A smart parking lot scheduling method and system based on the Internet of Things

Abstract

The present invention relates to the technical field of parking lot scheduling, and discloses a parking lot scheduling method and system for a smart parking lot based on the Internet of Things. The method comprises obtaining parking space occupancy data, target parking position information, estimated parking time and parking space topology; performing occupancy state judgment logic to obtain an occupancy state matrix; performing shortest path distance calculation to obtain a target distance matrix; performing inverse calculation to obtain an initial priority score; judging whether the parking space affects the entry and exit path according to the parking space topology, if so, generating a parking space influence relationship matrix; if not, not generating; dynamically adjusting the initial priority score to obtain a priority score matrix; performing weighted summation to obtain a comprehensive priority score matrix; performing greedy algorithm calculation to obtain a parking space allocation result; dynamically updating the parking space topology and the parking space influence relationship matrix to obtain a new parking space allocation result for parking space scheduling. The method can improve the efficiency of parking space scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field of parking lot parking space scheduling, and in particular to a parking space scheduling method and system for a smart parking lot based on the Internet of Things. Background Art

[0002] At present, smart parking lots are a new way to solve the parking problem. They use IoT technology to achieve intelligent management and scheduling of parking spaces to improve the utilization of parking spaces and the user's parking experience. However, in the scheduling of parking spaces in smart parking lots, how to dynamically adjust the priority of parking space allocation to meet the needs of different users is a key technical issue.

[0003] In one prior art, the existing smart parking lot scheduling system relies on preset scheduling rules, which cannot adapt to the dynamically changing scenarios in the parking lot, such as fluctuations in traffic flow, changes in parking space occupancy status, etc. In addition, the existing system does not fully consider the mutual influence between parking spaces when scheduling parking spaces. For example, the occupation of some parking spaces will hinder the entry and exit of other parking spaces, or cause the driving path of vehicles in the parking lot to change. These factors affect the efficiency and fairness of parking space scheduling.

[0004] The existing technology lacks an intelligent scheduling strategy that dynamically adjusts parking space allocation priorities based on real-time data, resulting in low parking space scheduling efficiency. Summary of the invention

[0005] The present invention provides a parking space scheduling method and device for a smart parking lot based on the Internet of Things, so as to improve the parking space scheduling efficiency of the parking lot.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a parking space scheduling method for a smart parking lot based on the Internet of Things, comprising:

[0007] Obtain parking space occupancy data, target parking location information, estimated parking time and parking space topology;

[0008] According to the parking space occupancy data, an occupancy state judgment logic is performed to obtain an occupancy state matrix;

[0009] According to the target parking position information, the occupancy state matrix and the parking space topology structure, a shortest path distance calculation is performed to obtain a target distance matrix;

[0010] Performing an inverse calculation based on the estimated parking duration and the target distance matrix to obtain an initial priority score;

[0011] According to the parking space topology structure, determine whether the parking space affects the entry and exit path, if so, generate a parking space influence relationship matrix; if not, do not generate;

[0012] According to the parking space influence relationship matrix, the initial priority score is dynamically adjusted to obtain a priority score matrix;

[0013] According to the priority score matrix, weighted summation is performed to obtain a comprehensive priority score matrix;

[0014] According to the comprehensive priority score matrix, a greedy algorithm is performed to obtain a parking space allocation result;

[0015] According to the parking space allocation result, the parking space topology structure and the parking space influence relationship matrix are dynamically updated to obtain a new parking space allocation result.

[0016] In an optional implementation, performing occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix includes:

[0017] According to the parking space occupancy data, occupancy marks and parking space numbers are performed to obtain an initial state matrix;

[0018] Determine whether there are missing data in the initial state matrix. If so, use the interpolation algorithm to supplement the missing values ​​to obtain a complete state matrix. If not, do nothing and use the initial state matrix as the complete state matrix.

[0019] According to the complete state matrix, a clustering algorithm is used for classification to obtain a clustering result;

[0020] According to the clustering results, a time series prediction algorithm is used to predict the future occupancy state to obtain a prediction state matrix;

[0021] According to the predicted state matrix, it is determined whether the deviation between the predicted value and the actual value exceeds a preset threshold. If so, the occupancy state logic is updated to obtain the occupancy state matrix; if not, no operation is performed.

[0022] In an optional implementation, the shortest path distance calculation is performed according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix, including:

[0023] According to the target parking position information and the parking space topology structure, a parking space weight value is calculated by a dynamic adjustment algorithm;

[0024] Calculate the shortest path distance according to the parking space weight value to obtain the shortest path distance;

[0025] Determine whether the shortest path distance is greater than a preset distance threshold, if so, recalculate the shortest path distance; if not, do not recalculate;

[0026] A matrix is ​​generated according to the shortest path distance and the occupancy state matrix to obtain a target distance matrix.

[0027] In an optional implementation, performing an inverse calculation based on the estimated parking duration and the target distance matrix to obtain an initial priority score includes:

[0028] According to the target distance matrix, data is extracted to obtain the distance between the parking space and the target position;

[0029] An inverse calculation is performed based on the distance between the parking space and the target location and the estimated parking time to obtain a priority score;

[0030] A normalization process is performed based on the priority scores to obtain initial priority scores.

[0031] In an optional implementation, judging whether a parking space affects an entry and exit path according to the parking space topology structure, and if so, generating a parking space influence relationship matrix; if not, not generating a parking space influence relationship matrix, includes:

[0032] According to the parking space topology structure and in combination with the obstacle distribution, a parking space map model is constructed;

[0033] According to the parking space map model, a path analysis algorithm is used to obtain a path influence degree;

[0034] It is determined whether the path influence degree is greater than a preset influence threshold value. If so, a parking space influence relationship matrix is ​​generated; if not, no matrix is ​​generated.

[0035] In an optional implementation, the initial priority score is dynamically adjusted according to the parking space influence relationship matrix to obtain a priority score matrix, including:

[0036] According to the parking space influence relationship matrix, the values ​​of each element in the matrix are analyzed to obtain the parking space influence degree;

[0037] According to the parking space influence, the difficulty of entering and exiting each adjacent parking space is evaluated, and the initial priority score is adjusted to obtain an adjusted priority score;

[0038] A score matrix is ​​generated according to the adjusted priority scores to obtain a priority score matrix.

[0039] In an optional implementation, performing weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix includes:

[0040] According to the priority score matrix, element-wise multiplication is performed with a preset fairness index weight and a preset efficiency index weight to obtain a weighted priority score matrix;

[0041] According to the weighted priority score matrix, based on the preset parking space occupancy index, element-level multiplication fusion is performed to obtain a preliminary priority score matrix;

[0042] According to the preliminary priority score matrix, the matrix elements are normalized to obtain the comprehensive priority score matrix.

[0043] In an optional implementation, performing a greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result includes:

[0044] Matching each element in the comprehensive priority score matrix with the user request information to screen out high-scoring vacant parking spaces;

[0045] Performing greedy calculation on the plurality of high-scoring vacant parking spaces to perform secondary sorting to obtain an optimal vacant parking space;

[0046] According to the optimal free parking space, the parking space status information is updated to obtain a parking space allocation result.

[0047] In a second aspect, the present invention provides a smart parking lot scheduling system based on the Internet of Things, comprising:

[0048] A data acquisition module is used to obtain parking space occupancy data, target parking location information, estimated parking time and parking space topology;

[0049] A state matrix module is used to perform occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix;

[0050] A distance matrix module, used to calculate the shortest path distance according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix;

[0051] an inverse calculation module, configured to perform an inverse calculation based on the estimated parking duration and the target distance matrix to obtain an initial priority score;

[0052] A relationship matrix module is used to determine whether a parking space affects an entry and exit path according to the parking space topology structure, and if so, generate a parking space influence relationship matrix; if not, do not generate a parking space influence relationship matrix;

[0053] A scoring matrix module, used to dynamically adjust the initial priority score according to the parking space influence relationship matrix to obtain a priority score matrix;

[0054] A weighted summation module, used for performing weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix;

[0055] A greedy algorithm module, used to perform greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result;

[0056] The result output module is used to dynamically update the parking space topology structure and the parking space influence relationship matrix according to the parking space allocation result to obtain a new parking space allocation result.

[0057] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned methods for scheduling parking spaces in a smart parking lot based on the Internet of Things.

[0058] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned smart parking lot parking space scheduling methods based on the Internet of Things.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] The present invention discloses a parking space scheduling method for a smart parking lot based on the Internet of Things, comprising obtaining parking space occupancy data, target parking position information, estimated parking time and parking space topological structure; performing occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix; performing shortest path distance calculation according to the target parking position information, the occupancy state matrix and the parking space topological structure to obtain a target distance matrix; performing inverse calculation according to the estimated parking time and the target distance matrix to obtain an initial priority score; judging whether the parking space affects the entry and exit path according to the parking space topological structure, if so, generating a parking space influence relationship matrix; if not, not generating; dynamically adjusting the initial priority score according to the parking space influence relationship matrix to obtain a priority score matrix; performing weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix; performing greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result; dynamically updating the parking space topological structure and the parking space influence relationship matrix according to the parking space allocation result to obtain a new parking space allocation result.

[0061] The present invention obtains parking space occupancy data in real time, performs occupancy status judgment logic, obtains an occupancy status matrix, performs shortest path distance calculation, and obtains a target distance matrix to determine the paths of multiple potential parking spaces. Then, by estimating the parking time, an inverse calculation is performed to obtain the initial priority score, and the score is adjusted based on the parking space influence relationship matrix. The present invention integrates fairness and efficiency indicators, generates a comprehensive priority score matrix, and uses a greedy algorithm to allocate parking spaces. At the same time, the present invention dynamically adjusts the weight according to the changing trend of traffic flow, and updates the parking space topology structure and the influence relationship matrix in real time, so as to realize dynamic scheduling optimization of parking space resources and improve the efficiency of parking space scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a flowchart of a smart parking lot scheduling method based on the Internet of Things provided by the first embodiment of the present invention;

[0063] Figure 2 It is a structural diagram of a smart parking lot scheduling system based on the Internet of Things provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] Reference Figure 1 The first embodiment of the present invention provides a parking space scheduling method for a smart parking lot based on the Internet of Things, comprising the following steps:

[0066] S11, obtaining parking space occupancy data, target parking location information, estimated parking time and parking space topology;

[0067] S12, performing occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix;

[0068] S13, performing shortest path distance calculation according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix;

[0069] S14, performing an inverse calculation based on the estimated parking duration and the target distance matrix to obtain an initial priority score;

[0070] S15, judging whether the parking space affects the entry and exit paths according to the parking space topology structure, and if so, generating a parking space influence relationship matrix; if not, not generating a parking space influence relationship matrix;

[0071] S16, dynamically adjusting the initial priority score according to the parking space influence relationship matrix to obtain a priority score matrix;

[0072] S17, performing weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix;

[0073] S18, performing a greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result;

[0074] S19, dynamically updating the parking space topology structure and the parking space influence relationship matrix according to the parking space allocation result to obtain a new parking space allocation result.

[0075] In step S11, parking space occupancy data, target parking location information, estimated parking time and parking space topology are obtained, including:

[0076] In a specific embodiment, the occupancy status of parking spaces is detected in real time through geomagnetic sensors, cameras or infrared sensors, and users report the status of parking spaces through mobile applications or parking lot systems, and the occupancy status of parking spaces is predicted in combination with historical parking data. When entering the parking lot, users specify the target location through mobile applications or terminal devices, and the target area is automatically recommended based on the user's historical parking habits or preferences. When entering the parking lot, users enter the estimated parking time through mobile applications or terminal devices, or the parking time is predicted based on the user's historical parking records. The parking lot management system pre-configures the parking space topology based on the topological structure generated by the architectural design of the parking lot or by scanning the parking lot layout in real time through a laser radar or camera.

[0077] It should be noted that parking space occupancy data refers to the real-time occupancy status (free or occupied) of each parking space in the parking lot. In this embodiment, 0 means free and 1 means occupied. Target parking location information refers to the target area or specific location where the user wants to park. It can be a specific parking space number (such as A-01). It can also be a certain area (such as an area near an elevator). Estimated parking time refers to the user's estimated parking time, in minutes or hours (such as 30 minutes, 2 hours). The parking space topology refers to the layout and connection relationship of parking spaces in the parking lot, including the distance between parking spaces, paths, entrance and exit locations, etc. There are mainly two forms: graph structure: parking spaces are nodes, paths are edges, and weights represent distances or travel time; matrix form: represents the distance or connectivity between parking spaces.

[0078] In step S12, an occupancy state judgment logic is performed according to the parking space occupancy data to obtain an occupancy state matrix, including:

[0079] According to the parking space occupancy data, occupancy marks and parking space numbers are performed to obtain an initial state matrix;

[0080] Determine whether there are missing data in the initial state matrix. If so, use the interpolation algorithm to supplement the missing values ​​to obtain a complete state matrix. If not, do nothing and use the initial state matrix as the complete state matrix.

[0081] According to the complete state matrix, a clustering algorithm is used for classification to obtain a clustering result;

[0082] According to the clustering results, a time series prediction algorithm is used to predict the future occupancy state to obtain a prediction state matrix;

[0083] According to the predicted state matrix, it is determined whether the deviation between the predicted value and the actual value exceeds a preset threshold. If so, the occupancy state logic is updated to obtain the occupancy state matrix; if not, no operation is performed.

[0084] In a specific embodiment, first, data is collected through parking sensors and cameras. These data include vehicle entry and exit information, parking space occupancy status, etc. For example, the geomagnetic sensor can detect the presence of metal objects, and the optical sensor determines the parking space status by reflected light. The image data collected by the camera is processed by a computer vision algorithm to identify vehicle outlines, license plates, and other information. Each parking space has a unique number, such as A01, B03, etc. The system associates the sensor signal, image data, parking space number, and timestamp. The timestamp is accurate to seconds, such as "2024-06-2214:30:05", to ensure the timing of the data. The occupancy status judgment logic combines multiple factors, such as sensor signal duration, image recognition results, etc. If it is determined to be occupied, the parking space occupancy flag is set to true. The initial state matrix records the occupancy status of each parking space at different time points. Assuming that there are 100 parking spaces in the parking lot, the observation period is 24 hours, and the sampling interval is 5 minutes, the matrix dimension is 100×288. The matrix elements are 0 or 1, indicating free or occupied, respectively. Interpolation algorithms, such as linear interpolation or spline interpolation, can be used to estimate missing values ​​based on data from nearby time points to obtain a complete state matrix. Cluster analysis helps identify parking space usage patterns. K-means or hierarchical clustering algorithms can be used to classify parking spaces into two categories: high-frequency occupancy and low-frequency occupancy. Clustering features may include average daily occupancy time, peak occupancy rate, etc. Highly occupied parking spaces are located in convenient locations or close to popular facilities. For high-frequency occupied parking spaces, the system uses time series prediction algorithms such as ARIMA or LSTM neural networks to predict the occupancy status in the future. The prediction results form a predicted state matrix and are compared with the actual collected data. If the prediction accuracy is lower than the preset threshold, such as 85%, the occupancy status judgment logic needs to be updated.

[0085] In step S13, the shortest path distance is calculated according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix, including:

[0086] According to the target parking position information and the parking space topology structure, a parking space weight value is calculated by a dynamic adjustment algorithm;

[0087] Calculate the shortest path distance according to the parking space weight value to obtain the shortest path distance;

[0088] Determine whether the shortest path distance is greater than a preset distance threshold, if so, recalculate the shortest path distance; if not, do not recalculate;

[0089] A matrix is ​​generated according to the shortest path distance and the occupancy state matrix to obtain a target distance matrix.

[0090] In a specific embodiment, the real-time traffic monitoring system collects traffic flow and road congestion through various sensors and cameras. The cameras distributed in various areas can determine the degree of road congestion through image recognition technology. The dynamic weight adjustment algorithm adjusts the weight value of each parking space according to the real-time road conditions and parking space topology information. When the traffic flow is large or the road congestion is serious, the weight value of the parking space in the area is increased and its priority is reduced. When the traffic flow is small and the road is unobstructed, the weight value of the parking space in the area is reduced and its priority is increased. The shortest path distance from each free parking space to the target position is calculated, and a target distance matrix containing the shortest path distance from each free parking space to the target position is generated. For example, even if parking space A is closer than parking space B in a straight-line distance, if the path to A is seriously congested, the algorithm will recommend B as a better choice.

[0091] It should be noted that when calculating the shortest path distance, the Dijkstra algorithm (a greedy algorithm) is used to determine the shortest path from each free parking space to the target location based on the parking space topology and real-time traffic information. When calculating the shortest path from the parking space to the target location, the parking space topology provides information on nodes (parking spaces and intersections) and edges (paths). Real-time traffic information can affect the weight of the edge (such as distance or time). The Dijkstra algorithm traverses all nodes to find the shortest path. If the road congestion on a path changes, the distance of the path is recalculated to ensure real-time update of the path distance. Through the real-time traffic monitoring system, the traffic flow and road congestion data in the parking area are continuously obtained, and the parking space weight and target distance matrix are recalculated at preset time intervals.

[0092] In step S14, an inverse calculation is performed based on the estimated parking duration and the target distance matrix to obtain an initial priority score, including:

[0093] According to the target distance matrix, data is extracted to obtain the distance between the parking space and the target position;

[0094] An inverse calculation is performed based on the distance between the parking space and the target location and the estimated parking time to obtain a priority score;

[0095] A normalization process is performed based on the priority scores to obtain initial priority scores.

[0096] It should be noted that the distance between each free parking space and the target position is extracted from the pre-established target distance matrix, denoted as D i , in meters, where i is the parking space number and the estimated parking time is T. The inverse calculation method is used, and the priority score P is calculated according to the formula i =T / D i , calculate the priority score P of each free parking space i . The calculated priority score P i Normalize the scores to ensure that they are between 0 and 1, and get the initial priority score. Determine whether there are multiple parking spaces with the same highest priority score. If so, further sort them based on the frequency of use of the parking spaces or the distance from the entrance. Output the final priority sorting list for users to choose the best parking space.

[0097] In a specific embodiment, assume that there are three free parking spaces A, B, and C, and their distances to the target location are 100 meters, 200 meters, and 300 meters, respectively. For the parking time T of 4 hours, the distances to the three parking spaces A, B, and C are 100 meters, 200 meters, and 300 meters, respectively, and their initial priority scores are:

[0098] A parking space priority score: P A =T / D A =4 / 100=0.04

[0099] B parking space priority score: P B =T / D B =4 / 200=0.02

[0100] C parking space priority score: P C =T / D C =4 / 300≈0.0013

[0101] Normalization:

[0102] Initial priority score P for parking space A A '= =1

[0103] Initial priority score P for parking space B B '= ≈0.5

[0104] C parking space initial priority score P C '= =0

[0105] According to the above initial priority scores, the parking space priority ranking can be obtained as A>B>C, and parking space A is the preferred parking space.

[0106] In step S15, according to the parking space topology structure, it is determined whether the parking space affects the entry and exit path. If so, a parking space influence relationship matrix is ​​generated; if not, no matrix is ​​generated, including:

[0107] According to the parking space topology structure and in combination with the obstacle distribution, a parking space map model is constructed;

[0108] According to the parking space map model, a path analysis algorithm is used to obtain a path influence degree;

[0109] It is determined whether the path influence degree is greater than a preset influence threshold value. If so, a parking space influence relationship matrix is ​​generated; if not, no matrix is ​​generated.

[0110] In a specific embodiment, there are 100 parking spaces in the underground parking lot of a shopping mall, which are distributed in 5 areas, with 20 parking spaces in each area. The adjacency relationship between parking spaces can be represented by an adjacency matrix, and obstacles such as pillars and walls are marked at the corresponding positions. Through parking space sensors or video analysis, it is possible to accurately determine whether a parking space is occupied. Assuming that the parking space numbered A15 is occupied, the system immediately marks the position in the parking space map and records the occupation time, vehicle information, etc. When analyzing the impact of the target parking space occupancy on the surrounding parking spaces, the vehicle entry and exit paths need to be considered. Taking the A15 parking space as an example, the new entry and exit paths of the affected parking spaces can be calculated through path analysis algorithms, such as the Dijkstra algorithm. If the original path is blocked, the system will look for alternative paths and evaluate their feasibility. The system can set the difficulty level, such as 1-5, and the parking space difficulty increases from the original level 2 to level 4. If the impact exceeds the preset threshold, such as the difficulty increases by more than 2 levels, it will be included in the parking space impact relationship matrix. The matrix elements can use values ​​from 0 to 1 to represent the degree of influence, with 0 representing no influence and 1 representing complete influence.

[0111] Assume that there are two parking spaces A and B in a parking lot. The occupation of parking space A will hinder the entry and exit of parking space B. By constructing a parking space graph model and applying a path analysis algorithm, it is calculated that the path influence of parking space A on parking space B is 0.7, while the preset influence threshold is 0.5. Since 0.7 is greater than 0.5, the occupation of parking space A significantly affects the entry and exit path of parking space B. The system will generate a parking space influence relationship matrix to record the degree of influence of parking space A on parking space B.

[0112] In step S16, the initial priority score is dynamically adjusted according to the parking space influence relationship matrix to obtain a priority score matrix, including:

[0113] According to the parking space influence relationship matrix, the values ​​of each element in the matrix are analyzed to obtain the parking space influence degree;

[0114] According to the parking space influence, the difficulty of entering and exiting each adjacent parking space is evaluated, and the initial priority score is adjusted to obtain an adjusted priority score;

[0115] A score matrix is ​​generated according to the adjusted priority scores to obtain a priority score matrix.

[0116] In a specific embodiment, the parking space influence degree is obtained by analyzing the value of each element in the parking space relationship influence matrix. The value of each element in the matrix ranges from 0 to 1, 0 means no influence, and 1 means complete influence. When parsing the matrix, the system will set a threshold (such as 0.6). If the parking space exceeds this threshold, it will be considered to have a significant impact. For example, the element (3, 5) = 0.7 means that when parking space No. 3 is occupied, the parking space influence on parking space No. 5 is 70%. 0.7>0.6 (threshold), then the system identifies it as a significant impact. Then evaluate the difficulty of the parking space. Assume that the parking lot is divided into three areas, A, B, and C, and the difficulty coefficients of each area are 1.2, 1, and 0.8 respectively. If parking space No. 8 is located in area B, its initial priority score is 80 points. Considering the difficulty coefficient of area B, its score will be reduced accordingly for dynamic adjustment.

[0117] It should be noted that when allocating parking spaces, the system will give priority to parking spaces with low difficulty coefficients. Combined with the path score and the number of areas, the difficulty of entering and exiting each adjacent parking space is evaluated to quantify the impact. According to the impact of the parking space, the initial priority score of the target parking space is adjusted to generate an adjusted priority score matrix. The parking space map model is dynamically updated to reflect the changes in the parking space occupancy status in real time to ensure the timeliness and accuracy of the priority score matrix. According to the adjusted priority score matrix, the parking space allocation strategy is optimized to improve the efficiency of parking space utilization.

[0118] In step S17, a weighted sum is performed according to the priority score matrix to obtain a comprehensive priority score matrix, including:

[0119] According to the priority score matrix, element-wise multiplication is performed with a preset fairness index weight and a preset efficiency index weight to obtain a weighted priority score matrix;

[0120] According to the weighted priority score matrix, based on the preset parking space occupancy index, element-level multiplication fusion is performed to obtain a preliminary priority score matrix;

[0121] According to the preliminary priority score matrix, the matrix elements are normalized to obtain the comprehensive priority score matrix.

[0122] It should be noted that the preset fairness index weight refers to the allocation of parking spaces with a focus on fairness, and the preset efficiency index weight refers to the allocation of parking spaces with a focus on efficiency. The parking space occupancy rate index refers to the frequency of use of each parking space. For example, the parking space occupancy rate index of parking space No. 1 is 0.9, indicating that the parking space is occupied all year round. The preset fairness index weight and the preset efficiency index weight are element-wise multiplied with the priority score matrix to ensure the fairness and efficiency of the result. The result obtained by fusing with the parking space occupancy rate index is given a higher priority. During the fusion process, if the parking space occupancy rate index is lower than the preset threshold, the score of the corresponding parking space is downgraded. The normalization process uses the maximum and minimum normalization method to ensure that the relative relationship of the score values ​​remains unchanged. The parking spaces are sorted according to the score values ​​of the comprehensive priority score matrix, and a parking space priority list is generated, which is stored in the database for subsequent parking space allocation algorithm calls. The parking spaces are sorted in descending order, and parking spaces with higher scores are allocated first.

[0123] In a specific embodiment, for a set threshold of 0.3, if the parking space occupancy index of parking space No. 2 is only 0.2, the system will appropriately lower the score in the comprehensive priority score matrix to guide more vehicles to use this relatively free parking space, thereby improving the overall parking efficiency.

[0124] In step S18, a greedy algorithm is performed according to the comprehensive priority score matrix to obtain a parking space allocation result, including:

[0125] Matching each element in the comprehensive priority score matrix with the user request information to screen out high-scoring vacant parking spaces;

[0126] Performing greedy calculation on the plurality of high-scoring vacant parking spaces to perform secondary sorting to obtain an optimal vacant parking space;

[0127] According to the optimal free parking space, the parking space status information is updated to obtain a parking space allocation result.

[0128] It should be noted that the system receives parking requests from users and extracts key information from the requests, such as user type, request time, and specific parking requirements. The system matches the user request information with the comprehensive priority scores of the available parking spaces, and selects the available parking spaces with the highest scores. If there are multiple parking spaces with the highest scores, the parking spaces are further sorted according to their distance from the user's current location, and the nearest parking space is selected for allocation. The parking space allocation results are generated and notified to the user through the system, including the specific location and navigation information of the parking space. The parking space status information is updated, the allocated parking spaces are marked as occupied, and synchronized to the parking space management system in real time to ensure the accuracy of subsequent request processing.

[0129] In a specific embodiment, when the system receives a parking request from a user, it extracts key information. For example, the user is a VIP member who wants to park an electric SUV at 2 pm and needs charging facilities. The system will match these requirements with the characteristics of the parking space and filter out the most suitable available parking space. If there are multiple parking spaces with the highest scores, the system will conduct a secondary screening. Suppose there are two parking spaces with the same score, one on the first underground floor and the other on the third underground floor. The system will give priority to allocating parking spaces closer to the ground to provide a more convenient parking experience. After the parking space is allocated, the system will immediately send a notification to the user, including detailed location information and navigation instructions. For example: "Your parking space has been allocated to No. 3, Zone A, First Basement Floor. Please follow the signs." At the same time, the system will update the status of the parking space to "Occupied" to ensure that it will not be allocated repeatedly.

[0130] In step S19, according to the parking space allocation result, the parking space topology structure and the parking space influence relationship matrix are dynamically updated to obtain a new parking space allocation result, including:

[0131] According to the parking space allocation result, the parking space number and allocation status are parsed to form an initial allocation data set. Through the system interface, the parking space status management system is accessed to extract the current parking space occupancy status matrix. The initial allocation data set is compared with the occupancy status matrix to determine the parking space information that needs to be updated. According to the comparison results, a new parking space occupancy status matrix is ​​generated to mark the parking space occupancy status. Through the data processing module, the updated parking space topology structure and the parking space influence relationship matrix are converted into a format that can be recognized by the system. Using the synchronous operation interface, the converted data is pushed to the parking space status management system to complete the status synchronization. Comprehensive traffic flow information, if the traffic flow data exceeds the preset threshold, the parking space shortage warning mechanism is triggered. After the warning mechanism is activated, the weights of the fairness and efficiency indicators are dynamically adjusted, and the weight values ​​are recalculated using the preset algorithm. According to the adjusted weights, the priority generation algorithm is used to regenerate the comprehensive priority score matrix to optimize the parking space allocation strategy. Repeat the above steps S11 to S18 to obtain a new parking space scheduling result and perform real-time dynamic updates.

[0132] In summary, the present invention discloses a parking space scheduling method for a smart parking lot based on the Internet of Things, including obtaining parking space occupancy data, target parking position information, estimated parking time and parking space topology; performing occupancy status judgment logic according to the parking space occupancy data to obtain an occupancy status matrix; performing shortest path distance calculation according to the target parking position information, the occupancy status matrix and the parking space topology to obtain a target distance matrix; performing inverse calculation according to the estimated parking time and the target distance matrix to obtain an initial priority score; judging whether the parking space affects the entry and exit path according to the parking space topology, if so, generating a parking space influence relationship matrix; if not, not generating; dynamically adjusting the initial priority score according to the parking space influence relationship matrix to obtain a priority score matrix; performing weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix; performing greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result; dynamically updating the parking space topology and the parking space influence relationship matrix according to the parking space allocation result to obtain a new parking space allocation result. The present invention improves the parking space scheduling efficiency by dynamically adjusting the priority of parking space allocation.

[0133] Reference Figure 2 The second embodiment of the present invention provides a smart parking lot scheduling system based on the Internet of Things, including:

[0134] A data acquisition module is used to obtain parking space occupancy data, target parking location information, estimated parking time and parking space topology;

[0135] A state matrix module is used to perform occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix;

[0136] A distance matrix module, used to calculate the shortest path distance according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix;

[0137] an inverse calculation module, configured to perform an inverse calculation based on the estimated parking duration and the target distance matrix to obtain an initial priority score;

[0138] A relationship matrix module is used to determine whether a parking space affects an entry and exit path according to the parking space topology structure, and if so, generate a parking space influence relationship matrix; if not, do not generate a parking space influence relationship matrix;

[0139] A scoring matrix module, used to dynamically adjust the initial priority score according to the parking space influence relationship matrix to obtain a priority score matrix;

[0140] A weighted summation module, used for performing weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix;

[0141] A greedy algorithm module, used to perform greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result;

[0142] The result output module is used to dynamically update the parking space topology structure and the parking space influence relationship matrix according to the parking space allocation result to obtain a new parking space allocation result.

[0143] Preferably, the state matrix module is specifically used to perform occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix, including:

[0144] According to the parking space occupancy data, occupancy marks and parking space numbers are performed to obtain an initial state matrix;

[0145] Determine whether there are missing data in the initial state matrix. If so, use the interpolation algorithm to supplement the missing values ​​to obtain a complete state matrix. If not, do nothing and use the initial state matrix as the complete state matrix.

[0146] According to the complete state matrix, a clustering algorithm is used for classification to obtain a clustering result;

[0147] According to the clustering results, a time series prediction algorithm is used to predict the future occupancy state to obtain a prediction state matrix;

[0148] According to the predicted state matrix, it is determined whether the deviation between the predicted value and the actual value exceeds a preset threshold. If so, the occupancy state logic is updated to obtain the occupancy state matrix; if not, no operation is performed.

[0149] Preferably, the distance matrix module is specifically used to perform shortest path distance calculation according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix, including:

[0150] According to the target parking position information and the parking space topology structure, a parking space weight value is calculated by a dynamic adjustment algorithm;

[0151] Calculate the shortest path distance according to the parking space weight value to obtain the shortest path distance;

[0152] Determine whether the shortest path distance is greater than a preset distance threshold, if so, recalculate the shortest path distance; if not, do not recalculate;

[0153] A matrix is ​​generated according to the shortest path distance and the occupancy state matrix to obtain a target distance matrix.

[0154] Preferably, the inverse calculation module is specifically used to perform inverse calculation according to the estimated parking time and the target distance matrix to obtain an initial priority score, including:

[0155] According to the target distance matrix, data is extracted to obtain the distance between the parking space and the target position;

[0156] An inverse calculation is performed based on the distance between the parking space and the target location and the estimated parking time to obtain a priority score;

[0157] A normalization process is performed based on the priority scores to obtain initial priority scores.

[0158] Preferably, the relationship matrix module is specifically used to determine whether the parking space affects the entry and exit path according to the parking space topology structure, and if so, generate a parking space influence relationship matrix; if not, do not generate it, including:

[0159] According to the parking space topology structure and in combination with the obstacle distribution, a parking space map model is constructed;

[0160] According to the parking space map model, a path analysis algorithm is used to obtain a path influence degree;

[0161] It is determined whether the path influence degree is greater than a preset influence threshold value. If so, a parking space influence relationship matrix is ​​generated; if not, no matrix is ​​generated.

[0162] Preferably, the score matrix module is specifically used to dynamically adjust the initial priority score according to the parking space influence relationship matrix to obtain a priority score matrix, including:

[0163] According to the parking space influence relationship matrix, the values ​​of each element in the matrix are analyzed to obtain the parking space influence degree;

[0164] According to the parking space influence, the difficulty of entering and exiting each adjacent parking space is evaluated, and the initial priority score is adjusted to obtain an adjusted priority score;

[0165] A score matrix is ​​generated according to the adjusted priority scores to obtain a priority score matrix.

[0166] Preferably, the weighted summation module is specifically used to perform weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix, including:

[0167] According to the priority score matrix, element-wise multiplication is performed with a preset fairness index weight and a preset efficiency index weight to obtain a weighted priority score matrix;

[0168] According to the weighted priority score matrix, based on the preset parking space occupancy index, element-level multiplication fusion is performed to obtain a preliminary priority score matrix;

[0169] According to the preliminary priority score matrix, the matrix elements are normalized to obtain the comprehensive priority score matrix.

[0170] Preferably, the greedy algorithm module is specifically used to perform greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result, including:

[0171] Matching each element in the comprehensive priority score matrix with the user request information to screen out high-scoring vacant parking spaces;

[0172] Performing greedy calculation on the plurality of high-scoring vacant parking spaces to perform secondary sorting to obtain an optimal vacant parking space;

[0173] According to the optimal free parking space, the parking space status information is updated to obtain a parking space allocation result.

[0174] It should be noted that the IoT-based smart parking lot parking space scheduling system provided in an embodiment of the present invention is used to execute all the process steps of the IoT-based smart parking lot parking space scheduling method in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0175] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, the steps in the above-mentioned data acquisition method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0176] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0177] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0178] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0179] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0180] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0181] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0182] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A parking space scheduling method for a smart parking lot based on the Internet of Things, characterized in that: include: Obtain parking space occupancy data, target parking location information, estimated parking time and parking space topology; According to the parking space occupancy data, an occupancy state judgment logic is performed to obtain an occupancy state matrix; According to the target parking position information, the occupancy state matrix and the parking space topology structure, a shortest path distance calculation is performed to obtain a target distance matrix; Performing an inverse calculation based on the estimated parking duration and the target distance matrix to obtain an initial priority score; According to the parking space topology structure, determine whether the parking space affects the entry and exit path, and if so, generate a parking space influence relationship matrix; If not, it is not generated; According to the parking space influence relationship matrix, the initial priority score is dynamically adjusted to obtain a priority score matrix; According to the priority score matrix, weighted summation is performed to obtain a comprehensive priority score matrix; According to the comprehensive priority score matrix, a greedy algorithm is performed to obtain a parking space allocation result; According to the parking space allocation result, dynamically updating the parking space topology structure and the parking space influence relationship matrix to obtain a new parking space allocation result; The weighted summation is performed according to the priority score matrix to obtain a comprehensive priority score matrix, including: According to the priority score matrix, element-wise multiplication is performed with a preset fairness index weight and a preset efficiency index weight to obtain a weighted priority score matrix; According to the weighted priority score matrix, based on the preset parking space occupancy index, element-level multiplication fusion is performed to obtain a preliminary priority score matrix; According to the preliminary priority score matrix, the matrix elements are normalized to obtain a comprehensive priority score matrix; The method of performing a greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result includes: Matching each element in the comprehensive priority score matrix with the user request information to filter out the highest-scoring parking space among the available parking spaces; If there is a parking space with the highest score, the parking space with the highest score is used as the optimal free parking space; If there are multiple parking spaces with the highest scores, greedy calculation is performed on the multiple parking spaces with the highest scores to perform secondary sorting according to the distance between the parking spaces and the user's current location, and the nearest parking space is selected as the optimal free parking space; According to the optimal free parking space, the parking space status information is updated to obtain a parking space allocation result.

2. The method for scheduling parking spaces in a smart parking lot based on the Internet of Things according to claim 1 is characterized in that: The method of performing occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix includes: According to the parking space occupancy data, occupancy marks and parking space numbers are performed to obtain an initial state matrix; Determine whether there are missing data in the initial state matrix. If so, use the interpolation algorithm to supplement the missing values ​​to obtain a complete state matrix. If not, do nothing and use the initial state matrix as the complete state matrix. According to the complete state matrix, a clustering algorithm is used for classification to obtain a clustering result; According to the clustering results, a time series prediction algorithm is used to predict the future occupancy state to obtain a prediction state matrix; According to the predicted state matrix, it is determined whether the deviation between the predicted value and the actual value exceeds a preset threshold. If so, the occupancy state logic is updated to obtain the occupancy state matrix; if not, no operation is performed.

3. The method for scheduling parking spaces in a smart parking lot based on the Internet of Things according to claim 1 is characterized in that: The shortest path distance calculation is performed according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix, including: According to the target parking position information and the parking space topology structure, a parking space weight value is calculated by a dynamic adjustment algorithm; Calculate the shortest path distance according to the parking space weight value to obtain the shortest path distance; Determine whether the shortest path distance is greater than a preset distance threshold, if so, recalculate the shortest path distance; if not, do not recalculate; A matrix is ​​generated according to the shortest path distance and the occupancy state matrix to obtain a target distance matrix.

4. The method for scheduling parking spaces in a smart parking lot based on the Internet of Things according to claim 1 is characterized in that: The inverse calculation is performed according to the estimated parking duration and the target distance matrix to obtain an initial priority score, including: According to the target distance matrix, data is extracted to obtain the distance between the parking space and the target position; An inverse calculation is performed based on the distance between the parking space and the target location and the estimated parking time to obtain a priority score; A normalization process is performed based on the priority scores to obtain initial priority scores.

5. The method for scheduling parking spaces in a smart parking lot based on the Internet of Things according to claim 1 is characterized in that: The determining, based on the parking space topology, whether the parking space affects the entry and exit paths, and if so, generating a parking space influence relationship matrix; If not, it will not be generated, including: According to the parking space topology structure and in combination with the obstacle distribution, a parking space map model is constructed; According to the parking space map model, a path analysis algorithm is used to obtain a path influence degree; It is determined whether the path influence degree is greater than a preset influence threshold value. If so, a parking space influence relationship matrix is ​​generated; if not, no matrix is ​​generated.

6. The method for scheduling parking spaces in a smart parking lot based on the Internet of Things according to claim 1 is characterized in that: The initial priority score is dynamically adjusted according to the parking space influence relationship matrix to obtain a priority score matrix, including: According to the parking space influence relationship matrix, the values ​​of each element in the matrix are analyzed to obtain the parking space influence degree; According to the parking space influence, the difficulty of entering and exiting each adjacent parking space is evaluated, and the initial priority score is adjusted to obtain an adjusted priority score; A score matrix is ​​generated according to the adjusted priority scores to obtain a priority score matrix.

7. A smart parking lot scheduling system based on the Internet of Things, characterized in that: The method for scheduling parking spaces in a smart parking lot based on the Internet of Things according to any one of claims 1 to 6 comprises: A data acquisition module is used to obtain parking space occupancy data, target parking location information, estimated parking time and parking space topology; A state matrix module is used to perform occupancy state judgment logic according to the parking space occupancy data to obtain an occupancy state matrix; A distance matrix module, used to calculate the shortest path distance according to the target parking position information, the occupancy state matrix and the parking space topology structure to obtain a target distance matrix; an inverse calculation module, configured to perform an inverse calculation based on the estimated parking duration and the target distance matrix to obtain an initial priority score; A relationship matrix module is used to determine whether a parking space affects an entry and exit path according to the parking space topology structure, and if so, generate a parking space influence relationship matrix; if not, do not generate a parking space influence relationship matrix; A scoring matrix module, used to dynamically adjust the initial priority score according to the parking space influence relationship matrix to obtain a priority score matrix; A weighted summation module, used for performing weighted summation according to the priority score matrix to obtain a comprehensive priority score matrix; A greedy algorithm module, used to perform greedy algorithm calculation according to the comprehensive priority score matrix to obtain a parking space allocation result; The result output module is used to dynamically update the parking space topology structure and the parking space influence relationship matrix according to the parking space allocation result to obtain a new parking space allocation result.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the parking space scheduling method for a smart parking lot based on the Internet of Things as described in any one of claims 1 to 6.

Images