Urban and rural road traffic situation identification method and device, medium and equipment

Abstract

The invention discloses an urban and rural road traffic situation identification method and device, a medium and equipment, relates to the technical field of data processing, can be applied to financial science and technology business scenarios, and comprises the following steps: dividing urban and rural global road grids according to administrative division POI information, and calibrating geographic reference point locations for the road grids; calling geographic reference point locations between any two road grids to construct passage paths, and collecting multi-dimensional traffic situation characterization factors of the passage paths according to preset date types and time segment dimensions; based on a preset date type weight system and a preset time period weight system, performing weighted aggregation on the multi-dimensional traffic situation characterization factors to obtain a comprehensive traffic situation index of each road grid; and generating a target comprehensive traffic situation index associated with the travel characteristics of the target object according to the comprehensive traffic situation index of the road grid matched with the travel associated point location of the target object. According to the invention, accurate identification of urban and rural road traffic situations can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a method and device for identifying a traffic situation of an urban and rural road, a medium and equipment. BACKGROUND

[0002] In the application scenarios of road traffic management, public safety risk assessment, and financial technology, accurate identification of the traffic situation of a road is a core prerequisite for realizing the value of multiple businesses. With the continuous expansion of the traffic network and the acceleration of the integration of urban and rural areas, the scale, frequency, and complexity of the traffic situation of urban and rural roads (including ordinary municipal roads and township roads) have significantly increased. The dynamic changes in the traffic situation of urban and rural roads not only affect the efficiency of regional traffic operation, but also directly affect the risk pricing accuracy of businesses related to travel risks such as car insurance pricing in the field of financial technology. Therefore, higher requirements are placed on the coverage, data availability, real-time performance, and evaluation accuracy of traffic situation identification technology.

[0003] In the prior art, the identification of the traffic situation of a road mainly relies on data collected by special monitoring equipment such as ETC card readers and gantries on expressways. This technical solution can accurately capture key situation indicators such as traffic speed and flow on expressways, thereby enabling effective analysis and judgment of the risk of expressway travel. This technology has formed a mature application system in the field of expressway traffic management and risk assessment, and its data collection stability and professionalism have been verified by the industry.

[0004] However, since the layout range of the monitoring equipment on expressways is limited to the expressway network, it cannot be extended to urban and rural road scenarios such as ordinary municipal roads and township roads, making it difficult to effectively capture key situation information such as traffic congestion and slow traffic on urban and rural roads. At the same time, due to the high level of user authorization, strong privacy sensitivity, and high commercial acquisition cost of some navigation data that can cover urban and rural roads, it is difficult to achieve large-scale and low-cost application, ultimately making it impossible for the existing technology to form a complete identification of the traffic situation of the entire road network and meet the application needs of multiple fields for urban and rural road situation data. SUMMARY

[0005] Therefore, the present application provides a method and device for identifying the traffic situation of an urban and rural road, which can accurately identify the traffic situation of an urban and rural road.

[0006] According to a first aspect of the present application, a method for identifying the traffic situation of an urban and rural road is provided, comprising: According to the administrative division POI information, the spatial division of the urban and rural road grid is performed according to a preset administrative region granularity, and a geographic reference point is labeled for each road grid to construct a global road grid spatial index. Based on the global road grid spatial index, the geographic reference points between any two road grids are retrieved, and a travel path is constructed. According to the preset date type and time period dimension, the public navigation service interface is called to collect multi-dimensional traffic situation characterization factors for each travel path. Based on the preset date type weighting system and time period weighting system, a spatiotemporal cross-weighting unit is constructed to weight and aggregate the multi-dimensional traffic situation characterization factors to obtain the comprehensive traffic situation index of each road grid. The travel-related points of the target object are matched to the corresponding road grid. Based on the comprehensive traffic situation index of the matched road grid, a target comprehensive traffic situation index associated with the travel characteristics of the target object is generated.

[0007] According to a second aspect of this application, a device for identifying urban and rural road traffic conditions is provided, comprising: The module is used to spatially divide the urban and rural road grid according to the preset administrative region granularity based on the POI information of administrative divisions, and to mark the geographical reference points for each road grid to build a spatial index of the entire road grid. The data acquisition module is used to retrieve the geographic reference points between any two road grids based on the global road grid spatial index, construct travel routes, and collect multi-dimensional traffic situation characterization factors for each travel route by calling the public navigation service interface according to the preset date type and time dimension. The aggregation module is used to construct a spatiotemporal cross-weighted unit based on a preset date type weighting system and time period weighting system, and to perform weighted aggregation on the multi-dimensional traffic situation characterization factors to obtain the comprehensive traffic situation index of each road grid. The generation module is used to match the travel-related points of the target object to the corresponding road grid, and generate a target comprehensive traffic situation index associated with the travel characteristics of the target object based on the comprehensive traffic situation index of the matched road grid.

[0008] According to a third aspect of this application, a storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the above-described method for identifying urban and rural road traffic conditions.

[0009] According to a fourth aspect of this application, an electronic device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-described method for identifying urban and rural road traffic conditions.

[0010] By employing the aforementioned technical solutions, the method, apparatus, medium, and equipment for identifying urban and rural road traffic conditions provided in this application, firstly, by dividing urban and rural road networks into grids based on administrative division-type POI information at a preset administrative granularity and marking geographic reference points, and constructing a spatial index for the entire road network, this approach breaks through the limitations of existing technologies that rely on the deployment of dedicated monitoring equipment for highways. It extends the scope of traffic condition identification from highway networks to ordinary municipal roads, township roads, and other urban and rural road networks, providing a unified and accurate spatial foundation for the collection and association of traffic condition data across the entire region, effectively solving the problem of missing urban and rural road condition information. Secondly, by retrieving grid geographic reference points based on this spatial index to construct travel routes, and by calling public navigation service interfaces according to date type and time segment dimension to collect multi-dimensional traffic condition characterization factors, this approach avoids the drawbacks of existing navigation data covering urban and rural roads, such as high user authorization levels, strong privacy sensitivity, and high commercial acquisition costs. Large-scale, low-cost, and multi-temporal traffic situation data collection ensures data availability and feasibility for widespread application. Furthermore, by constructing spatiotemporal cross-weighted units through a pre-defined date type weighting system and time period weighting system, multi-dimensional traffic situation characterization factors are weighted and aggregated to generate a comprehensive traffic situation index for each road grid. This accurately quantifies the differences in traffic situation across different date types and time periods, making traffic situation assessments more aligned with actual road network operation patterns and improving the accuracy of situation assessments. Finally, the travel-related points of the target object are matched to the corresponding road grid, and a target comprehensive traffic situation index associated with the travel characteristics of the target object is generated based on the comprehensive traffic situation index. This enables precise mapping of the entire traffic situation from the grid level to the individual level, not only fully covering the traffic situation identification needs of the entire road network but also accurately adapting to application scenarios such as differentiated pricing for auto insurance and credit risk control in the fintech field, providing high-quality traffic situation data support for cross-domain decision-making.

[0011] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a method for identifying urban and rural road traffic conditions according to an embodiment of this application is shown. Figure 2 A flowchart illustrating a method for identifying urban and rural road traffic conditions according to another embodiment of this application is shown. Figure 3 A schematic diagram of the structure of an urban and rural road traffic situation identification device provided in an embodiment of this application is shown. Detailed Implementation

[0013] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0014] In existing technologies, road traffic situation recognition mainly relies on data collected by dedicated monitoring equipment such as ETC checkpoints and gantries on highways for analysis. This technical solution can accurately capture core situation indicators such as vehicle speed and traffic volume within the highway area, thereby achieving effective assessment of highway traffic risks. This type of technology has formed a mature application system in highway traffic management and risk assessment scenarios, and its data collection stability and professionalism have been verified by the industry.

[0015] However, because the deployment range of highway monitoring equipment is limited to the highway network and cannot be extended to ordinary municipal roads, rural roads, and other urban and rural road scenarios, key situational information such as traffic congestion and slow traffic on urban and rural roads is difficult to capture effectively. At the same time, some navigation data that can cover urban and rural roads are difficult to promote and apply on a large scale and at low cost due to issues such as high user authorization levels, strong privacy sensitivity, and high commercial acquisition costs. Ultimately, existing technologies cannot form a complete identification of the traffic situation of the entire road network and cannot meet the application needs of multiple fields for urban and rural road situational data.

[0016] To address the aforementioned technical problems, embodiments of the present invention provide a method for identifying urban and rural road traffic conditions, such as... Figure 1 As shown, the method includes: Step 110: Based on the POI information of administrative divisions, divide the urban and rural road grid into spatial grids according to the preset administrative region granularity, mark the geographical reference points for each road grid, and construct a spatial index of the entire road grid.

[0017] Among them, administrative division POI information refers to geographic information data containing different administrative levels (such as provinces, cities, districts / counties, streets / townships), covering core attributes such as administrative region boundary vectors, administrative location coordinates, and jurisdiction labels, which is the basic data support for dividing road grids; the preset administrative region granularity refers to the road grid division level standard pre-set according to business scenario needs, usually including street / township level, district / county level, etc., to match the situation recognition needs of different precision; the urban and rural whole-area road grid refers to the spatial units formed by dividing all roads within the city and township areas into a unified spatial framework according to the preset administrative region granularity, which are non-overlapping and fully covered, and are the basic carrier for traffic situation data collection and aggregation; the geographic reference point refers to the core anchor point coordinates marked for each road grid, usually selecting representative points such as the regional geometric center, core road network hubs or administrative locations, for the spatial positioning and association of grids; the whole-area road grid spatial index refers to the established association retrieval system containing attributes such as spatial coordinates, administrative affiliation, and geographic reference points of each road grid, which can realize the rapid retrieval of grid information and efficient matching of spatial relationships.

[0018] In this embodiment of the disclosure, administrative division-type POI information can be used as the data base. First, the preset administrative region granularity (such as street / township level) is determined according to the situation recognition accuracy required by the business. Then, based on this granularity, the roads in the entire urban and rural area are divided into a fully covered, non-overlapping road grid according to the administrative boundaries and road network distribution characteristics. Subsequently, the regional geometric center or core road network hub is selected as the geographic reference point for each road grid to clarify its spatial anchor point. Finally, by establishing the association mapping between the grid and the reference point, administrative affiliation and other attributes, a spatial index of the entire road grid that can support fast retrieval and attribute retrieval is constructed, providing a unified spatial foundation for the subsequent collection, aggregation and matching of traffic situation data.

[0019] This technical step, by using administrative division-based POI information as a basis and dividing urban and rural roads into grids at a preset granularity, breaks through the limitation of existing technologies that only cover highways, achieving full spatial coverage of the entire road network, including ordinary municipal roads and township roads. At the same time, the calibration of geographic reference points can provide precise spatial positioning anchors for the grid, and the construction of the spatial index of the entire road grid can establish an efficient attribute association and retrieval mechanism. This not only solves the problem of the lack of a unified spatial carrier for urban and rural road situation identification, but also ensures the targeting, aggregation accuracy, and matching efficiency of subsequent traffic situation data collection, laying a core spatial foundation for the complete identification of the entire traffic situation.

[0020] Step 120: Based on the global road grid spatial index, retrieve the geographic reference points between any two road grids and construct the travel path. According to the preset date type and time dimension, call the public navigation service interface to collect the multi-dimensional traffic situation characterization factors of each travel path.

[0021] Among them, the travel path refers to the actual road network route connecting two grids, formed by pairing up any two geographical reference points of the road grids, and is the specific carrier of traffic situation data collection; the preset date type and time period dimension refer to the time classification standards pre-divided according to traffic travel patterns, where the date type usually includes weekdays and non-weekdays, and the time period dimension refers to dividing the whole day into multiple monitoring intervals such as peak, off-peak, and early morning, forming a multi-temporal and spatial collection dimension; the public navigation service interface refers to the road network data interface opened by the map service provider and publicly callable, which has the characteristics of low cost and large-scale access, and can obtain relevant data on the route traffic status without the need for high-level user authorization; the multi-dimensional traffic situation characterization factor refers to the core indicators that can reflect the route traffic status, which may include the proportion of congested road sections, the proportion of slow-moving road sections, the proportion of unobstructed road sections, the proportion of unknown road sections, etc., used to comprehensively depict the characteristics of traffic situation.

[0022] In this embodiment of the disclosure, the geographic reference point coordinates of all road grids within the urban and rural areas can be quickly retrieved based on a pre-constructed global road grid spatial index. The geographic reference points of any two grids are paired as start and end points to construct a set of travel routes covering the entire road network. Then, according to the pre-set weekday / non-weekday date type and peak, off-peak, and early morning time periods, the public navigation service interface is called in batches to collect multi-dimensional traffic situation characterization factors such as the proportion of congested road sections, slow-moving road sections, unobstructed road sections, and unknown road sections of each travel route under different spatiotemporal dimensions, forming a structured multi-spatiotemporal traffic situation basic dataset.

[0023] This technical approach, by constructing travel routes based on a comprehensive road grid spatial index, ensures that traffic situation data collection covers the entire urban and rural road network, effectively overcoming the limitations of existing technologies that are only limited to highways. Simultaneously, by using public navigation service interfaces to collect data, it avoids the drawbacks of traditional navigation data, such as high authorization thresholds, strong privacy sensitivity, and high acquisition costs, enabling large-scale, low-cost traffic situation data collection. Furthermore, through precise division of date type and time period dimensions, it ensures the integrity of the collected data across multiple spatiotemporal dimensions, providing comprehensive and high-quality basic data support for subsequent weighted aggregation to generate accurate traffic situation indices.

[0024] Step 130: Based on the preset date type weight system and time period weight system, construct a spatiotemporal cross-weight unit, and perform weighted aggregation of multi-dimensional traffic situation characterization factors to obtain the comprehensive traffic situation index of each road grid.

[0025] The preset date type weighting system refers to a set of weights pre-set based on regional traffic flow patterns and business needs, used to quantify the importance of traffic conditions on different date types (weekdays / weekdays). The total weight value is 1, reflecting the degree of influence of different date types on the overall traffic situation. The time period weighting system refers to a set of weights pre-set based on regional traffic peak characteristics and travel patterns, used to quantify the importance of traffic conditions on different time periods (such as morning peak, off-peak, evening peak, and early morning). The total weight value is 1, reflecting the impact of traffic condition differences on the overall assessment. The spatiotemporal cross-weighting unit refers to the product operation of a single weight in the date type weighting system and a single weight in the time period weighting system. The resulting "date type + time period" combined weight unit is used to accurately quantify the weight ratio of traffic situation under specific spatiotemporal dimensions; weighted aggregation refers to the accumulation of multi-dimensional traffic situation characterization factors for each road grid by combining the weight values ​​of spatiotemporal cross-weight units through the calculation method of "factor value × unit weight", thereby realizing the integrated processing of multi-spatiotemporal dimension factor data; the comprehensive traffic situation index is a standardized index that can comprehensively reflect the traffic operation status (congestion, slow traffic, smooth traffic) of a single road grid under all spatiotemporal dimensions after normalization processing by weighted aggregation of multi-dimensional traffic situation characterization factors. The value range is usually 0-100 or 0-1, which is convenient for intuitively assessing the grid traffic situation level.

[0026] In this embodiment of the disclosure, a date type weighting system including weekday and non-weekday weights and a time period weighting system covering peak, off-peak, and early morning periods can be preset based on regional traffic flow patterns and business scenario requirements. By multiplying the individual weights in the two weighting systems one by one, a set of spatiotemporal cross-weighting units corresponding to "date type + time period" can be constructed. Then, for each road grid, multi-dimensional traffic situation characterization factor data under each spatiotemporal cross-weighting unit is extracted. By calculating the sum of the products of each dimension factor value and the corresponding weight of the spatiotemporal cross-weighting unit, the weighted aggregation of multi-spatiotemporal dimension factor data is completed. Finally, the weighted aggregation results of each dimension factor are normalized to ensure that the sum of the weighted values ​​of each dimension factor is 100%, and finally, a comprehensive traffic situation index that can comprehensively reflect the spatiotemporal traffic situation level of the road grid is obtained.

[0027] This technical process, by pre-setting a date type and time segment weighting system that aligns with actual traffic patterns and business needs, and combining it with the construction logic of spatiotemporal cross-weighting units of "date + time segment," enables differentiated quantification of traffic conditions across different spatiotemporal dimensions, avoiding the distortion caused by single-weight assessments. Simultaneously, through weighted aggregation and normalization of multi-dimensional traffic condition representation factors, it integrates scattered factor data into a standardized comprehensive traffic condition index. This index comprehensively covers core condition characteristics such as congestion and slow traffic, and allows for intuitive comparison and quantitative assessment of traffic conditions across different road grids. This effectively improves the accuracy and scientific rigor of traffic condition assessments, providing standardized and high-value condition data support for subsequent adaptation to individual travel characteristics and multi-domain applications.

[0028] Step 140: Match the travel-related points of the target object to the corresponding road grid, and generate a target comprehensive traffic situation index associated with the travel characteristics of the target object based on the comprehensive traffic situation index of the matched road grid.

[0029] The target entity refers to the subject that needs to obtain personalized traffic situation assessment results, including but not limited to individuals, vehicles, and emergency equipment, whose travel behavior is directly related to business scenarios such as fintech. Travel-related points refer to the authorized location coordinates (such as origin, destination, and waypoints) generated by the target entity during its travel process. The coordinate system is consistent with the road grid spatial index and is the core basis for grid matching. Travel characteristics refer to the personalized travel attributes of the target entity, which may include high-frequency travel periods, preferred date types (weekdays / weekends), and travel frequency distribution. These are the core basis for index adaptation and adjustment. The target comprehensive traffic situation index is an index generated after personalized adaptation based on the comprehensive traffic situation index matched to the road grid of the target entity and its travel characteristics. It can accurately depict the actual traffic situation level faced by the target entity.

[0030] In this embodiment of the disclosure, the authorized travel-related point data of the target object can be obtained first and the coordinate calibration can be completed. The travel-related points can be matched to the corresponding road grid through the spatial retrieval function of the global road grid spatial index. Then, the comprehensive traffic situation index generated by the road grid can be retrieved. Then, combined with the travel characteristics of the target object (such as high-frequency travel time and preferred date type), the comprehensive traffic situation index can be personalized and optimized by adjusting the weight ratio of the corresponding spatiotemporal dimensions. Finally, a target comprehensive traffic situation index that is highly consistent with the actual travel scenario of the target object can be generated.

[0031] This technical step achieves the transformation from a general situation assessment of the entire grid to a personalized situation assessment by accurately matching the travel-related points of the target object with the road grid. This effectively solves the problem that general indices cannot adapt to individual travel differences. At the same time, the index adaptation logic based on travel characteristics allows the target comprehensive traffic situation index to accurately reflect the actual traffic congestion, traffic risks and other conditions faced by the target object. This not only improves the personalization and accuracy of traffic situation assessment, but also provides customized situation data support for cross-domain applications such as risk pricing in fintech scenarios, further expanding the application boundaries of traffic situation recognition technology.

[0032] In summary, the method for identifying urban and rural road traffic conditions provided in this application, by dividing urban and rural road networks into grids based on administrative division-type POI information at a preset administrative granularity, calibrating geographic reference points, and constructing a spatial index for the entire road network, can overcome the limitations of existing technologies that rely on the deployment of dedicated highway monitoring equipment. It extends the identification scope to the entire road network, including ordinary municipal roads and rural roads, providing a unified spatial reference for the collection and association of situational data and solving the problem of missing urban and rural road situational information. Based on this spatial index, it retrieves grid reference points to construct travel routes and calls public navigation service interfaces to collect multi-dimensional situational characterization factors according to date type and time segment dimension. This avoids the high authorization threshold, privacy sensitivity, and high cost associated with traditional navigation data. Despite its high cost, this approach enables large-scale, low-cost, and multi-temporal / spatial situational data collection, ensuring data availability and feasibility for wider application. By constructing spatiotemporal cross-weighted units through a pre-defined weighting system, it weights and aggregates multi-dimensional factors to generate comprehensive traffic situation indices for each grid. This accurately quantifies traffic situation differences across different dates and time periods, improving the accuracy and relevance of situational assessments. By matching the travel-related locations of target individuals to corresponding grids and generating target comprehensive traffic situation indices tailored to their travel characteristics based on the comprehensive index, it achieves precise mapping of the overall situation from the grid level to the individual level. This not only fully covers the needs of comprehensive road network situational identification but also precisely adapts to application scenarios such as fintech, providing high-quality data support for cross-domain decision-making.

[0033] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, and to fully illustrate the implementation of this embodiment, this embodiment also provides another method for identifying urban and rural road traffic conditions, such as... Figure 2 As shown, the method includes: Step 210: Based on the POI information of administrative divisions, divide the urban and rural road grid into spatial grids according to the preset administrative region granularity, mark the geographical reference points for each road grid, and construct a spatial index of the entire road grid.

[0034] For embodiments of this disclosure, step 210 may include the following steps: Step 210-1: Determine the administrative region granularity of the road grid based on business scenario requirements, and extract administrative division POI information within the entire region based on the administrative region granularity.

[0035] For the embodiments disclosed herein, the appropriate administrative region granularity (fine-grained or medium-coarse-grained) of the road grid can be determined based on the core requirements of specific business scenarios such as financial technology (e.g., risk assessment accuracy, resource layout dimensions). Then, using this granularity as a screening criterion, administrative division POI information covering the entire urban and rural area can be extracted from the geographic information data source to ensure that the extracted POI data fully matches the preset administrative level, which can provide a hierarchical and comprehensive geographic data foundation for the subsequent accurate division of the road grid.

[0036] Step 210-2: Based on the administrative division POI information, select the regional geometric center or core road network node as the geographic reference point and define the initial grid boundary of each road grid.

[0037] The initial grid boundary refers to the road grid spatial boundary that is initially delineated based on the geographic reference point as the anchor point and combined with the administrative boundary range in the administrative division POI information. It covers the corresponding administrative region and has no overlap, and is the basic framework for subsequent grid calibration.

[0038] In this embodiment of the disclosure, the boundary range and road network distribution characteristics of each administrative region can be determined based on the extracted POI information of administrative divisions. If the road network distribution of a region is balanced and there are no significant core hubs, the geometric center of the region is calculated as the geographic reference point. If there are core road network nodes such as major road intersections and transportation hubs with prominent functions in the region, the node is selected as the geographic reference point first. Then, the selected geographic reference point is used as the spatial anchor point. Combined with the administrative jurisdiction in the POI information, the initial boundary of the road grid that can completely cover the corresponding administrative region and whose boundaries and administrative affiliations are consistent is initially delineated to form the initial grid framework corresponding to each administrative region.

[0039] Step 210-3: Based on the regional road network distribution data, calibrate the initial grid boundary, correct the deviation between the initial grid boundary and the actual road network topology, and obtain the final grid spatial coordinates of each road grid.

[0040] Among them, regional road network distribution data refers to a set of geographic data containing core information such as road orientation, intersection location, road grade (arterial road / secondary arterial road / local road), road network connectivity, and road mileage within the region. It is the basic data reflecting the actual spatial structure of the road network. Actual road network topology refers to the connection relationship and spatial layout structure between roads and intersections within the region, reflecting the actual traffic logic and spatial distribution characteristics of the road network. Grid spatial coordinates refer to the set of precise geographic coordinates of the boundary vertices of the road grid after calibration. It is the core basis for clarifying the spatial range of the grid and realizing spatial positioning and association.

[0041] In this embodiment of the disclosure, regional road network distribution data including road orientation, intersection distribution, and road network connectivity can be obtained first, and its coordinate system can be uniformly calibrated with the coordinate system of the initial grid boundary. Then, the initial grid boundary layer and the calibrated road network distribution data layer are superimposed and compared to accurately identify the types and locations of deviations that do not conform to the actual road network topology, such as the initial boundary cutting main roads and splitting intersections. Subsequently, differentiated corrections are implemented for different deviations (such as translating the boundary along the road centerline and merging grids to adapt to intersections). Finally, the accurate geographic coordinates of the vertices of each road grid boundary are determined to obtain grid spatial coordinates that conform to the actual road network topology.

[0042] This technical step calibrates the initial grid boundary by introducing regional road network distribution data, which can effectively correct the deviation between the initial boundary and the actual road network topology, ensuring that the road grid range is highly compatible with the road network structure and avoiding the problem of distorted traffic situation data collection caused by unreasonable boundaries. At the same time, the accurate grid spatial coordinates can provide a reliable spatial reference for subsequent route construction and multi-dimensional situation factor collection, ensuring the accuracy of traffic situation identification from a spatial perspective and laying a solid foundation for generating a high-quality comprehensive traffic situation index.

[0043] Step 210-4: Establish attribute associations between each road grid and geographic reference point, and generate a global road grid spatial index containing grid spatial coordinates and administrative affiliation.

[0044] For the embodiments of this disclosure, the geographic reference points corresponding to each road grid can be sorted out first, and a one-to-one mapping relationship between grid ID and reference point code can be established to realize the attribute association between the two. Then, the core attributes such as the accurate grid spatial coordinates, complete administrative affiliation links and associated geographic reference point coordinates of each road grid can be integrated and entered into the index system according to a unified data structure specification. Finally, a full-domain road grid spatial index covering the entire urban and rural area, containing multi-dimensional attributes and supporting efficient retrieval can be constructed.

[0045] Step 220: Batch retrieve the geographic reference point coordinates of all road grids from the global road grid spatial index to form a grid point coordinate library.

[0046] In this embodiment of the disclosure, the existing global road grid spatial index can be used to retrieve the geographic reference point coordinate data corresponding to all road grids in the index at once through its batch data retrieval function. The retrieved data is then format-validated (invalid data with empty coordinates or abnormal format is removed) and the coordinate system is unified (ensuring that all coordinates follow the same geographic coordinate system). The valid coordinate data is then organized and archived according to the preset data storage specifications (such as classification by administrative affiliation and associated grid ID), ultimately forming a grid point coordinate library that covers the entire urban and rural area, is complete in data, and has a unified format.

[0047] Step 230: Pair up the geographic reference points in the grid point coordinate library to generate multiple travel paths between urban and rural road grids.

[0048] For embodiments of this disclosure, the steps may include: based on the administrative affiliation attribute of the global road grid spatial index, dividing the grid point coordinate database into sub-databases for each city according to the city's administrative boundaries; performing pairwise pairing operations on geographic reference points within the sub-databases of each city's grid points to generate intra-city travel routes; filtering the generated intra-city travel routes for validity, removing invalid routes whose path length exceeds a preset length threshold or whose path crosses a restricted area, to obtain the final multiple travel routes.

[0049] Among them, administrative affiliation attribute refers to the administrative jurisdiction level information (such as province-city-district / county) corresponding to the road grid, which is mainly used to define the spatial scope of point pairing; city administrative boundary refers to the geographical boundary that divides the jurisdiction of different cities, which is used to restrict the regional boundary of point pairing and avoid the generation of invalid cross-city paths; grid point sub-database refers to the set of point coordinates of each city after splitting the grid point coordinate database according to the city administrative boundary, which only contains the geographic reference point coordinates of all road grids within the corresponding city; preset length threshold refers to the pre-set upper limit of path length (such as 100km), which is used to eliminate paths that are too long and have no actual traffic demand; restricted area refers to areas that cannot be passed normally due to traffic control, geographical barriers, etc. (such as military management areas, unconnected road sections); invalid path refers to a path whose length exceeds the preset threshold or crosses a restricted area and has no actual traffic value.

[0050] This technical step generates a grid point sub-database by dividing the city into zones according to urban administrative boundaries and pairs them within the sub-database. This avoids the generation of long-distance invalid paths across cities and can significantly reduce the redundant costs of subsequent data collection. At the same time, by setting a length threshold and filtering the validity of restricted areas, paths without practical travel significance can be further eliminated, ensuring the practicality and relevance of the final travel paths. This not only achieves comprehensive coverage of effective travel paths between urban and rural road grids, but also ensures path quality, laying an efficient and reliable foundation for subsequent collection of accurate traffic situation data based on paths.

[0051] Step 240: Based on regional traffic patterns, the date type is divided into two categories: weekdays and non-weekdays, and the whole day is divided into multiple time period monitoring intervals to form a multi-temporal and spatial data collection dimension.

[0052] Among them, regional traffic travel patterns refer to the temporal distribution characteristics of people's travel behavior within a specific region, including the difference in travel flow between weekdays and non-weekdays, and the peak / off-peak distribution of travel at different times throughout the day, which is the core basis for time dimension division; date type refers to the time classification according to traffic travel patterns, which is mainly divided into two categories: weekdays (Monday to Friday, excluding statutory holidays) and non-weekdays (Saturday, Sunday and statutory holidays), reflecting the differences in travel characteristics on different dates; multi-time period monitoring intervals refer to the multiple continuous time segments formed by dividing the 24 hours of the day according to the temporal change characteristics of traffic flow (such as peak, off-peak, and low flow in the early morning), used to accurately capture the traffic situation at different times; multi-temporal and spatial collection dimensions refer to the time dimension system formed by combining date type (weekday / non-weekday) and multi-time period monitoring intervals, which can cover traffic scenarios of all time periods and all date types, providing time division standards for multi-dimensional data collection.

[0053] For the embodiments of this disclosure, the regional traffic patterns can be extracted by analyzing historical traffic flow data and travel behavior statistics within the region, clarifying the differences in travel flow between weekdays and non-weekdays and the distribution of traffic congestion at different times of the day. Based on these patterns, the date type is divided into two categories: weekdays and non-weekdays. Then, combined with the characteristics of concentrated peak hours, smooth off-peak hours, and low traffic flow in the early morning, the 24 hours of the day are divided into multiple differentiated time period monitoring intervals, and finally combined to form a multi-temporal and spatial collection dimension corresponding to the date type and time period monitoring interval.

[0054] For example, a provincial capital city analyzed regional traffic patterns over the past six months and found that weekday commuting peaks were 7-9 am and 5-7 pm, while non-weekday traffic was high but without a significant peak between 10 am and 4 pm. Based on this, the city categorized dates into weekdays and non-weekdays and divided the day into seven monitoring intervals: morning peak (7-9 am), morning off-peak (9-12 am), midday (12-2 pm), afternoon off-peak (2-5 pm), evening peak (5-7 pm), nighttime (7-11 pm), and early morning (11 pm - 7 am the next day). This resulted in 14 multi-temporal and spatial data collection dimensions (such as "weekday - morning peak" and "non-weekday - afternoon off-peak"). Subsequently, traffic situation data for each route can be accurately collected according to these dimensions under different time scenarios.

[0055] This technical step divides the time dimension based on regional traffic patterns, ensuring that the date type and time period monitoring interval are consistent with actual travel characteristics and avoiding the problem of time dimension being out of sync with traffic situation caused by subjective division. At the same time, the multi-temporal and spatial collection dimensions can comprehensively cover traffic status under different time scenarios, which can support the subsequent batch collection of traffic situation data according to multiple temporal and spatial dimensions, ensuring the temporal integrity and relevance of the collected data, and laying a scientific temporal dimension foundation for the subsequent construction of spatiotemporal cross-weighted units and accurate weighted aggregation of traffic situation factors.

[0056] Step 250: Batch call the public navigation service interface according to multiple spatiotemporal collection dimensions to collect multi-dimensional traffic situation representation factors for each travel path, including the proportion of congested road sections, slow-moving road sections, unobstructed road sections, and unknown road sections.

[0057] Among them, the multi-dimensional traffic situation characterization factor refers to the core quantitative indicators that can comprehensively reflect the traffic status of the travel route. Specifically, it can include the proportion of congested road sections (mileage of congested road sections / total mileage of the route), the proportion of slow-moving road sections (mileage of slow-moving road sections / total mileage of the route), the proportion of unobstructed road sections (mileage of unobstructed road sections / total mileage of the route), and the proportion of unknown road sections (mileage of road sections with unclear status / total mileage of the route). The sum of the four types of factors is 100%.

[0058] In this embodiment of the disclosure, the public navigation service interface can be called in batches through a programmatic manner according to the pre-constructed multi-temporal and spatiotemporal acquisition dimensions. The coordinates of the start and end points of each valid travel path and the corresponding temporal and spatiotemporal dimension parameters are passed to the interface to obtain the real-time road network traffic status data of each path in different temporal and spatiotemporal scenarios. The data is parsed and calculated to obtain the proportion of congested road sections, slow-moving road sections, unobstructed road sections, and unknown road sections for each path. Finally, a multi-dimensional traffic situation characterization factor dataset covering the entire temporal and spatiotemporal dimension and the entire travel path is formed.

[0059] This technical step, by calling public navigation service interfaces in batches, can avoid the drawbacks of traditional dedicated monitoring equipment having limited coverage, high barriers to authorization of private navigation data, and high costs, while also enabling large-scale, low-cost collection of traffic situation data. At the same time, by collecting multi-dimensional characterization factors in multiple time and space dimensions, it can ensure the temporal integrity of the data and the comprehensiveness of the situation description, accurately capturing the differences in traffic situation on different dates and at different times.

[0060] Step 260: Based on the preset date type weight system and time period weight system, construct a spatiotemporal cross-weight unit, and weight and aggregate the multi-dimensional traffic situation characterization factors to obtain the comprehensive traffic situation index of each road grid.

[0061] For embodiments of this disclosure, step 260 may include the following steps: Step 260-1: Based on regional traffic flow patterns and business scenario requirements, set the basic weight for date type and the differentiated weight for time period.

[0062] Among them, regional traffic flow patterns refer to the inherent characteristics of traffic flow changes over time within a specific region, including differences in traffic distribution between weekdays and non-weekdays, and the distribution of peak and trough traffic flows at different times of the day (peak / off-peak / early morning), which serve as the objective data basis for weight setting; business scenario requirements refer to the core demands of application fields such as fintech for traffic situation assessment (e.g., car insurance pricing needs to focus on commuting time risks, and emergency services need to focus on traffic efficiency), which serve as the application guidance basis for weight setting; date type basic weight refers to the set of weights used to quantify the importance of traffic situation on weekdays and non-weekdays, with a total weight value of 1, reflecting the degree of influence of different date types on the overall traffic situation assessment; time period differentiation weight refers to the set of weights used to distinguish the importance of traffic situation at different times of the day, with a total weight value of 1, reflecting the differentiated contribution of traffic characteristics at different times to the assessment results.

[0063] For the embodiments disclosed herein, historical traffic flow monitoring data within the region can be analyzed first to extract regional traffic flow patterns such as the proportion of traffic flow on weekdays and non-working days, and the degree of traffic concentration in each time period. Then, combined with the core requirements of specific business scenarios, a weight allocation scheme that can balance objective laws and application needs can be comprehensively determined. Basic weights for date types corresponding to weekdays and non-working days are set separately, as well as time-differentiated weights for each time period such as morning peak, off-peak, evening peak, and early morning, forming a dual weight system that both conforms to the actual road network operation characteristics and adapts to business application scenarios.

[0064] For example, a city implementing differentiated pricing for auto insurance found that weekday traffic flow accounts for 70% of the total weekly traffic flow, with morning peak (7-9 am) and evening peak (5-7 pm) accounting for 25% and 23% of the daily peak flow, respectively. Considering the core need for accurate risk assessment of commuting in auto insurance, the city set a basic weighting for date type as 0.7 for weekdays and 0.3 for non-weekdays, and a differentiated weighting for time period as 0.25 for morning peak, 0.25 for evening peak, 0.4 for off-peak hours (9-5 pm, 7-11 pm), and 0.1 for early morning hours (11 pm-7 am the next day), thus forming a weighting system adapted to auto insurance risk assessment scenarios.

[0065] This technical step uses regional traffic flow patterns as an objective basis for weight setting, ensuring that the weight allocation conforms to the actual operating status of the road network and avoiding evaluation bias caused by subjective settings. At the same time, it optimizes the weight allocation in combination with business scenario requirements, enabling the weight system to accurately match the core demands of cross-domain applications. It can not only achieve differentiated quantification of the importance of traffic conditions on different dates and at different times, but also provide a scientific weight foundation for the subsequent construction of spatiotemporal cross-weighted units and the generation of accurate comprehensive traffic condition indices, effectively improving the adaptability of traffic condition assessment to business applications.

[0066] Step 260-2: Multiply the basic weight of the date type with the differentiated weight of the corresponding time period to generate the spatiotemporal cross-weight unit for each date type and time period combination.

[0067] In this embodiment of the disclosure, a pre-defined basic weight for date type (working day, non-working day) and a corresponding time period differential weight (morning peak, off-peak, evening peak, early morning, etc.) can be defined. For all pairwise combinations formed by each date type and each time period, the basic weight corresponding to the date type and the differential weight corresponding to the time period in each combination are multiplied one by one. Through this operation, the weights of the date dimension and the time period dimension are merged, and finally a set of spatiotemporal cross-weight units covering all date-time period combinations and with a total weight of 1 is generated.

[0068] For example, following the weight settings for differentiated pricing of auto insurance in step 260-1 (basic weight for date type: weekdays 0.7, non-working days 0.3; differentiated weight for time period: morning peak 0.25, evening peak 0.25, off-peak 0.4, early morning 0.1), the basic weight for each date type is multiplied by the corresponding differentiated weights for all time periods to generate 8 spatiotemporal cross-weight units: weekday-morning peak (0.7 × 0.25 = 0.175), weekday-evening peak (0.7 × 0.25 = 0.1), etc. 75) Weekday - Off-peak (0.7×0.4=0.28), Weekday - Early morning (0.7×0.1=0.07), Non-working day - Morning peak (0.3×0.25=0.075), Non-working day - Evening peak (0.3×0.25=0.075), Non-working day - Off-peak (0.3×0.4=0.12), Non-working day - Early morning (0.3×0.1=0.03), the total weight of all units is 1, forming a spatiotemporal cross-weighted unit set adapted to the commuting risk assessment of auto insurance business.

[0069] This technical step generates spatiotemporal cross-weighted units by multiplying the basic weight of date type with the differentiated weight of time period. This enables deep integration of the weights of the date and time periods, accurately quantifying the importance of traffic conditions for specific "date-time period" combinations. It avoids the drawback of single-dimensional weights failing to reflect the spatiotemporal synergistic effects. At the same time, the sum of the weights of all cross-units remains 1, ensuring the standardization and scientific nature of subsequent weighted aggregation calculations. This provides weight support for the accurate integration of multi-dimensional traffic condition representation factors, adapting to all spatiotemporal scenarios, making the final comprehensive traffic condition index more closely match the spatiotemporal characteristics of actual road network operation.

[0070] Step 260-3: For each dimension of traffic situation characterization factor corresponding to each road grid, calculate the sum of the product of the factor value and the unit weight in each spatiotemporal cross-weight unit to obtain the weighted calculation result of each dimension of traffic situation characterization factor.

[0071] For the embodiments of this disclosure, for each road grid in the entire urban and rural area, firstly, the traffic situation characterization factors of the four dimensions of congested road segment proportion, slow-moving road segment proportion, unobstructed road segment proportion, and unknown road segment proportion can be determined. Then, the specific factor value corresponding to each dimension factor in all spatiotemporal cross-weighted units can be extracted. Each factor value is multiplied by the unit weight of the corresponding spatiotemporal cross-weighted unit. Then, the calculation results of all "factor value × unit weight" under the same dimension are accumulated and summed to finally obtain the weighted calculation result of the traffic situation characterization factor of each dimension under each road grid.

[0072] For example, the set of spatiotemporal cross-weighted units (such as 0.175 for weekday-morning peak, 0.175 for weekday-evening peak, etc.) that undertake the differentiated pricing business of auto insurance in steps 260-1 and 260-2 are shown in Table 1. For a street-level road grid, assume that the factor values ​​of its traffic situation characterization factors in different cross-units are as follows: the proportion of congested road sections is 60% for weekday-morning peak, 55% for weekday-evening peak, 30% for weekday-off-peak, and 5% for weekday-early morning; and 20%, 25%, 15%, and 3% for non-working days, respectively. The factor values ​​of other dimensions (slow traffic, smooth traffic, unknown) are set according to the corresponding logic. Then, for the dimension of congested road section proportion, the product of "factor value × unit weight" of each unit is calculated (60% × 0.175 = 0). 0.105, 55%×0.175=0.09625, 30%×0.28=0.084, 5%×0.07=0.0035, 20%×0.075=0.015, 25%×0.075=0.01875, 15%×0.12=0.018, 3%×0.03=0.0009. Then, these product results are summed (0.105+0.09625+0.084+0.0035+0.015+0.01875+0.018+0.0009=0.3414), yielding a weighted calculation result of 34.14% for the congested road segment percentage in this grid. Similarly, the weighted calculation results for the percentages of slow-moving, unobstructed, and unknown road segments can be calculated, forming complete weighted data for each dimension of the grid.

[0073] Table 1. Factor values ​​of congested road segment percentage within different intersection units.

[0074] This technical step, through targeted calculations by road grid and dimension, ensures that the weighted aggregation of traffic situation characterization factors accurately corresponds to the actual situation of each grid. At the same time, by multiplying the factor values ​​with the unit weights of the spatiotemporal cross-weighted units and then summing them, it can fully integrate the differentiated importance of different "date-time period" combinations. This allows the weighted calculation results to not only comprehensively cover traffic situation data across all spatiotemporal dimensions, but also highlight the impact of key spatiotemporal scenarios on situation assessment, effectively improving the accuracy and scientific nature of data aggregation. It can provide reliable intermediate data support for subsequent normalization processing to generate a comprehensive traffic situation index.

[0075] Step 260-4: Normalize the weighted calculation results of multiple traffic situation characterization factors corresponding to each road grid to obtain the comprehensive traffic situation index of each road grid.

[0076] Among them, the multiple weighted calculation results of the multi-dimensional traffic situation characterization factors refer to the four independent values ​​obtained by summing the proportions of congested road segments, slow-moving road segments, unobstructed road segments, and unknown road segments under each road grid through the sum of "factor value × unit weight" of all spatiotemporal cross-weighted units. These are intermediate quantitative results reflecting the situation in each dimension. Normalization processing refers to using a unified standardization algorithm (such as linear normalization) to convert the weighted calculation results of the four dimensions under the same road grid into values ​​with a consistent range (usually 0-1 or 0-100) that meet the evaluation logic, eliminating the difference in dimensions between dimensions and ensuring that the results can be comprehensively integrated. The comprehensive traffic situation index is a single standardized index obtained by integrating the weighted calculation results of each dimension after normalization processing. It can intuitively and comprehensively reflect the overall traffic operation status (congestion, slow-moving, and unobstructed) of a single road grid in all spatiotemporal dimensions, facilitating cross-grid situation comparison and quantitative evaluation.

[0077] For each road grid, the weighted calculation results corresponding to the four traffic situation characterization factors of congestion, slow traffic, smooth traffic, and unknown can be summarized first. A preset normalization algorithm (such as mapping the weighted values ​​of each dimension to the 0-100 range proportionally and retaining the contribution weight of each dimension to the overall situation) is used to standardize the weighted calculation results of these four dimensions, eliminate the numerical differences and dimensional effects of data from different dimensions, and finally integrate them to form a single comprehensive traffic situation index that can comprehensively reflect the traffic situation level of the road grid in all time and space.

[0078] For example, following the example of differentiated pricing for auto insurance in step 260-3, the weighted calculation results of traffic situation characterization factors in various dimensions of a street-level road grid are as follows: congested road sections account for 34.14%, slow-moving road sections account for 42.36%, unobstructed road sections account for 21.5%, and unknown road sections account for 2%. These results can be mapped to an index range of 0-100 using a linear normalization algorithm (setting the contribution weights of congestion, slow-moving, unobstructed, and unknown to the situation index as 0.6, 0.3, 0.1, and 0, respectively). The comprehensive traffic situation index is calculated as follows: 34.14×0.6 + 42.36×0.3 + 21.5×0.1 + 2×0 = 20.484 + 12.708 + 2.15 = 35.34. This index directly reflects the traffic situation of the grid, which is mainly characterized by moderate to light congestion, under all time and space conditions, and can be directly used for the quantitative assessment of travel risks for auto insurance users.

[0079] This technical step, through normalization processing, effectively solves the problem of inconsistent numerical ranges and inability to directly integrate multi-dimensional weighted calculation results, ensuring that the contribution ratio of each dimension's situational characteristics to the comprehensive index is reasonable. At the same time, the generated comprehensive traffic situation index transforms scattered multi-dimensional data into an intuitive and standardized single indicator, which can not only completely retain the core information of traffic situation in each dimension, but also realize direct comparison and quantitative evaluation of traffic situation between different road grids. This can significantly improve the practicality and readability of traffic situation data, and provide a simple and accurate core evaluation basis for subsequent cross-domain applications such as target object travel characteristic adaptation and fintech.

[0080] Step 270: Match the travel-related points of the target object to the corresponding road grid, and generate a target comprehensive traffic situation index associated with the travel characteristics of the target object based on the comprehensive traffic situation index of the matched road grid.

[0081] For embodiments of this disclosure, step 270 may include the following steps: Step 270-1: Obtain the authorized travel-related locations of the target object.

[0082] Step 270-2: Based on the preset spatial distance threshold, retrieve candidate road grids within the preset range corresponding to the travel-related points.

[0083] Among them, the preset spatial distance threshold refers to the distance standard (usually in meters / kilometers) set in advance according to the accuracy requirements of the business scenario (such as the accuracy of the association between travel points and grids), which is used to define the effective association range between travel-related points and road grids; the preset range refers to the circular or polygonal geographical range with the travel-related points as the center and the preset spatial distance threshold as the radius, which is the spatial boundary for searching candidate road grids; the candidate road grid refers to the set of road grids whose geographical reference points fall within the preset range of travel-related points after spatial distance calculation, which is the preliminary screening result for subsequent accurate matching of target grids.

[0084] In this embodiment of the disclosure, the precise coordinates of the authorized travel-related points of the target object can be obtained first to ensure that its coordinate system is consistent with the coordinate system of the global road grid spatial index. Then, taking the travel-related point as the center, the corresponding geographic preset range is delineated based on the preset spatial distance threshold. Through the spatial retrieval function of the global road grid spatial index, the actual spatial distance between the geographic reference point of each road grid and the travel-related point is calculated in batches. All road grids with a spatial distance less than or equal to the preset threshold are filtered out, and finally a candidate road grid set corresponding to the travel-related point is formed.

[0085] This technical step defines the search range by setting a preset spatial distance threshold, which can ensure the spatial correlation between candidate road grids and travel-related points, avoiding the introduction of irrelevant grids or the omission of relevant grids. At the same time, relying on the efficient search capabilities of the global road grid spatial index, it can achieve rapid screening of candidate grids, significantly reducing the calculation range of subsequent accurate matching. This not only improves the efficiency and accuracy of grid retrieval, but also lays a focused and efficient foundation for subsequently determining the core road grid corresponding to the target object and generating a personalized target comprehensive traffic situation index.

[0086] Step 270-3: Based on the historical travel trajectory data of the target object, count the frequency of the first trip of the target object in each candidate road grid, and determine the candidate road grid with the highest frequency of the first trip as the core associated road grid.

[0087] Among them, historical travel trajectory data refers to the authorized travel location sequence data of the target object (such as car insurance users) within a certain period (such as the past 3 months), which includes continuous coordinate points, timestamps and other information during the travel process, reflecting the actual travel path and activity range of the target object; the first travel frequency refers to the cumulative number of times the target object's historical travel trajectory passes through or stops at a certain candidate road grid within the statistical period, which is the core indicator for quantifying the closeness of the connection between the target object and the grid; the candidate road grid refers to the set of road grids with strong correlations selected based on the target object's travel-related points and according to a preset spatial distance threshold, which is the selection range of core related grids; the core related road grid refers to the grid with the highest first travel frequency of the target object among the candidate road grids, which can accurately correspond to the core travel area where the target object is most frequently active, and is the core carrier for generating personalized situation indexes in the future.

[0088] In this embodiment of the disclosure, the historical travel trajectory data authorized by the target object can be obtained, the trajectory data can be calibrated and noise removed, all valid positioning points in the trajectory can be extracted, and the candidate road grid to which each valid positioning point belongs can be determined one by one through the spatial matching function of the global road grid spatial index. The number of positioning points of the target object in each candidate grid (i.e., the first travel frequency) is accumulated according to the grid dimension. The first travel frequency values ​​of all candidate grids are compared, and the candidate road grid with the highest frequency is determined as the core associated road grid that is most closely related to the travel of the target object.

[0089] For example, if a candidate road grid set (A001, A002, A003) is determined, the user's historical travel trajectory data for the past 3 months is obtained. After processing, 1200 valid location points are extracted. Through spatial matching, it is found that 680 location points fall in grid A001 (corresponding to the area around the commuting departure point), 320 fall in grid A002, and 200 fall in grid A003. The first travel frequency is calculated as follows: 680 times for A001, 320 times for A002, and 200 times for A003. Since grid A001 has the highest first travel frequency, it is determined as the user's core associated road grid.

[0090] This technical step is based on the historical travel trajectory data of the target object to count the first travel frequency. This ensures that the determination of the core associated road grid is consistent with the actual travel behavior of the target object, and can avoid the association deviation caused by simply relying on spatial distance matching. At the same time, through the frequency-first filtering logic, the core travel area where the target object is most frequently active can be accurately identified, so that the subsequently generated target comprehensive traffic situation index can focus on the user's high-frequency travel scenarios, which greatly improves the personalization and accuracy of the situation assessment.

[0091] Step 270-4: Adapt and adjust the comprehensive traffic situation index of the core associated road grid based on the travel time preferences of the target object to obtain the target comprehensive traffic situation index.

[0092] For embodiments of this disclosure, the steps may include: based on historical travel trajectory data, calculating the second travel frequency of the target object in each time period; filtering time periods with a travel frequency ratio exceeding a preset threshold based on the second travel frequency as high-frequency travel time periods for the target object; retrieving traffic situation characterization factor data corresponding to the core associated road grid during high-frequency travel time periods; calculating the average proportion of traffic situation characterization factors of each dimension within the high-frequency travel time period based on the traffic situation characterization factor data; determining the spatiotemporal cross-weighting unit corresponding to the high-frequency travel time period; multiplying the average proportion of traffic situation characterization factors of each dimension with the unit weight of the spatiotemporal cross-weighting unit; summing the product results for all high-frequency travel time periods to obtain the time period preference correction value of traffic situation characterization factors of each dimension; replacing the weighted calculation results of the corresponding dimension traffic situation characterization factors in the original comprehensive traffic situation index with the time period preference correction value; normalizing the multiple weighted calculation results of the replaced multi-dimensional traffic situation characterization factors to obtain the target comprehensive traffic situation index associated with the travel frequency and travel time of the target object.

[0093] Among them, travel time preference refers to the time-based tendency of the target object based on actual travel behavior, which is mainly reflected by high-frequency travel periods and reflects its main travel time characteristics; second travel frequency refers to the cumulative number of trips of the target object in each preset time period (such as morning peak and off-peak) based on historical travel trajectory data, used to quantify the travel activity level of the target object in different time periods; high-frequency travel period refers to the period when the proportion of second travel frequency to total travel frequency exceeds a preset threshold (such as 30%), which is the most important travel time interval of the target object; traffic situation characterization factor data refers to the proportion of congested road sections, slow-moving road sections, and smooth-moving road sections recorded by the core associated road grid in the high-frequency travel period. The specific values ​​for the proportion of accessible road segments and the proportion of unknown road segments; the average proportion refers to the proportion obtained by taking the arithmetic mean of the traffic situation characterization factor data of the core associated road grid in all high-frequency travel periods; the time period preference correction value refers to the value obtained by multiplying the average proportion of traffic situation characterization factors in each dimension with the weight of the spatiotemporal cross-weight unit of the corresponding high-frequency travel period, and then summing the product results over all high-frequency periods, which is used to correct the original weighted calculation result; the target comprehensive traffic situation index refers to the personalized index that fits the travel time preferences of the target object after replacing the weighted calculation result of the corresponding dimension in the original comprehensive traffic situation index with the time period preference correction value and then normalizing it.

[0094] Following the examples in steps 270-4 and 260-4 of the implementation plan, if the core associated road grid of the car insurance user is determined to be A001, the second travel frequency is statistically analyzed based on the user's historical travel trajectory data for the past 3 months. It is found that the proportion of travel during the morning peak (7-9 am) is 35%, and the proportion of travel during the evening peak (17-19 pm) is 32%, both exceeding the preset threshold of 30%. Therefore, these two time periods are determined to be high-frequency travel periods. The traffic situation characterization factor data of grid A001 during these two time periods are retrieved, and the average proportion of congested road sections is calculated to be 58%, the average proportion of slow-moving road sections is 30%, the average proportion of unobstructed road sections is 10%, and the average proportion of unknown road sections is 2%. The spatiotemporal cross-weight unit corresponding to the high-frequency time periods is determined to be weekday-morning peak (0.175) and weekday-evening peak (0.175). The time period preference correction values ​​for each dimension are calculated (congestion: 58%×0.175 + 58%×0.175=0.203, slow-moving: 30%×0.175 + 30% × 0.175 = 0.105, Smooth Traffic: 10% × 0.175 + 10% × 0.175 = 0.035, Unknown: 2% × 0.175 + 2% × 0.175 = 0.007; Replace the original weighted calculation results (original congestion 34.14%, slow traffic 42.36%, etc.) with these correction values, and calculate using the same normalization algorithm (congestion 0.6, slow traffic 0.3, smooth traffic 0.1, unknown 0), to obtain the target comprehensive traffic situation index = 0.203 × 100 × 0.6 + 0.105 × 100 × 0.3 + 0.035 × 100 × 0.1 = 12.18 + 3.15 + 0.35 = 15.68 (the correction values ​​here are calculated after percentage conversion). This index accurately reflects the traffic situation faced by users during high-frequency commuting periods.

[0095] This technical step involves mining the historical travel trajectory data of the target object to accurately identify its high-frequency travel periods and travel period preferences. Based on these preferences, the comprehensive traffic situation index of the core associated road grid is specifically modified, which avoids the problem of general indices ignoring individual travel differences at different times. At the same time, by combining average proportion calculation with spatiotemporal cross-weighting units, it can be ensured that the modification process not only fits the actual traffic situation during high-frequency periods, but also retains the scientific nature of the weighting system. The final target comprehensive traffic situation index can accurately depict the traffic situation experience of the target object in major travel scenarios, greatly improving the personalization and accuracy of situation assessment.

[0096] In summary, the technical solution in this application, by dividing urban and rural road networks into grids based on administrative division POI information at a preset administrative granularity, calibrating geographic benchmarks, and constructing a spatial index for the entire road network, can overcome the limitations of existing technologies that rely on the deployment of dedicated highway monitoring equipment. It extends the identification scope to the entire road network, including ordinary municipal roads and rural roads, providing a unified spatial benchmark for the collection and association of situational data and solving the problem of missing urban and rural road situational information. Based on this spatial index, it retrieves grid benchmarks to construct travel routes and calls public navigation service interfaces according to date type and time segment to collect multi-dimensional situational characterization factors. This avoids the drawbacks of traditional navigation data, such as high authorization thresholds, privacy sensitivity, and high costs. It can achieve large-scale, low-cost, multi-temporal and spatial situational data collection, ensuring data availability and feasibility for promotion; by constructing spatiotemporal cross-weighted units through a preset weight system, it can generate comprehensive traffic situation indices for each grid by weighting and aggregating multi-dimensional factors, which can accurately quantify the differences in traffic situation on different dates and at different times, improving the accuracy and relevance of situational assessment; by matching the travel-related points of the target object to the corresponding grid, it can generate a target comprehensive traffic situational index that fits its travel characteristics based on the comprehensive index, which can achieve accurate mapping of the overall situation from the grid level to the individual level. It can not only fully cover the needs of the entire road network situational identification, but also accurately adapt to application scenarios in multiple fields such as financial technology, providing high-quality data support for cross-domain decision-making.

[0097] Furthermore, as Figure 1 and Figure 2 The specific implementation of the method shown in this embodiment provides a device for identifying urban and rural road traffic conditions, such as... Figure 3 As shown, the device includes: a construction module 31, a collection module 32, an aggregation module 33, and a generation module 34.

[0098] Module 31 can be used to spatially divide the urban and rural road grid according to the preset administrative region granularity based on POI information of administrative division, and to mark the geographical reference points for each road grid to build a spatial index of the entire road grid. The data acquisition module 32 can be used to retrieve the geographic reference points between any two road grids based on the global road grid spatial index, construct travel routes, and collect multi-dimensional traffic situation characterization factors for each travel route by calling the public navigation service interface according to the preset date type and time dimension. The aggregation module 33 can be used to construct a spatiotemporal cross-weighted unit based on a preset date type weight system and time period weight system, and to perform weighted aggregation of multi-dimensional traffic situation characterization factors to obtain the comprehensive traffic situation index of each road grid. The generation module 34 can be used to match the travel-related points of the target object to the corresponding road grid, and generate a target comprehensive traffic situation index associated with the travel characteristics of the target object based on the comprehensive traffic situation index of the matched road grid.

[0099] In some embodiments of this application, the construction module 31 can be specifically used to determine the administrative region granularity of the road grid in combination with business scenario requirements, extract administrative division-type POI information within the entire region based on the administrative region granularity; select the regional geometric center or core road network node as the geographic reference point based on the administrative division-type POI information, and define the initial grid boundary of each road grid; calibrate the initial grid boundary based on the regional road network distribution data, correct the deviation between the initial grid boundary and the actual road network topology, and obtain the final grid spatial coordinates of each road grid; establish the attribute association between each road grid and the geographic reference point, and generate a global road grid spatial index containing grid spatial coordinates and administrative affiliation.

[0100] In some embodiments of this application, the acquisition module 32 can be specifically used to batch retrieve the geographic reference point coordinates of all road grids from the global road grid spatial index to form a grid point coordinate library; pair the geographic reference points in the grid point coordinate library to generate multiple travel paths between urban and rural global road grids; based on regional traffic travel patterns, the date type is divided into two categories: weekdays and non-weekdays, and the whole day is divided into multiple time period monitoring intervals to form a multi-temporal and spatial acquisition dimension; according to the multi-temporal and spatial acquisition dimension, the public navigation service interface is called in batches to collect multi-dimensional traffic situation characterization factors corresponding to each travel path, including the proportion of congested road sections, the proportion of slow-moving road sections, the proportion of unobstructed road sections, and the proportion of unknown road sections.

[0101] In some embodiments of this application, when pairing geographic reference points in the grid point coordinate library to generate multiple travel paths between urban and rural road grids, the acquisition module 32 can specifically be used to partition the grid point coordinate library according to the administrative affiliation attribute of the urban road grid spatial index, forming grid point sub-libraries for each city; perform pairwise pairing operations on geographic reference points in each city's grid point sub-library to generate travel paths within the city; and perform validity screening on the generated travel paths within the city, removing invalid paths whose path length exceeds a preset length threshold or whose path crosses a restricted area, to obtain the final multiple travel paths.

[0102] In some embodiments of this application, the aggregation module 33 can be specifically used to set a basic weight for date type and a differentiated weight for time period based on regional traffic flow patterns and business scenario requirements; multiply the basic weight for date type with the corresponding differentiated weight for time period to generate a spatiotemporal cross-weight unit for each combination of date type and time period; calculate the sum of the products of the factor value and the unit weight in each spatiotemporal cross-weight unit for each dimension of traffic situation characterization factor corresponding to each road grid to obtain the weighted calculation result of each dimension of traffic situation characterization factor; normalize the multiple weighted calculation results of the multi-dimensional traffic situation characterization factors corresponding to each road grid to obtain the comprehensive traffic situation index of each road grid.

[0103] In some embodiments of this application, the generation module 34 can be specifically used to obtain authorized travel-related points of the target object; based on a preset spatial distance threshold, retrieve candidate road grids within a preset range corresponding to the travel-related points; based on the target object's historical travel trajectory data, count the target object's first travel frequency in each candidate road grid, and determine the candidate road grid with the highest first travel frequency as the core associated road grid; and adapt and adjust the comprehensive traffic situation index of the core associated road grid based on the target object's travel time preferences to obtain the target comprehensive traffic situation index.

[0104] Correspondingly, when adapting and adjusting the comprehensive traffic situation index of the core associated road grid based on the travel time preferences of the target object to obtain the target comprehensive traffic situation index, the generation module 34 can be used to: statistically analyze the second travel frequency of the target object in each time period based on historical travel trajectory data; filter the time periods with the proportion of travel frequency exceeding a preset threshold based on the second travel frequency as the high-frequency travel time periods of the target object; retrieve the traffic situation characterization factor data of the core associated road grid corresponding to the high-frequency travel time periods; calculate the average proportion of traffic situation characterization factors of each dimension in the high-frequency travel time periods based on the traffic situation characterization factor data; determine the spatiotemporal cross-weight unit corresponding to the high-frequency travel time period; multiply the average proportion of traffic situation characterization factors of each dimension with the unit weight of the spatiotemporal cross-weight unit; and sum the product results of all high-frequency travel time periods to obtain the time period preference correction value of the traffic situation characterization factor of each dimension; replace the weighted calculation result of the corresponding dimension traffic situation characterization factor in the original comprehensive traffic situation index with the time period preference correction value; normalize the multiple weighted calculation results of the replaced multi-dimensional traffic situation characterization factors to obtain the target comprehensive traffic situation index associated with the travel frequency and travel time of the target object.

[0105] It should be noted that other corresponding descriptions of the functional units involved in the urban and rural road traffic situation identification device provided in this embodiment can be found in [reference]. Figure 1 and Figure 2The corresponding descriptions in [the document] will not be repeated here.

[0106] Based on the above, Figure 1 and Figure 2 Accordingly, this embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the above-described method. Figure 1 and Figure 2 The method for identifying urban and rural road traffic conditions is shown.

[0107] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause an electronic device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0108] Based on the above, Figure 1 and Figure 2 The method shown, and Figure 3 To achieve the above objectives, the present application also provides an electronic device, specifically a personal computer, tablet computer, server, or other network device, as shown in the virtual device embodiment. This device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to achieve the above-described objectives. Figure 1 and Figure 2 The method for identifying urban and rural road traffic conditions is shown.

[0109] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0110] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0111] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platform, or it can be implemented by hardware.

[0113] This invention, through the division of urban and rural road networks into grids based on administrative division-type POI information at a preset administrative granularity, the marking of geographic reference points, and the construction of a spatial index for the entire road network, overcomes the limitations of existing technologies that rely on the deployment of dedicated highway monitoring equipment. It extends the identification scope to the entire road network, including ordinary municipal roads and rural roads, providing a unified spatial reference for the collection and association of situational data and solving the problem of missing urban and rural road situational information. Based on this spatial index, it retrieves grid reference points to construct travel routes and calls public navigation service interfaces according to date type and time segment to collect multi-dimensional situational characterization factors. This avoids the drawbacks of traditional navigation data, such as high authorization thresholds, privacy sensitivity, and high costs, and enables [the following is a separate, unrelated sentence:] Large-scale, low-cost, and multi-temporal-dimensional situational data collection ensures data availability and feasibility for widespread application. By constructing spatiotemporal cross-weighted units through a pre-set weighting system, multi-dimensional factors are weighted and aggregated to generate comprehensive traffic situation indices for each grid. This accurately quantifies the differences in traffic situation on different dates and at different times, improving the accuracy and relevance of situational assessments. By matching the travel-related points of target objects to the corresponding grids and generating target comprehensive traffic situation indices that fit their travel characteristics based on the comprehensive index, a precise mapping of the overall situation from the grid level to the individual level can be achieved. This not only fully covers the needs of overall road network situational identification but also accurately adapts to application scenarios in multiple fields such as fintech, providing high-quality data support for cross-domain decision-making.

[0114] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0115] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A method for identifying the traffic situation of urban and rural roads, characterized in that, Comprise: According to the administrative division type POI information, the spatial division of urban and rural global road grid is carried out according to the preset administrative region granularity, and the geographic reference point is calibrated for each road grid, and the global road grid spatial index is constructed; Based on the global road grid spatial index, the geographic reference points between any two road grids are called, and the passing path is constructed, and according to the preset date type and time period dimension, the multi-dimensional traffic situation representation factor of each passing path is collected by calling the public navigation service interface; Based on the preset date type weight system and time period weight system, a time-space cross weight unit is constructed, the multi-dimensional traffic situation representation factor is weighted and aggregated, and the comprehensive traffic situation index of each road grid is obtained; The travel associated point of the target object is matched to the corresponding road grid, and based on the comprehensive traffic situation index of the matched road grid, the target comprehensive traffic situation index associated with the travel characteristics of the target object is generated.

2. The method of claim 1, wherein, According to the administrative division type POI information, the spatial division of urban and rural global road grid is carried out according to the preset administrative region granularity, and the geographic reference point is calibrated for each road grid, and the global road grid spatial index is constructed, comprising: Determine the administrative region granularity of road grid combined with business scene demand, extract administrative division type POI information within global range based on the administrative region granularity; Based on the administrative division type POI information, select the regional geometric center or core road network node as the geographic reference point, and define the initial grid boundary of each road grid; Based on the regional road network distribution data, the initial grid boundary is calibrated, the deviation of the initial grid boundary and the actual road network topology is corrected, and the final grid space coordinates of each road grid are obtained; Establish the attribute association of each road grid and the geographic reference point, and generate the global road grid spatial index containing the grid space coordinates and administrative attribution.

3. The method of claim 1, wherein, Based on the global road grid spatial index, the geographic reference points between any two road grids are called, and the passing path is constructed, and according to the preset date type and time period dimension, the multi-dimensional traffic situation representation factor of each passing path is collected by calling the public navigation service interface, comprising: Batch call the geographic reference point coordinates of all road grids from the global road grid spatial index to form a grid point coordinate library; The geographic reference points in the grid point coordinate library are paired two by two to generate a plurality of passing paths between urban and rural global road grids; Based on the regional traffic travel rule, the date type is divided into working day and non-working day, and the whole day is divided into multiple time period monitoring intervals to form multiple time-space collection dimensions; According to the multi-time-space collection dimension, the public navigation service interface is called in batches to collect the multi-dimensional traffic situation representation factor of each passing path, including congestion section proportion, slow section proportion, smooth section proportion and unknown section proportion.

4. The method of claim 3, wherein, The geographic reference points in the grid point coordinate library are paired two by two to generate a plurality of passing paths between urban and rural global road grids, comprising: According to the administrative attribution attribute of the global road grid spatial index, the grid point coordinate library is partitioned according to the city administrative boundary to form the grid point sub-library of each city; The two-by-two pairing operation of the geographic reference points is performed in the grid point sub-library of each city to generate a passing path in the city; The generated passing path in the city is subjected to effectiveness screening to eliminate invalid paths whose path length exceeds a preset length threshold or which pass through a forbidden area, thereby obtaining a plurality of final passing paths.

5. The method of claim 1, wherein, The preset date type weight system and the time period weight system are used to construct a space-time cross weight unit, and the multi-dimensional traffic situation representation factors are subjected to weighted aggregation to obtain a comprehensive traffic situation index of each road grid, including: According to the regional traffic flow rule and in combination with the business scene demand, a date type basic weight and a time period differentiated weight are set; The date type basic weight and the corresponding time period differentiated weight are subjected to product operation to generate a space-time cross weight unit of each date type and time period combination; For each dimension traffic situation representation factor corresponding to each road grid, the sum of the product of the factor value in each space-time cross weight unit and the unit weight is calculated to obtain a weighted calculation result of each dimension traffic situation representation factor; The plurality of weighted calculation results of the multi-dimensional traffic situation representation factors corresponding to each road grid are subjected to normalization processing to obtain a comprehensive traffic situation index of each road grid.

6. The method of claim 5, wherein, The travel associated point of the target object is matched to the corresponding road grid, and based on the comprehensive traffic situation index of the matched road grid, a target comprehensive traffic situation index associated with the travel characteristics of the target object is generated, including: An authorized travel associated point of a target object is obtained; Based on a preset spatial distance threshold, candidate road grids within a preset range corresponding to the travel associated point are retrieved; Based on historical travel trajectory data of the target object, a first travel frequency of the target object in each candidate road grid is counted, and the candidate road grid with the highest first travel frequency is determined as a core associated road grid; Based on the travel time period preference of the target object, the comprehensive traffic situation index of the core associated road grid is adaptively adjusted to obtain a target comprehensive traffic situation index.

7. The method of claim 6, wherein, Based on the travel time period preference of the target object, the comprehensive traffic situation index of the core associated road grid is adaptively adjusted to obtain a target comprehensive traffic situation index, including: Based on the historical travel trajectory data, a second travel frequency of the target object in each time period is counted, and a time period with a second travel frequency ratio exceeding a preset threshold is selected as a high-frequency travel time period of the target object based on the second travel frequency; The traffic situation representation factor data corresponding to the high-frequency travel time period of the core associated road grid is called, and the average proportion of each dimension traffic situation representation factor in the high-frequency travel time period is calculated based on the traffic situation representation factor data; The space-time cross weight unit corresponding to the high-frequency travel time period is determined, the average proportion of each dimension traffic situation representation factor is multiplied by the unit weight of the space-time cross weight unit, and the sum of the product results of all high-frequency travel time periods is summed to obtain a time period preference correction value of each dimension traffic situation representation factor; The time period preference correction value is used to replace the weighted calculation result of the corresponding dimension traffic situation representation factor in the original comprehensive traffic situation index, and the multiple weighted calculation results of the multiple dimension traffic situation representation factors after replacement are normalized to obtain a target comprehensive traffic situation index associated with the travel frequency and travel time period of the target object.

8. A device for recognizing traffic situation of urban and rural roads, characterized in that, Comprise: The construction module is configured to perform spatial division of a global road grid according to administrative division type POI information and according to a preset administrative region granularity, and to label a geographic reference point for each road grid to construct a global road grid spatial index; The acquisition module is configured to call geographic reference points between any two road grids based on the global road grid spatial index, to construct a travel path, and to call a multi-dimensional traffic situation representation factor of each travel path according to a preset date type and time period dimension and by invoking a public navigation service interface; The aggregation module is configured to construct a space-time cross weight unit based on a preset date type weight system and a time period weight system, to weight and aggregate the multi-dimensional traffic situation representation factor, and to obtain a comprehensive traffic situation index of each road grid; The generation module is configured to match a travel associated point of a target object to a corresponding road grid, to generate a target comprehensive traffic situation index associated with a travel feature of the target object based on the comprehensive traffic situation index of the matched road grid.

9. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the method of any one of claims 1 to 7.

10. An electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 7.

Images