations,/>Is the/>, of the adjacency matrixCharacteristic value of location,/>Is the/>, of the degree matrixCharacteristic value of location,/>And semantically encoding the number of the feature vectors for the real estate registration information.
In the real estate registration information sharing management system based on big data technology, the normalization unit is configured to: symmetric normalization processing is carried out on the Laplace matrix by the following normalization formula so as to obtain the normalized Laplace matrix; wherein, the normalization formula is: ; wherein/> For the adjacency matrix,/>For the degree matrix,/>Representing an identity matrix,/>And normalizing the Laplace matrix.
In the real estate registration information sharing management system based on big data technology, the risk judging module includes: the feature distribution optimizing unit is used for carrying out feature distribution optimization on the real estate registration full-sample domain association feature matrix to obtain an optimized real estate registration full-sample domain association feature vector; and the classification unit is used for enabling the optimized real estate registration full-sample domain association feature vector to pass through a risk evaluator based on a classifier to obtain a risk evaluation result, wherein the risk evaluation result is used for representing a risk level.
In the real estate registration information sharing management system based on big data technology, the classification unit includes: the full-connection coding subunit is used for carrying out full-connection coding on the optimized real estate registration full-sample domain association feature vector by using a full-connection layer of the risk estimator based on the classifier so as to obtain a full-connection coding feature vector; the probability subunit is used for inputting the fully-connected coding feature vector into a Softmax classification function of the risk estimator based on the classifier to obtain a probability value of the optimized real estate registration full-sample domain association feature vector belonging to each risk level label; and the evaluation result generation subunit is used for determining the risk level label corresponding to the maximum probability value as the risk evaluation result.
According to another aspect of the present application, there is provided a real estate registration information sharing management method based on big data technology, comprising:
Acquiring a set of real estate registration information;
carrying out semantic coding on the set of real estate registration information to obtain a set of real estate registration information semantic coding feature vectors;
inputting the set of the semantic coding feature vectors of the real estate registration information into a joint cluster analysis network to obtain a real estate registration full-sample domain association feature matrix;
determining a risk assessment result of real estate registration information based on the real estate registration full-sample domain association feature matrix;
And opening a data acquisition interface for acquiring the set of real estate registration information and setting open rights for the risk assessment result.
Compared with the prior art, the real estate registration information sharing management system and method based on the big data technology provided by the application adopt the artificial intelligence technology based on deep learning to perform semantic understanding and joint cluster analysis on the set of real estate registration information so as to capture the whole sample domain semantic association characteristics of the real estate registration information and mine potential risk factors in the set of real estate registration information, thereby realizing risk assessment of the real estate registration information and further performing open authority setting according to the risk assessment result. Thus, the sharing of the real estate registration information can be ensured to be safer and more efficient, so that the utilization efficiency and the value of the real estate registration information are improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a block diagram of a real estate registration information sharing management system based on big data technology according to an embodiment of the present application.
Fig. 2 is a schematic architecture diagram of a real estate registration information sharing management system based on big data technology according to an embodiment of the present application.
Fig. 3 is a block diagram of a real estate registration information semantic coding module in a real estate registration information sharing management system based on big data technology according to an embodiment of the present application.
Fig. 4 is a block diagram of a joint cluster analysis module in a real estate registration information sharing management system based on big data technology according to an embodiment of the present application.
Fig. 5 is a block diagram of a risk determination module in a real estate registration information sharing management system based on big data technology according to an embodiment of the present application.
Fig. 6 is a flowchart of a real estate registration information sharing management method based on big data technology according to an embodiment of the present application.
Detailed Description
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular description of embodiments of the application, as illustrated in the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. Meanwhile, the accompanying drawings are included to provide a further understanding of embodiments of the application, and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not to limit the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a block diagram of a real estate registration information sharing management system based on big data technology according to an embodiment of the present application. Fig. 2 is a schematic architecture diagram of a real estate registration information sharing management system based on big data technology according to an embodiment of the present application. As shown in fig. 1 and 2, a real estate registration information sharing management system 100 based on big data technology according to an embodiment of the present application includes: a real estate registration information acquisition module 110 for acquiring a set of real estate registration information; a real estate registration information semantic coding module 120, configured to semantically code the set of real estate registration information to obtain a set of real estate registration information semantic coding feature vectors; the joint cluster analysis module 130 is configured to input the set of semantic coding feature vectors of the real estate registration information into a joint cluster analysis network to obtain a real estate registration full-sample domain association feature matrix; the risk determination module 140 is configured to determine a risk assessment result of the real estate registration information based on the real estate registration full-sample domain association feature matrix; and the permission setting module 150 is used for opening a data acquisition interface for acquiring the set of real estate registration information and setting open permissions for the risk assessment result.
As described above in the background art, real estate registration information management faces a great challenge due to the large amount, large types, and frequent updating of real estate registration information. The traditional real estate registration information management system generally adopts a database technology to store and manage information, but the method has the problems of low inquiry efficiency, difficult information sharing and weak risk control. Aiming at the technical problems, the technical concept of the application is to adopt an artificial intelligence technology based on deep learning to perform semantic understanding and joint cluster analysis on a set of real estate registration information so as to capture the whole sample domain semantic association characteristics of the real estate registration information and mine potential risk factors in the set of real estate registration information, thereby realizing risk assessment of the real estate registration information and further performing open authority setting according to a risk assessment result. Thus, the sharing of the real estate registration information can be ensured to be safer and more efficient, so that the utilization efficiency and the value of the real estate registration information are improved.
In the real estate registration information sharing management system 100 based on big data technology, the real estate registration information obtaining module 110 is configured to obtain a set of real estate registration information. It should be understood that the real estate registration information generally includes information about properties, locations, areas, values, etc. of real estate such as houses, lands, buildings, etc., and by acquiring the set of real estate registration information, comprehensive understanding and grasping of real estate registration information can be achieved, and a data sharing platform is established, so that related institutions or individuals can acquire and use the information, and information sharing and resource utilization are promoted. However, in the data sharing management, it is considered that sensitive information such as personal privacy and business secrets may be contained in the set of real estate registration information. Therefore, in order to ensure the security and privacy of information, it is necessary to perform authority control on data access while opening the data acquisition interface. Based on the above, in the technical scheme of the application, risk assessment needs to be further carried out on the information in the set of the real estate registration information so as to identify the risk level thereof, so that corresponding open rights are set according to the risk level thereof, sensitive information is ensured not to be acquired by unauthorized users, and information security is ensured.
In the real estate registration information sharing management system 100 based on big data technology, the real estate registration information semantic coding module 120 is configured to perform semantic coding on the set of real estate registration information to obtain a set of real estate registration information semantic coding feature vectors. Specifically, fig. 3 is a block diagram of a real estate registration information semantic coding module in a real estate registration information sharing management system based on big data technology according to an embodiment of the present application. As shown in fig. 3, the real estate registration information semantic coding module 120 includes: a data preprocessing unit 121, configured to perform data cleaning, format conversion and data integration on each real estate registration information in the set of real estate registration information to obtain a set of preprocessed real estate registration information; the semantic coding unit 122 is configured to semantically code each preprocessed real estate registration information in the preprocessed real estate registration information set to obtain a set of semantic coding feature vectors of the real estate registration information.
Specifically, the data preprocessing unit 121 is configured to perform data cleansing, format conversion and data integration on each real estate registration information in the set of real estate registration information to obtain a set of preprocessed real estate registration information. It should be appreciated that considering that each real property registration information in the set of real property registration information may come from a different data source, there are problems of non-uniformity of data formats, data missing, data duplication, and the like. Therefore, in order to improve the consistency and accuracy of the data, the data cleaning, format conversion and data integration are further performed on each real estate registration information in the set of real estate registration information, so that noise and redundancy in the data are eliminated, and the data quality is improved. In particular, data cleansing can help identify and correct erroneous, missing, or inconsistent data in a data set to ensure accuracy and integrity of the data, helping to improve the accuracy of subsequent data risk analysis. The format conversion and the data integration can unify the formats and structures of different data sources, so that the data has a consistent expression mode, the difference between the data can be eliminated, and the data is easier to compare and analyze. That is, the real estate registration information after being cleaned, format converted and integrated has better readability and usability, and errors and confusion in the subsequent information analysis process can be reduced, so that the analysis efficiency and accuracy of risk analysis are improved.
Specifically, the semantic coding unit 122 is configured to perform semantic coding on each preprocessed real estate registration information in the preprocessed real estate registration information set to obtain a set of semantic coding feature vectors of the real estate registration information. In a specific example of the present application, the encoding mode of performing semantic encoding on each piece of preprocessed real estate registration information in the preprocessed real estate registration information set is to pass each piece of preprocessed real estate registration information in the preprocessed real estate registration information set through a real estate information semantic encoder based on a Transformer model to obtain the real estate registration information semantic encoding feature vector set. It should be appreciated that the transducer model is a natural language processing model based on self-attention mechanisms. According to the technical scheme, the real estate information semantic encoder is based on a Transformer idea, and utilizes a self-attention mechanism to perform parallel calculation on each word in the preprocessed real estate registration information, so that the long-distance dependence characteristic of the information can be effectively captured, namely, the upper part and the lower part Wen Yuyi of each word in the preprocessed real estate registration information are associated, original high-dimensional text information is converted into vector representation with semantic information, the dimension of data is reduced, the processing efficiency of the data is improved, the global semantic content of the preprocessed real estate registration information can be more fully described, and basic data is provided for subsequent risk analysis.
In the real estate registration information sharing management system 100 based on big data technology, the joint cluster analysis module 130 is configured to input the set of semantic coding feature vectors of the real estate registration information into a joint cluster analysis network to obtain a real estate registration full sample domain association feature matrix. It should be appreciated that, considering that there is a complex association between the respective real estate registration information, for example, real estate in the same region may be affected by the same policy; the same design style or building material may exist for real property projects of the same developer; real estate for the same time period may be affected by the same market economics, etc. Therefore, in order to deeply mine potential association relations between the real estate registration information, in the technical scheme of the application, the set of semantic coding feature vectors of the real estate registration information is input into a joint cluster analysis network for association analysis. Specifically, the joint cluster analysis network performs cluster analysis on the set of the semantic coding feature vectors of the real estate registration information by learning the association relation among the semantic coding feature vectors of each real estate registration information so as to mine global association features of the set of the real estate registration information, such as similarity and difference of the real estate registration information among different areas, different developers and different time periods, so that global semantics of the real estate registration information are more comprehensively known, and more accurate and comprehensive data support is provided for subsequent risk assessment and disclosure authority setting.
Fig. 4 is a block diagram of a joint cluster analysis module in a real estate registration information sharing management system based on big data technology according to an embodiment of the present application. As shown in fig. 4, the joint cluster analysis module 130 includes: an adjacency correlation unit 131, configured to construct an adjacency matrix and a degree matrix of the set of real estate registration information semantic coding feature vectors, where feature values of each position on a non-diagonal line in the adjacency matrix are weights between nodes between every two real estate registration information semantic coding feature vectors in the set of real estate registration information semantic coding feature vectors, and feature values of each position on a diagonal line in the degree matrix are sums of weights between nodes between each real estate registration information semantic coding feature vector and all other real estate registration information semantic coding feature vectors; a laplacian matrix calculation unit 132, configured to perform element-to-bit subtraction and difference processing on the degree matrix and the adjacent matrix to obtain a laplacian matrix; a normalization unit 133, configured to perform symmetric normalization processing on the laplace matrix to obtain a normalized laplace matrix; a eigenvalue decomposition unit 134, configured to arrange eigenvalues of the normalized laplace matrix from large to small, take first K eigenvalues, decompose the normalized laplace matrix based on the first K eigenvalues to obtain K real estate registration full sample domain associated eigenvectors, where K is the number of the real estate registration information semantic coding eigenvectors; and the normalization processing unit 135 is configured to perform two-dimensional arrangement after performing normalization processing on the K real estate registration full-sample domain association feature vectors respectively, so as to obtain the real estate registration full-sample domain association feature matrix.
More specifically, the adjacency association unit 131 is configured to: constructing an adjacency matrix and a degree matrix of the set of real estate registration information semantically encoded feature vectors in an adjacency correlation formula; wherein, the adjacent association formula is: ; wherein/> Is the/>, of the set of real estate registration information semantically encoded feature vectorsSemantic coding feature vector of real estate registration information,/>Is/>Semantic coding feature vector of real estate registration information,/>For the/>Semantic coding feature vectors of personal real estate registration information and the/>Standard deviation between semantically encoded feature vectors of individual real estate registration information,/>Representing the square of the 2-norm of the feature vector,/>The element pair bit subtracting difference processing is represented,Representing natural exponential function operations,/>Is the/>, of the adjacency matrixCharacteristic value of location,/>Is the/>, of the degree matrixCharacteristic value of location,/>And semantically encoding the number of the feature vectors for the real estate registration information.
More specifically, the normalization unit 133 is configured to: symmetric normalization processing is carried out on the Laplace matrix by the following normalization formula so as to obtain the normalized Laplace matrix; wherein, the normalization formula is: ; wherein/> For the adjacency matrix,/>For the degree matrix,/>Representing an identity matrix,/>And normalizing the Laplace matrix.
In the real estate registration information sharing management system 100 based on big data technology, the risk determination module 140 is configured to determine a risk assessment result of the real estate registration information based on the real estate registration full sample domain association feature matrix. Specifically, fig. 5 is a block diagram of a risk determination module in the real estate registration information sharing management system based on big data technology according to an embodiment of the present application. As shown in fig. 5, the risk determination module 140 includes: the feature distribution optimizing unit 141 is configured to perform feature distribution optimization on the real estate registration full-sample domain association feature matrix to obtain an optimized real estate registration full-sample domain association feature vector; and the classification unit 142 is configured to pass the optimized real estate registration full-sample domain association feature vector through a risk estimator based on a classifier to obtain a risk estimation result, where the risk estimation result is used to represent a risk level.
Specifically, the feature distribution optimizing unit 141 is configured to perform feature distribution optimization on the real estate registration full-sample domain association feature matrix to obtain an optimized real estate registration full-sample domain association feature vector. It should be understood that, in the above technical solution, the set of real estate registration information semantic coding feature vectors expresses coding semantic features of each real estate registration information, so that after the set of real estate registration information semantic coding feature vectors is input into a joint cluster analysis network, joint cluster analysis is performed on the coding semantic features of each real estate registration information, so that the real estate registration full-sample domain correlation feature matrix expresses joint cluster semantics of each real estate registration information in a global sample space domain, and at the same time, the feature expression of the real estate registration full-sample domain correlation feature matrix deviates from coding semantic features of individual real estate registration information in a local sample space domain, thereby affecting the expression effect of the real estate registration full-sample domain correlation feature matrix. And further consider that after joint cluster analysis, the characteristic distribution structure of the real estate registration full-sample domain association characteristic matrix is changed relative to the set of the real estate registration information semantic coding characteristic vectors.
Therefore, in the technical solution of the present application, it is desirable to optimize the real estate registration full sample domain association feature matrix by further fusing the real estate registration full sample domain association feature matrix and the set of real estate registration information semantic coding feature vectors.
In a specific example of the present application, the feature distribution optimizing unit 141 is configured to: and optimizing and fusing the real estate registration full-sample domain association feature matrix and the set of real estate registration information semantic coding feature vectors by using the following optimization fusion formula to obtain an optimized real estate registration full-sample domain association feature vector, wherein the optimization fusion formula is as follows:，/> is a first feature vector obtained after the real estate registration full-sample domain association feature matrix is unfolded, and is a first feature vector obtained after the real estate registration full-sample domain association feature matrix is unfolded Is a second feature vector after cascade of each real estate registration information semantic coding feature vector in the set of real estate registration information semantic coding feature vectors,/>，Feature vector/>And/>Having the same length/>，/>And/>Is a scale superparameter,/>Representing the operation of a vector multiplication,Represents the transpose of the feature vector, and/>Is the distance difference superparameter,/>Is the/> of the optimized real estate registration full sample domain associated feature vectorAnd characteristic values.
Here, aiming at the problem that manifold network structure interaction reconstruction is difficult due to manifold distribution distance between the real estate registration full-sample domain association feature matrix and the set of real estate registration information semantic coding feature vectors in a feature fusion scene, the feature fusion expression effect of the set of real estate registration full-sample domain association feature matrix and the real estate registration information semantic coding feature vectors is improved by effectively approximating a low-order mesoscale Hilbert space primitive structure to a network substructure in a complex manifold network structure to construct low-order mesoscale sub-manifold interaction behavior based on distance expression, so that abnormal sub-manifold interaction in a network is understood on a network interaction level. Thus, will be again composed ofThe formed optimized real estate registration full-sample domain association feature vector is used as a classification feature vector to be classified by a classifier, and the accuracy of a classification result can be improved by improving the expression effect of the real estate registration full-sample domain association feature matrix.
Specifically, the classifying unit 142 is configured to pass the optimized real estate registration full sample domain associated feature vector through a risk estimator based on a classifier to obtain the risk estimation result, where the risk estimation result is used to represent a risk level. It should be understood that the classifier is a common machine learning algorithm, and can classify input data according to characteristic information of the input data. In the technical scheme of the application, the risk evaluator based on the classifier is based on a classification algorithm, and performs feature learning and analysis on the optimized real estate registration full-sample domain associated feature vector so as to map the optimized real estate registration full-sample domain associated feature vector to different risk grade labels, thereby realizing risk evaluation on the set of real estate registration information.
In one specific example of the present application, the classification unit 142 includes: the full-connection coding subunit is used for carrying out full-connection coding on the optimized real estate registration full-sample domain association feature vector by using a full-connection layer of the risk estimator based on the classifier so as to obtain a full-connection coding feature vector; the probability subunit is used for inputting the fully-connected coding feature vector into a Softmax classification function of the risk estimator based on the classifier to obtain a probability value of the optimized real estate registration full-sample domain association feature vector belonging to each risk level label; and the evaluation result generation subunit is used for determining the risk level label corresponding to the maximum probability value as the risk evaluation result.
In the real estate registration information sharing management system 100 based on big data technology, the authority setting module 150 is configured to open a data acquisition interface for acquiring the set of real estate registration information and set an open authority for the risk assessment result. That is, through the open data interface, other departments and institutions can acquire real estate registration information for respective business requirements, provide convenient and efficient data services for related departments and institutions, and promote information sharing and resource utilization. And simultaneously, controlling the authority of the set of real estate registration information according to the risk assessment result, so as to ensure that only authorized users can access the set of real estate registration information, and further ensure that sensitive information is not revealed and abused. For example, for real estate registration information with a lower risk level, its access rights may be properly relaxed so that more users or institutions can acquire and use it; for real estate registration information with higher risk level, corresponding access limit needs to be set, if user name and password need to be input for identity verification, only specific users or institutions are allowed to access.
In summary, the real estate registration information sharing management system based on big data technology according to the embodiment of the application is clarified, semantic understanding and joint cluster analysis are carried out on the set of real estate registration information by adopting artificial intelligence technology based on deep learning, so that the whole sample domain semantic association characteristics of the real estate registration information are captured, potential risk factors in the set of real estate registration information are mined, risk assessment of the real estate registration information is realized, and then open authority setting is carried out according to a risk assessment result. Thus, the sharing of the real estate registration information can be ensured to be safer and more efficient, so that the utilization efficiency and the value of the real estate registration information are improved.
Fig. 6 is a flowchart of a real estate registration information sharing management method based on big data technology according to an embodiment of the present application. As shown in fig. 6, the real estate registration information sharing management method based on big data technology according to the embodiment of the present application includes the steps of: s1, acquiring a set of real estate registration information; s2, carrying out semantic coding on the set of the real estate registration information to obtain a set of semantic coding feature vectors of the real estate registration information; s3, inputting the set of the semantic coding feature vectors of the real estate registration information into a joint cluster analysis network to obtain a real estate registration full-sample domain association feature matrix; s4, determining a risk assessment result of the real estate registration information based on the real estate registration full-sample domain association feature matrix; s5, opening a data acquisition interface for acquiring the set of real estate registration information and setting open rights for the risk assessment result.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described large data technology-based real estate registration information sharing management method have been described in detail in the above description of the large data technology-based real estate registration information sharing management system with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
The basic principles of the present invention have been described above in connection with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be construed as necessarily possessed by the various embodiments of the invention. Furthermore, the particular details of the above-described embodiments are for purposes of illustration and understanding only, and are not intended to limit the invention to the particular details described above, but are not necessarily employed.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, and for example, the module division is merely a logical function division, and other manners of division may be implemented in practice. The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. The units recited in the system claims may also be implemented by means of software or hardware.
Finally, it should be noted that the foregoing description has been presented for the purposes of illustration and description. Furthermore, the foregoing embodiments are merely for illustrating the technical scheme of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the technical scheme of the present invention.
Claims (9)
1. A real estate registration information sharing management system based on big data technology, characterized by comprising:
The real estate registration information acquisition module is used for acquiring a set of real estate registration information;
the real estate registration information semantic coding module is used for carrying out semantic coding on the set of real estate registration information to obtain a set of real estate registration information semantic coding feature vectors;
The joint cluster analysis module is used for inputting the set of the real estate registration information semantic coding feature vectors into a joint cluster analysis network to obtain a real estate registration full-sample domain association feature matrix;
The risk judging module is used for determining a risk assessment result of the real estate registration information based on the real estate registration full-sample domain association feature matrix;
And the permission setting module is used for opening a data acquisition interface for acquiring the set of real estate registration information and setting open permissions for the risk assessment result.
2. The real estate registration information sharing management system based on big data technology of claim 1 characterized by the fact that the real estate registration information semantic coding module comprises:
The data preprocessing unit is used for carrying out data cleaning, format conversion and data integration on each real estate registration information in the set of real estate registration information to obtain a set of preprocessed real estate registration information;
the semantic coding unit is used for carrying out semantic coding on each piece of preprocessed real estate registration information in the preprocessed real estate registration information set to obtain a set of semantic coding feature vectors of the real estate registration information.
3. The real estate registration information sharing management system based on big data technology of claim 2 characterized by the semantic coding unit for:
And passing each piece of preprocessed real estate registration information in the preprocessed real estate registration information set through a real estate information semantic encoder based on a transducer model to obtain the real estate registration information semantic encoding feature vector set.
4. The real estate registration information sharing management system based on big data technology of claim 3 wherein the joint cluster analysis module comprises:
An adjacency association unit, configured to construct an adjacency matrix and a degree matrix of the set of real estate registration information semantic coding feature vectors, where feature values of each position on a non-diagonal line in the adjacency matrix are weights between nodes between every two real estate registration information semantic coding feature vectors in the set of real estate registration information semantic coding feature vectors, and feature values of each position on a diagonal line in the degree matrix are sums of weights between nodes between each real estate registration information semantic coding feature vector and all other real estate registration information semantic coding feature vectors;
the Laplace matrix calculation unit is used for carrying out element pair phase subtraction and difference processing on the degree matrix and the adjacent matrix to obtain a Laplace matrix;
The normalization unit is used for carrying out symmetrical normalization processing on the Laplace matrix to obtain a normalized Laplace matrix;
The characteristic value decomposition unit is used for arranging the characteristic values of the normalized Laplace matrix from large to small, taking the first K characteristic values, and decomposing the normalized Laplace matrix based on the first K characteristic values to obtain K real estate registration full-sample domain associated characteristic vectors, wherein K is the number of the real estate registration information semantic coding characteristic vectors;
And the standardized processing unit is used for respectively carrying out standardized processing on the K real estate registration full-sample domain association feature vectors and then carrying out two-dimensional arrangement to obtain the real estate registration full-sample domain association feature matrix.
5. The real estate registration information sharing management system based on big data technology of claim 4 wherein the adjacency association unit is used for:
Constructing an adjacency matrix and a degree matrix of the set of real estate registration information semantically encoded feature vectors in an adjacency correlation formula; wherein, the adjacent association formula is: ; wherein/> Is the/>, of the set of real estate registration information semantically encoded feature vectorsSemantic coding feature vector of real estate registration information,/>Is/>Semantic coding feature vector of real estate registration information,/>For the/>Semantic coding feature vectors of personal real estate registration information and the/>Standard deviation between semantically encoded feature vectors of individual real estate registration information,/>Representing the square of the 2-norm of the feature vector,/>Representing element pair bit minus difference processing,/>Representing natural exponential function operations,/>Is the/>, of the adjacency matrixCharacteristic value of location,/>Is the/>, of the degree matrixCharacteristic value of location,/>And semantically encoding the number of the feature vectors for the real estate registration information.
6. The real estate registration information sharing management system based on big data technology of claim 5 characterized by the normalization unit for:
symmetric normalization processing is carried out on the Laplace matrix by the following normalization formula so as to obtain the normalized Laplace matrix; wherein, the normalization formula is: ; wherein/> For the adjacency matrix,/>For the degree matrix,/>Representing an identity matrix,/>And normalizing the Laplace matrix.
7. The real estate registration information sharing management system based on big data technology of claim 6 wherein the risk decision module comprises:
The feature distribution optimizing unit is used for carrying out feature distribution optimization on the real estate registration full-sample domain association feature matrix to obtain an optimized real estate registration full-sample domain association feature vector;
And the classification unit is used for enabling the optimized real estate registration full-sample domain association feature vector to pass through a risk evaluator based on a classifier to obtain a risk evaluation result, wherein the risk evaluation result is used for representing a risk level.
8. The real estate registration information sharing management system based on big data technology of claim 7 wherein the classification unit comprises:
The full-connection coding subunit is used for carrying out full-connection coding on the optimized real estate registration full-sample domain association feature vector by using a full-connection layer of the risk estimator based on the classifier so as to obtain a full-connection coding feature vector;
the probability subunit is used for inputting the fully-connected coding feature vector into a Softmax classification function of the risk estimator based on the classifier to obtain a probability value of the optimized real estate registration full-sample domain association feature vector belonging to each risk level label;
and the evaluation result generation subunit is used for determining the risk level label corresponding to the maximum probability value as the risk evaluation result.
9. The real estate registration information sharing management method based on the big data technology is characterized by comprising the following steps:
Acquiring a set of real estate registration information;
carrying out semantic coding on the set of real estate registration information to obtain a set of real estate registration information semantic coding feature vectors;
inputting the set of the semantic coding feature vectors of the real estate registration information into a joint cluster analysis network to obtain a real estate registration full-sample domain association feature matrix;
determining a risk assessment result of real estate registration information based on the real estate registration full-sample domain association feature matrix;
And opening a data acquisition interface for acquiring the set of real estate registration information and setting open rights for the risk assessment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410401522.6A CN118195320A (en) | 2024-04-03 | 2024-04-03 | Real estate registration information sharing management system and method based on big data technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410401522.6A CN118195320A (en) | 2024-04-03 | 2024-04-03 | Real estate registration information sharing management system and method based on big data technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118195320A true CN118195320A (en) | 2024-06-14 |
Family
ID=91402330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410401522.6A Pending CN118195320A (en) | 2024-04-03 | 2024-04-03 | Real estate registration information sharing management system and method based on big data technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118195320A (en) |
-
2024
- 2024-04-03 CN CN202410401522.6A patent/CN118195320A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Heterogeneous domain adaptation: An unsupervised approach | |
| Jing et al. | Heterogeneous cross-company defect prediction by unified metric representation and CCA-based transfer learning | |
| CN109657947B (en) | Enterprise industry classification-oriented anomaly detection method | |
| CN111985207B (en) | Access control policy acquisition method and device and electronic equipment | |
| CN112232524A (en) | Multi-label information identification method and device, electronic equipment and readable storage medium | |
| Yang et al. | DOMFN: A divergence-orientated multi-modal fusion network for resume assessment | |
| Hewapathirana | Change detection in dynamic attributed networks | |
| Prasad et al. | An effective assessment of cluster tendency through sampling based multi-viewpoints visual method | |
| Alqahtani et al. | Gaussian mixture models based on principal components and applications | |
| CN117349437A (en) | Government information management system and method based on intelligent AI | |
| Manziuk et al. | Structural Alignment Method of Conceptual Categories of Ontology and Formalized Domain. | |
| CN113946871A (en) | Privacy preserving data record integration method, system and computer readable storage medium | |
| CN116805039A (en) | Feature screening method, device, computer equipment and data disturbance method | |
| AU2023202418A1 (en) | IntegTechPLUS - Further extensions for distributed block chain systems enabling systemizing and processing of distributed components including with temporal, spatial and or ordinally displaced inputs including data and stream aggregations in fast and closely coupled architectures (especially but not limited to quantum processors and AI learning & de/constructions) with : process model, standard interface needs for implementing and managing various types of processing pipelines with block chain architecture able to also coordinate authenticable calculations. | |
| Bu et al. | A High‐Order CFS Algorithm for Clustering Big Data | |
| CN118195320A (en) | Real estate registration information sharing management system and method based on big data technology | |
| Elliot et al. | Data environment analysis and the key variable mapping system | |
| Zhang et al. | Research on case preprocessing based on deep learning | |
| Zhang | Mathematical modeling of multiscale network traffic combination prediction based on fuzzy support vector machine | |
| Ahmad | AI-Enabled Spatial Intelligence: Revolutionizing Data Management and Decision Making in Geographic Information Systems | |
| Zhang | Application of fusion of fuzzy mathematical clustering analysis in enterprise financial management cloud platform | |
| Hu et al. | Category-aware app permission recommendation based on sparse linear model | |
| Hy | Employing Machine Learning in the Policy-based Blockchain Selection Process | |
| Lai et al. | Extended variational inference for Dirichlet process mixture of Beta‐Liouville distributions for proportional data modeling | |
| Zhang et al. | A Credit Conflict Detection Model Based on Decision Distance and Probability Matrix |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |