Community micro-update multi-source heterogeneous data fusion and standardization processing method and system

Abstract

The application provides a community micro-update multi-source heterogeneous data fusion and standardization processing method and system. The method obtains the multi-source records corresponding to the community micro-update object, converts the continuous environmental records into seasonal anchor points according to the seasonal running track in cold regions, concatenates the multi-source records of the same collection object under different seasonal anchor points into an object seasonal sequence with the micro-update object as the traction, extracts the expression deviation caused by the seasonal anchor points along the sequence and strips it into a drift copy, retains the baseline copy stably associated with the micro-update object, generates a spatial constraint skeleton according to the service radius, the entry connection relationship and the walking access path, projects the baseline copy and the drift copy to the spatial constraint skeleton and fragments backfill, and generates the boundary standardized dataset after the backfill of the spatial fragments. The application can eliminate the expression deviation caused by the seasonal difference in cold regions, limit the use of data within the actual service boundary of the micro-update object, and provide standardized data for health community evaluation.

Description

Technical Field

[0001] This invention relates to the fields of urban renewal and community data governance technology, specifically to a method and system for the fusion and standardization of multi-source heterogeneous data in community micro-renewal, and particularly to the fusion and standardization of multi-source heterogeneous data related to community micro-renewal objects in the context of seasonal differences in cold regions, in order to support the evaluation of healthy communities. Background Technology

[0002] Community micro-renewal involves the renovation of old residential areas, optimization of public spaces, improvement of pedestrian and cycling systems, and supplementation of service facilities. With the increasing demand for healthy community construction, existing research and applications are beginning to incorporate GIS spatial data, remote sensing imagery, POI data, on-site measurement data, and resident questionnaire data to comprehensively evaluate community environmental quality, resident activities, and health perception, thereby assisting in the formulation of micro-renewal plans and the evaluation of their effects.

[0003] Existing multi-source data processing methods typically employ data cleaning, standardization, normalization, spatial overlay, or weighted fusion to aggregate data from different sources and scales into a unified indicator system. While these methods have some applicability in typical urban environments, they suffer from the following drawbacks: First, existing methods focus more on data aggregation and result scoring, with less attention paid to the differences in data expression across different collection periods and seasons. For cold-region urban communities, winter and summer temperatures, snow cover, road conditions, outdoor activity intensity, and facility usage patterns differ significantly, and data collected from the same community in different seasons often exhibits significant fluctuations. If these methods are directly fused using conventional approaches, seasonal changes can easily be mistaken for changes in the effectiveness of micro-updates.

[0004] Second, existing urban renewal evaluation methods typically standardize multi-source data and directly enter the scoring or weighting process, making it difficult to distinguish the impact of seasonal factors and the micro-renewal objects themselves on data expression, and lacking a data caliber correction mechanism for scenarios such as road traffic in cold winters, snow cover, and reduced outdoor activities.

[0005] Third, existing community microclimate monitoring methods can describe local climate conditions, but they have not solved the problem of consistent data integration between microclimate conditions and heterogeneous data such as GIS, POI, questionnaires, and activity records.

[0006] Fourth, existing general data governance or concept drift adaptation technologies do not define the spatial service boundaries of community micro-update objects, which can easily extrapolate local fragment data to the entire community, resulting in unclear boundaries for healthy community evaluation and affecting the stability and comparability of the evaluation. Summary of the Invention

[0007] The technical problem to be solved by this invention is: in the scenario of micro-update evaluation of cold-region communities, how to fuse and standardize multi-source records with different collection time periods, collection locations, collection objects and source formats, so that it can not only eliminate the expression bias caused by seasonal differences in cold regions, but also limit its use to the spatial boundaries of the actual role of community micro-update objects, thereby providing standardized data with consistent caliber and clear boundaries for healthy community evaluation.

[0008] To address the aforementioned technical problems, this invention provides a method for multi-source heterogeneous data fusion and standardization processing in community micro-updates, comprising: Obtain the multi-source records corresponding to the community micro-update objects. The multi-source records carry the collection time period, collection location, collection object, and source format. Based on the cold-season movement trajectory of the area where the community micro-update object is located, the continuous environmental records are transcribed into seasonal anchor points corresponding to the collection period; Using the community micro-update object as a guide, multi-source records of the same collected object under different seasonal anchor points are strung together to form an object seasonal sequence; The expression shift caused by the seasonal anchor is extracted along the seasonal sequence of the object, and the expression shift is stripped from the corresponding multi-source record into a drift copy, while the baseline copy that is stably associated with the community micro-update object is retained. A spatial constraint skeleton is generated based on the service radius, entrance connection relationship and walking access path of the community micro-update object. The baseline copy and the drift copy are projected onto the spatial constraint skeleton and the fragments are backfilled so that the drift copy corrects the expression of the corresponding spatial fragment. The backfilled spatial fragments are aggregated to generate a standardized dataset within the boundaries for evaluating healthy communities.

[0009] Furthermore, the step of transcribing continuous environmental records into seasonal anchor points corresponding to the collection period based on the cold-season movement trajectory of the area where the community micro-update object is located includes: Based on the accessibility relationships between community roads, public spaces, and micro-renewal facilities, the continuous environmental record is divided into environmental segments corresponding to the accessibility processes of residents' activities; Environmental segments within the same data collection period are sequentially spliced ​​together to form seasonal segments that reflect the impact of cold seasons on community usage. By attaching the seasonal segments to the corresponding collection periods, the multi-source records acquire a unified seasonal anchor point before entering the seasonal sequence of the object.

[0010] Further, the step of extracting the expression shift caused by the seasonal anchor along the seasonal sequence of the object, and stripping the expression shift from the corresponding multi-source record into a drift copy, while retaining the baseline copy stably associated with the community micro-update object, includes: According to the sequential relationship of the same collected object in the seasonal sequence of the object, multi-source records with different source formats are transcribed into object state fragments; In the object state fragment, the time period representation brought in by the seasonal anchor and the spatial representation brought in by the community micro-update object are separated; The time period representation is written into the drift copy, the spatial representation is written into the base copy, and the object correspondence between the drift copy and the base copy is maintained, so that the subsequent spatial constraint skeleton can perform piecewise backfilling on the same collected object.

[0011] Furthermore, the continuous environmental record is segmented into environmental segments corresponding to residents' accessibility processes based on the accessibility relationships between community roads, public spaces, and micro-renewal facilities, including: Using the community access node corresponding to the collection location as the starting point for segmentation, the continuous environmental records are divided along the arrival order of residents from the residential entrance to the micro-renewal facilities; Group environment records within the same arrival order into node environment segments, and group environment records between adjacent passing nodes into path environment segments. By connecting the node environment segment and the path environment segment according to the order of passage, an environmental segment corresponding to the reachability process of residents' activities is obtained.

[0012] Furthermore, the step of using the community micro-update object as a guide to concatenate multi-source records of the same collected object at different seasonal anchor points into an object seasonal sequence includes: Extract the object identifier and location attribution relationship corresponding to the same collected object from the multi-source records; Multiple source records with the same object identifier and whose location affiliation points to the same community micro-update object are grouped into the same object cluster; Based on the chronological relationship of the seasonal anchor points during the collection period, the multi-source records within the object cluster are sequentially connected to form the object seasonal sequence.

[0013] Furthermore, the separation of the time-period representation brought in by the seasonal anchor and the spatial representation brought in by the community micro-update object in the object state fragment includes: Extract object state segments of the same collected object at adjacent seasonal anchor points along the seasonal sequence of the object; Content that changes synchronously with seasonal anchor points is categorized into time-period expression, while content that remains consistent with the collection location and micro-update object service relationship is categorized into spatial expression. After writing to the drift copy and the base copy respectively, the retracement relationship between the two and the same object state fragment is preserved.

[0014] Furthermore, the step of generating a spatial constraint skeleton based on the service radius, entrance connection relationship, and pedestrian access path of the community micro-update object includes: Using the location of the community micro-renewal object as the skeleton center, the connection nodes for residents to enter the service area of ​​the community micro-renewal object are determined along the entrance connection relationship; Connect the skeleton center and the connecting node according to the pedestrian access path to form access branches; The spatial units that intersect with the access branch within the service radius are incorporated into the skeleton range to obtain the spatial constraint skeleton.

[0015] Further, the step of projecting the baseline copy and the drift copy onto the spatial constraint skeleton and performing fragment backfilling includes: The reference copy is projected onto the spatial unit in the spatial constraint skeleton according to the acquisition location to form a reference spatial segment; The drifted copy is projected onto the reference space segment according to the corresponding seasonal anchor point to form a seasonally corrected segment; The seasonal correction fragments are backfilled into the baseline spatial fragments corresponding to the same collected object according to the anaphoric relationship, so that the backfilled spatial fragments retain both the spatial affiliation of the micro-updated object and the cold-region seasonal expression.

[0016] Furthermore, the summarized backfilled spatial fragments generate a standardized dataset within the boundaries for evaluating healthy communities, including: According to the accessible branches in the spatial constraint skeleton, the backfilled spatial fragments are merged into the corresponding skeleton range; Boundary splitting is performed on backfilled spatial segments that cross the skeleton's boundaries, while retaining the content of segments within the skeleton's boundaries; The retained fragments are rearranged according to the collection object, seasonal anchor point, and spatial unit to generate a standardized dataset within the boundary.

[0017] This invention also provides a multi-source heterogeneous data fusion and standardization processing system for community micro-updates, comprising: The multi-source record acquisition module is used to acquire multi-source records corresponding to community micro-update objects. The multi-source records carry the collection time period, collection location, collection object and source format. The seasonal anchor point generation module is used to transcribe continuous environmental records into seasonal anchor points corresponding to the collection period based on the cold-season running trajectory of the area where the community micro-update object is located. The object seasonal sequence construction module is used to connect multiple source records of the same collected object under different seasonal anchor points into an object seasonal sequence, with the community micro-update object as the guide. The drift copy stripping module is used to extract the expression offset caused by the seasonal anchor along the seasonal sequence of the object, and strip the expression offset from the corresponding multi-source record into a drift copy, while retaining the baseline copy that is stably associated with the community micro-update object; The spatial constraint skeleton generation module is used to generate a spatial constraint skeleton based on the service radius, entrance connection relationship and pedestrian access path of the community micro-update object; The fragment projection backfilling module is used to project the reference copy and the drift copy onto the spatial constraint skeleton respectively and perform fragment backfilling, so that the drift copy corrects the expression of the corresponding spatial fragment; The standardized output module is used to summarize the backfilled spatial fragments and generate a standardized dataset within the boundaries for the evaluation of healthy communities.

[0018] Through the above technical solution, the present invention has the following beneficial effects: This invention does not simply clean and normalize multi-source data before scoring. Instead, it first rewrites the seasonal operational trajectory in cold regions into seasonal anchor points, so that data from different collection periods have traceable seasonal references. This solves the problem that community space, activity, and perception data collected in different seasons cannot be directly compared.

[0019] This invention uses seasonal sequences to longitudinally connect cross-seasonal records of the same collected object, enabling the identification of expression changes of the same object under different seasonal conditions and avoiding seasonal fluctuations from being mistaken for changes in micro-update effects.

[0020] This invention separates the expression offset into a drift copy while retaining the baseline copy, enabling the seasonal effects and the stabilizing spatial effects of micro-update objects to be processed separately. This effectively solves the problem of difficulty in unifying standards due to different source formats, location scales, and object affiliations among multi-source records.

[0021] This invention limits the effective service range of micro-update objects by using a spatial constraint skeleton, and splits and backfills cross-boundary segments to reduce evaluation bias caused by local data extrapolation, thus solving the problem of unbounded extrapolation of local micro-update object data in healthy community evaluation.

[0022] The output of this invention is a standardized dataset within the boundary, which can serve as the data foundation for evaluating healthy communities and improve the comparability and stability of subsequent evaluations. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a method for multi-source heterogeneous data fusion and standardization processing in community micro-updates, provided in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a seasonal anchor point generation process provided in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram illustrating the process of constructing an object seasonal sequence and stripping copies, as provided in an embodiment of the present invention.

[0027] Figure 4 This is a schematic diagram of a spatial constraint skeleton generation provided in an embodiment of the present invention.

[0028] Figure 5 This is a schematic diagram of the structure of a multi-source heterogeneous data fusion and standardization processing system for community micro-updates provided in an embodiment of the present invention. Detailed Implementation

[0029] The present invention will now be described in detail with reference to specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present invention can be combined with each other.

[0030] Example 1: A method for multi-source heterogeneous data fusion and standardization processing in community micro-updates, such as... Figure 1 As shown, it includes steps S1-S6.

[0031] This embodiment provides a method for multi-source heterogeneous data fusion and standardization processing in community micro-updates. This method uses the community micro-update object as the processing guide, and takes the collection time period, collection location, collection object, and source format of multi-source records as a unified processing entry point. The system first generates seasonal anchor points based on the cold-region seasonal movement trajectory, then concatenates records of the same collection object under different seasonal anchor points into an object seasonal sequence. Subsequently, it removes the expression offset caused by the seasonal anchor points from the object seasonal sequence, forming a drift copy, while retaining a baseline copy stably associated with the micro-update object. Finally, it generates a spatial constraint skeleton based on the service radius, entry connection relationship, and walking access path, projects and backfills fragments onto the baseline copy and drift copy, and outputs a standardized dataset within the boundary.

[0032] Step S1: Obtain the multi-source record corresponding to the community micro-update object.

[0033] Among them, multi-source records carry the collection time period, collection location, collection object and source format.

[0034] The system first identifies a community micro-renewal object to be evaluated. The community micro-renewal object refers to a spatial unit or facility node within the community that undergoes partial renovation, functional supplementation, or environmental optimization, including but not limited to community entrances and exits, pocket parks, fitness activity areas, pedestrian walkway nodes, public service facilities, or micro-renewed composite public spaces.

[0035] The system retrieves multi-source records related to the micro-update object. These multi-source records refer to data records acquired from different data collection entities, using different record formats, targeting different data collection objects, and at different data collection periods, including but not limited to: (1) Remote sensing image interpretation results: such as spatial records of community green space coverage, paving type, building shadows, etc. obtained from satellite image or UAV image interpretation; (2) GIS spatial records: such as vector or raster data of community road networks, building outlines, public space boundaries, facility locations, etc.; (3) POI records: such as points of interest data on commercial services, public facilities and transportation stations within the community provided by platforms such as Gaode Maps and Baidu Maps; (4) On-site measurement records: such as the lighting level measured by the illuminance meter, the environmental noise measured by the noise meter, and the temperature and humidity recorded by the weather station; (5) Resident activity records: such as community walking routes, frequency of facility use, duration of outdoor stay, and other behavioral data collected through sensors or mobile devices; (6) Questionnaire perception records: such as residents’ subjective evaluation data on community environment satisfaction, health perception, and ease of use.

[0036] Each multi-source record carries the following four basic identifiers: Data collection period: Records the time range for data collection, which can be a specific date, week, month, or micro-update evaluation cycle. The data collection period is used to establish the time frame for subsequent seasonal anchor points.

[0037] Data collection location: Records the spatial location where data was collected, which can be latitude and longitude coordinates, address description, spatial unit number, or community access node identifier. The data collection location is used to support the spatial positioning of subsequent spatial constraint frameworks.

[0038] Data Collection Objects: The specific objects described by the recorded data, which can be fragments of resident activities, facility usage records, spatial units, or questionnaire data collection objects. Data collection objects are used to support the identification of subsequent seasonal sequences of objects.

[0039] Source format: The original format type of the recorded data, such as tabular records, spatial vectors, raster images, text questionnaires, or device logs. The source format is used to preserve the differences from the original source during subsequent transcription.

[0040] Through the above four types of basic identifiers, the system enables remote sensing image interpretation results, GIS spatial records, POI records, field measurement records, resident activity records, and questionnaire perception records to enter the same processing entry point, instead of listing indicators horizontally according to data source.

[0041] Step S2: Based on the cold-season movement trajectory of the community micro-update object's area, transcribe the continuous environmental records into seasonal anchor points corresponding to the collection period, such as... Figure 2 As shown.

[0042] The aforementioned seasonal operational trajectory in cold regions refers to the process by which environmental factors such as temperature, snow cover, sunshine duration, and road conditions change with the seasons in cold-region cities. Cold regions exhibit significant seasonal differences, with winters characterized by snow cover, low temperatures, shorter sunshine duration, and altered road conditions, leading to reduced outdoor activities, changes in facility usage, and decreased accessibility to community spaces.

[0043] The seasonal anchor points are not single temperature values ​​or simple seasonal labels, but rather time reference units used to reflect changes in the usage status of cold-region communities. The seasonal anchor points must reflect not only changes in the natural environment but also the impact of these changes on community accessibility, activities, and usage.

[0044] Specifically, the system segments continuous environmental records into environmental segments corresponding to residents' accessibility processes, based on the accessibility relationships between community roads, public spaces, and micro-renewal facilities. These accessibility relationships refer to the spatial connections between residents starting from their residential entrance and reaching micro-renewal facilities via community roads and public spaces.

[0045] The system uses the community access nodes corresponding to the data collection locations as the starting point for segmentation, and divides the continuous environmental records along the order in which residents arrive at the micro-renewal facilities from their residential entrances. These access nodes include locations such as residential entrances, road intersections, public space entrances, and facility entrances.

[0046] The system groups environmental records within the same arrival sequence into node environmental segments and environmental records between adjacent access nodes into path environmental segments. Node environmental segments reflect the environmental conditions at the access node, such as snow accumulation at the entrance, lighting conditions, and temperature; path environmental segments reflect the environmental conditions along the path between nodes, such as snow accumulation on the road, slippery road surface, and shading conditions.

[0047] The system connects the node environment segment and the path environment segment according to the order of passage to obtain the environment segment corresponding to the reachability process of residents' activities.

[0048] Subsequently, the system sequentially splices environmental segments within the same data collection period to form seasonal segments reflecting the impact of the cold season on community usage. These seasonal segments include not only natural environmental parameters such as temperature and snow cover, but also changes in usage caused by these parameters, such as changes in accessibility, difficulty of movement, and shrinkage of activity space.

[0049] Finally, seasonal segments are attached to the corresponding acquisition time periods, enabling multi-source records to obtain the corresponding total seasonal anchor point before entering the object's seasonal sequence. Each acquisition time period corresponds to one total seasonal anchor point, which may contain one or more sub-seasonal anchor points corresponding to access branches.

[0050] To ensure that seasonal anchor points can be executed and verified by the program, the system sets an anchor point identifier, data collection period, access branch road identifier, traffic node identifier, path environment segment identifier, temperature, snow depth, sunshine duration, road traffic status, lighting status, and data source identifier for each seasonal anchor point. Continuous environmental records are first written into node environment segments and path environment segments according to the traffic node where the data collection location falls or the path segment between adjacent traffic nodes. Then, the node environment segments and path environment segments on the same access branch road are sequentially spliced ​​according to the data collection period.

[0051] When multiple access routes exist within the same data collection period, the system generates sub-seasonal anchor points corresponding to each access route. When a downstream object record only requires an anchor point for one data collection period, the system prioritizes selecting the corresponding sub-seasonal anchor point based on the access route where the object's data collection location is located. If the access route cannot be determined, the system selects the access route closest to the community micro-update object. Records that still cannot be determined are marked as pending confirmation records and do not participate in expression offset stripping. Thus, each multi-source record entering the object's seasonal sequence has a traceable seasonal anchor point source.

[0052] Step S3: Using the community micro-update object as a guide, concatenate multi-source records of the same collected object under different seasonal anchor points into an object seasonal sequence, such as... Figure 3 As shown.

[0053] The purpose of this step is to place the expression changes of the same collected object under different seasonal conditions into the same vertical processing structure, rather than horizontally stacking data from different sources into an indicator set.

[0054] Specifically, the system extracts the object identifier and location attribution relationship corresponding to the same collected object from multi-source records.

[0055] Object identifiers are used to identify the same resident activity segment, the same facility usage record, the same spatial unit, or the same questionnaire subject. Object identifiers can be device IDs, spatial unit numbers, questionnaire numbers, activity trajectory numbers, or object-specific codes generated by combining spatial location and time windows.

[0056] Location attribution is used to identify whether a record refers to the same micro-update object in the same community. Location attribution is determined by the spatial association between the collection location and the location of the micro-update object, such as if the record collection location is within the service radius of the micro-update object, the activity trajectory of the record collection object passes through the micro-update object, or the record collection object explicitly mentions the micro-update object in the questionnaire.

[0057] The system groups multi-source records with the same object identifier and location affiliation pointing to the same community micro-update object into the same object cluster. The object cluster is a preliminary set of the object's seasonal sequence, with records within the cluster corresponding to the same collected object but scattered under different seasonal anchor points.

[0058] When records from different sources do not have the same object identifier, a unique combined object code is generated based on whether the collection location falls into the same spatial unit, the collection time period overlaps or is adjacent, the collection object type is consistent, or the same micro-update object belongs to. Records that do not meet the combined conditions are entered into a single-source object cluster or a set to be confirmed and do not participate in cross-source concatenation.

[0059] The system sequentially connects multi-source records within an object cluster according to the chronological order of seasonal anchor points during the data collection period, forming an object seasonal sequence. This object seasonal sequence arranges multi-source records of the same collected object at different seasonal anchor points in chronological order, allowing the impact of seasonal changes on the object's representation to be traced.

[0060] Step S4: Extract the expression offset caused by the seasonal anchor along the seasonal sequence of the object, and strip the expression offset from the corresponding multi-source record into a drift copy, while retaining the baseline copy that is stably associated with the community micro-update object.

[0061] This processing mechanism is used to distinguish between "data representation changes caused by seasonal changes in cold regions" and "data representation changes caused by the spatial effects of micro-updated objects".

[0062] Specifically, the system transcribes multi-source records with different source formats into object state fragments according to the sequential relationship of the same collected object in the seasonal sequence of the object.

[0063] The object state fragment is the record content corresponding to a single node in the object's seasonal sequence, which has a unified separable structure after format transcribing. The transcribing process unifies different source formats such as tabular records, spatial vectors, raster image interpretation results, text questionnaires, or equipment logs into a fragment structure containing two separable parts: time period expression and spatial expression.

[0064] The transcription process does not change the actual content of the record, but rather provides structured annotations. For example, for resident activity records, the transcription process breaks down "reduced walking activities around pocket parks in winter" into a time period expression "reduced walking activities in winter" and a spatial expression "around pocket parks"; for questionnaire perception records, the transcription process breaks down "feeling that parks are inconvenient to use in winter" into a time period expression "inconvenient in winter" and a spatial expression "park usage".

[0065] An object state fragment includes at least the object state fragment identifier, original record identifier, object identifier, collection period, seasonal anchor point identifier, collection location, spatial unit identifier, source format, original record value, candidate time period expression field, candidate spatial expression field, and field source marker. When records with different source formats enter the object state fragment, the system only adds field markers and backreferences, without deleting the original record values.

[0066] For table records and equipment logs, the system marks fields related to the collection period, temperature, snow cover, lighting duration, and activity frequency changes as candidate time period expression fields, and fields related to the collection location, facility location, spatial unit, entrance, or access path as candidate spatial expression fields. For spatial vector and raster image interpretation results, the system writes the collection period and environmental status into candidate time period expression fields, and writes spatial units, boundaries, paths, or facility locations into candidate spatial expression fields. For text questionnaires, the system writes text fragments containing information about season, cold weather, snow cover, lighting duration, or differences in winter and summer usage into candidate time period expression fields, and writes text fragments containing micro-update object names, facility types, entrances, paths, or spatial locations into candidate spatial expression fields.

[0067] The system separates the time-period representation brought in by the seasonal anchor and the spatial representation brought in by the community micro-update object in the object state fragment.

[0068] The time-period expressions change synchronously with the seasonal anchor points, reflecting the impact of seasonal factors on the data. Time-period expressions include, but are not limited to: a decrease in walking activity records due to winter snow accumulation, changes in winter road accessibility records, a reduction in winter outdoor space usage records, mentions of cold and snow in winter questionnaires, and an increase in winter lighting duration, etc.

[0069] Spatial representation maintains continuity with the data collection location and the service relationships of micro-updated objects, reflecting the spatial impact of micro-updated objects on the data. Spatial representation includes, but is not limited to: facility service range, accessibility relationships, spatial unit affiliation, object location affiliation, facility type, and service functions.

[0070] The system writes the time-period representation to the drift copy and the spatial representation to the base copy. The drift copy reflects the representational changes caused by seasonal factors, while the base copy reflects the stable spatial effects of micro-update objects.

[0071] The system maintains the object correspondence between the drift copy and the base copy. The object correspondence is achieved through back-pointing relationships, which record that both the drift copy and the base copy originate from the same object state fragment, enabling subsequent spatial constraint skeletons to perform piecewise backfilling on the same acquired object.

[0072] The system determines field affiliation based on field source, time synchronization, and spatial continuity: field values ​​that change with the same object between adjacent seasonal anchors, and whose changes can be explained by the temperature, snow cover, sunshine duration, or access status fields in the seasonal anchors, are written into the time period representation; field values ​​that point to micro-update objects, access branches, spatial units, entrance connection relationships, or service radii, and maintain the same spatial affiliation under adjacent seasonal anchors, are written into the spatial representation.

[0073] When the same field has both time-based and spatial attributes, the system retains the original field value and records the time-based expression label in the drift copy and the spatial expression label in the base copy. When a field cannot be assigned according to the above rules, the system writes the field to the set of fields to be confirmed and does not participate in the backfilling of the base copy by the drift copy. The drift copy includes a drift copy identifier, an object state fragment identifier, a seasonal anchor identifier, and time-based expression fields and values; the base copy includes a base copy identifier, an object state fragment identifier, a spatial unit identifier, an access branch identifier, and spatial expression fields and values.

[0074] Step S5: Generate a spatial constraint skeleton based on the service radius, entrance connection relationship, and walking access path of the community micro-update object. Project the baseline copy and the drift copy onto the spatial constraint skeleton respectively and perform fragment backfilling, so that the drift copy corrects the expression of the corresponding spatial fragment. The generation process of the spatial constraint skeleton is as follows: Figure 4 As shown.

[0075] The spatial constraint skeleton is used to limit the effective scope of micro-update objects on community spatial data, avoiding the extrapolation of local spatial fragments to the entire community. The spatial constraint skeleton is not a simple service radius buffer, but rather considers the actual service range of entrance connectivity and pedestrian access paths.

[0076] Specifically, the system uses the location of the community micro-update object as the skeleton center. The skeleton center is the spatial location of the micro-update object, which can be a point coordinate, the geometric center of an area, or the location of the main entrance.

[0077] The system determines the connection nodes for residents to enter the service area of ​​the micro-renewal project based on the entrance connection relationships. The entrance connection relationships refer to the spatial connections that allow residents to enter the service area of ​​the micro-renewal project from their residential entrance. Connection nodes include community entrances / exits, building entrances, road intersections, and other starting points for residents' activities.

[0078] The system connects the framework center and connecting nodes based on pedestrian access routes, forming access branches. The pedestrian access routes refer to the walking paths residents take from connecting nodes to micro-update objects, and can be derived from GIS road networks, field measurements, or community spatial data. Access branches are the set of paths from connecting nodes to the framework center, reflecting the network of paths actually accessible to residents.

[0079] The system incorporates spatial units intersecting with access roads within the service radius coverage area into the skeleton scope, resulting in a spatial constraint skeleton. The service radius can be determined based on facility type, community scale, or planning specifications. For example, the service radius of a pocket park can be set at 300 meters, the service radius of a fitness activity area can be set at 500 meters, and the service radius of a pedestrian road node can be set at 200 meters.

[0080] The spatial constraint skeleton includes both the linear range covered by the access branches and the planar spatial units that intersect with the access branches within the service radius. Only multi-source records located within the spatial constraint skeleton are considered to be affected by the spatial action of the micro-update object.

[0081] Subsequently, the system projects the baseline copy and the drift copy onto the spatial constraint skeleton and performs fragment backfilling.

[0082] The system projects the baseline copy onto spatial cells in the spatial constraint skeleton according to the acquisition location, forming a baseline spatial segment. The baseline spatial segment is the spatial positioning result of the baseline copy in the spatial constraint skeleton, and each baseline spatial segment corresponds to a spatial cell or a access branch.

[0083] The system projects the drift copy onto the reference space segment according to the corresponding seasonal anchor point, forming a seasonally corrected segment. The seasonally corrected segment is the result of the temporal superposition of the drift copy on the reference space segment, and is used to correct the expression of the reference space segment under different seasonal anchor points.

[0084] During backfilling, seasonally corrected fragments are associated with the corresponding baseline spatial fragments of the same collected object according to the anaphoric relationship. Backfilling does not replace the spatial affiliation of the baseline spatial fragments, but adds seasonal anchor points and their time period expression fields under the same object and the same spatial unit, generating standardized fragments with seasonal caliber markers. If the same baseline spatial fragment corresponds to multiple seasonally corrected fragments, multiple standardized fragments are generated according to the collection time period order of the seasonal anchor points, while retaining the same baseline spatial fragment identifier.

[0085] The backfilled spatial segment includes at least the standardized segment identifier, the baseline spatial segment identifier, the object identifier, the spatial unit identifier, the access branch identifier, the seasonal anchor point identifier, the spatial expression field, the time period expression field, the original record identifier, and the backfill status. The backfill status is used to mark whether the seasonally corrected segment has been backfilled, is pending confirmation, or has not been matched.

[0086] Step S6: Summarize the backfilled spatial fragments to generate a standardized dataset within the boundaries for evaluating healthy communities.

[0087] The standardized dataset within the boundaries is not a direct health score, but rather standardized data for subsequent community health assessments. This setup keeps the focus of protection on data fusion and standardization mechanisms, rather than on the assessment criteria or scoring results.

[0088] Specifically, the system merges backfilled spatial fragments into the corresponding skeleton range according to the access branches in the spatial constraint skeleton. The merging process is performed according to the spatial relationship between the acquisition location of the spatial fragment and the access branch. Spatial fragments located within the service range of the same access branch are merged into the skeleton range corresponding to that access branch.

[0089] The system performs boundary splitting on spatial segments that span both inside and outside the skeleton, retaining only the segments within the skeleton. Boundary splitting ensures that only data affected by the spatial action of the micro-update object enters the normalized dataset, preventing data outside the skeleton from being mistakenly identified as the result of the micro-update object.

[0090] For records that span both inside and outside the skeleton area, the system performs boundary processing according to record type: For activity trajectory records, the trajectory segments that intersect with the skeleton area are retained, and fragment values ​​are generated according to the length of the intersecting trajectory segments or the duration of stay; For spatial unit records, spatial units with an overlap area ratio greater than zero are retained, and the area or coverage fields are converted according to the overlap area ratio, while the category field retains its original value and records the overlap ratio; For questionnaire records, the record is retained only if the questionnaire text or collection location can point to a spatial unit within the skeleton area, and questionnaire records that cannot point to a spatial unit are entered into the pending confirmation set.

[0091] Finally, the system rearranges the retained fragment content according to the collection object, seasonal anchor point, and spatial unit to generate a standardized dataset within the boundary.

[0092] The standardized dataset within the boundary has the following structural characteristics: (1) Each record corresponds to a standardized expression of a collection object within a specific spatial unit under a specific seasonal anchor point; (2) Each record contains both the spatial representation of the baseline copy and the temporal representation of the drift copy, so that the record reflects both the spatial role of the micro-updated object and the influence of seasonal factors. (3) All records are located within the spatial constraint skeleton to ensure that the data corresponding to the records is affected by the spatial effect of the micro-update object; (4) The records are organized according to the hierarchical relationship of the data collection object, seasonal anchor point and spatial unit, which facilitates the subsequent aggregation analysis of the healthy community evaluation by object, season or space.

[0093] This standardized dataset within the boundary can be called by the subsequent Healthy Community Assessment module to analyze the impact of micro-update objects on residents' activities, spatial accessibility, and health perception, and to support consistent representation across different collection seasons and data sources.

[0094] Example 2: Specific Application Scenarios Taking the micro-renewal of a pocket park in an old community in a cold-region city as an example, the pocket park is located between two residential buildings. The renewal includes repairing the pedestrian entrance, adding fitness equipment, improving lighting, and updating paving. The system uses this pocket park as the object of community micro-renewal and obtains spatial records, activity records, and perception records for different seasons before and after the renewal.

[0095] The system first retrieves multi-source records. Multi-source records include: Remote sensing image interpretation results: Green cover and paving type records obtained from UAV image interpretation in the summer of 20X4 and the winter of 20X5. The data collection locations were pocket parks and a 50-meter radius around them. The data collection objects were spatial units, and the source format was raster image. GIS spatial records: Vector data of community road network, building outlines, and pocket park boundaries. The data was collected within the community area, and the collected objects are spatial features. The source format is Shapefile vector. Resident activity records: Resident walking trajectory data from June 20X4 to February 20X5, collected within a 200-meter radius of the pocket park, collected from activity trajectory numbers, and sourced from GPS trajectory logs; On-site measurement records: Illuminance measurement records for July, October 20X4 and January 20X5, collected from 5 measuring points in the pocket park, with the measuring point numbers as the data source, and the data source format being an Excel spreadsheet; Questionnaire perception record: Resident satisfaction questionnaires from August 20X4 and January 20X5, collected from residents around the pocket park, with questionnaire numbers as the data source, and online questionnaire JSON data.

[0096] Each record carries four basic identifiers: collection time period, collection location, collection object, and source format.

[0097] In this application scenario, the UAV image interpretation results are written into object status segments according to the acquisition time period and spatial unit. Green cover and paving type are used as spatial expression fields, and the image acquisition season is used as time period expression fields. The GIS road network and pocket park boundaries are used to generate spatial constraint skeletons and are not used as seasonal expression fields. POI records are written into spatial expression fields according to facility location and facility type. Illuminance measurement, temperature, snow depth and sunshine duration are written into time period expression fields according to the acquisition time period, and the measurement point number or path environment segment identifier is retained as spatial reference.

[0098] The system then acquires continuous environmental records for the area, including temperature, snow depth, and sunshine duration data recorded by weather stations. The system then segments these continuous environmental records into environmental segments based on accessibility between community roads, public spaces, and pocket parks.

[0099] For example, for a path from a building entrance to a pocket park, the system identifies three access nodes: the building entrance, the road intersection, and the park entrance. The system groups the temperature and snow accumulation records at the building entrance into a node environment segment; the road snow accumulation and slippery surface records between the building entrance and the road intersection into a path environment segment; the road snow accumulation and shading conditions records between the road intersection and the park entrance into another path environment segment; and the snow accumulation and lighting records at the park entrance into a node environment segment. The system connects these node environment segments and path environment segments according to the order of access to obtain an environmental fragment.

[0100] The system sequentially stitches together environmental segments within the same data collection period to form seasonal segments. For example, the seasonal segment corresponding to the data collection period in July 20X4 includes information such as "temperature 25-30℃, no snow accumulation, ample sunshine, and smooth road traffic"; the seasonal segment corresponding to the data collection period in January 20X5 includes information such as "temperature -15 to -5℃, snow accumulation 5-10cm, shortened sunshine duration, and slippery road sections". The system then links these seasonal segments to their corresponding data collection periods to create seasonal anchor points.

[0101] The system uses pocket parks as a guide to connect multi-source records of the same object at different seasonal anchor points into a seasonal sequence of the object.

[0102] For example, for the walking record of resident with activity trajectory number A001, the system identified that this trajectory passed around the pocket park in July, October 20X4, and January 20X5. The system concatenates these three records according to seasonal anchor points to form the object's seasonal sequence "A001-Summer-Autumn-Winter". This sequence shows that A001 passed through the pocket park 3 times a week in summer, 2 times a week in autumn, and 0.5 times a week in winter, indicating that seasonal changes affect the frequency of the object's activities.

[0103] The system extracts representation offsets along the seasonal sequence of the object. For the seasonal sequence of object A001, the system identifies "activity frequency decreases synchronously with seasonal anchors" as the time-period representation and "passes through the vicinity of the pocket park" as the spatial representation. The system writes the time-period representation "3 times / week in summer, 2 times / week in autumn, and 0.5 times / week in winter" into the drift copy; and the spatial representation "200 meters around the pocket park, walking path passes through the park entrance" into the baseline copy. The system maintains the anaphoric relationship between the two and labels them as originating from the seasonal sequence of object A001.

[0104] Similarly, for the perception record with questionnaire number Q023, the system identified "inconvenience in winter" as a time period expression and "ease of use of pocket parks" as a spatial expression. The system wrote "Winter: inconvenience (snow, cold)" into the drift copy and "pocket park: lighting, paving, fitness equipment" into the baseline copy.

[0105] The system generates a spatial constraint skeleton based on the pocket park's service radius (300 meters), entrance connections, and pedestrian access paths. Using the pocket park's geometric center as the skeleton's center, the system identifies four unit entrances from two surrounding residential buildings as connection nodes. Based on the GIS road network and on-site measured paths, it connects the skeleton center and the connection nodes, forming four access routes. The system incorporates spatial units within the 300-meter service radius that intersect with these access routes into the skeleton's scope, resulting in the spatial constraint skeleton.

[0106] The aforementioned service radius can be pre-configured based on facility type, community scale, or planning specifications; temperature, snow depth, and sunshine duration are derived from meteorological station or on-site measurement records; activity frequency is statistically obtained from residents' walking trajectory logs according to the collection period. The system retains these source identifiers in the standardized segments to facilitate subsequent verification of the formation process of seasonal anchors and expression offsets.

[0107] The system projects the baseline copy onto the spatial constraint skeleton according to the acquisition location. For example, the baseline copy of A001, "200 meters around the pocket park, the walking path passes through the park entrance", is projected onto the access branch 2 and spatial unit U05 in the skeleton to form a baseline spatial segment.

[0108] The system projects drift copies onto a reference space segment according to seasonal anchor points. For example, the drift copy of A001, "3 times / week in summer, 2 times / week in autumn, and 0.5 times / week in winter," is projected onto the reference space segment, forming three seasonally corrected segments. The system then backfills these three seasonally corrected segments into the reference space segment corresponding to A001 according to the anaphoric relationship, so that the backfilled space segment simultaneously contains the spatial attribution of "accessible branch 2, spatial unit U05" and the seasonal expression of "3 times / week in summer, 2 times / week in autumn, and 0.5 times / week in winter."

[0109] The system summarizes the backfilled spatial fragments, merges them according to the access branches of the spatial constraint skeleton, performs boundary splitting on fragments that cross the skeleton range, and finally rearranges them according to the collection object, seasonal anchor point and spatial unit to generate a standardized dataset within the boundary.

[0110] This standardized dataset within the boundary contains standardized representations of various objects collected within the pocket park's service area at different seasonal anchor points; fields such as activity frequency and ease of use retain seasonal variation markers, and its spatial scope is limited to the actual service area of ​​the pocket park. Subsequent healthy community assessments can be aggregated and analyzed by seasonal anchor points, access routes, or spatial units.

[0111] Figure 5 This is a schematic diagram illustrating a specific implementation of a multi-source heterogeneous data fusion and standardization processing system for community micro-updates provided in this invention. The system may include: The multi-source record acquisition module M1 is used to acquire multi-source records corresponding to community micro-update objects. The multi-source records carry the collection time period, collection location, collection object and source format. The seasonal anchor point generation module M2 is used to transcribe continuous environmental records into seasonal anchor points corresponding to the collection period based on the cold-season running trajectory of the area where the community micro-update object is located. The object seasonal sequence construction module M3 is used to connect multiple source records of the same collected object under different seasonal anchor points into an object seasonal sequence, with the community micro-update object as the guide. The drift copy stripping module M4 is used to extract the expression offset caused by the seasonal anchor along the seasonal sequence of the object, and strip the expression offset from the corresponding multi-source record into a drift copy, while retaining the baseline copy that is stably associated with the community micro-update object. The spatial constraint skeleton generation module M5 is used to generate a spatial constraint skeleton based on the service radius, entrance connection relationship and pedestrian access path of the community micro-update object. The fragment projection backfilling module M6 is used to project the reference copy and the drift copy onto the spatial constraint skeleton respectively and perform fragment backfilling, so that the drift copy corrects the expression of the corresponding spatial fragment; The standardized output module M7 is used to summarize the backfilled spatial fragments and generate a standardized dataset within the boundaries for the evaluation of healthy communities.

[0112] The community micro-update multi-source heterogeneous data fusion and standardization processing system of this invention is used to implement the aforementioned community micro-update multi-source heterogeneous data fusion and standardization processing method. Therefore, the specific implementation of the community micro-update multi-source heterogeneous data fusion and standardization processing system can be found in the embodiment section of the community micro-update multi-source heterogeneous data fusion and standardization processing method above. The specific implementation can be referred to the description of the corresponding embodiment, and will not be repeated here.

[0113] The present invention also provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the multi-source heterogeneous data fusion and standardization processing method for community micro-updates described above.

[0114] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the multi-source heterogeneous data fusion and standardization processing method for community micro-updates described above.

[0115] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory, random access memory, portable hard drives, magnetic disks, or optical disks.

[0116] Embodiments of the present invention also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the multi-source heterogeneous data fusion and standardization processing method for community micro-updates.

[0117] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0118] The foregoing has provided a detailed description of the multi-source heterogeneous data fusion and standardization processing method and system for community micro-updates provided by this invention. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and core ideas of this invention. It should be noted that those skilled in the art can make various improvements and modifications to this invention without departing from its principles, and these improvements and modifications also fall within the protection scope of this invention.

Claims

1. A method for fusing and standardizing multi-source heterogeneous data in community micro-updates, characterized in that, include: Obtain the multi-source records corresponding to the community micro-update objects. The multi-source records carry the collection time period, collection location, collection object, and source format. Based on the cold-season movement trajectory of the area where the community micro-update object is located, the continuous environmental records are transcribed into seasonal anchor points corresponding to the collection period; Using the community micro-update object as a guide, multi-source records of the same collected object under different seasonal anchor points are strung together to form an object seasonal sequence; The expression shift caused by the seasonal anchor is extracted along the seasonal sequence of the object, and the expression shift is stripped from the corresponding multi-source record into a drift copy, while the baseline copy that is stably associated with the community micro-update object is retained. A spatial constraint skeleton is generated based on the service radius, entrance connection relationship and walking access path of the community micro-update object. The baseline copy and the drift copy are projected onto the spatial constraint skeleton and the fragments are backfilled so that the drift copy corrects the expression of the corresponding spatial fragment. The backfilled spatial fragments are aggregated to generate a standardized dataset within the boundaries for evaluating healthy communities.

2. The method according to claim 1, characterized in that, The step of transcribing continuous environmental records into seasonal anchor points corresponding to the collection period based on the cold-season movement trajectory of the community micro-update object's location includes: Based on the accessibility relationships between community roads, public spaces, and micro-renewal facilities, the continuous environmental record is divided into environmental segments corresponding to the accessibility processes of residents' activities; Environmental segments within the same data collection period are sequentially spliced ​​together to form seasonal segments that reflect the impact of cold seasons on community usage. By attaching the seasonal segments to the corresponding collection periods, the multi-source records acquire a unified seasonal anchor point before entering the seasonal sequence of the object.

3. The method according to claim 1, characterized in that, The process of extracting the expression shift caused by the seasonal anchor along the seasonal sequence of the object, and stripping the expression shift from the corresponding multi-source record into a drift copy, while retaining the baseline copy stably associated with the community micro-update object, includes: According to the sequential relationship of the same collected object in the seasonal sequence of the object, multi-source records with different source formats are transcribed into object state fragments; In the object state fragment, the time period representation brought in by the seasonal anchor and the spatial representation brought in by the community micro-update object are separated; The time period representation is written into the drift copy, the spatial representation is written into the base copy, and the object correspondence between the drift copy and the base copy is maintained, so that the subsequent spatial constraint skeleton can perform piecewise backfilling on the same collected object.

4. The method according to claim 2, characterized in that, The continuous environmental record is divided into environmental segments corresponding to residents' accessibility processes, based on the accessibility relationships between community roads, public spaces, and micro-renewal facilities. These segments include: Using the community access node corresponding to the collection location as the starting point for segmentation, the continuous environmental records are divided along the arrival order of residents from the residential entrance to the micro-renewal facilities; Group environment records within the same arrival order into node environment segments, and group environment records between adjacent passing nodes into path environment segments. By connecting the node environment segment and the path environment segment according to the order of passage, an environmental segment corresponding to the reachability process of residents' activities is obtained.

5. The method according to claim 1, characterized in that, The process of using the community micro-update object as a guide to connect multiple source records of the same collected object at different seasonal anchor points into an object seasonal sequence includes: Extract the object identifier and location attribution relationship corresponding to the same collected object from the multi-source records; Multiple source records with the same object identifier and whose location affiliation points to the same community micro-update object are grouped into the same object cluster; Based on the chronological relationship of the seasonal anchor points during the collection period, the multi-source records within the object cluster are sequentially connected to form the object seasonal sequence.

6. The method according to claim 3, characterized in that, The separation of the time-period representation brought in by the seasonal anchor and the spatial representation brought in by the community micro-update object in the object state fragment includes: Extract object state segments of the same collected object at adjacent seasonal anchor points along the seasonal sequence of the object; Content that changes synchronously with seasonal anchor points is categorized into time-period expression, while content that remains consistent with the collection location and micro-update object service relationship is categorized into spatial expression. After writing to the drift copy and the base copy respectively, the retracement relationship between the two and the same object state fragment is preserved.

7. The method according to claim 1, characterized in that, The process of generating a spatial constraint skeleton based on the service radius, entrance connection relationships, and pedestrian access paths of the community micro-update object includes: Using the location of the community micro-renewal object as the skeleton center, the connection nodes for residents to enter the service area of ​​the community micro-renewal object are determined along the entrance connection relationship; Connect the skeleton center and the connecting node according to the pedestrian access path to form access branches; The spatial units that intersect with the access branch within the service radius are incorporated into the skeleton range to obtain the spatial constraint skeleton.

8. The method according to claim 7, characterized in that, The step of projecting the baseline copy and the drift copy onto the spatial constraint skeleton and performing fragment backfilling includes: The reference copy is projected onto the spatial unit in the spatial constraint skeleton according to the acquisition location to form a reference spatial segment; The drifted copy is projected onto the reference space segment according to the corresponding seasonal anchor point to form a seasonally corrected segment; The seasonal correction fragments are backfilled into the baseline spatial fragments corresponding to the same collected object according to the anaphoric relationship, so that the backfilled spatial fragments retain both the spatial affiliation of the micro-updated object and the cold-region seasonal expression.

9. The method according to claim 8, characterized in that, The summarized and backfilled spatial fragments generate a standardized dataset within the boundaries for healthy community assessment, including: According to the accessible branches in the spatial constraint skeleton, the backfilled spatial fragments are merged into the corresponding skeleton range; Boundary splitting is performed on backfilled spatial segments that cross the skeleton area, while retaining the content of segments within the skeleton area; The retained fragments are rearranged according to the collection object, seasonal anchor point, and spatial unit to generate a standardized dataset within the boundary.

10. A multi-source heterogeneous data fusion and standardization processing system for community micro-updates, characterized in that, include: The multi-source record acquisition module is used to acquire multi-source records corresponding to community micro-update objects. The multi-source records carry the collection time period, collection location, collection object, and source format. The seasonal anchor point generation module is used to transcribe continuous environmental records into seasonal anchor points corresponding to the collection period based on the cold-season running trajectory of the area where the community micro-update object is located. The object seasonal sequence construction module is used to connect multiple source records of the same collected object under different seasonal anchor points into an object seasonal sequence, with the community micro-update object as the guide. The drift copy stripping module is used to extract the expression offset caused by the seasonal anchor along the seasonal sequence of the object, and strip the expression offset from the corresponding multi-source record into a drift copy, while retaining the baseline copy that is stably associated with the community micro-update object; The spatial constraint skeleton generation module is used to generate a spatial constraint skeleton based on the service radius, entrance connection relationship and pedestrian access path of the community micro-update object; The fragment projection backfilling module is used to project the reference copy and the drift copy onto the spatial constraint skeleton respectively and perform fragment backfilling, so that the drift copy corrects the expression of the corresponding spatial fragment; The standardized output module is used to summarize the backfilled spatial fragments and generate a standardized dataset within the boundaries for the evaluation of healthy communities.

Images