Real estate file quality analysis and evaluation method and system based on data analysis
Through data analysis-based methods, two quality assessments of real estate archives were carried out, which solved the problems of missing and inconsistency in the storage process, and improved the accuracy and completeness of the archives.
Patent Information
- Application Number
- CN202510281762.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-11
- Publication Date
- 2025-06-13
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When real estate files are stored on a computer, they may forget to back up some files, and even the uploaded data may be inconsistent with the data in the real object, which reduces the accuracy of real estate files.
Using a data analysis method, the composition analysis of the constituent materials of real estate archives is performed through a feature extraction algorithm, and the first and second evaluation standards of real estate archives quality are generated, and two quality evaluations are conducted to determine the quality evaluation scores of real estate archives, and modify and supplement them according to the evaluation results to improve the accuracy of the archives.
It effectively solves the possible data missing and inconsistency of real estate archives during storage, and improves the accuracy and completeness of archives.
Smart Images
Figure CN120146689A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of real estate file quality assessment, and specifically relates to a method and system for analyzing and evaluating real estate file quality based on data analysis. Background Art
[0002] Real estate files refer to various original records with preservation value collected and generated by real estate registration departments during the real estate registration process. These records truly reflect the natural conditions of real estate property rights and the ownership of rights, and have characteristics such as legality, evidentiary nature, and dynamics.
[0003] In order to better protect real estate files, the physical real estate files will be stored in a computer for backup. However, when storing real estate files on the computer, some files may be forgotten to be backed up, and even the data uploaded may be inconsistent with the data in the physical files, reducing the accuracy of real estate files. Summary of the Invention
[0004] To solve the above technical problems, a method and system for analyzing and evaluating real estate file quality based on data analysis are provided. This technical solution solves the problem that when storing real estate files on the computer, some files may be forgotten to be backed up, and even the data uploaded may be inconsistent with the data in the physical files, reducing the accuracy of real estate files as mentioned in the above background art.
[0005] To achieve the above purposes, the technical solution adopted by the present invention is as follows: A method for analyzing and evaluating real estate file quality based on data analysis, including: Based on a feature extraction algorithm, perform component analysis on the constituent materials of real estate files to generate the first evaluation criterion for real estate file quality; Based on the first evaluation criterion for real estate file quality, conduct the first quality evaluation on the real estate files to be evaluated, and determine the first quality evaluation score, where the first quality evaluation score can be either full marks or not full marks; Perform subclass material analysis on the constituent materials of real estate files to generate the second evaluation criterion for real estate file quality; Based on the second evaluation criterion for real estate file quality, conduct the second quality evaluation on the real estate files to be evaluated, and determine the real estate file quality evaluation score.
[0006] Preferably, the step of performing component analysis on the constituent materials of real estate files based on a feature extraction algorithm to generate the first evaluation criterion for real estate file quality specifically includes the following steps: Perform type analysis on the constituent materials of real estate files to determine the types of constituent materials of real estate files; Obtain the first example material corresponding to the composition material type of the real estate file, and the first example material is read from the database system; Perform component analysis on the first example material through a feature extraction algorithm to determine the priority of the composition material type of the real estate file; Generate the first quality evaluation criterion for the real estate file according to the priority of the composition material type of the real estate file.
[0007] Preferably, the first quality evaluation of the real estate file to be evaluated based on the first quality evaluation criterion of the real estate file to determine the first quality evaluation score specifically includes the following steps: Classify the real estate file to be evaluated based on the composition material type of the real estate file to obtain different types of materials to be evaluated; Based on the first quality evaluation criterion of the real estate file, perform matching processing on different types of materials to be evaluated to determine whether there is a lack of composition material type in the real estate file to be evaluated; Based on the first quality evaluation criterion of the real estate file, perform quality evaluation on whether there is a lack of composition material type in the real estate file to be evaluated to determine the first quality evaluation score.
[0008] Preferably, the quality evaluation on whether there is a lack of composition material type in the real estate file to be evaluated based on the first quality evaluation criterion of the real estate file to determine the first quality evaluation score specifically includes the following steps: If there is no lack of composition material type in the real estate file to be evaluated, the first quality evaluation score of the real estate file to be evaluated is full marks; If there is a lack of composition material type in the real estate file to be evaluated, determine the missing material type; Based on the first quality evaluation criterion of the real estate file, perform type score evaluation on the missing material type to obtain the first quality evaluation score, and the first quality evaluation score is not full marks; Among them, the specific calculation formula for obtaining the first quality evaluation score is: ; In the formula, the is the first quality evaluation score; the is the score corresponding to the first composition material type in the first quality evaluation criterion of the real estate file; the takes a value of 0 or 1. When there is a lack of a certain type of material = 1, when there is no lack of composition material type = 0; the is the score corresponding to all missing material types; the j is the specific number of composition material types of the real estate file.
[0009] Preferably, the sub - material analysis of the constituent materials of the real estate file to generate the second evaluation criterion for the quality of the real estate file specifically includes the following steps: Conduct sub - material analysis on the types of constituent materials of the real estate file to determine the types of sub - materials included in the types of constituent materials; Obtain the second sample materials corresponding to the types of sub - materials included in the types of constituent materials, and the second sample materials are read from the database system; Based on the text analysis algorithm, conduct content analysis on the second sample materials to determine the sub - materials that need to introduce external data sources; Based on the feature extraction algorithm, conduct component analysis on the second sample materials to determine the priority of the types of sub - materials; Generate the second evaluation criterion for the quality of the real estate file according to the priority of the types of sub - materials.
[0010] Preferably, the generation of the second evaluation criterion for the quality of the real estate file according to the priority of the types of sub - materials specifically includes the following steps: Obtain the evaluation criterion for the data integrity of the sub - materials, and the evaluation criterion for the data integrity of the sub - materials is read from the database system; Generate a to - be - verified label according to the sub - materials that need to introduce external data sources, insert the to - be - verified label into the corresponding sub - materials in the real estate file to be evaluated, and establish a communication connection between the to - be - verified label and the external data source; Generate the second evaluation criterion for the quality of the real estate file according to the priority of the types of sub - materials and the evaluation criterion for the data integrity of the sub - materials.
[0011] Preferably, the second quality evaluation of the real estate file to be evaluated based on the second evaluation criterion for the quality of the real estate file to determine the quality evaluation score of the real estate file specifically includes the following steps: Based on the first quality evaluation score, conduct classification processing on the real estate file to be evaluated to determine the full - score real estate file to be evaluated and the non - full - score real estate file to be evaluated; Based on the second evaluation criterion for the quality of the real estate file, conduct the second quality evaluation on the full - score real estate file to be evaluated and the non - full - score real estate file to be evaluated respectively to determine the quality evaluation score of the real estate file.
[0012] Preferably, the second quality evaluation of the full - score real estate file to be evaluated and the non - full - score real estate file to be evaluated based on the second evaluation criterion for the quality of the real estate file to determine the quality evaluation score of the real estate file specifically includes the following steps: If the real estate file to be evaluated is a full - score real estate file to be evaluated; Based on the sub-material type, perform matching processing on the full-mark files to be evaluated, and determine whether there is a lack of sub-material type in the full-mark files to be evaluated; If there is a lack of sub-material type, based on the second evaluation criterion for the quality of real estate files, evaluate the missing sub-material type to obtain the sub-material missing score; If there is a lack of sub-material type, based on the data integrity evaluation criterion for sub-class materials, analyze the data integrity of the remaining sub-materials in the full-mark files to be evaluated to obtain the sub-material data integrity score; If there is a lack of sub-material type, perform a search for verification tags on the remaining sub-materials in the full-mark files to be evaluated. If there are no verification tags, there is no need to perform data verification. If there are verification tags, based on the external data source, evaluate the data consistency of the data to be verified to obtain the data consistency score; Perform calculation processing on the scores with missing sub-material types to determine the real estate file quality evaluation score; Among them, the specific calculation formula for the real estate file quality evaluation score is: ; In the formula, the is the real estate file quality evaluation score with missing sub-material types; the is the sub-material missing score; the is the specific quantity of the sub-material missing score; the is the sum of all sub-material data integrity scores; the is the data consistency score; the takes a value of 0 or 1. When there are no verification tags or the data is consistent, = 0; when there are verification tags and the data is inconsistent, = 1; If there is no lack of sub-material type, based on the data integrity evaluation criterion for sub-class materials, analyze the data integrity of all sub-materials in the full-mark files to be evaluated to obtain the sub-material data integrity score; If there is no lack of sub-material type, perform a search for verification tags on all sub-materials in the full-mark files to be evaluated, determine the position of the verification tags, and based on the external data source, evaluate the data consistency of the data to be verified to obtain the data consistency score; Perform calculation processing on the scores without missing sub-material types to determine the real estate file quality evaluation score; Among them, the specific calculation formula for the real estate file quality evaluation score is: ; In the formula, the is the real estate file quality assessment score without the lack of sub - material types; the is the sum of the data integrity scores of all sub - materials; the is the data consistency score; the takes a value of 0 or 1. When the data is consistent, = 0; when the data is inconsistent, = 1.
[0013] Preferably, based on the second real estate file quality assessment standard, the second quality assessment is respectively carried out on the full - score files to be evaluated and the non - full - score files to be evaluated, and the steps to determine the real estate file quality assessment score are as follows: If the real estate file to be evaluated is a non - full - score file to be evaluated; Based on the sub - material types, matching processing is carried out on the non - full - score files to be evaluated to determine whether there is a lack of sub - material types in the non - full - score files to be evaluated; If there is a lack of sub - material types, based on the second real estate file quality assessment standard, assessment processing is carried out on the missing sub - material types to obtain the sub - material missing score; If there is a lack of sub - material types, based on the data integrity assessment standard of sub - materials, data integrity analysis is carried out on the remaining sub - materials in the non - full - score files to be evaluated to obtain the sub - material data integrity score; If there is a lack of sub - material types, a search for verification tags is carried out on the remaining sub - materials in the non - full - score files to be evaluated. If there is no verification tag, data verification is not required. If there is a verification tag, based on the external data source, data consistency assessment is carried out on the data to be verified to obtain the data consistency score; Calculation processing is carried out on the scores with the lack of sub - material types to determine the real estate file quality assessment score; Among them, the specific calculation formula of the real estate file quality assessment score is: ; In the formula, the is the first - time quality assessment score; the is the real estate file quality assessment score with the lack of sub - material types; the is the sub - material missing score; the is the specific quantity of the sub - material missing score; the is the sum of the data integrity scores of all sub - materials; the is the data consistency score; the takes a value of 0 or 1. When there is no verification tag or the data is consistent, = 0; when there is a verification tag and the data is inconsistent, = 1; If there is no lack of sub - material types, based on the data integrity evaluation criteria for sub - materials, perform data integrity analysis on all sub - materials in the file to be evaluated that is not full marks, and obtain the sub - material data integrity scores; If there is no lack of sub - material types, perform retrieval of labels to be verified on all sub - materials in the file to be evaluated that is not full marks, determine the positions of the labels to be verified, and based on external data sources, perform data consistency evaluation on the data to be verified, and obtain the data consistency scores; Perform calculation processing on the scores without lack of sub - material types to determine the real estate file quality evaluation scores; Among them, the specific calculation formula for the real estate file quality evaluation scores is: ; In the formula, the is the real estate file quality evaluation score without lack of sub - material types; the is the first - time quality evaluation score; the is the sum of all sub - material data integrity scores; the is the data consistency score; the takes a value of 0 or 1. When there is no label to be verified or the data is consistent, = 0; when there is a label to be verified and the data is inconsistent, = 1.
[0014] Furthermore, a real estate file quality analysis and evaluation system based on data analysis is proposed, which is used to implement a real estate file quality analysis and evaluation method based on data analysis as described above, including: A quality evaluation terminal, which is used to perform material analysis, priority analysis, data integrity evaluation, and generation of labels to be verified on the constituent materials of real estate files, determine the first real estate file quality evaluation criterion and the second real estate file quality evaluation criterion, and sequentially perform quality evaluation on the real estate files to be evaluated according to the first real estate file quality evaluation criterion and the second real estate file quality evaluation criterion to determine the real estate file quality evaluation scores; A database system, which is used to store the data integrity evaluation criteria of the first example materials, the second example materials, and the sub - materials; Among them, the quality evaluation terminal is internally integrated with: An analysis control module, which is used to control data transmission and information interaction between various modules; A data reading module, which is used to read data from the database system; A priority analysis module that performs priority analysis on the first example material and the second example material respectively; A first evaluation criterion generation module that generates a first evaluation criterion for the quality of real estate files according to the priority of the composition material types of the real estate files; A content analysis module that is used to perform content analysis on the second example material to determine the sub-class materials that need to introduce external data sources; A second evaluation criterion generation module that generates a second evaluation criterion for the quality of real estate files according to the priority of the sub-class material types and the data integrity evaluation criterion of the sub-class materials; A file quality evaluation module that performs a secondary quality evaluation on the real estate files to be evaluated according to the first evaluation criterion for the quality of real estate files and the second evaluation criterion for the quality of real estate files, and determines the quality evaluation score of the real estate files.
[0015] Furthermore, a storage medium is proposed, on which a computer program is stored, and when the computer program is called and run, it executes a method for analyzing and evaluating the quality of real estate files based on data analysis as described above.
[0016] Compared with the prior art, the present invention provides a method and system for analyzing and evaluating the quality of real estate files based on data analysis, and has the following beneficial effects: The present invention first performs type analysis and data analysis on the composition materials of real estate files to generate a first evaluation criterion for the quality of real estate files and a second evaluation criterion for the quality of real estate files. Then, according to the first evaluation criterion for the quality of real estate files and the second evaluation criterion for the quality of real estate files, the real estate files to be evaluated are evaluated to determine the quality of the real estate files to be evaluated. Finally, the real estate files are modified and supplemented according to the quality of the real estate files to be evaluated, so as to improve the accuracy of the real estate files. Description of the Drawings
[0017] Figure 1 It is a schematic flowchart of steps S100 - S400 in a method for analyzing and evaluating the quality of real estate files based on data analysis proposed by the present invention; Figure 2 It is a structural block diagram of a system for analyzing and evaluating the quality of real estate files based on data analysis proposed by the present invention. Detailed Embodiments
[0018] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.
[0019] Refer toFigure 1 As shown in the figure, a method for analyzing and evaluating the quality of real estate archives based on data analysis includes: S100. Based on the feature extraction algorithm, perform component analysis on the constituent materials of the real estate archives to generate the first evaluation criterion for the quality of real estate archives; The feature extraction algorithm includes principal component analysis algorithm, linear discriminant analysis algorithm, independent component analysis algorithm, etc. In this application, the principal component analysis algorithm is used to perform component analysis on the constituent materials of the real estate archives; S200. Based on the first evaluation criterion for the quality of real estate archives, conduct the first quality evaluation on the real estate archives to be evaluated, and determine the first quality evaluation score, where the first quality evaluation score can be either full marks or not full marks; S300. Conduct sub-category material analysis on the constituent materials of the real estate archives to generate the second evaluation criterion for the quality of real estate archives; It can be understood that in addition to the major categories, there are many sub-categories in the real estate archives. Therefore, by setting two evaluation criteria, the quality of the major categories and sub-categories can be evaluated respectively; S400. Based on the second evaluation criterion for the quality of real estate archives, conduct the second quality evaluation on the real estate archives to be evaluated, and determine the quality evaluation score of the real estate archives; Those skilled in the art can understand that real estate archives are generally physical archives. However, if the physical archives are not properly stored, they may be missing or even damaged. To avoid the above situations, the physical real estate archives are backed up and stored in a computer. However, during the process of uploading the real estate archives to the computer, some data may be forgotten to be uploaded or there may be data missing. Therefore, after the upload of the real estate archives is completed, the quality of the real estate archives is evaluated to determine whether there are data missing or data errors. When the above situations are determined, they are modified and supplemented, which improves the accuracy of the real estate archives.
[0020] Refer to Figure 2 As shown in the figure, a system for analyzing and evaluating the quality of real estate archives based on data analysis is proposed, which is used to implement a method for analyzing and evaluating the quality of real estate archives based on data analysis as described above, including: A quality evaluation terminal, which is used to perform material analysis, priority analysis, data integrity evaluation, and generation of labels to be verified on the constituent materials of the real estate archives, determine the first evaluation criterion for the quality of real estate archives and the second evaluation criterion for the quality of real estate archives, and successively conduct quality evaluations on the real estate archives to be evaluated according to the first evaluation criterion for the quality of real estate archives and the second evaluation criterion for the quality of real estate archives, and determine the quality evaluation score of the real estate archives; A database system for storing data integrity evaluation criteria for a first example material, a second example material, and subclass materials; Among them, the following are integrated inside the quality evaluation terminal: An analysis control module for controlling data transmission and information interaction between various modules; A data reading module for reading data from the database system; A priority analysis module for performing priority analysis on the first example material and the second example material respectively; A first evaluation criterion generation module for generating a first evaluation criterion for the quality of real estate files according to the priority of the composition material types of real estate files; A content analysis module for performing content analysis on the second example material to determine subclass materials that need to introduce external data sources; A second evaluation criterion generation module for generating a second evaluation criterion for the quality of real estate files according to the priority of subclass material types and the data integrity evaluation criteria of subclass materials; A file quality evaluation module for performing a secondary quality evaluation on the real estate file to be evaluated according to the first evaluation criterion for the quality of real estate files and the second evaluation criterion for the quality of real estate files, and determining the real estate file quality evaluation score.
[0021] Embodiment 1 S101. Based on a feature extraction algorithm, performing component analysis on the composition materials of real estate files to generate a first evaluation criterion for the quality of real estate files, which specifically includes the following steps: S102. Performing type analysis on the composition materials of real estate files to determine the composition material types of real estate files; S103. Obtaining the first example material corresponding to the composition material type of the real estate file, where the first example material is read from the database system; S104. Performing component analysis on the first example material through a feature extraction algorithm to determine the priority of the composition material types of real estate files; The feature extraction algorithm uses a principal component analysis algorithm to perform component analysis on it to determine whether it is an essential material or an auxiliary material (i.e., the priority of the composition material types of real estate files); S105. Generating a first evaluation criterion for the quality of real estate files according to the priority of the composition material types of real estate files; In this embodiment, the real estate archives consist of many sub - type data to form different types of major - type data (i.e., the types of constituent materials of the real estate archives). In order to reduce the computational complexity of quality assessment, the quality assessment of different types of major - type data is carried out first. It should be noted that the priorities of different types of major - type data are different. Some are essential materials and some are auxiliary materials. Therefore, the first quality assessment standard for real estate archives is generated according to the priority. Then, the missing data assessment is carried out on the real estate archives to be evaluated to determine whether the missing data is essential material or auxiliary material. Because the importance of essential materials and auxiliary materials is different, their evaluated quality scores are also different.
[0022] Embodiment 2 Based on the first quality assessment standard for real estate archives, the first quality assessment of the real estate archives to be evaluated is carried out, and the steps for determining the first quality assessment score are as follows: S201. Based on the types of constituent materials of the real estate archives, classify the real estate archives to be evaluated to obtain different types of materials to be evaluated; S202. Based on the first quality assessment standard for real estate archives, perform a matching process on different types of materials to be evaluated to determine whether there is a lack of constituent material types in the real estate archives to be evaluated; S203. Based on the first quality assessment standard for real estate archives, conduct a quality assessment on whether there is a lack of constituent material types in the real estate archives to be evaluated to determine the first quality assessment score; In this embodiment, the first quality assessment standard for real estate archives only evaluates the major - type data (i.e., the types of constituent materials of the real estate archives) in the real estate archives to be evaluated to determine whether there is a lack. If there is a lack, the missing materials are evaluated according to the priority in the first quality assessment standard for real estate archives to determine whether the missing materials are essential materials. If they are essential materials, the first quality assessment score will be significantly reduced. For example, the score for the lack of high - priority data may be 0.4 points, while the score for the lack of low - priority data may be 0.05 points. Because their functions are different, their importance is different, and the scores are also different.
[0023] Embodiment 3 Based on the first quality assessment standard for real estate archives, conduct a quality assessment on whether there is a lack of constituent material types in the real estate archives to be evaluated to determine the first quality assessment score, which specifically includes the following steps: S2031. If there is no lack of constituent material types in the real estate archives to be evaluated, the first quality assessment score of the real estate archives to be evaluated is full marks; S2032. If there is a lack of constituent material types in the real estate archives to be evaluated, determine the type of missing materials; S2033. Based on the first evaluation criterion for the quality of real estate files, evaluate the type scores of the missing material types to obtain the first quality evaluation score, and the first quality evaluation score is not a full score. Among them, the specific calculation formula for obtaining the first quality evaluation score is: ; In the formula, the is the first quality evaluation score; the is the score corresponding to the first constituent material type in the first evaluation criterion for the quality of real estate files; the takes a value of 0 or 1. When there is a lack of a certain type of material = 1, and when there is no lack of constituent material types = 0; the is the score corresponding to all missing material types; the j is the specific number of constituent material types of the real estate files. In this embodiment, the missing material types are evaluated through the priority in the first evaluation criterion for the quality of real estate files to determine their corresponding scores. If there is no data missing, it means that the first-round quality evaluation is a full score. However, this only means that there is no missing data in the large category, but it cannot guarantee that there is no missing data in the sub-category data within the large category. Therefore, the second evaluation criterion for the quality of real estate files is generated to evaluate the quality of the sub-category data, and finally the quality of the real estate files is determined. In the above formula, each missing material type corresponds to a score, and the sum of all missing material types is 1. When there is a missing material type, its coefficient = 1, and the quality score of this item needs to be deducted. If this item of material is not missing, there is no need to deduct the score of this item, and its coefficient = 0.
[0024] Example 4 The analysis of the sub-category materials of the constituent materials of the real estate files to generate the second evaluation criterion for the quality of real estate files specifically includes the following steps: S301. Analyze the sub-category materials of the constituent material types of the real estate files to determine the sub-category material types included in the constituent material types; S302. Obtain the second example materials corresponding to the sub-category material types included in the constituent material types, and the second example materials are read from the database system; S303. Based on the text analysis algorithm, perform content analysis on the second example materials to determine the sub-category materials that need to introduce external data sources; Here, the text analysis algorithm uses the bag-of-words model to perform content analysis to determine data such as house area and house location; It is understandable that there will be data such as house area and house location in real estate files that need to be verified. For example, Zhang San lives in No. 1001, 10th floor, Unit 7, a certain community, and his residential area is 104 square meters. However, when entering data, if it is input as No. 1003, 10th floor, Unit 7, a certain community, the data will not match. Such data cannot be judged and can only be verified through external data sources. S304, performing component analysis on the second example material based on a feature extraction algorithm to determine the priority of the sub-class material type; The feature extraction algorithm here also uses the principal component analysis algorithm; S305, generating a second evaluation standard for the quality of real estate archives according to the priority of the sub-category material type; In this embodiment, after the first assessment of the real estate archives to be assessed using the first assessment standard for real estate archive quality, it is possible to determine which major categories of data are missing, and there is no need to conduct a secondary assessment of the missing major categories of data. This indirectly reduces the amount of calculation in the quality assessment process. If the assessment is conducted once, the amount of data may be too large to cause stalls. If it is split into two assessments, the probability of stalls can be reduced.
[0025] Example 5 Generating the second assessment standard for real estate archive quality according to the priority of sub-category material types specifically includes the following steps: S3051. Obtaining a data integrity evaluation standard for a sub-category material, wherein the data integrity evaluation standard for a sub-category material is read from a database system; S3052: Generate a tag to be verified based on the sub-category material introduced from the external data source as needed, insert the tag to be verified into the corresponding sub-category material in the real estate file to be evaluated, and establish a communication connection between the tag to be verified and the external data source; S3053, generating a second assessment standard for the quality of real estate archives according to the priority of the sub-category material type and the data integrity assessment standard of the sub-category material; In this embodiment, sub-category materials may be missing during the upload process. For example, network fluctuations may occur during the upload of image data, resulting in upload failure. If no review is performed, the staff may think that the upload is successful. In addition, some data requires staff to upload by typing on the keyboard. During the upload process, the staff may have something temporary to do, resulting in half of the data being transmitted. If the time is too long, the staff may think that the data has been uploaded and proceed to upload the next data. Therefore, the quality of the real estate archives is reduced. Therefore, in order to avoid the above situation, the data integrity assessment standard for sub-category materials is introduced to assess the integrity of the data to determine whether there is any data missing.
[0026] Example 6 Based on the second evaluation standard for the quality of real estate files, conduct a second quality evaluation on the real estate files to be evaluated, and determine the quality evaluation scores of the real estate files, which specifically include the following steps: S401. Based on the first quality evaluation scores, classify the real estate files to be evaluated to determine the full-mark files to be evaluated and the files to be evaluated that are not full-mark; S402. Based on the second evaluation standard for the quality of real estate files, conduct a second quality evaluation on the full-mark files to be evaluated and the files to be evaluated that are not full-mark respectively, and determine the quality evaluation scores of the real estate files; In this embodiment, each quality evaluation of real estate files is not for one file but for many files, and the lack of large-category data is relatively serious. Therefore, by separately evaluating the full-mark files to be evaluated and the files to be evaluated that are not full-mark. Because the evaluation time for files without missing large-category data is longer, while the evaluation time for files with missing large-category data is shorter than that for files without missing large-category data, so the full-mark files to be evaluated and the files to be evaluated that are not full-mark are separately evaluated.
[0027] Embodiment 7 Based on the second evaluation standard for the quality of real estate files, conduct a second quality evaluation on the full-mark files to be evaluated and the files to be evaluated that are not full-mark respectively, and determine the quality evaluation scores of the real estate files, which specifically include the following steps: S40210. If the real estate file to be evaluated is a full-mark file to be evaluated; S40211. Based on the sub-material type, conduct a matching process on the full-mark file to be evaluated to determine whether there is a lack of sub-material type in the full-mark file to be evaluated; S40212. If there is a lack of sub-material type, based on the second evaluation standard for the quality of real estate files, conduct an evaluation process on the missing sub-material type to obtain the sub-material missing score; S40213. If there is a lack of sub-material type, based on the data integrity evaluation standard for sub-class materials, conduct a data integrity analysis on the remaining sub-materials in the full-mark file to be evaluated to obtain the sub-material data integrity score; S40214. If there is a lack of sub-material type, conduct a search for verification tags on the remaining sub-materials in the full-mark file to be evaluated. If there is no verification tag, there is no need to conduct data verification. If there is a verification tag, based on the external data source, conduct a data consistency evaluation on the data to be verified to obtain the data consistency score; S40215. Conduct a calculation process on the scores with missing sub-material types to determine the quality evaluation scores of the real estate files; Among them, the specific calculation formula for the quality evaluation scores of the real estate files is: ; Wherein, the is the quality assessment score of the real estate file with missing sub - material types; the is the sub - material missing score; the is the specific quantity of the sub - material missing score; the is the sum of the data integrity scores of all sub - materials; the is the data consistency score; the takes a value of 0 or 1. When there is no label to be verified or the data is consistent, = 0; when there is a label to be verified and the data is inconsistent, = 1; It can be understood that there may be multiple or just one missing sub - material type, but their corresponding importance levels are different. Therefore, their missing scores are also different. So, through summation calculation, the scores of all missing sub - material types are calculated. However, the second assessment standard for the quality of real estate files is not only to calculate the missing scores, but also to judge the integrity and accuracy of some data in the sub - materials. The accuracy is verified through external data sources. Finally, by summing and taking the difference of the above three scores, the quality assessment score of the real estate file can be obtained; S40216. If there is no missing sub - material type, based on the data integrity assessment standard of the subclass materials, analyze the data integrity of all sub - materials in the full - mark file to be evaluated, and obtain the data integrity score of the sub - materials; S40217. If there is no missing sub - material type, retrieve the labels to be verified for all sub - materials in the full - mark file to be evaluated, determine the positions of the labels to be verified, and based on the external data source, conduct a data consistency assessment on the data to be verified, and obtain the data consistency score; S40218. Calculate and process the scores of the files without missing sub - material types to determine the quality assessment score of the real estate file; Among them, the specific calculation formula for the quality assessment score of the real estate file is: ; Wherein, the is the quality assessment score of the real estate file without missing sub - material types; the is the sum of the data integrity scores of all sub - materials; the is the data consistency score; the takes a value of 0 or 1. When the data is consistent, = 0; when the data is inconsistent, = 1; In this embodiment, if there is no lack of sub-material types, the corresponding score will not be deducted. It is only necessary to verify whether the data in the sub-materials is normal and whether the data is complete. Then, by summing and taking the difference of the above two scores, the quality assessment score of the real estate file can be obtained.
[0028] Embodiment 8 Based on the second evaluation standard for the quality of real estate files, the second quality evaluation is respectively carried out on the to-be-evaluated files with full marks and the to-be-evaluated files that are not full marks. Determining the quality assessment score of the real estate file specifically includes the following steps: S40220. If the to-be-evaluated real estate file is not a to-be-evaluated file with full marks; S40221. Based on the sub-material types, perform matching processing on the to-be-evaluated files that are not full marks to determine whether there is a lack of sub-material types in the to-be-evaluated files that are not full marks; S40222. If there is a lack of sub-material types, based on the second evaluation standard for the quality of real estate files, perform evaluation processing on the missing sub-material types to obtain the sub-material missing score; S40223. If there is a lack of sub-material types, based on the data integrity evaluation standard of the sub-class materials, perform data integrity analysis on the remaining sub-materials in the to-be-evaluated files that are not full marks to obtain the sub-material data integrity score; S40224. If there is a lack of sub-material types, perform a search for the to-be-verified labels on the remaining sub-materials in the to-be-evaluated files that are not full marks. If there is no to-be-verified label, there is no need to perform data verification. If there is a to-be-verified label, based on the external data source, perform data consistency evaluation on the to-be-verified data to obtain the data consistency score; S40225. Perform calculation processing on the scores with missing sub-material types to determine the quality assessment score of the real estate file; Among them, the specific calculation formula for the quality assessment score of the real estate file is: ; In the formula, the is the first quality assessment score; the is the quality assessment score of the real estate file with missing sub-material types; the is the sub-material missing score; the is the specific quantity of the sub-material missing score; the is the sum of all sub-material data integrity scores; the is the data consistency score; the takes a value of 0 or 1. When there is no to-be-verified label or the data is consistent, = 0; when there is a to-be-verified label and the data is inconsistent, = 1; S40226. If there is no lack of sub-material types, based on the data integrity evaluation criteria for sub-class materials, perform data integrity analysis on all sub-materials in the file to be evaluated that are not full marks, and obtain the sub-material data integrity scores. S40227. If there is no lack of sub-material types, perform a search for labels to be verified on all sub-materials in the file to be evaluated that are not full marks, determine the positions of the labels to be verified, and based on external data sources, perform data consistency evaluation on the data to be verified to obtain data consistency scores. S40228. Perform calculation processing on the scores where there is no lack of sub-material types to determine the real estate file quality evaluation scores. Among them, the specific calculation formula for the real estate file quality evaluation scores is: ; In the formula, the is the real estate file quality evaluation score where there is no lack of sub-material types; the is the first quality evaluation score; the is the sum of all sub-material data integrity scores; the is the data consistency score; the takes a value of 0 or 1. When there is no label to be verified or the data is consistent, = 0; when there is a label to be verified and the data is inconsistent, = 1; The processing procedure of this embodiment is substantially the same as that of Embodiment 7.
[0029] Furthermore, a storage medium is proposed, on which a computer program is stored. When the computer program is called and run, it executes a method for analyzing and evaluating the quality of real estate files based on data analysis as described above. Among them, the storage medium can be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state disk (SSD), etc.
[0030] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.
Claims
1. A real estate archive quality analysis and evaluation method based on data analysis, characterized in that: include: Based on the feature extraction algorithm, the composition of the real estate archives is analyzed to generate the first evaluation standard of the real estate archives quality; Based on the first quality assessment standard for real estate archives, a first quality assessment is performed on the real estate archives to be assessed, and a first quality assessment score is determined, wherein the first quality assessment score is either a full score or a non-full score; Conduct sub-category material analysis on the constituent materials of real estate archives and generate the second assessment standard for the quality of real estate archives; Based on the second assessment standard for real estate archives quality, a second quality assessment is conducted on the real estate archives to be assessed to determine the real estate archives quality assessment score.
2. A real estate archive quality analysis and evaluation method based on data analysis according to claim 1, characterized in that: The method of performing component analysis on the constituent materials of the real estate archives based on the feature extraction algorithm and generating the first evaluation standard for the quality of the real estate archives specifically includes the following steps: Conduct type analysis on the constituent materials of real estate archives and determine the types of constituent materials of real estate archives; Acquire a first example material corresponding to a constituent material type of a real estate file, wherein the first example material is read from a database system; Performing component analysis on the first sample material by a feature extraction algorithm to prioritize the types of constituent materials of the real estate archive; The first assessment standard for the quality of real estate archives is generated according to the priority of the types of materials that constitute the real estate archives.
3. The real estate archive quality analysis and evaluation method based on data analysis according to claim 1 is characterized in that: The first quality assessment of the real estate archives to be assessed is performed based on the first quality assessment standard of the real estate archives, and the first quality assessment score is determined, which specifically includes the following steps: Based on the material types of real estate archives, the real estate archives to be evaluated are classified and processed to obtain different types of materials to be evaluated; Based on the first assessment standard of real estate archive quality, different types of materials to be assessed are matched to determine whether there are any missing constituent material types in the real estate archive to be assessed; Based on the first assessment standard for real estate archive quality, a quality assessment is conducted on whether there are any missing constituent material types in the real estate archives to be assessed, and the first quality assessment score is determined.
4. A real estate archive quality analysis and evaluation method based on data analysis according to claim 3, characterized in that: Based on the first quality assessment standard of real estate archives, the quality assessment is conducted to determine whether there is a missing type of constituent material in the real estate archives to be assessed, and the first quality assessment score is determined, which specifically includes the following steps: If there is no missing component material type in the real estate file to be evaluated, the first quality assessment score of the real estate file to be evaluated will be full marks; If there are missing constituent material types in the real estate files to be assessed, determine the missing material types; Based on the first assessment standard for real estate archive quality, a type score assessment is performed on the type of missing materials to obtain a first quality assessment score, which is not a full score.
5. The real estate archive quality analysis and evaluation method based on data analysis according to claim 1 is characterized in that: The sub-category material analysis of the constituent materials of the real estate archives to generate the second assessment standard for the quality of the real estate archives specifically includes the following steps: Conduct sub-class material analysis on the constituent material types of real estate archives to determine the sub-class material types contained in the constituent material types; Acquire a second example material corresponding to a subclass material type included in the constituent material type, wherein the second example material is read from a database system; Based on the text analysis algorithm, content analysis is performed on the second example material to determine the sub-category materials that need to be introduced into the external data source; Based on the feature extraction algorithm, component analysis is performed on the second example material to determine the priority of the sub-class material type; Generate the second assessment standard for real estate archive quality based on the priority of sub-category material types.
6. A real estate archive quality analysis and evaluation method based on data analysis according to claim 5, characterized in that: The step of generating the second evaluation standard for the quality of real estate archives according to the priority of the sub-class material types specifically includes the following steps: Acquiring a data integrity assessment standard for a sub-category material, wherein the data integrity assessment standard for the sub-category material is read from a database system; Generate a tag to be verified based on the sub-category materials of the external data source as needed, insert the tag to be verified into the corresponding sub-category materials in the real estate file to be evaluated, and establish a communication connection between the tag to be verified and the external data source; The second assessment standard for real estate archive quality is generated based on the priority of sub-category material types and the data completeness assessment standard of sub-category materials.
7. The real estate archive quality analysis and evaluation method based on data analysis according to claim 1 is characterized in that: The second quality assessment of the real estate archives to be assessed is conducted based on the second assessment standard for the quality of real estate archives, and the determination of the quality assessment score of the real estate archives specifically includes the following steps: Based on the first quality assessment score, the real estate files to be assessed are classified and the full-score files to be assessed and the incomplete-score files to be assessed are determined; Based on the second assessment standard for real estate archives quality, a second quality assessment is conducted on the archives to be assessed that have received full marks and the archives to be assessed that have not received full marks, respectively, to determine the real estate archives quality assessment scores.
8. The real estate archive quality analysis and evaluation method based on data analysis according to claim 1 is characterized in that: The second quality assessment of the archives to be assessed with full marks and the archives to be assessed with incomplete marks based on the second quality assessment standard of the real estate archives, and determining the quality assessment score of the real estate archives specifically includes the following steps: If the real estate file to be evaluated is a full-score file to be evaluated; Based on the sub-material type, the full-score files to be evaluated are matched to determine whether there are any sub-material types missing in the full-score files to be evaluated; If there is a missing sub-material type, the missing sub-material type is evaluated and processed based on the second assessment standard for real estate archive quality to obtain the sub-material missing score; If there is a missing sub-material type, based on the data integrity assessment criteria for sub-type materials, conduct data integrity analysis on the remaining sub-materials in the full-score to-be-assessed archive to obtain the sub-material data integrity score; If there is a missing sub-material type, the remaining sub-materials in the full-score to-be-evaluated archive are searched for the tags to be verified. If there is no tag to be verified, no data verification is required. If there is a tag to be verified, the data consistency is evaluated based on the external data source to obtain the data consistency score. Calculate and process the scores for missing sub-material types to determine the quality assessment score of the real estate archives; If there is no missing sub-material type, based on the data integrity assessment criteria for sub-class materials, perform data integrity analysis on all sub-materials in the full-score to-be-assessed archive to obtain the sub-material data integrity score; If there is no missing sub-material type, search for the tags to be verified for all sub-materials in the full-score to-be-evaluated file, determine the location of the tags to be verified, and perform data consistency evaluation on the data to be verified based on the external data source to obtain the data consistency score; The scores for the missing sub-material types that do not exist are calculated to determine the real estate archive quality assessment score.
9. The real estate archive quality analysis and evaluation method based on data analysis according to claim 7 is characterized in that: The second quality assessment of the archives to be assessed with full marks and the archives to be assessed with incomplete marks based on the second quality assessment standard of the real estate archives, and determining the quality assessment score of the real estate archives specifically includes the following steps: If the real estate file to be evaluated is not a full-marked file to be evaluated; Based on the sub-material type, the files to be evaluated that are not full marks are matched to determine whether there are sub-material type missing in the files to be evaluated that are not full marks; If there is a missing sub-material type, the missing sub-material type is evaluated and processed based on the second assessment standard for real estate archive quality to obtain the sub-material missing score; If there are sub-material types missing, based on the data integrity assessment criteria for sub-type materials, conduct data integrity analysis on the remaining sub-materials in the to-be-assessed archives that are not fully scored, and obtain the sub-material data integrity scores; If there is a missing sub-material type, the remaining sub-materials in the to-be-evaluated archives that are not full marks will be searched for tags to be verified. If there is no tag to be verified, no data verification is required. If there is a tag to be verified, the data consistency of the to-be-verified data will be evaluated based on the external data source to obtain the data consistency score. Calculate and process the scores for missing sub-material types to determine the quality assessment score of the real estate archives; If there is no missing sub-material type, based on the data integrity assessment criteria for sub-class materials, perform data integrity analysis on all sub-materials in the archives to be assessed that are not full marks, and obtain the sub-material data integrity score; If there is no missing sub-material type, search for the tags to be verified for all sub-materials in the to-be-evaluated archives that are not full marks, determine the location of the tags to be verified, and perform data consistency evaluation on the to-be-verified data based on the external data source to obtain the data consistency score; The scores for the missing sub-material types that do not exist are calculated to determine the real estate archive quality assessment score.
10. A real estate archive quality analysis and evaluation system based on data analysis, used to implement a real estate archive quality analysis and evaluation method based on data analysis as claimed in any one of claims 1 to 9, characterized in that: include: A quality assessment terminal, the quality assessment terminal is used to perform material analysis, priority analysis, data integrity assessment and to-be-verified label generation on the constituent materials of the real estate archives, determine the first quality assessment standard of the real estate archives and the second quality assessment standard of the real estate archives, and perform quality assessment on the real estate archives to be assessed in turn according to the first quality assessment standard of the real estate archives and the second quality assessment standard of the real estate archives, and determine the quality assessment score of the real estate archives; A database system, the database system being used to store data integrity evaluation criteria for the first example material, the second example material, and the sub-category material; The quality assessment terminal internally integrates: An analysis control module, which is used to control data transmission and information interaction between various modules; A data reading module, wherein the data reading module is used to read data from a database system; a priority analysis module, the priority analysis module performing priority analysis on the first example material and the second example material respectively; A first evaluation standard generating module, which generates a first evaluation standard for the quality of real estate archives according to the priority of the constituent material types of the real estate archives; A content analysis module, the content analysis module is used to perform content analysis on the second example material to determine sub-category materials that need to be introduced into the external data source; A second evaluation standard generating module, which generates a second evaluation standard for the quality of real estate archives according to the priority of the sub-class material type and the data integrity evaluation standard of the sub-class material; The archive quality assessment module performs a secondary quality assessment on the real estate archives to be assessed according to the first real estate archive quality assessment standard and the second real estate archive quality assessment standard to determine the real estate archive quality assessment score.