Parking guiding method and device based on dynamic grid division

Abstract

The embodiment of the invention discloses a parking guiding method and device based on dynamic grid division. A specific embodiment of the method comprises the steps of obtaining geographic information data, parking resource data and dynamic activity data of a target area; generating a target dynamic grid for parking guidance; for each dynamic grid of the target dynamic grids, executing the following generation steps: determining a plurality of corresponding parking index values based on real-time parking related data corresponding to the dynamic grids and historical parking related data acquired in advance; comprehensive weight vectors corresponding to the multiple parking index values are determined; generating parking resource quantification information; generating a target grid set corresponding to the parking request information; generating guiding path information corresponding to the target grid set, and sending the guiding path information to the target user terminal; and executing parking guide operation. According to the embodiment, the accuracy of parking guidance and the utilization rate of urban parking resources are improved, and the time consumed by a user for searching a parking space is shortened.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and more specifically to a parking guidance method and apparatus based on dynamic grid partitioning. Background Technology

[0002] With the continuous growth of urban motor vehicle ownership, "parking difficulties" have become a prominent problem affecting urban traffic efficiency and residents' travel experience. Currently, the management and guidance of parking resources mainly rely on traditional parking guidance methods. These methods typically operate based on basic data such as the occupancy rate and turnover rate of parking spaces in individual parking lots or on-street parking spots, and provide drivers with information on available parking spaces through guidance screens or mobile applications.

[0003] However, when using the above method for parking guidance, the following technical problems often arise: Traditional parking guidance methods lack a holistic and dynamic understanding of regional parking resources and fail to incorporate real-time traffic and user preferences, resulting in low accuracy in guiding users to park and wasting significant time and computing resources.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide parking guidance methods, apparatuses, electronic devices, and computer-readable media based on dynamic grid partitioning to address one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a parking guidance method based on dynamic grid partitioning, comprising: acquiring geographic information data, parking resource data, and dynamic activity data of a target area; generating a target dynamic grid for parking guidance based on the geographic information data, parking resource data, and dynamic activity data; for each dynamic grid of the target dynamic grid, performing the following generation steps: determining multiple parking indicator values ​​corresponding to the dynamic grid based on real-time parking-related data and pre-acquired historical parking-related data; determining a comprehensive weight vector corresponding to the multiple parking indicator values; generating parking resource quantification information based on the comprehensive weight vector; in response to receiving parking request information from a target user, generating a target grid set corresponding to the parking request information based on the parking resource quantification information set; generating guidance path information corresponding to the target grid set, and sending the guidance path information to a target user terminal; and in response to the target user terminal receiving the guidance path information, performing a parking guidance operation.

[0008] Secondly, some embodiments of this disclosure provide a parking guidance device based on dynamic grid partitioning, comprising: an acquisition unit configured to acquire geographic information data, parking resource data, and dynamic activity data of a target area; a first generation unit configured to generate a target dynamic grid for parking guidance based on the aforementioned geographic information data, parking resource data, and dynamic activity data; a first execution unit configured to perform the following generation steps for each dynamic grid of the target dynamic grid: determining multiple parking index values ​​corresponding to the dynamic grid based on real-time parking-related data and pre-acquired historical parking-related data; determining a comprehensive weight vector corresponding to the multiple parking index values; generating parking resource quantification information based on the comprehensive weight vector; a second generation unit configured to generate a target grid set corresponding to the parking request information based on the parking resource quantification information set in response to receiving parking request information from a target user; a generation and sending unit configured to generate guidance path information corresponding to the target grid set and send the guidance path information to a target user terminal; and a second execution unit configured to perform a parking guidance operation in response to the target user terminal receiving the guidance path information.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, such that when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: The parking guidance method based on dynamic grid partitioning in some embodiments of this disclosure improves the efficiency of parking guidance and the utilization rate of urban parking resources, reducing the time users spend searching for parking spaces. Specifically, the reason for the low efficiency of parking guidance and the low utilization rate of urban parking resources is that existing technologies use only a single dimension of information for parking guidance, information updates are lagging, and personalized guidance capabilities are lacking, leading to resource mismatch and ineffective patrols. Based on this, the parking guidance method based on dynamic grid partitioning in some embodiments of this disclosure first acquires geographic information data, parking resource data, and dynamic activity data of the target area. By integrating geographic information, parking resources, and dynamic activity data, a comprehensive and multi-dimensional data foundation is provided for subsequent analysis, ensuring the accuracy and real-time nature of parking evaluation. Then, based on the aforementioned geographic information data, parking resource data, and dynamic activity data, a target dynamic grid for parking guidance is generated. By partitioning the dynamic grid based on the aforementioned geographic information data, parking resource data, and dynamic activity data, refined spatial management and dynamic adaptation of parking resources are achieved, improving the flexibility and accuracy of regional parking analysis. Next, for each dynamic grid of the aforementioned target dynamic grid, the following generation steps are performed: Based on the real-time parking-related data and pre-acquired historical parking-related data corresponding to the aforementioned dynamic grid, multiple corresponding parking indicator values ​​are determined. Multi-dimensional parking indicators are determined by combining real-time and historical parking-related data to comprehensively reflect the supply and demand, congestion, and convenience of parking resources, providing a quantitative basis for evaluation. A comprehensive weight vector corresponding to the aforementioned multiple parking indicator values ​​is determined. By determining the comprehensive weight vector, expert experience and data patterns are considered, making the evaluation results more scientific and reasonable. Based on the aforementioned comprehensive weight vector, quantitative parking resource information is generated. Generating quantitative parking resource information supports precise decision-making. Secondly, in response to receiving parking request information from target users, a target grid set corresponding to the aforementioned parking request information is generated based on the quantitative parking resource information set. Grids are filtered and sorted according to parking request information and preferences to achieve personalized parking recommendations, improving user satisfaction and guidance efficiency. Thirdly, guidance path information corresponding to the aforementioned target grid set is generated, and this guidance path information is sent to the target user terminal. The path from the user's location to the target grid is planned and optimized, combined with real-time traffic information, to ensure the accuracy and efficiency of guidance. Finally, in response to the target user terminal receiving the aforementioned guidance path information, a parking guidance operation is executed. The terminal performs path parsing, real-time navigation, and scene switching, completing the entire service from guidance to parking, thus improving parking guidance efficiency. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the parking guidance method based on dynamic grid partitioning according to the present disclosure; Figure 2 These are schematic diagrams illustrating the structure of some embodiments of a parking guidance device based on dynamic grid partitioning according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] refer to Figure 1The diagram illustrates a flow 100 of some embodiments of a parking guidance method based on dynamic grid partitioning according to the present disclosure. This parking guidance method based on dynamic grid partitioning includes the following steps: Step 101: Obtain geographic information data, parking resource data, and dynamic activity data for the target area.

[0021] In some embodiments, the executing entity (e.g., an electronic device) of the above-described parking guidance method based on dynamic grid partitioning can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed in the hardware devices listed above. It can be implemented as multiple software programs or software modules to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0022] In some embodiments, the aforementioned implementing entity may acquire geographic information data, parking resource data, and dynamic activity data of the target area. The target area may refer to a pre-defined city or specific region requiring parking guidance. The geographic information data describes the basic feature data of the target area's geographic characteristics. This geographic information data includes road network data and point-of-interest (POI) data. The road network data may be structured data describing road connectivity. For example, the road network data may include linear data such as road name, width, number of lanes, and whether it is a one-way street. The POI data may be geographic coordinates and attribute data representing locations of interest to people. POIs may be shopping malls, hospitals, schools, office buildings, or transportation hubs. The parking resource data may be real-time data characterizing the parking facility supply status within the target area. The dynamic activity data may be data reflecting the real-time or near-real-time distribution and movement of population or vehicles within the target area in a spatiotemporal dimension. For example, the dynamic activity data may include mobile phone signaling data and vehicle GPS trajectories.

[0023] In some optional implementations of certain embodiments, the aforementioned executing entity may acquire geographic information data, parking resource data, and dynamic activity data of the target area, which may include the following steps: The first step is to acquire geographic information data through a target database interface. This geographic information data includes road network data and point-of-interest (POI) data. The target database interface can be a database access point used to acquire geographic information data. For example, the target database interface could be an open interface of a city GIS system.

[0024] The second step is to acquire parking resource data through a parking lot sensor network. This parking lot sensor network can be a collection of sensing devices deployed in the parking lot. For example, it could be a network of parking space geomagnetic sensors.

[0025] The third step involves acquiring dynamic activity data through a target mobile platform, whereby this dynamic activity data represents dynamic population distribution information. This target mobile platform can be a mobile application or platform that collects user location data. For example, it could be the user location data platform of a map app. The dynamic population distribution information can be the real-time flow and aggregation of the population within the target area, such as the population density around office buildings during the morning rush hour.

[0026] Step 102: Based on geographic information data, parking resource data, and dynamic activity data, generate a target dynamic grid for parking guidance.

[0027] In some embodiments, the executing entity may generate a target dynamic grid for parking guidance based on the aforementioned geographic information data, parking resource data, and dynamic activity data. The target dynamic grid may be a region division unit that can be dynamically adjusted according to parking demand.

[0028] In some optional implementations of certain embodiments, the executing entity may generate a target dynamic grid for parking guidance based on the aforementioned geographic information data, parking resource data, and dynamic activity data, which may include the following steps: The first step is to construct an initial regular grid for the target area. This initial regular grid can be a base grid for the target area divided into fixed sizes (e.g., 500m × 500m).

[0029] The second step involves refining the initial regular grid using the road network data from the aforementioned geographic information data, resulting in a refined grid. This refined grid can be a grid whose boundaries have been adjusted based on the road network data. In practice, first, road network data (e.g., main roads and secondary roads) is extracted from the geographic information data. Then, the initial grid boundaries are adjusted according to road directions to ensure the grid edges align with the roads, thus obtaining the refined grid. The third step involves associating the point-of-interest (POI) data and parking resource data from the aforementioned geographic information data with the refined grid, resulting in an associated grid. This associated grid can be a grid that binds POI and parking resource information. In practice, first, POI data (e.g., shopping malls, hospitals) and parking resource data (e.g., the number of parking spaces) are extracted. Then, these are bound to the refined grid according to their spatial location. Finally, the associated grid is generated.

[0030] The fourth step, based on the aforementioned dynamic activity data, is to determine the human activity intensity value for each grid within the correlated grid. This human activity intensity value can be a quantitative measure of the frequency of population activity within the grid. For example, the intensity value for the office building grid during morning rush hour is 80 (out of 100). In practice, first, dynamic activity data (e.g., pedestrian density) is determined. Then, the number of people active per unit time in each grid of the correlated grid is determined to convert this into a human activity intensity value.

[0031] The fifth step involves using the aforementioned human activity intensity values ​​to optimize the boundaries of the correlated mesh, resulting in an optimized mesh. This optimized mesh can be a mesh whose boundaries are adjusted based on the human activity intensity. In practice, first, an intensity threshold is set (e.g., a human activity intensity value > 70 requires splitting). Then, high-intensity regions in the correlated mesh are split, and low-intensity regions are merged, ultimately yielding the optimized mesh. For example, a mesh with a human activity intensity value of 80 is split into two smaller meshes, and adjacent meshes with an intensity value of 20 are merged.

[0032] Step 6: Assign a unique grid identifier to each grid cell in the optimized grid to generate the target dynamic grid. This unique grid identifier can be a unique code used to distinguish each grid cell (e.g., "G-001", "G-002"). In practice, first, the optimized grid cells are sorted by their spatial location. Then, a unique grid identifier is assigned to each grid cell in the optimized grid. Finally, the target dynamic grid with the identifiers is generated.

[0033] Step 103: For each dynamic mesh of the target dynamic mesh, perform the following generation steps: Step 1031: Based on the real-time parking-related data corresponding to the dynamic grid and the pre-acquired historical parking-related data, determine the corresponding multiple parking indicator values.

[0034] In some embodiments, the executing entity can determine multiple parking indicator values ​​based on real-time parking-related data corresponding to the dynamic grid and pre-acquired historical parking-related data. The historical parking-related data can be parking data from a past period. For example, the historical parking-related data may include the parking space utilization rate of a certain grid from 8 to 10 am daily over the past three months. The multiple parking indicator values ​​can be multi-dimensional quantitative parameters reflecting the parking status.

[0035] In some optional implementations of certain embodiments, the execution entity can determine multiple corresponding parking indicator values ​​based on the real-time parking-related data corresponding to the dynamic grid and the pre-acquired historical parking-related data, which may include the following steps: The first step is to generate predicted parking demand information corresponding to the dynamic grid based on the aforementioned real-time parking data and historical parking data. This predicted parking demand information can be an estimate of parking demand within the grid. For example, it could predict that a grid will need 120 parking spaces after one hour. In practice, firstly, real-time parking data (e.g., current traffic flow) and historical data from the same period in the past are extracted. Then, predicted parking demand information is generated using a prediction model (e.g., a time series model).

[0036] The second step is to obtain the real-time parking supply information corresponding to the aforementioned dynamic grid. This real-time parking supply information can be the number of parking spaces currently available in the dynamic grid. In practice, this real-time parking supply information can be obtained through a parking lot sensor network.

[0037] The third step is to determine the corresponding supply-demand ratio based on the aforementioned predicted parking demand information and real-time parking supply information. This supply-demand ratio can be the ratio of demand to supply.

[0038] The fourth step is to generate a traffic congestion index based on the traffic-related information of the roads associated with the dynamic grid. This traffic-related information can be traffic status data of surrounding roads. For example, the traffic-related information could be the average vehicle speed of roads surrounding a certain dynamic grid, such as 20 km / h. In practice, first, real-time vehicle speed and traffic flow data of the roads associated with the dynamic grid are obtained. Then, these are substituted into the congestion index formula (e.g., 1 - actual vehicle speed / free-flow vehicle speed). Finally, the traffic congestion index is generated.

[0039] The fifth step involves determining the parking convenience index value for the dynamic grid based on the aforementioned geographic information data and parking resource data. This parking convenience index value can be a quantified measure of the ease of reaching the destination after parking. In practice, firstly, data such as walking distance from parking lots to surrounding points of interest and the number of entrances / exits within the dynamic grid are extracted. Then, scores are assigned according to preset rules (e.g., 30 points for walking distance ≤ 3 minutes, 20 points for 3 to 5 minutes, and 10 points for > 5 minutes; 20 points for ≥ 2 entrances / exits, and 10 points for 1 entrance / exit). Finally, the parking convenience index value is obtained.

[0040] The sixth step is to integrate the aforementioned supply-demand ratio, traffic congestion index, and parking convenience index into multiple parking index values. In practice, the supply-demand ratio, traffic congestion index, and parking convenience index values ​​can be integrated into a dataset in a unified format to serve as multiple parking index values.

[0041] Step 1032: Determine the comprehensive weight vector corresponding to multiple parking indicator values.

[0042] In some embodiments, the executing entity may determine a comprehensive weight vector corresponding to the plurality of parking indicator values. This comprehensive weight vector may be a vector that combines subjective and objective weight vectors to characterize the importance of the parking indicators.

[0043] In some optional implementations of certain embodiments, the execution entity may determine the comprehensive weight vector corresponding to the plurality of parking indicator values, which may include the following steps: The first step is to construct a hierarchical parking resource model based on the aforementioned parking indicator values. This hierarchical model can be a structural model that divides multiple parking indicators into levels. It can include a target layer (comprehensive evaluation value), a criterion layer (supply / demand), and an indicator layer (specific indicators, such as supply-demand ratio and traffic congestion index). In practice, first, the "comprehensive evaluation value of grid parking resources" is defined. Then, the logical relationships between multiple parking indicator values ​​(e.g., supply-demand ratio index, traffic congestion index, and parking convenience index) are determined, and they are categorized under different evaluation criteria (e.g., "efficiency" and "accessibility") to form a criterion layer. Finally, a hierarchical parking resource model is established from the target layer to the criterion layer, and then to the specific indicator layer. This hierarchical parking resource model can be a tree structure.

[0044] The second step involves generating a set of judgment matrices based on the aforementioned parking resource hierarchy model and preset rules. These preset rules can be scaling rules for constructing the judgment matrices, such as the "1-9 scaling method" (where 1 represents equal importance and 9 represents extreme importance). The judgment matrix set is a collection of pairwise comparisons of indicators at each level. For example, the comparison matrix between the supply-demand ratio and the traffic congestion index could be [[1, 3], [1 / 3, 1]]. In practice, firstly, based on the hierarchical relationship of indicators in the parking resource hierarchy model, the importance of indicators is compared pairwise according to preset rules (e.g., the 1-9 scaling method), and finally, a set of judgment matrices is generated. For example, comparing the supply-demand ratio and the traffic congestion index, considering the former to be 3 times more important, the matrix [[1, 3], [1 / 3, 1]] is generated.

[0045] Third, for each judgment matrix in the above judgment matrix set, perform the following determination steps: Sub-step one: Determine the eigenvectors corresponding to the judgment matrix. These eigenvectors can be vectors reflecting the relative weights of each element in the matrix. In practice, first, determine the eigenvector corresponding to the largest eigenvalue of the judgment matrix. Sub-step two involves normalizing the aforementioned feature vectors to obtain a hierarchical single-rank weight vector. This hierarchical single-rank weight vector can be a normalized feature vector. In practice, first, based on the feature vectors, then, each element value in the feature vector is divided by the sum of all elements in the vector. Finally, a hierarchical single-rank weight vector is obtained where the sum of the weights of all elements is 1. For example, the feature vector [3, 1] is normalized to [0.75, 0.25]. The fourth step is to aggregate the single-ranking weight vectors at each level to obtain the subjective weight vector. This subjective weight vector can be an indicator weight vector based on expert judgment. First, based on the single-ranking weight vectors at each level (target layer, criterion layer, indicator layer), starting from the target layer, the weights of the upper-level elements are multiplied by the local weights of the lower-level elements relative to those upper-level elements, and then weighted and synthesized.

[0046] The fifth step is to use principal component analysis (PCA) to determine the objective weight vectors corresponding to the multiple parking indicator values. These objective weight vectors can be indicator weights based on data patterns. In practice, the multiple parking indicator values ​​are first standardized. Then, principal component analysis is used to extract principal components and calculate loadings to obtain the objective weight vectors.

[0047] The sixth step is to merge the subjective weight vector with the objective weight vector to obtain the comprehensive weight vector. In practice, first, a fusion coefficient is set for the subjective weight vector and the objective weight vector (for example, each accounting for 50%), then the weighted sum is calculated according to the coefficient, and finally the comprehensive weight vector is obtained.

[0048] Step 1033: Generate quantitative information on parking resources based on the comprehensive weight vector.

[0049] In some embodiments, the executing entity can generate parking resource quantification information based on the comprehensive weight vector. This parking resource quantification information can be a grid-based comprehensive quantitative evaluation result that includes a score and resource level. For example, the parking resource quantification information could be {Grid G001: Score 85, Resource Level: Excellent}.

[0050] In some optional implementations of certain embodiments, the execution entity may generate parking resource quantification information based on the aforementioned comprehensive weight vector, which may include the following steps: The first step is to determine the corresponding weighted comprehensive score information based on the aforementioned comprehensive weight vector and the multiple parking indicator values. This weighted comprehensive score information can be the sum of the weighted product of the multiple parking indicator values. For example: Supply-demand ratio (0.5 × 80) + Traffic congestion index (0.3 × 70) + Parking convenience index (0.2 × 90) = 79 points.

[0051] The second step is to standardize the weighted composite score information to obtain a standardized score. This standardized score can be a score normalized to a fixed range.

[0052] The third step is to determine the resource level corresponding to the standardized scores mentioned above, thus obtaining the grid level identifier. The resource level can be a rating of parking resource quality based on the scores. For example, 80 to 100 points is "Excellent," and 60 to 79 points is "Medium." The grid level identifier can be a symbol or text indicating the grid resource level. For example, "Excellent," "Medium," and "Poor."

[0053] The fourth step involves associating the aforementioned grid level identifier with the corresponding dynamic grid to generate parking resource quantification information with level labels. In practice, first, a unique identifier for the dynamic grid is obtained (e.g., "G-001"). Then, the grid level identifier is bound to the identifier. Finally, parking resource quantification information with level labels is generated.

[0054] Step 104: In response to receiving the parking request information from the target user, generate the target grid set corresponding to the parking request information based on the parking resource quantification information set.

[0055] In some embodiments, the execution entity may, in response to receiving parking request information from a target user, generate a target grid set corresponding to the parking request information based on a parking resource quantification information set. The target user may be the driver initiating the parking request. The parking request information may be parking-related demand data submitted by the target user. For example, the parking-related demand data may be {current location: [116.35, 39.90], destination: [116.37, 39.92], preference: “distance priority”}. The target grid set may be a collection of one or more parking grids recommended to the user.

[0056] In some optional implementations of certain embodiments, the execution entity may, in response to receiving parking request information from a target user, generate a target grid set corresponding to the parking request information based on a parking resource quantification information set, which may include the following steps: The first step, based on the parking request information mentioned above, is to extract the destination coordinates and user preference constraints of the target user. The destination coordinates can be the latitude and longitude coordinates of the target user's desired final destination. The user preference constraints can refer to the parking selection preferences explicitly or implicitly specified by the user in the request. For example, these constraints could be the user's selection of "lowest cost," "shortest walking distance," or "maximum probability of finding a parking space."

[0057] The second step involves filtering the aforementioned parking resource quantification information set based on the user preference conditions to generate a candidate grid set. This candidate grid set can be a preliminary set of alternative grids that meet the user's preferences. In practice, firstly, user preference constraints (e.g., "shortest walking distance") are applied. Then, based on these constraints, each grid record in the parking resource quantification information set is filtered (e.g., only grids with resource levels of "Excellent" and "Good" are recommended to the user, while filtering out grids with "Medium" and "Poor" ratings). Finally, all grids that meet the preference conditions are output, forming the candidate grid set.

[0058] The third step is to determine the Euclidean distance between the destination coordinates and the geometric center of each candidate grid in the candidate grid set to generate an initial distance set. This initial distance set can be the set of straight-line distances from the center point of each candidate grid to the destination coordinates.

[0059] The fourth step involves refining the initial distance set based on pre-acquired real-time road traffic conditions to obtain effective travel time information. These real-time road traffic conditions can be current road traffic status data, such as congestion on a certain road segment with an average speed of 15 km / h. In practice, first, real-time road traffic conditions are acquired (e.g., vehicle speed on congested road segments). Then, the actual travel time (distance ÷ real-time speed) is determined by combining the initial distance. Finally, the effective travel time information is obtained. For example, a 400-meter distance might take 7 minutes to travel due to congestion.

[0060] Fifth, based on the aforementioned effective passage time information and the aforementioned parking resource quantification information set, the candidate grids in the aforementioned candidate grid set are sorted to generate a grid recommendation sequence. The aforementioned grid recommendation sequence can be a list of candidate grids ranked by merit, for example, G-002 (8 minutes), G-005 (10 minutes).

[0061] Step 6: Generate a target grid set based on the preset filtering rules and the grid recommendation sequence mentioned above. The preset filtering rules can be conditions for selecting target grids; for example, selecting the top 3 grids in the grid recommendation sequence with a rating of "Excellent".

[0062] Step 105: Generate the guide path information corresponding to the target grid set, and send the guide path information to the target user terminal.

[0063] In some embodiments, the execution entity can generate guidance path information corresponding to the target grid set and send the guidance path information to the target user terminal. The guidance path information can be multi-terminal compatible data including road navigation and parking space guidance. The target user terminal can be a device used by the user to receive navigation information, such as a smartphone or in-vehicle navigation terminal.

[0064] In addressing the aforementioned technical challenges by employing technical solutions, the application scenario—urban core business districts, transportation hubs, and other areas with high parking demand and complex road conditions—often presents the following technical problems: traditionally recommended grids are ineffective due to temporary traffic control or severe congestion, and traditional navigation cannot provide seamless connections from roads to specific parking spaces. This wastes significant time and computational resources. Considering the following requirements for this application scenario: high reliability, seamless end-to-end guidance, and dynamic adaptability, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the execution entity may generate the boot path information corresponding to the target mesh set and send the boot path information to the target user terminal, which may include the following steps: The first step is to generate a valid guidance grid set by determining the real-time reachability status of each target grid in the aforementioned target grid set. The real-time reachability status can be the current accessibility status of the target grid; for example, if construction is underway at the entrance of a grid, its reachability status is "unreachable." The valid guidance grid set can be a subset of target grids excluding those that are unreachable. In practice, firstly, based on the real-time reachability status of the target grid set, it is determined whether each grid is accessible, and finally, unreachable grids are removed to generate the valid guidance grid set.

[0065] The second step involves matching the aforementioned effective guidance grid set with pre-acquired user historical behavior data to obtain personalized priority grids. This user historical behavior data can be records of the user's past parking preferences, such as historical data showing the user frequently chooses parking spaces near elevators. The personalized priority grids can be priority recommendation grids that match the user's historical habits. Priority recommendations include grids for parking spaces near elevators.

[0066] The third step involves generating an initial path set based on the personalized priority grid and the user's real-time location information corresponding to the parking request information. The user's real-time location information can be the target user's current latitude and longitude coordinates. The initial path set can be a basic path from the user's real-time location to the personalized priority grid. In practice, first, the user's real-time location information and the coordinates of the personalized priority grid are obtained; then, at least one basic route is planned; and finally, the initial path set is generated.

[0067] The fourth step involves optimizing the initial path set based on the acquired real-time dynamic traffic status information to obtain the final guided path. This real-time dynamic traffic status information can reflect the current traffic conditions of the road network. For example, a sudden congestion on a road segment with a speed of 10 km / h. The final guided path can be the optimal path selected after optimization based on the initial path set and real-time traffic information. In practice, firstly, based on the real-time dynamic traffic status information (e.g., congested road segments), congested routes are eliminated and the remaining paths are optimized. Finally, the final guided path is obtained. For example, avoiding congested main roads and selecting the shortest time path on secondary roads.

[0068] The fifth step is to obtain the real-time parking space status information of the endpoint grid corresponding to the final guidance path. The endpoint grid can be the target grid pointed to by the final guidance path. The real-time parking space status information can be the location data of currently available parking spaces within the endpoint grid, for example, parking space number 3 in area B of the "G-008" underground parking garage is available. In practice, firstly, parking space data of the endpoint grid is obtained through the parking lot sensor network. Then, currently available parking spaces are filtered, and finally, the real-time parking space status information is obtained.

[0069] Step 6: Based on the aforementioned real-time berth status information, generate an internal navigation path from the entrance of the endpoint grid to the target berth. This internal navigation path can be an in-yard guide from the endpoint grid entrance to the target berth. In practice, first, the locations of the endpoint grid entrance and the target berth (e.g., Area B, berth 3) are determined. Then, driving and walking routes within the yard are planned, and finally, the internal navigation path is generated.

[0070] The seventh step involves encapsulating the aforementioned internal navigation path and final boot path into a multi-terminal compatible format to obtain the boot path information. In practice, this is done by first integrating the final boot path and the internal navigation path, then encapsulating them in a multi-terminal compatible format (e.g., JSON) to obtain the boot path information.

[0071] Step 8: Send the aforementioned guidance path information to the target user terminal. In practice, first, obtain the target user terminal identifier (e.g., device ID), and then push the guidance path information through the wireless communication network.

[0072] The above-described steps, as an inventive point of this disclosure, solve the aforementioned technical problem: "Traditional methods cannot effectively reach the recommended grid due to temporary traffic control or severe congestion, and traditional parking guidance methods cannot provide seamless connection from roads to specific parking spaces, wasting a significant amount of time and computational resources." The reasons for these technical problems are as follows: traditional methods lack dynamic response capabilities to real-time traffic constraints; the guidance service stops at the parking lot entrance and is not linked to the internal parking space status; the recommendation strategy is simplistic and does not consider individual user preferences. This invention, by constructing a technical chain of "dynamic accessibility verification -> personalized matching -> seamless integration of internal and external paths," achieves high reliability, accuracy, and a seamless experience throughout the parking guidance service, saving users additional time, road traffic resources, and computational resources in finding parking spaces.

[0073] In addressing the technical challenges mentioned above, the application scenario—real-time parking guidance in complex urban traffic environments—often involves various user terminals and unstable network conditions, leading to the following technical problems: guidance path information transmission is easily interrupted by network fluctuations; terminal incompatibility causes navigation failure, wasting significant transmission resources and time. Considering the specific requirements of this application scenario—ensuring real-time and complete information transmission, and adapting to different terminal types and network conditions—we have decided to adopt the following solution: Optionally, the aforementioned executing entity may send the aforementioned boot path information to the target user terminal, which may include the following steps: The first step is to generate personalized transmission strategy information corresponding to the target user terminal. This personalized transmission strategy information can be a transmission scheme customized based on the terminal and network conditions. For example, a strategy of "high compression rate, low frequency update" could be developed for users in a weak 4G network environment. First, the device type, screen resolution, and current network signal strength of the target user terminal are determined. Then, the data encoding format, compression level, and update frequency parameters are determined based on the target user terminal's device type, screen resolution, and current network signal strength. Finally, a personalized transmission strategy tailored to the terminal and network conditions is generated.

[0074] The second step involves encoding and compressing the aforementioned guidance path information based on the personalized transmission strategy information to generate adaptive data packets. These adaptive data packets can be transmission data units that have undergone optimized encoding and compression. In practice, firstly, a suitable encoding format can be selected based on the transmission strategy (e.g., binary Protocol Buffers encoding for path coordinates). Then, a corresponding compression algorithm is applied to compress the data. Finally, adaptive data packets are generated.

[0075] The third step involves generating transmission channel information based on pre-acquired real-time network status monitoring data and a list of available transmission channels. This information includes a primary transmission channel and at least one backup transmission channel. The primary transmission channel can be a core data transmission link that is prioritized for use, such as a 5G mobile data network for a user terminal. The at least one backup transmission channel can be a backup communication path activated when the primary channel fails, such as public Wi-Fi provided in a shopping mall or a direct connection channel between devices. In practice, first, the status of each available transmission channel is determined, including latency, bandwidth, and stability. Then, the transmission cost and real-time quality of each channel are determined. Finally, the channel with the best quality is selected as the primary transmission channel, and 1-2 backup transmission channels are prepared as at least one backup channel.

[0076] The fourth step is to fragment the adaptive data packet to obtain fragmented data packets. These fragmented data packets can be a sequence of small data units formed by dividing the adaptive data packet. For example, a 200KB data packet can be fragmented into ten 20KB data segments.

[0077] The fifth step involves using the primary transmission channel and at least one backup transmission channel to transmit the fragmented data packets to the target user terminal in parallel. In practice, firstly, most data fragments are sent through the primary transmission channel. Then, critical fragments are simultaneously transmitted through the backup channel or used as redundancy backups. Finally, the transmission status of each fragment is determined to ensure that at least one channel successfully delivers each fragment. For example, fragments 1 to 8 are sent via 5G, and fragments 7 to 10 are sent via Wi-Fi as redundancy.

[0078] Step 6: In response to the target user terminal receiving the fragmented data packets, the fragmented data packets are reassembled to obtain the boot path information. Specifically, the target user terminal first receives data fragments from different channels. Then, the fragments are sorted and their integrity verified according to their sequence numbers. Finally, the valid fragments are reassembled to restore the complete boot path information.

[0079] The above-described steps, as an inventive point of this disclosure, solve the technical problem that "the transmission of guidance path information is easily interrupted due to network fluctuations and navigation failures caused by terminal incompatibility, wasting a large amount of transmission resources and time costs." The reasons for these technical problems are as follows: no transmission strategy was developed specifically for terminal characteristics, there was a lack of multi-channel redundancy design, and data transmission was not adapted to network conditions. This invention achieves stable and efficient transmission of guidance path information through personalized encoding, multi-channel parallel transmission, and data fragmentation and reassembly, saving resources and user waiting time caused by repeated transmission failures.

[0080] Step 106: In response to the target user terminal receiving the guidance path information, execute the parking guidance operation.

[0081] In some embodiments, the execution entity may perform a parking guidance operation in response to the target user terminal receiving the guidance path information.

[0082] In addressing the technical challenges mentioned above, and considering the application scenario—where users require real-time, seamless end-to-end parking guidance while driving—the following technical issues often arise: traditional methods can only display the path and cannot achieve a smooth transition and continuous guidance from the macroscopic road to the microscopic parking space, wasting significant time and computational resources. To meet the following requirements for this application scenario: continuous guidance, seamless operation, and support for real-time position calibration and progressive guidance, we decided to adopt the following solution: In some optional implementations of certain embodiments, the execution entity may perform a parking guidance operation in response to the target user terminal receiving the guidance path information, which may include the following steps: The first step is to extract the sequence of key points based on the aforementioned guidance path information. This sequence of key points can be a sequence of points from the guidance path information (e.g., turning points, entrances). In practice, first, the coordinates of key nodes are extracted from the guidance path information. Then, the sequence of key points is generated according to their coordinate order.

[0083] The second step involves matching the aforementioned sequence of key points along the path with the local map data of the target user's terminal to generate a visual navigation interface. This local map data can be pre-stored base map data on the target user's terminal device. The visual navigation interface can be a graphical interface displayed on the target user's terminal screen, integrating a map, guided route, vehicle location, and prompts. In practice, first, the target user's terminal's local map data is retrieved. Then, the sequence of key points along the path is overlaid onto the corresponding locations on the map. Finally, the visual navigation interface is generated.

[0084] The third step involves comparing the real-time location of the target user with the sequence of key points along the path using the positioning module and motion sensor of the target user's terminal, and then executing progressive parking guidance through the visual navigation interface to obtain real-time guidance information. The positioning module can be a component that acquires the terminal's location, such as a mobile phone's GPS module. The motion sensor can be a device that detects the terminal's motion state, such as a mobile phone's accelerometer or gyroscope. The real-time guidance information is dynamically updated navigation instructions. The progressive parking guidance can be navigation instructions pushed out gradually according to distance. In practice, first, the user's real-time location is obtained through the positioning module, and the driving status is detected through the motion sensor. Then, the real-time location is compared with the sequence of key points along the path, and real-time guidance information is gradually pushed out through the visual navigation interface. For example, if the user is detected approaching an intersection, the interface displays a "Approaching the left turn intersection" prompt.

[0085] The fourth step, based on the aforementioned real-time guidance information, is to determine the real-time distance between the target user's target vehicle and the target grid entrance corresponding to the guidance path information. This real-time distance information can be the current distance between the target vehicle and the target grid entrance. In practice, firstly, the vehicle's real-time positioning coordinates are continuously acquired. Then, the straight-line or path distance between these coordinates and the target grid entrance coordinates is determined. Finally, the continuously updated real-time distance information is output.

[0086] The fifth step involves triggering a navigation switching operation in response to the real-time distance information being less than a preset distance threshold, to obtain the internal navigation path from the aforementioned guidance path information. The preset distance threshold can be a predetermined distance value for triggering navigation switching. For example, it could be set to trigger switching when the distance to the parking lot entrance is 100 meters. The internal navigation path can be the driving route from inside the parking lot to a specific parking space. In practice, firstly, the real-time distance information is continuously compared with the preset distance threshold (e.g., 100 meters). Then, when the distance is less than the threshold, a switching command is sent. Finally, the preset internal navigation path data is extracted from the guidance path information.

[0087] The sixth step involves loading the map data corresponding to the internal navigation path to guide the target vehicle to the target parking space. This map data can be an internal parking lot map required for the internal navigation. In practice, first, the parking lot map data (parking space distribution) corresponding to the internal navigation path is loaded. Then, a visual navigation interface guides the vehicle to the target parking space to complete the parking guidance.

[0088] The above-described operation steps, as an inventive point of this disclosure, solve the technical problem mentioned in the background art: "Traditional methods can only simply display the path, failing to achieve a smooth transition and continuous guidance from macroscopic roads to microscopic parking spaces, wasting a significant amount of time and computing resources." The reasons for this technical problem are as follows: the lack of a mechanism for switching between road and parking lot navigation, and the absence of real-time location comparison and progressive guidance logic. This invention, through path key point matching, real-time location comparison, and seamless navigation switching, achieves continuous guidance throughout the entire process from road to parking space, saving time costs and energy wasted in searching for parking spaces.

[0089] The above-described embodiments of this disclosure have the following beneficial effects: The parking guidance method based on dynamic grid partitioning in some embodiments of this disclosure improves the efficiency of parking guidance and the utilization rate of urban parking resources, reducing the time users spend searching for parking spaces. Specifically, the reason for the low efficiency of parking guidance and the low utilization rate of urban parking resources is that existing technologies use only a single dimension of information for parking guidance, information updates are lagging, and personalized guidance capabilities are lacking, leading to resource mismatch and ineffective patrols. Based on this, the parking guidance method based on dynamic grid partitioning in some embodiments of this disclosure first acquires geographic information data, parking resource data, and dynamic activity data of the target area. By integrating geographic information, parking resources, and dynamic activity data, a comprehensive and multi-dimensional data foundation is provided for subsequent analysis, ensuring the accuracy and real-time nature of parking evaluation. Then, based on the aforementioned geographic information data, parking resource data, and dynamic activity data, a target dynamic grid for parking guidance is generated. By partitioning the dynamic grid based on the aforementioned geographic information data, parking resource data, and dynamic activity data, refined spatial management and dynamic adaptation of parking resources are achieved, improving the flexibility and accuracy of regional parking analysis. Next, for each dynamic grid of the aforementioned target dynamic grid, the following generation steps are performed: Based on the real-time parking-related data and pre-acquired historical parking-related data corresponding to the aforementioned dynamic grid, multiple corresponding parking indicator values ​​are determined. Multi-dimensional parking indicators are determined by combining real-time and historical parking-related data to comprehensively reflect the supply and demand, congestion, and convenience of parking resources, providing a quantitative basis for evaluation. A comprehensive weight vector corresponding to the aforementioned multiple parking indicator values ​​is determined. By determining the comprehensive weight vector, expert experience and data patterns are considered, making the evaluation results more scientific and reasonable. Based on the aforementioned comprehensive weight vector, quantitative parking resource information is generated. Generating quantitative parking resource information supports precise decision-making. Secondly, in response to receiving parking request information from target users, a target grid set corresponding to the aforementioned parking request information is generated based on the quantitative parking resource information set. Grids are filtered and sorted according to parking request information and preferences to achieve personalized parking recommendations, improving user satisfaction and guidance efficiency. Thirdly, guidance path information corresponding to the aforementioned target grid set is generated, and this guidance path information is sent to the target user terminal. The path from the user's location to the target grid is planned and optimized, combined with real-time traffic information, to ensure the accuracy and efficiency of guidance. Finally, in response to the target user terminal receiving the aforementioned guidance path information, a parking guidance operation is executed. The terminal performs path parsing, real-time navigation, and scene switching, completing the entire service from guidance to parking, thus improving parking guidance efficiency.

[0090] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a parking guidance device based on dynamic grid partitioning. These device embodiments are similar to... Figure 1Corresponding to the method embodiments shown, this parking guidance device based on dynamic grid partitioning can be specifically applied to various electronic devices.

[0091] like Figure 2 As shown, a parking guidance device 200 based on dynamic grid partitioning includes: an acquisition unit 201, a first generation unit 202, a first execution unit 203, a second generation unit 204, a generation and transmission unit 205, and a second execution unit 206. The acquisition unit 201 is configured to acquire geographic information data, parking resource data, and dynamic activity data of a target area. The first generation unit 202 is configured to generate a target dynamic grid for parking guidance based on the aforementioned geographic information data, parking resource data, and dynamic activity data. The first execution unit 203 is configured to perform the following generation steps for each dynamic grid of the target dynamic grid: determine multiple corresponding parking index values ​​based on real-time parking-related data and pre-acquired historical parking-related data corresponding to the dynamic grid; determine a comprehensive weight vector corresponding to the multiple parking index values; and generate parking resource quantification information based on the comprehensive weight vector. The second generation unit 204 is configured to, in response to receiving parking request information from a target user, generate a target grid set corresponding to the parking request information based on the parking resource quantification information set. The generation and transmission unit 205 is configured to generate guidance path information corresponding to the target grid set and send the guidance path information to the target user terminal. The second execution unit 206 is configured to perform a parking guidance operation in response to the target user terminal receiving the guidance path information.

[0092] It is understandable that the units described in the parking guidance device 200 based on dynamic grid partitioning are related to the reference... Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the image segmentation apparatus 200 and the units contained therein, and will not be repeated here.

[0093] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device (e.g., an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0094] like Figure 3As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0095] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0096] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0097] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0098] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0099] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire geographic information data, parking resource data, and dynamic activity data of the target area; generate a target dynamic grid for parking guidance based on the aforementioned geographic information data, parking resource data, and dynamic activity data; for each dynamic grid of the target dynamic grid, perform the following generation steps: determine multiple corresponding parking indicator values ​​based on real-time parking-related data and pre-acquired historical parking-related data corresponding to the dynamic grid; determine a comprehensive weight vector corresponding to the multiple parking indicator values; generate parking resource quantification information based on the comprehensive weight vector; in response to receiving parking request information from a target user, generate a target grid set corresponding to the parking request information based on the parking resource quantification information set; generate guidance path information corresponding to the target grid set, and send the guidance path information to the target user terminal; in response to the target user terminal receiving the guidance path information, perform a parking guidance operation.

[0100] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including an acquisition unit, a first generation unit, a first execution unit, a second generation unit, a generation and transmission unit, and a second execution unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit can also be described as "a unit that acquires geographic information data, parking resource data, and dynamic activity data of a target area."

[0103] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0104] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A parking guidance method based on dynamic grid partitioning, comprising: Acquire geographic information data, parking resource data, and dynamic activity data for the target area; Based on the geographic information data, the parking resource data, and the dynamic activity data, a target dynamic grid for parking guidance is generated. For each dynamic mesh of the target dynamic mesh, the following generation steps are performed: Based on the real-time parking-related data corresponding to the dynamic grid and the pre-acquired historical parking-related data, multiple corresponding parking indicator values ​​are determined. Determine the comprehensive weight vector corresponding to the multiple parking indicator values; Based on the comprehensive weight vector, quantitative information on parking resources is generated; In response to receiving parking request information from a target user, a target grid set corresponding to the parking request information is generated based on a parking resource quantification information set; Generate the guidance path information corresponding to the target grid set, and send the guidance path information to the target user terminal; In response to the target user terminal receiving the guidance path information, a parking guidance operation is performed.

2. The method according to claim 1, wherein, The acquisition of geographic information data, parking resource data, and dynamic activity data of the target area includes: Geographic information data is obtained through the target database interface, wherein the geographic information data includes: road network data and point of interest data; Acquire parking resource data through parking lot sensor networks; Dynamic activity data is acquired through a target mobile platform, wherein the dynamic activity data represents dynamic population distribution information.

3. The method according to claim 1, wherein, The step of generating a target dynamic grid for parking guidance based on the geographic information data, the parking resource data, and the dynamic activity data includes: Construct the initial rule grid for the target region; The initial rule grid is corrected using the road network data from the geographic information data to obtain the corrected grid; The point of interest data of the geographic information data, the parking resource data, and the corrected grid are associated to obtain the associated grid; Based on the dynamic activity data, the intensity value of human activity in each grid in the associated grid is determined; Using the human activity intensity value, the associated mesh is optimized to obtain an optimized mesh; Each grid cell in the optimized grid is assigned a unique grid identifier to generate the target dynamic grid.

4. The method according to claim 1, wherein, The process involves determining multiple parking indicator values ​​based on real-time parking-related data corresponding to the dynamic grid and pre-acquired historical parking-related data, including: Based on the real-time parking-related data and the historical parking-related data, predictive parking demand information corresponding to the dynamic grid is generated; Obtain the real-time parking supply information corresponding to the dynamic grid; Based on the predicted parking demand information and the real-time parking supply information, the corresponding supply-demand ratio index value is determined; Based on the traffic-related information of the roads associated with the dynamic grid, a traffic congestion index is generated; Based on the geographic information data and the parking resource data, the parking convenience index value of the dynamic grid is determined; The supply-demand ratio, traffic congestion index, and parking convenience index are integrated into multiple parking index values.

5. The method according to claim 1, wherein, Determining the comprehensive weight vector corresponding to the multiple parking indicator values ​​includes: Based on the aforementioned multiple parking indicator values, a parking resource hierarchy model is constructed; Based on the parking resource hierarchy model and preset rules, a set of judgment matrices is generated; For each judgment matrix in the set of judgment matrices, the following determination steps are performed; Determine the eigenvectors corresponding to the judgment matrix; The feature vector is normalized to obtain a hierarchical single-sorting weight vector; Aggregate the single-ranking weight vectors at each level to obtain the subjective weight vector; Principal component analysis was used to determine the objective weight vectors corresponding to the multiple parking index values. The subjective weight vector and the objective weight vector are fused to obtain a comprehensive weight vector.

6. The method according to claim 1, wherein, The process of generating parking resource quantification information based on the comprehensive weight vector includes: Based on the comprehensive weight vector and the multiple parking indicator values, the corresponding weighted comprehensive score information is determined; The weighted composite score information is standardized to obtain a standardized score; Determine the resource level corresponding to the standardized score to obtain the grid level identifier; By associating the grid level identifier with the corresponding dynamic grid, quantitative information on parking resources with level labels is generated.

7. The method according to claim 1, wherein, The step of generating the target grid set corresponding to the parking request information based on the parking resource quantification information set includes: Based on the parking request information, extract the destination coordinates and user preference constraints of the target user; Based on the user preference conditions, the quantitative information set of parking resources is filtered to generate a candidate grid set; Determine the Euclidean distance between the destination coordinates and the geometric center of each candidate grid in the candidate grid set to generate an initial distance set; Based on the pre-acquired real-time road traffic conditions, the initial distance set is corrected to obtain effective travel time information; Based on the effective passage time information and the parking resource quantification information set, each candidate grid in the candidate grid set is sorted to generate a grid recommendation sequence; A target grid set is generated based on the preset filtering rules and the grid recommendation sequence.

8. A parking guidance device based on dynamic grid partitioning, comprising: The acquisition unit is configured to acquire geographic information data, parking resource data, and dynamic activity data of the target area; The first generation unit is configured to generate a target dynamic grid for parking guidance based on the geographic information data, the parking resource data, and the dynamic activity data. The first execution unit is configured to perform the following generation steps for each dynamic mesh of the target dynamic mesh: Based on the real-time parking-related data corresponding to the dynamic grid and the pre-acquired historical parking-related data, multiple corresponding parking indicator values ​​are determined. Determine the comprehensive weight vector corresponding to the multiple parking indicator values; Based on the comprehensive weight vector, quantitative information on parking resources is generated; The second generation unit is configured to generate a target grid set corresponding to the parking request information based on the parking resource quantification information set in response to receiving parking request information from a target user. The generation and transmission unit is configured to generate the guidance path information corresponding to the target grid set and to send the guidance path information to the target user terminal. The second execution unit is configured to perform a parking guidance operation in response to the target user terminal receiving the guidance path information.

9. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images