Personalized region analysis method and system based on multi-dimensional data

Abstract

The invention relates to the technical field of computers, in particular to a personalized region analysis method and system based on multi-dimensional data. Multi-source data is preprocessed to obtain structured preprocessed data, demand information of a target user is analyzed to obtain a plurality of atomic subdivision points, a mapping rule base is created based on the atomic subdivision points, and an atomic dimension set is generated in combination with the mapping rule base and the user demand information. And based on data fields, filtering conditions and preference directions in the atomic dimension set, performing screening, calculation or derivative index processing on the preprocessed data, generating regional data fragments corresponding to the atomic subdivision points, generating target user-oriented regional analysis data from the regional data fragments, and sending the target user-oriented regional analysis data to the target user. According to the method, the personalized appeal is structurally disassembled into the atomic dimension subdivision points, so that a computer can really'understand 'the comprehensive demand of a user, the association indexes are called as required based on the atomic dimension subdivision points, and accurate matching of the analysis dimension and the user demand is realized.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method and system for personalized region analysis based on multidimensional data. Background Technology

[0002] Currently, when choosing a location for family residences or business operations, the main technical methods are as follows: 1. These platforms primarily offer property listings, providing only basic information such as property attributes, average regional prices, and basic school district tags. Users must manually search through multiple pages to find what suits their needs; the system cannot understand comprehensive requirements like "quiet environment," "30-minute subway commute," or "suitable community for families with children," let alone automatically break them down and match them. 2. Fixed-indicator regional rating tools: Some websites assign fixed scores to regions based on limited publicly available data (such as air quality and schools). The indicators and weights are pre-set, meaning all users see the same rating system. There's a lack of understanding and breakdown of user needs, let alone the ability to select different data indicators or combine different analytical views based on different requirements. 3. Many users have to manually search through government websites, statistical websites, and map software, compiling the data manually. Subjective needs like "quietness" and "family-friendlyness" are difficult to systematically break down into objective indicators that can be directly processed by a computer.

[0003] In existing technologies, the system does not "understand" or "deconstruct" user needs, causing users to passively adapt to the system's fixed indicators instead of the system actively selecting indicators based on user needs. Since data matching is hard-coded, the indicators and weights are hard-coded into the program, and it cannot automatically select related data according to different needs. This results in output results that are not personalized enough and cannot be interpreted. Furthermore, the same set of reports is given to everyone, without providing a specific explanation for "why this area is suitable / unsuitable" for a particular user. Summary of the Invention

[0004] The purpose of this invention is to provide a personalized regional analysis method and system based on multidimensional data to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, one objective of this invention is to provide a personalized region analysis method based on multidimensional data, comprising: Multi-source data from multiple target areas are collected and preprocessed to obtain structured preprocessed data; the structured processing includes generating a list of key indicators, calculating satisfaction level markers, and optional scores or levels; Obtain the target user's input request information and parse the target user's request information to obtain multiple atomic sub-points; A mapping rule base is created based on atomic subdivision points, and an atomic dimension set is generated by combining the mapping rule base with user demand information. The mapping rule base includes the correspondence between typical demands and standardized atomic dimension labels, related data indicators and parameter thresholds, which is used to guide the dynamic selection of data dimensions according to user demands. Based on the data fields, filtering conditions, and preference directions in the atomic dimension set, the preprocessed data is filtered, calculated, or derived into indicators to generate regional data fragments corresponding to each atomic subdivision point. The regional data fragments are organized, aligned, and structured according to thematic modules to generate regional analysis data for the target users.

[0006] Preferably, the step of collecting multi-source data from multiple target areas and preprocessing the multi-source data to obtain structured preprocessed data includes the following steps: Create a multi-source database; Set the acquisition parameters, collect multi-source data from multiple target areas, and input all the collected data information into the multi-source database. Randomly select a target area from the multi-source database; the multi-source data includes population and household data, housing price and rent data, and traffic data. Randomly select multi-source data for a target region from a multi-source database; Determine whether duplicate data exists in the multi-source data within the target area; If duplicate data exists in the multi-source data within the target area, delete the duplicate data; Return multi-source data from a randomly selected target region in the multi-source database, until all target regions in the multi-source database have been selected, resulting in multiple preprocessed data.

[0007] Preferably, the step of obtaining user request information and parsing the user request information to obtain multiple atomic subdivision points includes the following steps: Collect information on the needs of multiple target users; Perform natural language processing on each request to extract the core request of each target user; Establish a mapping rule base to map core requirements into different atomic dimension labels; A set of atomic dimensions is generated by combining the mapping rule base with the core needs of multiple target users.

[0008] Preferably, the step of performing natural language processing on each request information to extract the core request of each target user includes the following steps: Randomly select the request information of a target user; The request information was standardized to obtain a standardized text, which was then segmented into words and tagged with parts of speech. By combining BERT and canonical text, intent recognition can be performed to obtain the user's core objectives. Extract key parameters of the core objective to fill the slots and obtain the core needs of the target user; Return the request information of a randomly selected target user until all target users have been selected, and obtain the core request of each target user.

[0009] Preferably, the step of establishing a mapping rule base, which maps core requirements to different atomic dimension labels, includes the following steps: Create multiple rule labels; For each core requirement, a mapping relationship between the core requirement and the rule label is established, resulting in multiple mapping rules; the collection of multiple mapping rules is the mapping rule library.

[0010] Preferably, the step of creating a mapping rule base based on atomic subdivision points, and generating an atomic dimension set by combining the mapping rule base with user request information; the mapping rule base includes the correspondence between typical requests and standardized atomic dimension labels, associated data indicators and parameter thresholds, used to guide the dynamic selection of data dimensions according to user requests, including the following steps: To understand the core needs of target users; Based on the core requirements and mapping rule base, the preprocessed data of multiple target areas is initially filtered to obtain multiple filtered data; The filtered data is aggregated and calculated to obtain the data indicator value for each target area; Multiple target regions are sorted based on data indicator values, and the target regions that meet the core needs of the target users are obtained based on the sorting results.

[0011] Preferably, the step of filtering, calculating, or deriving indicators from the preprocessed data based on the data fields, filtering conditions, and preference directions in the atomic dimension set to generate regional data fragments corresponding to each atomic subdivision point includes the following steps: Obtain multiple regional data fragments based on atomic dimension subdivision; each regional data fragment contains the data indicator value of the corresponding atomic dimension subdivision point and the associated filtering conditions or preference direction; The data segments of the region are categorized according to preset thematic modules; the thematic modules include at least two of the following: commuting convenience, educational resources, safety and environment, and living convenience. For multiple regional data segments under each thematic section, align the data indicator values ​​of the same atomic dimension sub-points and organize them into comparable structured data; Based on the core needs of the target users and preset thresholds, each data segment in the region is marked with the degree to which the core needs are met; The data fragments of regions that have been categorized, aligned, and marked with a degree of satisfaction by thematic modules are used to generate structured analysis data according to a preset display template; this data is then used to present the analysis results of each region under different thematic modules.

[0012] Preferably, the process of organizing, aligning, and structuring the regional data fragments according to thematic sections to generate regional analysis data for target users includes generating a list of key indicators, calculating satisfaction level markers, and optional scores or grades, comprising the following steps: Obtain structured region analysis data; The structured analysis data is displayed to the user in a single region or multiple regions side by side; Multiple target regions are acquired and compared to obtain the optimal region.

[0013] On the other hand, this application also provides a personalized regional analysis system based on multidimensional data, applied to the personalized regional analysis method based on multidimensional data described in any of the preceding statements. The system includes a data acquisition component and an analysis component. The acquisition component acquires multi-source data of the target region and the target user's request information. The analysis component is communicatively connected to the acquisition component. All data information acquired by the acquisition component is input to the analysis component. The analysis component parses the target user's request information to obtain multiple atomic subdivision points. These are then combined with a mapping rule base and the user's request information to generate an atomic dimension set. Finally, data mining is performed on the preprocessed data based on the atomic dimension set to obtain regional analysis data oriented towards the target user.

[0014] Preferably, the acquisition component includes a regional data acquisition module and a user data acquisition module. The regional data acquisition module acquires multi-source data of the target area, and the user data acquisition module acquires the demand information of the target users.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: By collecting multi-source data from multiple target regions and preprocessing the multi-source data to obtain structured preprocessed data, the application obtains the target user's input request information and parses the target user's request information to obtain multiple atomic sub-points. A mapping rule base is created based on the atomic sub-points, and an atomic dimension set is generated by combining the mapping rule base with the user's request information. Based on the data fields, filtering conditions, and preference directions in the atomic dimension set, the preprocessed data is filtered, calculated, or derived to generate regional data fragments corresponding to each atomic sub-point. Finally, the regional data fragments are organized, aligned, and structured according to thematic sections to generate regional analysis data for the target user. This application breaks through the limitation of traditional systems that rely on users to manually match fixed tags by structurally decomposing the user's fuzzy personalized requests into atomic dimension sub-points and clarifying the data fields, filtering conditions, and preference directions associated with each sub-point, enabling the computer to truly "understand" the user's comprehensive needs. It also calls associated indicators on demand based on the atomic dimension sub-points to generate targeted regional data fragments, achieving accurate matching between analysis dimensions and user needs. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a personalized regional analysis method based on multidimensional data. Figure 2 This is a schematic diagram of the framework of a personalized regional analysis system based on multidimensional data. The reference numerals are as follows: 100, Data Acquisition Component; 101, Regional Data Acquisition Module; 102, User Data Acquisition Module; 200. Analysis Components. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1 like Figure 1 As shown, one of the objectives of this invention is to provide a personalized region analysis method based on multidimensional data, comprising: S100: Collect multi-source data from multiple target areas and preprocess the multi-source data to obtain structured preprocessed data; the structured processing includes generating a list of key indicators, calculating satisfaction level markers, and optional scores or levels; S200: Obtain the target user's input request information and parse the target user's request information to obtain multiple atomic subdivision points; S300: Create a mapping rule base based on atomic subdivision points, and generate an atomic dimension set by combining the mapping rule base with user demand information; the mapping rule base includes the correspondence between typical demands and standardized atomic dimension labels, related data indicators and parameter thresholds, which is used to guide the dynamic selection of data dimensions according to user demands. S400, based on the data fields, filtering conditions and preference directions in the atomic dimension set, the preprocessed data is filtered, calculated or derived into indicators to generate regional data fragments corresponding to each atomic subdivision point; S500: The regional data fragments are organized, aligned, and structured according to thematic modules to generate regional analysis data for the target user.

[0019] It should be noted that by collecting multi-source data from multiple target areas and preprocessing the multi-source data to obtain structured preprocessed data, the target user's input request information is obtained and parsed to obtain multiple atomic sub-points. A mapping rule base is created based on the atomic sub-points, and an atomic dimension set is generated by combining the mapping rule base with the user's request information. Based on the data fields, filtering conditions, and preference directions in the atomic dimension set, the preprocessed data is filtered, calculated, or derived to generate regional data fragments corresponding to each atomic sub-point. Finally, the regional data fragments are organized, aligned, and structured according to thematic sections to generate regional analysis data for the target user. This application, by structurally decomposing the user's fuzzy personalized requests into atomic dimension sub-points and clarifying the data fields, filtering conditions, and preference directions associated with each sub-point, enables the computer to truly "understand" the user's comprehensive needs. This breaks through the limitations of traditional systems that rely on users manually matching fixed tags, and by calling associated indicators on demand based on atomic dimension sub-points, targeted regional data fragments are generated, achieving accurate matching between analysis dimensions and user needs.

[0020] In one embodiment of this application, S100 includes: S110, Create a multi-source database; S120, Set the acquisition parameters, collect multi-source data from multiple target areas respectively, and input all the collected data information into the multi-source database. Randomly select a target area database from the multi-source database; the multi-source data includes population and household data, housing price and rent data, and traffic data. S130, randomly select multi-source data for a target region from a multi-source database; S140, determine whether there is duplicate data in the multi-source data within the target area; S150, If duplicate data exists in the multi-source data within the target area, delete the duplicate data; S160 returns multi-source data from a randomly selected target region in the multi-source database, until all target regions in the multi-source database have been selected, resulting in multiple preprocessed data.

[0021] It should be noted that by collecting data from multiple sources, a complete data foundation covering the comprehensive needs of users can be built, and the multi-source database can be directly linked to the core needs of target users, thereby enabling personalized analysis.

[0022] After the data is collected, it is processed through data structuring to solve the problem of inconsistent formats from different data sources in the existing system. This ensures that the data is accurately retrieved according to the atomic dimension subdivision points, thereby improving data quality and ensuring the reliability of the subsequent analysis results.

[0023] In one embodiment of this application, S200 includes: S210 collects the demand information of multiple target users; S220 performs natural language processing on each request information to extract the core request of each target user. S230, Establish a mapping rule base to map core requirements into different atomic dimension labels; S240 combines the mapping rule base with the core demands of multiple target users to generate an atomic dimension set.

[0024] It should be noted that by obtaining personalized request information input by the target user and parsing the request information, multiple atomic sub-points are obtained. These atomic sub-points are then used to generate requests through keyword recognition, rule matching, or natural language processing. Each atomic sub-point is associated with a corresponding data field, filtering conditions, and preference direction (such as "quiet" corresponding to threshold requirements for noise level, distance from main roads, and nighttime activity density).

[0025] In one embodiment of this application, S220 includes: S221, randomly select the request information of a target user; S222, the request information is standardized to obtain standardized text, and the standardized text is segmented and labeled with parts of speech; S223 combines BERT and canonical text for intent recognition to obtain the user's core objectives; S224, extract the key parameters of the core target to complete the slot filling and obtain the core needs of the target user; S225 returns the request information of a randomly selected target user until all target users have been selected, and obtains the core request of each target user.

[0026] It should be noted that by converting the target user's demand information into machine-operable atomic subdivisions, the problem of difficulty in understanding user needs in existing technologies has been solved. Furthermore, a complete chain of "data collection - demand understanding - dimension suitability" has been realized, laying the foundation for subsequent targeted data mining and readable assembly. Overall, it significantly improves the personalization, accuracy, and user understandability of regional analysis, which is the core innovation chain that distinguishes it from existing technologies.

[0027] In one embodiment of this application, S230 includes: S231, Create multiple rule labels; S232. For each core requirement, establish a mapping relationship between the core requirement and the rule label to obtain multiple mapping rules; the collection of multiple mapping rules is the mapping rule library.

[0028] It should be noted that by using a mapping rule base to predefine associations between typical needs and data indicators, the generation of atomic dimension sets is ensured to be logical and reusable, avoiding the tedious manual configuration of each case. For example, the preset mapping rule base (such as "Quiet" → atomic dimension label "Environmental Noise", associated data indicator "Nighttime Decibels", threshold "≤50dB"; "Suitable for families with children" → atomic dimension label "Educational Resources", associated data indicator "Number of Class A Kindergartens within 1 Kilometer", threshold "≥2") instantiates atomic sub-points into specific atomic dimension sets (i.e., the list of data dimensions required for the current user analysis), realizing dynamic adaptation of different data dimensions to different user needs.

[0029] In one embodiment of this application, S300 includes: S310: Understanding the core needs of target users; S320 performs preliminary filtering on preprocessed data from multiple target regions based on core requirements and mapping rule base, resulting in multiple filtered data; S330 performs aggregation calculations on the filtered data to obtain the data indicator values ​​for each target area; S340 sorts multiple target areas based on data indicator values ​​and obtains the target areas that meet the core needs of the target users based on the sorting results.

[0030] It should be noted that this application instantiates the atomic sub-points into an atomic dimension set based on a preset demand-atomic dimension mapping rule library. The mapping rule library contains the correspondence between typical demands and standardized atomic dimension labels, related data indicators and parameter thresholds, which is used to guide the dynamic selection of data dimensions according to user demands. By dynamically selecting related data dimensions through the mapping rule library, the analysis results are highly personalized. Furthermore, since the atomic dimension set is used as an intermediate layer to uniformly guide subsequent data mining steps, the application of fixed indicators to all areas is avoided, which significantly improves the targeting of the analysis.

[0031] In one embodiment of this application, S400 includes: S410, Obtain multiple regional data segments obtained based on atomic dimension subdivision; each regional data segment contains the data indicator value of the corresponding atomic dimension subdivision point and the associated filtering conditions or preference direction; S420, the regional data segments are categorized according to preset thematic modules; the thematic modules include at least two categories from commuting convenience, educational resources, safety and environment, and living convenience; S430 aligns the data index values ​​of the same atomic dimension subdivision points for multiple regional data fragments under each thematic section and organizes them into comparable structured data; S440, based on the core needs of the target users and preset thresholds, marks the degree to which each regional data segment meets the core needs; S450 generates structured analysis data from regional data fragments that have been categorized, aligned, and marked with satisfaction levels according to a preset display template; this data is used to present the analysis results of each region under different thematic sections.

[0032] It should be noted that the data indicators include data such as commuting time, school rating, and noise level. The core requirements and preset thresholds are one of the requirements that include the data indicators. For example, if the core requirement of target user A is "commuting time within 30 minutes", then target areas whose data indicators do not meet this condition can be excluded.

[0033] This application transforms multi-source data into analytical results that conform to user cognitive logic through thematic segmentation and structuring. It also innovatively achieves interpretability of analytical results by marking the degree of satisfaction, solving the problem of uninterpretable output results in existing technologies and providing a foundation for subsequent comparison of different target areas.

[0034] In one embodiment of this application, S500 includes: S510, acquire structured region analysis data; S520, The structured analysis data is displayed to the user in a single region or multiple regions side by side; Specifically, the content displayed includes: a concise text description of each area (such as "This area is a 26-minute commute to the city center by subway and has three top-tier kindergartens nearby"); and a prominent display of core indicators (such as key values ​​and satisfaction level labels). S530: Acquire multiple target regions, compare the multiple target regions, and obtain the optimal region.

[0035] It should be noted that the structured regional analysis data mainly includes thematic sections of each target region, satisfaction level markers, and key indicator values. After completing step S530, a complete report of the optimal region's results can be generated for target users to read. Step S500 realizes the process from data filtering to user interaction. By displaying and comparing, the analysis results are transformed into information that users can perceive, making the output results more intuitive and improving users' decision-making efficiency.

[0036] like Figure 2 As shown, in one embodiment of this application, a personalized regional analysis system based on multidimensional data is also provided, applied to the personalized regional analysis method based on multidimensional data described in any of the preceding claims. The system includes a data acquisition component 100 and an analysis component 200. The data acquisition component 100 acquires multi-source data of the target region and the demand information of the target user. The analysis component 200 is communicatively connected to the data acquisition component 100. All data information acquired by the data acquisition component 100 is input to the analysis component 200. The analysis component 200 parses the demand information of the target user to obtain multiple atomic subdivision points, and combines a mapping rule base with the user demand information to generate an atomic dimension set. Finally, data mining is performed on the preprocessed data based on the atomic dimension set to obtain regional analysis data for the target user.

[0037] It should be noted that data is collected by the data acquisition component 100 and all collected data is input into the analysis component 200. The analysis component 200 uses technologies such as natural language processing and rule matching to structurally break down the target user's demand information into atomic dimension sub-points. Then, based on the atomic dimension sub-points, it calls relevant indicators from the pre-built multi-dimensional regional data warehouse as needed to generate targeted regional data fragments. The data fragments corresponding to the atomic dimensions are classified and aligned according to thematic sections. Through satisfaction level marking, key indicator list and optional rating levels, structured regional analysis data is generated.

[0038] In one embodiment of this application, the acquisition component 100 includes a regional data acquisition module 101 and a user data acquisition module 102. The regional data acquisition module 101 acquires multi-source data of the target area, and the user data acquisition module 102 acquires the demand information of the target user.

[0039] It should be noted that by collecting data from different targets using different collection modules, the leakage of personal information of target users is avoided, thereby improving data security.

[0040] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A personalized regional analysis method based on multidimensional data, characterized in that, include: Multi-source data from multiple target areas are collected, and the multi-source data is preprocessed to obtain structured preprocessed data; The structured processing includes generating a list of key indicators, calculating satisfaction level markers, and optional scores or grades; Obtain the target user's input request information and parse the target user's request information to obtain multiple atomic sub-points; A mapping rule base is created based on atomic subdivision points, and an atomic dimension set is generated by combining the mapping rule base with user demand information. The mapping rule base includes the correspondence between typical demands and standardized atomic dimension labels, related data indicators and parameter thresholds, which is used to guide the dynamic selection of data dimensions according to user demands. Based on the data fields, filtering conditions, and preference directions in the atomic dimension set, the preprocessed data is filtered, calculated, or derived into indicators to generate regional data fragments corresponding to each atomic subdivision point. The regional data fragments are organized, aligned, and structured according to thematic modules to generate regional analysis data for the target users.

2. The personalized region analysis method based on multidimensional data according to claim 1, characterized in that: The process of collecting multi-source data from multiple target areas and preprocessing the multi-source data to obtain structured preprocessed data includes the following steps: Create a multi-source database; Set the acquisition parameters, collect multi-source data from multiple target areas, and input all the collected data information into the multi-source database. Randomly select a target area from the multi-source database; the multi-source data includes population and household data, housing price and rent data, and traffic data. Randomly select multi-source data for a target region from a multi-source database; Determine whether duplicate data exists in the multi-source data within the target area; If duplicate data exists in the multi-source data within the target area, delete the duplicate data; Return multi-source data from a randomly selected target region in the multi-source database, until all target regions in the multi-source database have been selected, resulting in multiple preprocessed data.

3. The personalized region analysis method based on multidimensional data according to claim 2, characterized in that: The process of obtaining user request information and parsing it to obtain multiple atomic sub-points includes the following steps: Collect information on the needs of multiple target users; Perform natural language processing on each request to extract the core request of each target user; Establish a mapping rule base to map core requirements into different atomic dimension labels; A set of atomic dimensions is generated by combining the mapping rule base with the core needs of multiple target users.

4. The personalized region analysis method based on multidimensional data according to claim 3, characterized in that: The process of performing natural language processing on each request to extract the core request of each target user includes the following steps: Randomly select the request information of a target user; The request information was standardized to obtain a standardized text, which was then segmented into words and tagged with parts of speech. By combining BERT and canonical text, intent recognition can be performed to obtain the user's core objectives. Extract key parameters of the core objective to fill the slots and obtain the core needs of the target user; Return the request information of a randomly selected target user until all target users have been selected, and obtain the core request of each target user.

5. The personalized region analysis method based on multidimensional data according to claim 4, characterized in that: The establishment of the mapping rule base, which maps the core requirements to different atomic dimension labels, includes the following steps: Create multiple rule labels; For each core requirement, a mapping relationship between the core requirement and the rule label is established, resulting in multiple mapping rules; the collection of multiple mapping rules is the mapping rule library.

6. The personalized region analysis method based on multidimensional data according to claim 5, characterized in that: The process involves creating a mapping rule base based on atomic subdivision points, and then combining this mapping rule base with user request information to generate a set of atomic dimensions. The mapping rule base includes the correspondence between typical requests and standardized atomic dimension labels, associated data indicators, and parameter thresholds, used to guide the dynamic selection of data dimensions according to user requests. This process includes the following steps: To understand the core needs of target users; Based on the core requirements and mapping rule base, the preprocessed data of multiple target areas is initially filtered to obtain multiple filtered data; The filtered data is aggregated and calculated to obtain the data indicator value for each target area; Multiple target regions are sorted based on data indicator values, and the target regions that meet the core needs of the target users are obtained based on the sorting results.

7. The personalized region analysis method based on multidimensional data according to claim 6, characterized in that: The step of filtering, calculating, or deriving indicators from the preprocessed data based on the data fields, filtering conditions, and preference directions in the atomic dimension set to generate regional data fragments corresponding to each atomic sub-point includes the following steps: Obtain multiple regional data fragments based on atomic dimension subdivision; each regional data fragment contains the data indicator value of the corresponding atomic dimension subdivision point and the associated filtering conditions or preference direction; The data segments of the region are categorized according to preset thematic modules; the thematic modules include at least two of the following: commuting convenience, educational resources, safety and environment, and living convenience. For multiple regional data segments under each thematic section, align the data indicator values ​​of the same atomic dimension sub-points and organize them into comparable structured data; Based on the core needs of the target users and preset thresholds, each data segment in the region is marked with the degree to which the core needs are met; The data fragments from the regions that have been categorized, aligned, and marked with a degree of satisfaction by thematic sections are used to generate structured analysis data according to a preset display template; Used to present the analysis results of each region under different thematic sections.

8. The personalized region analysis method based on multidimensional data according to claim 7, characterized in that: The process of organizing, aligning, and structuring the regional data fragments according to thematic modules to generate regional analysis data for target users includes the following steps: Obtain structured region analysis data; The structured analysis data is displayed to the user in a single region or multiple regions side by side; Multiple target regions are acquired and compared to obtain the optimal region.

9. A personalized region analysis system based on multidimensional data, applied to the personalized region analysis method based on multidimensional data as described in any one of claims 1 to 8, characterized in that, include: Data acquisition components; The acquisition components collect multi-source data of the target area and the demand information of the target users, respectively. Analysis components; The analysis component is communicatively connected to the acquisition component. All data information acquired by the acquisition component is input to the analysis component. The analysis component parses the target user's request information to obtain multiple atomic sub-points. It then combines the mapping rule base with the user request information to generate an atomic dimension set. Finally, it performs data mining on the preprocessed data based on the atomic dimension set to obtain regional analysis data for the target user.

10. The personalized regional analysis system based on multidimensional data according to claim 9, characterized in that, The data acquisition component includes a regional data acquisition module and a user data acquisition module. The regional data acquisition module acquires multi-source data of the target area, and the user data acquisition module acquires the demand information of the target users.

Images