A grassroots social wisdom governance method and system based on big data analysis

Abstract

The application discloses a kind of based on big data analysis's grassroots social wisdom governance method and system, including constructing community governance model, user complaint information is collected and stored to community governance model;Call historical behavior record in preset time period in government affair complaint system of user, and verify user credibility;Complaint information is analyzed to the user credibility that meets the requirement, key word extraction and classification are carried out to complaint text information, and core key word is determined by identifying semantics, field attribute and context association;Complaint picture and video information user, complaint picture and video information need to meet preset shooting specification and add watermark;According to government affair responsibility matching degree and complaint type, complaint work order is distributed to corresponding government department.The application is updated dynamically locally by community governance model, only a single minimum community governance unit is updated, so as to avoid model full reconstruction, minimize resource occupation, overall improve grassroots governance response speed and resource utilization.

Description

Technical Field

[0001] This invention belongs to the field of grassroots social governance technology, specifically relating to a grassroots social smart governance method and system based on big data analysis. Background Technology

[0002] With the acceleration of urbanization, grassroots community governance faces challenges such as data fragmentation, ambiguous positioning, and inefficient updates.

[0003] Community governance involves multi-source data, including spatial information, humanistic data, and dynamic events. In traditional governance models, data is scattered across systems such as property management, community, and government affairs, lacking a unified linkage mechanism and facing difficulties in data integration, resulting in information silos. Existing complaint location relies heavily on textual descriptions, lacking sufficient spatial positioning accuracy to pinpoint specific locations, leading to high work order allocation deviation rates and low processing efficiency. Community governance models are mostly static structures, requiring complete model reconstruction for new complaints or facility changes, resulting in time-consuming updates, high resource consumption, and high model update costs, making it difficult to adapt to the needs of handling high-frequency dynamic events. The lack of a layered verification mechanism for the authenticity of complaint information leads to false complaints or malicious persistent petitions, interfering with the allocation of government resources and reducing public trust in governance.

[0004] To address the aforementioned issues, this invention proposes a grassroots social smart governance method and system based on big data analysis, which achieves accurate positioning, efficient updating, and intelligent application of governance data through dynamic local updates of the model. Summary of the Invention

[0005] In view of the problems raised in the background art, the purpose of this invention is to provide a grassroots social smart governance method and system based on big data analysis to solve the shortcomings of the background art.

[0006] To achieve the above-mentioned technical objectives, the technical solution adopted by the present invention is as follows: A grassroots social smart governance method based on big data analysis includes the following steps: A community governance model is constructed, and user complaint information is collected and stored in the community governance model. The complaint information includes text, images, and video information. Retrieve users' historical behavior records in the government complaint system within a preset time period and verify users' credibility. Users with high credibility can pass the verification directly, users with medium credibility need to complete biometric comparison and perform a specified action verification, and users with low credibility trigger enhanced verification. Analyze complaint information that meets the user credibility requirements, extract and classify keywords from complaint text information, and determine core keywords by identifying semantics, domain attributes and contextual relationships; for users who complain about images and videos, the complaint images and videos must meet the preset shooting specifications and have watermarks added; Complaints are assigned to the corresponding government departments for handling based on the matching degree of government responsibilities and the type of complaint.

[0007] In a preferred embodiment, the steps of constructing a community governance model, collecting user complaint information and storing it in the community governance model, wherein the complaint information is image and video information processing, include: Multi-dimensional data of the community is collected as the raw input for building the community governance model. After standardization processing, the multi-dimensional data is stored in the community governance model. The community governance model is combined with the physical space grid to form a three-level block system. The three levels of blocks are the first-level block, the second-level block, and the third-level block. The first-level block is the complete community boundary and basic community information. The second-level block is the functional area, which is divided into sub-regions according to its purpose. The third-level block is the grid within the second-level block, and each grid corresponds to the specific location of the community. Level 1 blocks, Level 2 blocks, and Level 3 blocks are encoded according to a hierarchical progression, and are denoted as Level 1 block code, Level 2 block code, and Level 3 block code, respectively. Complaint information is updated in conjunction with first-level, second-level, and third-level blocks. A mapping relationship between the location coordinates of the complaint and the third-level blocks is constructed based on spatial indexing and stored in the community governance model.

[0008] In a preferred embodiment, the steps of updating the complaint information in conjunction with the coordinated updates of first-level, second-level, and third-level blocks, constructing a mapping relationship between the complaint location coordinates and the third-level blocks based on spatial indexing, and storing this mapping relationship in the community governance model include: Based on the community governance model, a root node is established. Each root node is divided into four quadrants with the community center point as the origin. The coordinates of the center points of the four quadrants are used as first-level nodes. The first-level nodes are the center points of the first-level blocks. Each primary node is further divided into four quadrants with the center point of the primary node as the origin. The coordinates of the center points of the four quadrants are used as secondary nodes, and the secondary nodes are the center points of the secondary blocks. Each secondary node is further divided into four quadrants with the center point of the secondary node as the origin. The coordinates of the center points of the four quadrants are used as tertiary nodes. The tertiary nodes are the smallest governance units of the community and the center points of the tertiary blocks. An index table is constructed to store the mapping relationship between the three-level block codes and the coordinates of the three-level node center points based on the community governance model; The complaint location coordinates, third-level block codes, and third-level node center point coordinates are matched according to the index table, and the complaint location coordinates, third-level block codes, and third-level node center point coordinates are marked as complaint data to complete the dynamic local update of the community governance model.

[0009] In a preferred embodiment, the step of matching the complaint location coordinates, third-level block code, and third-level node center point coordinates according to the index table, and then using the complaint location coordinates, third-level block code, and third-level node center point coordinates as complaint data to complete the dynamic local update of the community governance model includes: Based on complaint data and index table queries, the location coordinates of complaints to be updated, the coordinates of the center point of the third-level node, and the associated third-level block codes in the community governance model are queried and recorded as the target unit. A static anchoring base is constructed for the target unit, and complaint data is stored in the static anchoring base. The static anchoring base interacts with the target unit and the community governance model. The static anchoring base includes a read / write control unit, a hash verification unit, and a metadata storage unit. The read / write control unit integrates a distributed lock interface for locking / unlocking the storage space of the static anchoring base. The hash verification unit generates a unique baseline hash code based on the complaint data of the target unit. The metadata storage unit is used to store the complaint data of the target unit. A bidirectional pointer anchoring is established between the target unit and the static anchoring base. The target unit generates a pointer to the static anchoring base through memory address mapping, which is used to read complaint data in the static anchoring base. The static anchoring base generates a pointer to the community governance model through three-level block encoding, which is used to write complaint data. The connection is ensured to be valid by comparing the hash check codes of the pointers at both ends. Configure a preset number of virtual carriers to capture complaint data for the corresponding target units; Distributed read-write locks are applied by the read-write control unit of the static anchor base. Write locks are applied to the complaint data of the target unit, and read locks are applied to the associated index paths of non-target units. During the locking period, the hash verification unit generates real-time verification codes to block write operation requests from non-target units. The static anchor base is decoupled from the data flow of the community governance model, and an incremental data snapshot of the target unit is generated. The complaint data is written into the incremental data snapshot by a preset number of virtual carriers, and then the incremental data snapshot is written into the static anchor base. Release the distributed read-write lock applied by the read-write control unit, and the static anchor base synchronizes the complaint data to the community governance model through bidirectional pointers, updates the index table mapping relationship, releases the read lock of non-target units, and restores the global read-write permissions of the community governance model.

[0010] In a preferred embodiment, the step of retrieving a user's historical behavior records in the government complaint system over a preset time period and verifying the user's credibility includes: Query user complaint history, which includes the number of complaints, complaint types, and complaint content; Check whether the user has a record of making false complaints or engaging in malicious harassment; A credibility score is generated based on credibility scoring rules to determine the user's credibility level.

[0011] In a preferred embodiment, the intermediate-trust user needs to complete the steps of biometric comparison and specified action execution verification, including: The system captures full-face images of users with moderate credibility using the front-facing camera of their mobile devices, extracts key facial features, and generates unique feature templates. The full-face images of medium-credibility users are compared 1:1 with facial data in the government identity information database; After successful facial data comparison, a specified action is executed for verification. The system randomly selects at least one action from a preset action library and guides the user with medium credibility to execute it via text.

[0012] In a preferred embodiment, the step of the low-trust user triggering enhanced verification includes: The system captures low-confidence full-face images of users using the front-facing camera of their mobile devices, extracts key facial features, and generates unique feature templates. The full-face images of users with low credibility are compared 1:1 with facial data in the government identity information database; After successful facial data comparison, a specified action is executed for verification. The system randomly selects at least three actions from a preset action library and guides the user with medium credibility to execute them via text. User complaints with low credibility will be manually reviewed. If there are more than two false complaint records, the user's complaint function will be restricted.

[0013] In a preferred embodiment, the step of extracting and classifying keywords from complaint text information, and determining core keywords by identifying semantics, domain attributes, and contextual relationships, includes: The complaint text information is segmented into words based on a dictionary and its part of speech is tagged. Classify the already segmented complaint text information; Core keywords were determined based on the frequency of occurrence of complaint text information that had already been segmented and categorized.

[0014] In a preferred embodiment, the complaint information includes a step of collecting image information, comprising: The system guides users to take pictures according to three levels of standards: panoramic, medium shot, and close-up. The panoramic picture information includes the complete scene environment, the medium shot picture information focuses on the subject of the problem, and the close-up picture information presents detailed features. Determine the shooting distance and horizontal angle for panoramic, medium, and close-up images respectively; Add time and location watermarks to different locations on panoramic, medium, and close-up images.

[0015] A grassroots social smart governance system based on big data analytics includes: The model building module, connected to the data acquisition module, is used to build a community governance model; The data acquisition module, connected to the credibility assessment module, is used to collect complaint information; The credibility assessment module, connected to the work order scheduling module, is used to assess user credibility. The work order scheduling module is used to assign complaint work orders to the corresponding government departments. The complaint work order includes complaint text information, complaint image and video information, three-level block code corresponding to the complaint location coordinates, and user credibility information.

[0016] The beneficial effects of this invention are: This invention constructs a community governance model containing first-level, second-level, and third-level blocks, collects text, image, and video complaint information, and matches it to the smallest community governance unit at the third-level node according to spatial index; generates a credibility score based on complaint history and credit record, and performs biometric, dynamic action verification, and manual review on users with medium and low credibility respectively; it segments and classifies text information and extracts core keywords, and takes images according to three levels of standards (panoramic, medium, and close-up) and adds spatiotemporal watermarks, and finally assigns work orders according to the matching degree of government responsibilities.

[0017] Its advantages lie in the dynamic and local updates of the community governance model, updating only the smallest community governance unit. By querying the index table through complaint location coordinates or codes, it accurately locates the unique third-level node and its corresponding code. By constructing a static anchoring base for the target unit, it uses bidirectional pointers, hash verification, and distributed read-write locks to prevent data tampering. By setting incremental data snapshots, it reduces the data transmission rate. By using multiple virtual carriers to collaboratively capture data, it improves data capture efficiency. This enables local dynamic updates of complaint data, avoids full model reconstruction, minimizes resource consumption, and reduces the error rate of complaint work order allocation, thereby improving the overall response speed and resource utilization of grassroots governance. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0019] Figure 1 This is a flowchart of the method of the present invention.

[0020] Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0022] Example 1, please refer to Figure 1 As shown in this embodiment, a grassroots social smart governance method based on big data analysis includes the following steps: S1. Construct a community governance model, collect user complaint information and store it in the community governance model. The complaint information includes text, images and video information. S2. Retrieve the user's historical behavior records in the government complaint system within a preset time period and verify the user's credibility. Users with high credibility can pass the verification directly, users with medium credibility need to complete biometric comparison and specified action execution verification, and users with low credibility trigger enhanced verification. S3. Analyze complaint information that meets the user credibility requirements, extract and classify keywords from complaint text information, and determine core keywords by identifying semantics, domain attributes and contextual relationships; for users who complain about images and videos, the complaint images and videos must meet the preset shooting specifications and have watermarks added; S4. Based on the matching degree of government responsibilities and the type of complaint, assign the complaint work order to the corresponding government department for handling.

[0023] Based on steps S1-S4, in traditional governance models, data is scattered across property management, community, and government systems, lacking a unified linkage mechanism and facing difficulties in data integration, resulting in information silos. Existing complaint location relies heavily on textual descriptions, lacking sufficient spatial positioning accuracy to pinpoint specific locations, leading to high work order allocation deviation rates and low processing efficiency. Community governance models are mostly static structures; new complaints or facility changes require complete model reconstruction, which is time-consuming, resource-intensive, and costly, making it difficult to adapt to the needs of handling high-frequency dynamic events. The lack of a layered verification mechanism for complaint information leads to false complaints or malicious persistent petitions, interfering with the allocation of government resources and reducing public trust in governance. This method achieves intelligent governance through a four-step closed loop: model construction, information collection, credibility verification, and work order allocation. It constructs a community governance model containing primary, secondary, and tertiary blocks, collects text, image, and video complaint information, and matches it to the smallest governance unit at the tertiary level using spatial indexing. Credibility scores are generated based on complaint history and records of dishonesty. Biometrics, dynamic action verification, and manual review are performed on users with low to medium credibility scores. Text information is segmented and categorized, and core keywords are extracted. Images are captured according to three standards (panoramic, medium, and close-up) and watermarked with spatiotemporal watermarks. Finally, work orders are allocated based on the matching degree of government responsibilities. Upon receiving a complaint work order, the government department extracts the issue type and location coordinates, and assigns it to the corresponding responsible person based on the responsibilities. This responsible person then matches the nearest frontline staff member based on the complaint location coordinates. The frontline staff member conducts an on-site investigation and handles the issue, simultaneously uploading watermarked photos and construction / repair videos to the grassroots social intelligent governance system. After the complaint is resolved, the system automatically pushes a result report to the user.

[0024] This embodiment uses dynamic local updates to the model, updating only the smallest community governance unit, thereby avoiding full model reconstruction, minimizing resource consumption, reducing the error rate in complaint work order allocation, and improving the overall response speed and resource utilization rate of grassroots governance.

[0025] In one embodiment, step S1, which involves constructing a community governance model, collecting user complaint information, and storing it in the community governance model, wherein the complaint information is image and video information processing, includes: S11. The construction of the community governance model is divided into two steps. First, comprehensive multi-dimensional data of the community is collected to provide raw input for the community governance model. Then, the collected multi-dimensional data is standardized and stored in the community governance model. S12. The community governance model is combined with the physical space grid to form a three-level block system for the community governance model. The three-level blocks are the first-level block, the second-level block, and the third-level block. The first-level block is the complete community boundary, including basic community information, such as community name, total land area, total number of households, and property management company. The second-level block is the functional area, which is divided into sub-areas according to purpose, such as high-rise residential area, multi-story residential area, public supporting area, and commercial and logistics area. The third-level block is the grid within the second-level block, and each grid corresponds to a specific location, such as the area in front of Unit 2 of Building 1 and the entrance to the underground garage of Building 3. S13. Level 1, Level 2, and Level 3 blocks are coded according to a hierarchical progression. Level 1 blocks are coded using the community name + fixed code format, such as XX Community-001. Level 2 blocks are coded using Level 1 block code - functional area name - functional area number, such as XX Community-001-High-rise Residential Area-01. Level 3 blocks are coded using Level 2 block code - the horizontal and vertical coordinates of the center point of the Level 3 block, such as XX Community-001-High-rise Residential Area-01-0305; 0305 represents the 3rd cell on the horizontal axis and the 5th cell on the vertical axis. S14. Complaint information is updated in conjunction with the first-level block, second-level block and third-level block. The mapping relationship between the location coordinates of the complaint and the third-level block is constructed based on the spatial index and stored in the community governance model.

[0026] Based on steps S11-S14, the multi-dimensional data collection for the community is divided into spatial data, human data, and dynamic event data. Spatial data includes the community boundary coordinates and building distribution, which are obtained through drone aerial photography. Building distribution includes the location, height, and number of units per building. Human data includes resident information and functional zoning. Resident information is obtained by connecting to the property registration system, including the number of residents and population structure. Dynamic event data consists of complaint information. After collection, the community governance model standardizes the collected data, unifying the format and ensuring data consistency. The first-level blocks are updated monthly. The system integrates basic community information with secondary block data. Secondary blocks are updated daily with complaint information and merged with tertiary block data. When tertiary blocks receive image or video complaints, the community governance model analyzes the complaint location using the watermark coordinates and matches it to the corresponding tertiary block. If a tertiary block receives text keywords, the model matches them to the corresponding tertiary block using a list of core keywords. The primary blocks of the tertiary model contain basic community information and are updated monthly. Secondary blocks are divided by functional areas and updated daily with complaint information. Tertiary blocks are 10m x 10m grid units corresponding to specific locations and updated with complaint information in real time. By encoding the primary, secondary, and tertiary blocks and embedding spatial location information within the encoding, a dynamic mapping between the encoding and the complaint location is achieved. Complaint information (text keywords, image watermark coordinates) is matched to the corresponding tertiary block via spatial indexing; for example, the text keyword "elevator malfunction" matches to the tertiary block "XX Community-01-High-Rise Residential Area-01-0305". The above steps embed spatial location information through three-level block coding, and combine the index table to map the location coordinates of the complaint with the three-level block coding, thereby improving positioning accuracy and data integration efficiency.

[0027] In one embodiment, the complaint information is updated in conjunction with the first-level block, second-level block, and third-level block. A mapping relationship between the complaint location coordinates and the third-level block is constructed based on a spatial index, and this mapping is stored in the community governance model. Step S14 includes: S141. Establish root nodes. Each root node is divided into four quadrants with the center point of the cell as the origin. The coordinates of the center points of the four quadrants are used as first-level nodes. S142. Each primary node is further divided into four quadrants with the center point of the primary node as the origin. The coordinates of the center points of the four quadrants are used as secondary nodes. The four quadrants of the secondary nodes correspond to the building groups of the community. S143. Each secondary node is further divided into four quadrants with the center point of the secondary node as the origin. The coordinates of the center points of the four quadrants are used as tertiary nodes. The tertiary nodes are the smallest governance units of the community. S144. Construct an index table to store the mapping relationship between the three-level block codes and the coordinates of the three-level node center points based on the community governance model; S145. Match the complaint location coordinates, third-level block code, and third-level node center point coordinates according to the index table, and mark the complaint location coordinates, third-level block code, and third-level node center point coordinates as complaint data to complete the dynamic local update of the community governance model.

[0028] Based on steps S141-S145, the root node is divided into four quadrants with the community center point as the origin. These four quadrants are equal in size and are further divided into northeast, southeast, northwest, and southwest. The coordinates of the center points of each quadrant form first-level nodes. Each first-level node is then further divided into four quadrants with its center point as the origin. The coordinates of the center points of these four quadrants form second-level nodes, which correspond to the building groups within the community. Each second-level node is also further divided into four quadrants with its center point as the origin. The coordinates of the center points of these four quadrants form third-level nodes. Third-level nodes are defined as the smallest governance unit of 10 meters × 10 meters, forming an index path from root node to first-level node to second-level node to third-level node. By storing the mapping relationship between the third-level block codes and the coordinates of the third-level node center points, the corresponding third-level node path is queried by inputting the complaint location coordinates. Matching the third-level block codes completes the precise location. By mapping the 10-meter grid units to the index table through the three-level node hierarchy, the accuracy of complaint location positioning is improved from the traditional building level to the specific grid level, further reducing the error rate in complaint work order allocation.

[0029] In one embodiment, step S145, which involves matching the complaint location coordinates, the third-level block code, and the third-level node center point coordinates according to the index table, and then using these coordinates as complaint data to complete the dynamic local update of the community governance model, includes: S1451. Based on the complaint data and index table, query the location coordinates of the complaint to be updated, the coordinates of the center point of the third-level node, and the associated third-level block code in the community governance model, and record them as the target unit. S1452. Construct a static anchoring base for the target unit and store complaint data in the static anchoring base. The static anchoring base serves as the processing carrier for the complaint data and interacts with the target unit and the community governance model. The static anchoring base includes a read / write control unit, a hash verification unit, and a metadata storage unit. The read / write control unit integrates a distributed lock interface for locking / unlocking the storage space of the static anchoring base. The hash verification unit generates a unique baseline hash code based on the complaint data of the target unit. The metadata storage unit stores the complaint data of the target unit, including the complaint location coordinates, three-level block code, three-level node center point coordinates, and index path. S1453. Establish bidirectional pointer anchoring between the target unit and the static anchoring base. The target unit generates a pointer to the static anchoring base through memory address mapping, which is used to read complaint data in the static anchoring base. The static anchoring base generates a pointer to the community governance model through three-level block encoding, which is used to write complaint data. The connection is ensured to be valid by comparing the hash check codes of the pointers at both ends. S1454. Configure a preset number of virtual carriers to capture complaint data of the corresponding target units; S1455. A distributed read-write lock is applied by the read-write control unit of the static anchoring base. A write lock is applied to the complaint data of the target unit, and a read lock is applied to the associated index path of the non-target unit. During the locking period, the hash verification unit generates a real-time verification code to block write operation requests from non-target units. S1456. The static anchor base is decoupled from the data flow of the community governance model, and an incremental data snapshot of the target unit is generated. The complaint data is written into the incremental data snapshot by a preset number of virtual carriers, and then the incremental data snapshot is written into the static anchor base. S1457. Release the distributed read-write lock applied by the read-write control unit. The static anchor base synchronizes the complaint data to the community governance model through bidirectional pointers, updates the index table mapping relationship, releases the non-target unit read lock, and restores the global read-write permissions of the community governance model.

[0030] As described in steps S1451-S1457 above, step S1451 receives the complaint location coordinates and third-level block code from the user complaint information. A matching query is performed using the index table of the community governance model. The index table stores the mapping relationship between the third-level block code and the coordinates of the center point of the third-level node. The query result is marked as the target unit. In step S1452, the static anchoring base construction allocates independent storage space to the target unit through the metadata storage unit. During the bidirectional pointer anchoring process between the target unit and the static anchoring base, the hash verification unit verifies the validity of the bidirectional pointer by calculating the combined hash value (target unit ID + base ID) of the target unit ID and the base ID. If the hash values ​​are inconsistent, the hash verification unit determines that the pointer is broken or the data has been tampered with, triggering a retry mechanism to ensure the accuracy of the anchoring relationship. The bidirectional pointers in step S1453 include "target unit → static anchor base pointer": the target unit generates a pointer to the physical storage address of the static anchor base through memory address mapping, generating a forward pointer used to read complaint data in the static anchor base; it also includes "static anchor base → community governance model pointer": the static anchor base generates a pointer to the community governance model by parsing the third-level block code of the target unit, generating a reverse pointer to the path of the third-level node of the main model, used to write complaint data; then the connection is ensured by comparing the hash checksums of the pointers at both ends: calculate the combined hash value Hash(target unit ID + static anchor base ID, such as target unit 1 + static anchor base 1), compare whether the hash values ​​of the target unit and the static anchor base are consistent, if they are inconsistent, the pointer is regenerated.

[0031] In step S1454, three virtual carriers are configured: Virtual Carrier 1, Virtual Carrier 2, and Virtual Carrier 3. Virtual Carrier 1 captures the complaint location coordinates, Virtual Carrier 2 captures the third-level block encoding index value, and Virtual Carrier 3 captures the coordinates of the third-level node center point. The collaborative work of multiple virtual carriers improves data capture efficiency. In step S1455, a write lock is applied to the complaint data of the target unit. An exclusive lock is used, allowing only updated complaint data to be written and preventing any other write operations. An exclusive lock is a resource locking mechanism with the core characteristic that only one process is allowed to hold the lock and perform a write operation at any time, while prohibiting other processes from performing any read or write operations on the target unit, thus ensuring the security of modifying the complaint data of the target unit.

[0032] Read locks are applied to the associated index paths of non-target units, using a shared lock to allow reading but prevent writing, ensuring that the data of non-target units is not tampered with during updates. The application of read-write locks involves the read-write control unit calling the distributed lock interface to generate a lock identifier based on the target unit ID and index path. Write locks are applied by applying an exclusive lock to the complaint data of the target unit, prohibiting any process from modifying the complaint data during the lock period. Read locks are applied by applying a shared lock to the index paths of non-target units (such as "root node - first-level node - second-level node - third-level node"), allowing only reading of the index table mapping relationship and blocking write operation requests. The incremental data snapshot in step S1456 is a lightweight data packet containing only complaint data generated after the static anchor base is unbound from the cell governance model data stream. This avoids a full update of the cell governance model, achieving efficient updates of the target unit. The components of the incremental data snapshot include the complaint location coordinates and the third-level block code. Step S1457 involves successfully applying the distributed read-write lock, confirming the lock states of the target unit and non-target units, and triggering the unbinding of the distributed read-write lock. The unbinding process of the distributed read-write lock is as follows: the static anchor base disconnects the data channel with the community governance model, and stops the data flow transmission between the target unit and the community governance model.

[0033] In one embodiment, step S2, which retrieves a user's historical behavior records in the government complaint system within a preset time period and verifies the user's credibility, includes: S21. Query the user's complaint history, which includes the number of complaints, the type of complaints, and the content of the complaints. S22. Check whether the user has a record of making false complaints or engaging in malicious harassment; S23. Generate a credibility score based on the credibility scoring rules to generate the user's credibility.

[0034] As described in steps S21-S23 above, a credit record refers to a user's dishonest behavior recorded by the government system for acts such as false complaints, malicious harassment, or providing forged evidence. A user with no credit record receives 100 points, and 20 points are deducted for each act of dishonesty. A user with a single act of dishonesty receives 80 points, requiring enhanced verification of subsequent complaints. A user with two acts of dishonesty receives 60 points, directly classified as low credibility, triggering enhanced verification. User credibility scores are divided into three categories: high, medium, and low. High credibility users with a score ≥ 80 can pass verification directly, medium credibility users with a score ≤ 60 and a score < 80 require enhanced verification of subsequent complaints, and low credibility users with a score < 60 are directly classified as low credibility, triggering enhanced verification. These steps, based on a credit profile derived from historical behavior and credit records, reduce the rate of false complaints and simultaneously decrease the volume of invalid work orders processed by government departments.

[0035] In one embodiment, the intermediate-trust user needs to complete step S2 of biometric comparison and specified action execution verification, including: S24. Collect a full-face image of a user with medium credibility using the front-facing camera of the user's mobile device, extract key facial features, and generate a unique feature template. S25. Compare the full-face image of the medium-credibility user with the facial data in the government identity information database at a 1:1 ratio; S26. After successful facial data comparison, a specified action is executed for verification. The system randomly selects 1-2 actions from the preset action library and guides the medium-confidence user to execute them through text.

[0036] As described in steps S24-S26 above, the key facial features of the user are extracted, including the eye area, nose area, mouth area, and contour area. The preset action library includes nodding, shaking, opening the mouth, blinking, raising the eyebrows, and turning the head. Specifically, when nodding, the user's head is required to swing up and down vertically with an amplitude of ≥30°; when shaking the head, the user's head is required to swing left and right horizontally with an amplitude of ≥45°; when opening the mouth, the user's mouth opens vertically for a distance of ≥2cm, corresponding to 1 / 5 of the face width; when blinking, the user's eyes complete a closing-opening cycle simultaneously for a duration of 0.5-1 second; when raising the eyebrows, the user's eyebrows move up ≥5mm; and when turning the head, the user's face turns ≥30° to the left and right, requiring one ear to be exposed. The system randomly selects 1-2 non-repeating actions from a preset action library, generates an action sequence, and guides the user to perform the action through text instructions, such as "Please complete the nodding action". If both actions are verified to be valid, the process is complete. This step can reduce interference from malicious complaints and reduce the number of invalid complaints.

[0037] In one embodiment, the step S2 of the low-trust user triggering enhanced verification includes: S27. Collect a low-confidence full-face image of a user using the front-facing camera of the user's mobile device, extract key facial features, and generate a unique feature template. S28. Compare the full-face images of low-confidence users with the facial data in the government identity information database at a 1:1 ratio; S29. After successful facial data comparison, a specified action is executed for verification. The system randomly selects at least three actions from a preset action library and guides the medium-confidence user to execute them via text. S30. Manually review low-credibility user complaints. If there are more than two false complaint records, restrict the user's complaint function.

[0038] As described in steps S24-S26 above, enhanced verification is triggered for users with low credibility. This involves adding action verification and manual review. Three to four non-repeating actions are randomly selected from a preset dynamic action library to generate a verification sequence, such as shaking the head, opening the mouth, raising eyebrows, and turning the head. After the action verification is passed, the system automatically pushes the user's complaint information, which includes text, image watermarks, and three-level block encoding location information, to the government platform for independent review by the reviewers. The reviewers check whether the keywords in the complaint text match the image watermark position and whether the image conforms to the shooting specifications. If the system finds that a user has ≥2 false complaint records within a year, the system triggers a restriction on the complaint function. By accumulating false complaint records, the system restricts the complaint function, creating a deterrent effect of the cost of dishonesty, thereby reducing the rate of repeated complaints by users. At the same time, it also limits the complaint privileges of malicious users to a certain extent, reducing ineffective interference with property management and community-level units.

[0039] In one embodiment, step S3, which involves extracting and classifying keywords from complaint text information and determining core keywords by identifying semantics, domain attributes, and contextual relationships, includes: S31. Segment the complaint text information into words based on a dictionary and tag its parts of speech; S32. Classify the already segmented complaint text information; S33. Determine core keywords based on the frequency of occurrence of complaint text information that has been segmented and categorized.

[0040] As described in steps S31-S33 above, a word segmentation dictionary is constructed by integrating professional terms in the field of grassroots governance, government-specific vocabulary, and the *Modern Chinese Dictionary*. Professional terms in grassroots governance typically include elevator malfunction, garbage sorting, and street vending; government-specific vocabulary typically includes work orders, completion of cases, and follow-up visits. The part-of-speech tagging system uses the *Chinese Part-of-Speech Tag Set* for definition. Typical nouns include elevator, garbage, and streetlights; verbs include damage, blockage, and occupation; and locative words include underground, corridor, and east side of the square. Complaint text information is categorized into three main types: public facilities, environmental sanitation, and public security. Public facilities complaints include elevators, streetlights, and fitness equipment; environmental sanitation complaints include garbage collection, sewage discharge, and noise pollution; and public security complaints include intrusion by strangers, objects thrown from heights, and unauthorized wiring. Core keywords are then determined by the frequency of occurrence in the segmented and categorized complaint text information and stored in a core keyword list. The core keyword list of complaint text information is then matched to the corresponding third-level block code, thereby improving the accuracy of work order allocation and reducing manual intervention costs.

[0041] In one embodiment, the complaint information includes step S3 of image information collection, which includes: S34. Guide users to take pictures according to the three-level standards of panoramic, medium shot and close-up. The panoramic picture information includes the complete scene environment, the medium shot picture information focuses on the subject of the problem, and the close-up picture information presents detailed features. S35. Determine the shooting distance and horizontal angle of panoramic, medium shot, and close-up images respectively; S36. Add time and location watermarks to different locations on the panoramic, medium shot, and close-up images respectively.

[0042] As described in steps S34-S36 above, the panoramic image information is used to fully present the spatial relationships of the complaint scene, including the relative positions of the problem subject and surrounding fixed reference objects; the mid-range image information is used to focus on the complete form of the problem subject, including its boundaries, size, color, and relationship with directly related objects, with the subject area accounting for ≥60%, solving the problem of blurred subjects in traditional single images; the close-up image information is used to highlight the microscopic features of the problem, with the detail area accounting for ≥80%, providing key visual evidence for subsequent liability determination. The panoramic image information has a horizontal viewing angle of no less than 120 degrees, a shooting distance of no less than 10 meters, and a vertical viewing angle covering the top of the scene to the ground. Its watermark is located in the lower right corner of the image. The medium-range image information has a horizontal viewing angle of 50-80 degrees, a shooting distance of 3-5 meters, and the main subject area of ​​the image occupies no less than 60% of the image. Its watermark is located in the lower left corner of the image. The close-up image information has a horizontal viewing angle of 20-30 degrees, a shooting distance of 0.5-2 meters, and the problem detail area occupies no less than 80% of the image. Its watermark is located at the top center of the image. By combining these three levels of images, the completeness of the complaint scene information is improved. At the same time, the accuracy of remote assessment by government personnel is improved, thereby reducing the frequency of on-site verification.

[0043] A grassroots social smart governance system based on big data analytics includes: The model building module, connected to the data acquisition module, is used to build a community governance model; The data acquisition module, connected to the credibility assessment module, is used to collect complaint information. The credibility assessment module, connected to the work order scheduling module, is used to assess user credibility. The work order scheduling module is used to assign complaint work orders to the corresponding government departments.

[0044] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A grassroots social smart governance method based on big data analysis, characterized in that: Includes the following steps: A community governance model is constructed, and user complaint information is collected and stored in the community governance model. The complaint information includes text, images, and video information. Retrieve users' historical behavior records in the government complaint system within a preset time period and verify users' credibility. Users with high credibility can pass the verification directly, users with medium credibility need to complete biometric comparison and perform a specified action verification, and users with low credibility trigger enhanced verification. Analyze complaint information that meets the user credibility requirements, extract and classify keywords from complaint text information, and determine core keywords by identifying semantics, domain attributes and contextual relationships; for users who complain about images and videos, the complaint images and videos must meet the preset shooting specifications and have watermarks added; Complaints will be assigned to the corresponding government departments for handling based on the matching degree of government responsibilities and the type of complaint. The steps of constructing a community governance model, collecting user complaint information and storing it in the model, where the complaint information includes image and video information processing, include: Multi-dimensional data of the community is collected as the raw input for building the community governance model. After standardization processing, the multi-dimensional data is stored in the community governance model. The community governance model is combined with the physical space grid to form a three-level block system. The three levels of blocks are the first-level block, the second-level block, and the third-level block. The first-level block is the complete community boundary and basic community information. The second-level block is the functional area, which is divided into sub-regions according to its purpose. The third-level block is the grid within the second-level block, and each grid corresponds to the specific location of the community. Level 1 blocks, Level 2 blocks, and Level 3 blocks are encoded according to a hierarchical progression, and are denoted as Level 1 block code, Level 2 block code, and Level 3 block code, respectively. Complaint information is updated in conjunction with the first-level, second-level, and third-level blocks. A mapping relationship between the location coordinates of the complaint and the third-level blocks is constructed based on spatial indexing and stored in the community governance model. The steps involved in updating complaint information in conjunction with first-level, second-level, and third-level blocks, constructing a mapping relationship between the complaint location coordinates and the third-level blocks based on spatial indexing, and storing this information in the community governance model include: Based on the community governance model, a root node is established. Each root node is divided into four quadrants with the community center point as the origin. The coordinates of the center points of the four quadrants are used as first-level nodes. The first-level nodes are the center points of the first-level blocks. Each primary node is further divided into four quadrants with the center point of the primary node as the origin. The coordinates of the center points of the four quadrants are used as secondary nodes, and the secondary nodes are the center points of the secondary blocks. Each secondary node is further divided into four quadrants with the center point of the secondary node as the origin. The coordinates of the center points of the four quadrants are used as tertiary nodes. The tertiary nodes are the smallest governance units of the community and the center points of the tertiary blocks. An index table is constructed to store the mapping relationship between the three-level block codes and the coordinates of the three-level node center points based on the community governance model; The complaint location coordinates, third-level block codes, and third-level node center point coordinates are matched according to the index table, and the complaint location coordinates, third-level block codes, and third-level node center point coordinates are used as complaint data to complete the dynamic local update of the community governance model. The steps of matching the complaint location coordinates, third-level block codes, and third-level node center point coordinates according to the index table, and then using these coordinates as complaint data to complete the dynamic local update of the community governance model include: Based on complaint data and index table queries, the location coordinates of complaints to be updated, the coordinates of the center point of the third-level node, and the associated third-level block codes in the community governance model are queried and recorded as the target unit. A static anchoring base is constructed for the target unit, and complaint data is stored in the static anchoring base. The static anchoring base interacts with the target unit and the community governance model. The static anchoring base includes a read / write control unit, a hash verification unit, and a metadata storage unit. The read / write control unit integrates a distributed lock interface for locking / unlocking the storage space of the static anchoring base. The hash verification unit generates a unique baseline hash code based on the complaint data of the target unit. The metadata storage unit is used to store the complaint data of the target unit. A bidirectional pointer anchoring is established between the target unit and the static anchoring base. The target unit generates a pointer to the static anchoring base through memory address mapping, which is used to read complaint data in the static anchoring base. The static anchoring base generates a pointer to the community governance model through three-level block encoding, which is used to write complaint data. The connection is ensured to be valid by comparing the hash check codes of the pointers at both ends. Configure a preset number of virtual carriers to capture complaint data for the corresponding target units; Distributed read-write locks are applied by the read-write control unit of the static anchor base. Write locks are applied to the complaint data of the target unit, and read locks are applied to the associated index paths of non-target units. During the locking period, the hash verification unit generates real-time verification codes to block write operation requests from non-target units. The static anchor base is decoupled from the data flow of the community governance model, and an incremental data snapshot of the target unit is generated. The complaint data is written into the incremental data snapshot by a preset number of virtual carriers, and then the incremental data snapshot is written into the static anchor base. Release the distributed read-write lock applied by the read-write control unit, and the static anchor base synchronizes the complaint data to the community governance model through bidirectional pointers, updates the index table mapping relationship, releases the read lock of non-target units, and restores the global read-write permissions of the community governance model.

2. The grassroots social smart governance method based on big data analysis according to claim 1, characterized in that: The steps for retrieving a user's historical behavior records in the government complaint system during a preset time period and verifying the user's credibility include: Query user complaint history, which includes the number of complaints, complaint types, and complaint content; Check whether the user has a record of making false complaints or engaging in malicious harassment; A credibility score is generated based on credibility scoring rules to determine the user's credibility level.

3. The grassroots social smart governance method based on big data analysis according to claim 1, characterized in that: The medium-trust level user needs to complete the steps of biometric comparison and specified action execution verification, including: The system captures full-face images of users with moderate credibility using the front-facing camera of their mobile devices, extracts key facial features, and generates unique feature templates. The full-face images of medium-credibility users are compared 1:1 with facial data in the government identity information database; After successful facial data comparison, a specified action is executed for verification. The system randomly selects at least one action from a preset action library and guides the user with medium credibility to execute it via text.

4. The grassroots social smart governance method based on big data analysis according to claim 1, characterized in that: The steps for triggering enhanced verification by a low-trust user include: The system captures low-confidence full-face images of users using the front-facing camera of their mobile devices, extracts key facial features, and generates unique feature templates. The full-face images of users with low credibility are compared 1:1 with facial data in the government identity information database; After successful facial data comparison, a specified action is executed for verification. The system randomly selects at least three actions from a preset action library and guides the user with medium credibility to execute them via text. User complaints with low credibility will be manually reviewed. If there are more than two false complaint records, the user's complaint function will be restricted.

5. The grassroots social smart governance method based on big data analysis according to claim 1, characterized in that: The steps of extracting and classifying keywords from complaint text information, and determining core keywords by identifying semantics, domain attributes, and contextual relationships, include: The complaint text information is segmented into words based on a dictionary and its part of speech is tagged. Classify the already segmented complaint text information; Core keywords were determined based on the frequency of occurrence of complaint text information that had already been segmented and categorized.

6. The grassroots social smart governance method based on big data analysis according to claim 1, characterized in that: The complaint information includes the steps of image information collection, including: The system guides users to take pictures according to three levels of standards: panoramic, medium shot, and close-up. The panoramic picture information includes the complete scene environment, the medium shot picture information focuses on the subject of the problem, and the close-up picture information presents detailed features. Determine the shooting distance and horizontal angle for panoramic, medium, and close-up images respectively; Add time and location watermarks to different locations on panoramic, medium, and close-up images.

7. A grassroots social smart governance system based on big data analysis, used to implement the grassroots social smart governance method based on big data analysis as described in any one of claims 1-6, characterized in that, include: The model building module, connected to the data acquisition module, is used to build a community governance model; The data acquisition module, connected to the credibility assessment module, is used to collect complaint information; The credibility assessment module, connected to the work order scheduling module, is used to assess user credibility. The work order scheduling module is used to assign complaint work orders to the corresponding government departments. The complaint work order includes complaint text information, complaint image and video information, three-level block code corresponding to the complaint location coordinates, and user credibility information.

Images