Intelligent parking method, device, electronic device and readable storage medium

Abstract

The present application provides a smart parking method, device, electronic device and readable storage medium, the method comprising: obtaining the position of a target illegally parked vehicle in a target parking lot; calculating the traffic flow reduction factor of the associated lane and the associated corner; modifying the entity relationship value and the entity value in the corresponding triple; diffusing the changes in the entity value in the parking lot knowledge graph in the parking lot knowledge graph; and calculating the navigation path for the target parked vehicle to travel to the target parking space based on the parking lot knowledge graph. The smart parking method, device, electronic device and readable storage medium provided by the embodiments of the present invention focus on solving the problem that the existing smart parking methods cannot accurately identify illegally parked vehicles in parking lots and quantitatively evaluate their impact on path planning, and use the data structure of the knowledge graph to evaluate and diffuse the impact of illegally parked vehicles on the traffic flow at different locations in the parking lot, so as to plan more accurate parking lot navigation guidance for parking vehicles.

Description

Technical Field

[0001] The present application relates to the field of intelligent parking technology, and in particular to an intelligent parking method, device, electronic device and readable storage medium. Background Art

[0002] Smart parking technology is an important means to improve user experience and management efficiency in modern parking lots. Smart parking lots use hardware devices such as parking space cameras, geomagnetism, sensors, etc. The parking system can monitor free parking spaces in real time and display the number and location information of parking spaces to users through mobile phones, large screens or other terminal devices. Users can realize smart parking guidance by clicking on the parking space on the map. When the user selects a target parking space, the smart navigation system will guide the user to park based on the parking space geographic information provided by the three-dimensional map module and the best path from the user's current location to the target parking space using the path planning algorithm.

[0003] When using the path planning algorithm to calculate the best path, the existing technology will consider the data collected by the traffic flow sensors and other devices installed in the smart parking lot, and avoid congested sections when navigating the user to the selected target parking space or the system-recommended parking space, thereby improving the user's parking efficiency. However, there are often some vehicles parked illegally in non-parking areas such as the aisle against the wall in the parking lot, causing the existing smart parking method to be unable to accurately identify and evaluate its impact on path planning, which in turn causes the user to spend a long time parking, which has become a problem that needs to be solved in the existing technology. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an intelligent parking method, device, electronic device and storage medium.

[0005] In a first aspect, an embodiment of the present invention provides an intelligent parking method, the method comprising:

[0006] Obtain the location of the target illegally parked vehicle in the target parking lot;

[0007] Calculating a traffic flow reduction factor of an associated lane and an associated corner according to the position of the target illegally parked vehicle in the target parking lot;

[0008] In the parking knowledge graph, the entity relationship value in the corresponding triple is modified according to the traffic flow reduction factor of the associated lane, and the entity value in the corresponding triple is modified according to the traffic flow reduction factor of the associated corner;

[0009] Diffusion of changes in entity values ​​in the parking knowledge graph;

[0010] The navigation path for the target parking vehicle to travel to the target parking space is calculated based on the parking lot knowledge graph.

[0011] Optionally, the calculating of the traffic flow reduction factors of the associated lane and the associated corner according to the position of the target illegally parked vehicle in the target parking lot specifically includes:

[0012] According to the position of the target illegally parked vehicle in the target parking lot, determining the lane where the vehicle position is located in the target parking lot as an associated lane, and determining two endpoints of the associated lane as associated corners;

[0013] The current lane traffic flow value of the associated lane is collected by the sensor, and the traffic flow reduction factor of the associated lane is obtained by comparing the current lane traffic flow with the lane historical traffic flow value corresponding to the associated lane;

[0014] The current corner traffic flow value of each associated corner is collected by the sensor, and the traffic flow reduction factor of each associated corner is obtained by comparing the current corner traffic flow with the historical corner traffic flow value corresponding to the associated corner.

[0015] Optionally, the modifying the entity relationship value in the corresponding triplet according to the traffic flow reduction factor of the associated lane specifically includes:

[0016] Obtaining the current value of the triple entity relationship corresponding to the associated lane in the parking lot knowledge graph;

[0017] A modified entity relationship value is obtained according to a ratio of a current value of the triple entity relationship to a traffic flow reduction factor of the associated lane.

[0018] Optionally, the modifying of the entity value in the corresponding triplet according to the traffic flow reduction factor of the associated corner specifically includes:

[0019] Obtain the current values ​​of the head entity and the tail entity of the triplet corresponding to the associated lane in the parking knowledge graph;

[0020] Obtaining a modified header entity value according to a ratio of a component of the associated lane in a direction of other lanes adjacent to the associated corner in the current value of the triplet header entity to a traffic flow reduction factor corresponding to the associated corner;

[0021] The modified tail entity value is obtained according to the ratio of the component of the associated lane in the direction of other lanes adjacent to the associated corner in the current value of the triplet tail entity to the traffic flow reduction factor corresponding to the associated corner.

[0022] Optionally, the step of diffusing the changes of entity values ​​in the parking lot knowledge graph in the parking lot knowledge graph specifically includes:

[0023] Obtaining an average value of the traffic flow reduction factor of the associated turning corner corresponding to the head entity and 1, and obtaining the traffic flow reduction factor after weakening;

[0024] Diffusion of the weakened traffic flow reduction factor to the diffusion entity at the other end of the triplet corresponding to other lanes adjacent to the associated corner and modification of the corresponding entity value in the diffusion entity;

[0025] The above process is repeated, the vehicle flow reduction factor is continuously weakened and then diffused, until the difference between the weakened vehicle flow reduction factor and 1 is less than the preset threshold.

[0026] Optionally, each node in the parking lot knowledge graph corresponds to a corner in the target parking lot, and each edge corresponds to a lane in the target parking lot.

[0027] Optionally, the target illegally parked vehicle position is obtained by analyzing image data collected by a shooting device disposed in the target parking lot.

[0028] In a second aspect, an embodiment of the present invention provides an intelligent parking device, the device comprising:

[0029] An illegal parking detection module is used to obtain the location of a target illegally parked vehicle in a target parking lot;

[0030] A data analysis module, used to calculate a traffic flow reduction factor of an associated lane and an associated corner according to a position of a target illegally parked vehicle in the target parking lot;

[0031] A data processing module, used to modify the entity relationship value in the corresponding triplet according to the traffic flow reduction factor of the associated lane in the parking knowledge graph, and modify the entity value in the corresponding triplet according to the traffic flow reduction factor of the associated corner;

[0032] The impact diffusion module is used to diffuse the changes of entity values ​​in the parking knowledge graph in the parking knowledge graph;

[0033] The parking navigation module is used to calculate the navigation path for the target parking vehicle to drive to the target parking space based on the parking lot knowledge graph.

[0034] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0035] one or more processors;

[0036] A memory for storing one or more programs;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors execute the method as described in the first aspect.

[0038] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having executable instructions stored thereon, wherein when the executable instructions are executed by a processor, the processor executes the method as described in the first aspect.

[0039] The intelligent parking method, device, electronic device and readable storage medium provided by the embodiments of the present invention focus on solving the problem that the existing intelligent parking methods are unable to accurately identify illegally parked vehicles in parking lots and quantitatively evaluate their impact on path planning. The data structure of the knowledge graph is used to evaluate and diffuse the impact of illegally parked vehicles on traffic flow at different locations in the parking lot, thereby being able to plan more accurate parking lot navigation instructions for parked vehicles and improve user parking efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings required for use in the embodiments of the present application are briefly introduced below.

[0041] Figure 1 A schematic diagram of a flow chart of an intelligent parking method provided by an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of a flow chart of a method for calculating a vehicle flow reduction factor provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of a diffusion process of a vehicle flow reduction factor provided by an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of the structure of an intelligent parking device provided by an embodiment of the present invention;

[0045] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0047] Similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0048] Smart parking technology is an important means to improve user experience and management efficiency in modern parking lots. Smart parking lots use hardware devices such as parking space cameras, geomagnetism, sensors, etc. The parking system can monitor free parking spaces in real time and display the number and location information of parking spaces to users through mobile phones, large screens or other terminal devices. Users can realize smart parking guidance by clicking on the parking space on the map. When the user selects a target parking space, the smart navigation system will guide the user to park based on the parking space geographic information provided by the three-dimensional map module and the best path from the user's current location to the target parking space using the path planning algorithm.

[0049] When using the path planning algorithm to calculate the best path, the existing technology will take into account the data collected by the traffic flow sensors and other devices installed in the smart parking lot, and avoid congested sections when navigating the user to the selected target parking space or the system-recommended parking space, thereby improving the user's parking efficiency. However, there are often some vehicles parked illegally in non-parking areas such as the aisle against the wall in the parking lot, causing the existing smart parking to be unable to accurately identify and evaluate their impact on path planning, which in turn causes the user to spend a long time parking, which has become a problem that needs to be solved in the existing technology.

[0050] Based on this, an embodiment of the present invention provides an intelligent parking method. Figure 1 A schematic flow chart of the intelligent parking method provided by an embodiment of the present invention is shown, which specifically includes steps S110 to S150.

[0051] Step S110, obtaining the position of the target illegally parked vehicle in the target parking lot.

[0052] Smart parking is an important part of modern urban traffic management. It realizes intelligent management and efficient use of parking resources by integrating advanced sensor technology, computer vision, Internet of Things (IoT) and big data analysis. Geomagnetic sensors, infrared sensors, radar sensors and other devices will be set up in different locations in smart parking lots to realize intelligent functions such as vehicle detection and traffic flow calculation; different types of cameras and other shooting equipment are also used to collect and monitor environmental data and behavior data in smart parking lots. These physical devices and intelligent algorithms support the realization of the function of smart parking lots to guide vehicles to park.

[0053] Illegal parking of vehicles in a parking lot refers to the behavior of parking vehicles in a parking lot that are not parked in the designated parking spaces or parking areas. Since the existing intelligent parking guidance technology cannot accurately identify illegally parked vehicles and quantitatively evaluate their impact, illegally parked vehicles will not accurately reflect the parking guidance results and the navigation path for users. When processing intelligent parking guidance with illegal parking, the embodiment of the present invention first needs to identify the location of the illegally parked vehicle this week. The target illegally parked vehicle location is obtained by analyzing the image data collected by the shooting device set in the target parking lot.

[0054] Specifically, this step requires the reasonable deployment of cameras at key locations in the target parking lot (including aisles, entrances and exits, wall areas and other locations where illegal parking is likely to occur). These devices should have high resolution, wide-angle vision and night vision capabilities to ensure that vehicle information can be clearly captured under any lighting conditions. Real-time image data in the parking lot is automatically collected through set time intervals or other trigger conditions. The camera transmits the captured image data to the central processing system or cloud server in real time for further analysis.

[0055] The central processing system or cloud server pre-processes the received image data, including denoising, contrast enhancement, distortion correction, etc., to improve the accuracy of subsequent analysis; at the same time, the image is timestamped for easy tracking and recording; further, advanced computer vision algorithms (such as deep learning models, such as YOLO, SSD, etc.) are used to detect vehicles on the pre-processed images. These algorithms can identify vehicle outlines, license plate numbers and other information in the image, thereby distinguishing between normal and illegally parked vehicles; finally, combined with the parking lot map information and the preset parking space coordinates, analyze whether the detected vehicle position exceeds the legal parking area. By comparing the distance or overlap between the vehicle position and the preset parking boundary, it is determined whether the vehicle is illegally parked.

[0056] For vehicles that are judged to be illegally parked, their positions can also be accurately located. That is, by using information such as the scale in the image, known reference objects (such as fixed signs in the parking lot), and vehicle size, through geometric calculations or image matching technology, the specific position coordinates (such as X, Y coordinates) of the illegally parked vehicle can be accurately calculated.

[0057] Step S120, calculating the traffic flow reduction factor of the associated lane and the associated corner according to the position of the target illegally parked vehicle in the target parking lot.

[0058] In a smart parking lot, if a vehicle is not parked in a parking space as required but in an illegal parking location such as an aisle, it will directly lead to obstruction of traffic flow in the lane, and will also affect the traffic efficiency of nearby corners. The lane where the illegally parked vehicle is located is the main passage for vehicles in the parking lot, and its smoothness is directly related to the traffic conditions of the entire parking lot. When an aisle is occupied, other vehicles have to detour or wait, which will undoubtedly increase the traffic pressure in the aisle and reduce its traffic capacity. At the same time, as the key point for vehicles to change their driving direction, the traffic efficiency of the corner also directly affects the overall traffic smoothness of the parking lot. When there is congestion in the aisle, the vehicles at the corner will also be affected, because the vehicle needs to turn at the corner. If there is congestion in front of the vehicle, the traffic efficiency at the corner will be greatly reduced.

[0059] Attached Figure 2 A schematic flow chart of a method for calculating a vehicle flow reduction factor provided in an embodiment of the present invention is shown, which specifically includes steps S121 to S123.

[0060] Step S121, according to the position of the target illegally parked vehicle in the target parking lot, determining the lane where the vehicle position is located in the target parking lot as an associated lane, and determining two endpoints of the associated lane as associated corners;

[0061] Step S122, collecting the current lane traffic flow value of the associated lane according to the sensor, and comparing the current lane traffic flow with the lane historical traffic flow value corresponding to the associated lane to obtain the traffic flow reduction factor of the associated lane;

[0062] Step S123, collecting the current corner traffic flow value of each associated corner according to the sensor, and comparing the current corner traffic flow with the corner historical traffic flow value corresponding to the associated corner to obtain the traffic flow reduction factor of each associated corner.

[0063] The traffic flow reduction factor is used in the embodiment of the present invention to quantitatively calculate the ratio of the traffic efficiency reduction at the associated lane and the associated corner. The lane where the target illegally parked vehicle is located in the target parking lot is used as the associated lane, and the two endpoints of the associated lane are used as the associated corner. That is, the lanes in the target parking lot are regarded as a combination of line segments, and the traffic flow at the associated lane and the associated corner is the location most directly affected by the target illegally parked vehicle.

[0064] Specifically, in the absence of illegal parking, infrared sensors and other equipment in the smart parking lot are used to record the number of vehicles passing through the aisle in the lane within a period of time (such as 10 minutes), which is recorded as N; N can also be improved to the lane's historical traffic flow value N', that is, the average traffic flow at the current time of each week in history. In the case of illegal parking, infrared sensors are also used to record the number of vehicles passing through the lane in the same period of time, recorded as n. Therefore, the percentage of traffic reduction = N' / n. For example, if the normal traffic flow N is 100 vehicles / hour, and the traffic flow n after illegal parking is 80 vehicles / hour, the traffic flow reduction factor of the associated lane is 1.25.

[0065] Similarly, the traffic flow reduction factors of the two associated corners of the target illegally parked vehicle position can be calculated.

[0066] Step S130, in the parking lot knowledge graph, modify the entity relationship value in the corresponding triple according to the traffic flow reduction factor of the associated lane, and modify the entity value in the corresponding triple according to the traffic flow reduction factor of the associated corner.

[0067] The embodiment of the present invention adopts the knowledge graph method to quantitatively calculate the impact of the target illegally parked vehicle on the traffic flow of the entire parking lot. The embodiment of the present invention only discusses the case of a single-story parking lot. For a multi-story parking lot, a separate knowledge graph can be established for each floor of the parking lot for calculation. The parking lot knowledge graph is exactly the same as the topological structure of the entire parking lot. The parking lot is composed of multiple lanes, which correspond to the edges of the parking lot knowledge graph; the connection between the lanes is the corner of the parking lot, which corresponds to the nodes in the parking lot knowledge graph. Each edge in the parking lot knowledge graph and the nodes at both ends of it constitute a triple. The nodes at both ends are entities, namely the head entity and the tail entity; the edge can be regarded as the entity relationship of the triple.

[0068] Each entity in the parking knowledge graph stores the traffic flow data at the corresponding corner. The data is a two-dimensional array structure that stores the traffic flow data from each lane at the corner to other lanes. Taking a cross-shaped corner intersection in the southeast, northwest and north directions as an example, the traffic flow data from the east lane to the south, west and north lanes are (x 1 ,y 1 ,z 1 ), the traffic flow data from the south lane to the west, north, and east lanes are (x 2 ,y 2 ,z 2 ), the traffic flow data from the west lane to the north, east, and south lanes are (x 3 ,y 3 ,z 3 ), the traffic flow data from the north lane to the east, south, and west lanes are (x4 ,y 4 ,z 4 ). Therefore, for this corner, the data stored in the entity of the parking knowledge graph is [(x 2 ,y 2 ,z 2 ), (x 3 ,y 3 ,z 3 ), (x 4 ,y 4 ,z 4 ), (x 1 ,y 1 ,z 1 )], the data starts from the south direction (i.e., the six o'clock direction) and is stored in a counterclockwise order. Each entity relationship in the parking knowledge graph stores the traffic flow data of the corresponding lane. The data is a one-dimensional array structure that stores the traffic flow data of the lane in both the forward and reverse directions. Similarly, it can be expressed as [m,n].

[0069] Before illegally parked vehicles are detected, the parking knowledge graph in the embodiment of the present invention can be used for intelligent parking guidance, and the traffic flow data stored in each triple in the parking knowledge graph is initialized by the real-time collected traffic flow data of each lane and corner. After illegally parked vehicles are not detected, this step adjusts the entity and entity relationship values ​​in some triples in the parking knowledge graph according to the traffic flow reduction factor.

[0070] Specifically, the process of modifying the above-mentioned entity relationship value includes: obtaining the current value of the triple entity relationship corresponding to the associated lane in the parking lot knowledge graph, and obtaining the modified entity relationship value based on the ratio of the current value of the triple entity relationship and the traffic flow reduction factor of the associated lane.

[0071] The process of modifying the above-mentioned entity value includes: obtaining the current values ​​of the triple head entity and the tail entity corresponding to the associated lane in the parking lot knowledge graph; obtaining the modified head entity value according to the ratio of the component of the associated lane in the current value of the triple head entity toward the other lanes adjacent to the associated corner to the traffic flow reduction factor corresponding to the associated corner; obtaining the modified tail entity value according to the ratio of the component of the associated lane in the current value of the triple tail entity toward the other lanes adjacent to the associated corner to the traffic flow reduction factor corresponding to the associated corner.

[0072] It is understandable that the parking knowledge graph with adjusted values ​​will take into account the impact of illegally parked vehicles on the accuracy of intelligent parking guidance when performing intelligent parking guidance.

[0073] Step S140, diffusion processing is performed on the changes of entity values ​​in the parking lot knowledge graph.

[0074] In the parking lot scenario, it is understandable that the impact of illegally parked vehicles on traffic flow is definitely not limited to the associated lanes and associated corners. This impact is a chain reaction, that is, if traffic congestion occurs in one location, it will gradually spread to other adjacent areas of the parking lot. This phenomenon is particularly serious when there are illegally parked vehicles in the parking lot. Therefore, it is necessary to quantitatively spread the impact of the traffic flow reduction factor calculated in the previous steps, that is, to adaptively modify the traffic flow values ​​in other affected entities.

[0075] Specifically, in this step, the average value of the traffic flow reduction factor corresponding to the associated turning angle of the head entity and 1 can be obtained to obtain the traffic flow reduction factor after weakening;

[0076] Diffusion of the weakened traffic flow reduction factor to the diffusion entity at the other end of the triplet corresponding to other lanes adjacent to the associated corner and modification of the corresponding entity value in the diffusion entity;

[0077] The above process is repeated, the vehicle flow reduction factor is continuously weakened and then diffused, until the difference between the weakened vehicle flow reduction factor and 1 is less than the preset threshold.

[0078] Specifically, attached Figure 3 A schematic diagram showing the diffusion process of the traffic flow reduction factor in this step.

[0079] In the topological structure of the local area of ​​the parking knowledge graph as shown in the figure, the asterisk position is the location of the illegally parked vehicle, A and B are their associated corners, and the entities in the AB triple and the traffic flow values ​​stored in the entity relationship have been modified through step S130. Assume that the traffic flow reduction factor a corresponding to the associated corner A is 1.2, and the traffic flow reduction factor b corresponding to the associated corner B is 1.1, and the preset threshold in this step is 1.05. At this time, the traffic flow reduction factor b needs to be diffused to other adjacent corners respectively. For example, corner A also forms a triple relationship with A1, A2 and A3, and A1, A2 and A3 are the diffusion entities of A. At this time, it is necessary to take the average of the traffic flow reduction factor a and 1 to obtain 1.1, and use 1.1 as the traffic flow reduction factor of A1, A2 and A3 and modify the values ​​in entities A1, A2 and A3. Furthermore, it is necessary to continue to transfer the traffic flow reduction factors of entities A1, A2, and A3 to the diffusion entities at the other end of the triplet corresponding to other adjacent lanes. The entities transferred for the second time are diffusion entities A11 and A12 of A1, diffusion entities A21 and A22 of A2, and diffusion entity A31 of A3. The weakened traffic flow reduction factor is the average value of 1.1 and 1, 1.05. At the same time, the entity values ​​in A11, A12, A21, A22, and A31 are modified. When you want to diffuse the traffic flow reduction factor again, the average value of 1.05 and 1, 1.025, is less than the preset threshold value 1.05. Therefore, the diffusion action of the traffic flow reduction factor originating from node A ends.

[0080] Similarly, the traffic flow reduction factor originating from node A will spread to B and then to B1 before ending.

[0081] The attenuation method of the traffic flow reduction factor and the selection of the preset threshold in this step can be set according to the actual needs of the user. The preset threshold is used as the diffusion termination condition of the traffic flow reduction factor in order to take into account the accurate assessment of the chain effect of illegally parked vehicles on the parking lot and the calculation efficiency of the diffusion process of the traffic flow reduction factor.

[0082] Step S150, calculating a navigation path for the target parking vehicle to travel to the target parking space based on the parking lot knowledge graph.

[0083] The updated parking knowledge graph reflects the latest traffic flow status of the parking lot where there are illegally parked vehicles. It is worth noting that steps S110~S140 only describe the handling method for one illegally parked vehicle. In the case of multiple illegally parked vehicles, the data in the parking knowledge graph can be updated according to steps S110~S140 for the location of each illegally parked vehicle. At the same time, for the data update operation for each illegally parked vehicle, the data modification process can be recorded in the system to facilitate the restoration of this part of the modified data when the illegally parked vehicle leaves, so as to ensure that the parking knowledge graph reflects the latest parking lot status.

[0084] Furthermore, the parking knowledge graph can also combine the physical structure information contained in the three-dimensional map of the smart parking lot, the parking space status information provided by the smart sensor, etc., to give the parking knowledge graph richer data content. For the target parking vehicle that wants to park, the navigation path for the target parking vehicle to drive to the target parking space can be obtained in combination with the path planning algorithm for the user's reference and selection.

[0085] The intelligent parking method provided by the embodiment of the present invention focuses on solving the problem that the existing intelligent parking methods are unable to accurately identify illegally parked vehicles in parking lots and quantitatively evaluate their impact on path planning. The data structure of the knowledge graph is used to evaluate and diffuse the impact of illegally parked vehicles on traffic flow at different locations in the parking lot, thereby being able to plan more accurate parking lot navigation guidance for parked vehicles and improve user parking efficiency.

[0086] Based on any of the above embodiments, Figure 4 The following is a schematic diagram showing the structure of the intelligent parking device provided by an embodiment of the present invention, and the specific contents are as follows:

[0087] The illegal parking detection module 410 is used to obtain the position of the target illegally parked vehicle in the target parking lot;

[0088] A data analysis module 420, configured to calculate a traffic flow reduction factor of an associated lane and an associated corner according to a position of a target illegally parked vehicle in the target parking lot;

[0089] The data processing module 430 is used to modify the entity relationship value in the corresponding triple according to the traffic flow reduction factor of the associated lane in the parking knowledge graph, and modify the entity value in the corresponding triple according to the traffic flow reduction factor of the associated corner;

[0090] The impact diffusion module 440 is used to diffuse the changes of entity values ​​in the parking knowledge graph in the parking knowledge graph;

[0091] The parking navigation module 450 is used to calculate the navigation path for the target parking vehicle to travel to the target parking space according to the parking lot knowledge graph.

[0092] The intelligent parking device provided in the embodiment of the present invention focuses on solving the problem that the existing intelligent parking method is unable to accurately identify illegally parked vehicles in the parking lot and quantitatively evaluate their impact on path planning. The data structure of the knowledge graph is used to evaluate and diffuse the impact of illegally parked vehicles on the traffic flow at different locations of the parking lot, so that more accurate parking lot navigation guidance can be planned for parked vehicles, thereby improving the parking efficiency of users.

[0093] Based on any of the above embodiments, Figure 5 The physical structure diagram of the electronic device provided by the embodiment of the present invention is shown, and the electronic device may include: a processor (processor) 510, a communication interface (CommunicationsInterface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the following method:

[0094] Obtain the location of the target illegally parked vehicle in the target parking lot;

[0095] Calculating a traffic flow reduction factor of an associated lane and an associated corner according to the position of the target illegally parked vehicle in the target parking lot;

[0096] In the parking knowledge graph, the entity relationship value in the corresponding triple is modified according to the traffic flow reduction factor of the associated lane, and the entity value in the corresponding triple is modified according to the traffic flow reduction factor of the associated corner;

[0097] Diffusion of changes in entity values ​​in the parking knowledge graph;

[0098] The navigation path for the target parking vehicle to travel to the target parking space is calculated based on the parking lot knowledge graph.

[0099] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0100] On the other hand, an embodiment of the present invention further provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method provided in each of the above embodiments is implemented, for example, including:

[0101] Obtain the location of the target illegally parked vehicle in the target parking lot;

[0102] Calculating a traffic flow reduction factor of an associated lane and an associated corner according to the position of the target illegally parked vehicle in the target parking lot;

[0103] In the parking knowledge graph, the entity relationship value in the corresponding triple is modified according to the traffic flow reduction factor of the associated lane, and the entity value in the corresponding triple is modified according to the traffic flow reduction factor of the associated corner;

[0104] Diffusion of changes in entity values ​​in the parking knowledge graph;

[0105] The navigation path for the target parking vehicle to travel to the target parking space is calculated based on the parking lot knowledge graph.

[0106] The device embodiments described above are merely illustrative, 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. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent parking method, characterized in that: The method comprises: Obtain the location of the target illegally parked vehicle in the target parking lot; Calculate the traffic flow reduction factor of the associated lane and the associated corner according to the position of the target illegally parked vehicle in the target parking lot; the traffic flow reduction factor is used to quantitatively calculate the proportion of the traffic efficiency reduction at the associated lane and the associated corner; In the parking knowledge graph, the entity relationship value in the corresponding triple is modified according to the traffic flow reduction factor of the associated lane, and the entity value in the corresponding triple is modified according to the traffic flow reduction factor of the associated corner; the entity stores the traffic flow data at the corresponding corner, and the entity relationship stores the traffic flow data at the corresponding lane; Diffusion of changes in entity values ​​in the parking knowledge graph; The navigation path for the target parking vehicle to drive to the target parking space is calculated based on the parking lot knowledge graph; The step of modifying the entity value in the corresponding triplet according to the traffic flow reduction factor of the associated corner specifically includes: Obtain the current values ​​of the head entity and the tail entity of the triplet corresponding to the associated lane in the parking knowledge graph; Obtaining a modified header entity value according to a ratio of a component of the associated lane in a direction of other lanes adjacent to the associated corner in the current value of the triplet header entity to a traffic flow reduction factor corresponding to the associated corner; Obtaining a modified tail entity value according to a ratio of a component of the associated lane in a direction of other lanes adjacent to the associated corner in the current value of the triplet tail entity to a traffic flow reduction factor corresponding to the associated corner; The process of diffusing the changes of entity values ​​in the parking lot knowledge graph in the parking lot knowledge graph specifically includes: Obtaining an average value of the traffic flow reduction factor of the associated turning corner corresponding to the head entity and 1, and obtaining the traffic flow reduction factor after weakening; Diffusion of the weakened traffic flow reduction factor to the diffusion entity at the other end of the triplet corresponding to other lanes adjacent to the associated corner and modification of the corresponding entity value in the diffusion entity; The vehicle flow reduction factor is continuously weakened and then diffused until the difference between the weakened vehicle flow reduction factor and 1 is less than a preset threshold.

2. The intelligent parking method according to claim 1, characterized in that: The calculating of the traffic flow reduction factors of the associated lane and the associated corner according to the position of the target illegally parked vehicle in the target parking lot specifically includes: According to the position of the target illegally parked vehicle in the target parking lot, determining the lane where the vehicle position is located in the target parking lot as an associated lane, and determining two endpoints of the associated lane as associated corners; The current lane traffic flow value of the associated lane is collected by the sensor, and the traffic flow reduction factor of the associated lane is obtained by comparing the current lane traffic flow with the lane historical traffic flow value corresponding to the associated lane; The current corner traffic flow value of each associated corner is collected by the sensor, and the traffic flow reduction factor of each associated corner is obtained by comparing the current corner traffic flow with the historical corner traffic flow value corresponding to the associated corner.

3. The intelligent parking method according to claim 1, characterized in that: The modifying of the entity relationship value in the corresponding triplet according to the traffic flow reduction factor of the associated lane specifically includes: Obtaining the current value of the triple entity relationship corresponding to the associated lane in the parking lot knowledge graph; A modified entity relationship value is obtained according to a ratio of a current value of the triple entity relationship to a traffic flow reduction factor of the associated lane.

4. The intelligent parking method according to claim 1, characterized in that: Each node in the parking lot knowledge graph corresponds to a corner in the target parking lot, and each edge corresponds to a lane in the target parking lot.

5. The intelligent parking method according to claim 1, characterized in that: The target illegally parked vehicle position is obtained by analyzing image data collected by a shooting device arranged in the target parking lot.

6. An intelligent parking device, characterized in that: The device comprises: An illegal parking detection module is used to obtain the location of a target illegally parked vehicle in a target parking lot; A data analysis module, used to calculate a traffic flow reduction factor of an associated lane and an associated corner according to the position of a target illegally parked vehicle in the target parking lot; the traffic flow reduction factor is used to quantitatively calculate a proportion of a reduction in traffic efficiency at an associated lane and an associated corner; A data processing module, for modifying the entity relationship value in the corresponding triplet in the parking knowledge graph according to the traffic flow reduction factor of the associated lane, and modifying the entity value in the corresponding triplet according to the traffic flow reduction factor of the associated corner; the entity stores the traffic flow data at the corresponding corner, and the entity relationship stores the traffic flow data at the corresponding lane; The impact diffusion module is used to diffuse the changes of entity values ​​in the parking knowledge graph in the parking knowledge graph; The parking navigation module is used to calculate the navigation path for the target parking vehicle to drive to the target parking space based on the parking lot knowledge graph; The step of modifying the entity value in the corresponding triplet according to the traffic flow reduction factor of the associated corner specifically includes: Obtain the current values ​​of the head entity and the tail entity of the triplet corresponding to the associated lane in the parking knowledge graph; Obtaining a modified header entity value according to a ratio of a component of the associated lane in a direction of other lanes adjacent to the associated corner in the current value of the triplet header entity to a traffic flow reduction factor corresponding to the associated corner; Obtaining a modified tail entity value according to a ratio of a component of the associated lane in a direction of other lanes adjacent to the associated corner in the current value of the triplet tail entity to a traffic flow reduction factor corresponding to the associated corner; The process of diffusing the changes of entity values ​​in the parking lot knowledge graph in the parking lot knowledge graph specifically includes: Obtaining an average value of the traffic flow reduction factor of the associated turning corner corresponding to the head entity and 1, and obtaining the traffic flow reduction factor after weakening; Diffusion of the weakened traffic flow reduction factor to the diffusion entity at the other end of the triplet corresponding to other lanes adjacent to the associated corner and modification of the corresponding entity value in the diffusion entity; The vehicle flow reduction factor is continuously weakened and then diffused until the difference between the weakened vehicle flow reduction factor and 1 is less than a preset threshold.

7. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors execute the method as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium having executable instructions stored thereon, characterized in that: When the executable instructions are executed by a processor, the processor executes the method according to any one of claims 1 to 5.

Images