Park parking space management method, system and equipment based on industrial Internet of Things, and medium

Through the industrial Internet of Things system, berth paths are generated or vehicle behavior is predicted based on vehicle type and park information, which solves the problem of low efficiency in finding berths in industrial parks and realizes efficient management and utilization of berths.

CN118982931APending Publication Date: 2024-11-19CHENGDU QINCHUAN IOT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411035827.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

In industrial parks, it is less efficient to find berths for vehicles, especially new energy vehicles and vehicles with wide bodies, which are difficult to find suitable charging or parking spaces, resulting in too long parking times.

Method used

Through the industrial Internet of Things system, request information is sent to the target vehicle to determine whether it can directly perform berth path planning. If possible, a planned path is generated; if not, predict its behavior or location, and send berth prompt information to it to guide It finds the right berth.

Benefits of technology

It improves the efficiency of vehicles in industrial parks to find berths, realizes efficient management and utilization of berths, and ensures that vehicles can quickly find suitable parking or charging potentials.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982931A_ABST
    Figure CN118982931A_ABST
Patent Text Reader

Abstract

The invention discloses a park parking space management method, system and device based on the industrial Internet of Things and a medium, and the method comprises the steps: responding to a first parking signal, and transmitting first request information for requesting to carry out parking space path planning for a target vehicle to the target vehicle; classifying the target vehicles according to first reply information from the target vehicles to obtain first vehicle types of the target vehicles; if the target vehicle is a first type of vehicle, generating a first planned path according to first park information and first vehicle information of the target park; if the target vehicle is a second type of vehicle, acquiring second vehicle information of the target vehicle; obtaining a first prediction result according to a pre-trained first prediction model and the second vehicle information; generating first prompt information according to the first park information and the first prediction result; and sending the first planned path to the target vehicle or sending first prompt information to the target equipment. According to the invention, efficient management and utilization of berths in the industrial park are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a park berth management method, system, equipment and medium based on the industrial Internet of Things. Background Art

[0002] In the prior art, vehicles in industrial parks usually search for parking spaces by themselves, and the park management usually only displays the remaining parking spaces in a certain parking area, which results in a long time for vehicles to complete parking. Moreover, since the remaining parking spaces are simply displayed, when searching for parking spaces, vehicles may encounter situations where there are parking spaces but they are not suitable. For example, new energy vehicles take a long time to find a parking space that cannot be charged, and vehicles with wider bodies take a long time to find a narrow parking space.

[0003] Therefore, there is a problem of low efficiency in vehicles finding parking spaces within the industrial park. Summary of the invention

[0004] The main purpose of this application is to provide a park parking space management method, system, equipment and medium based on the industrial Internet of Things, aiming to solve the technical problem of low efficiency of vehicles finding parking spaces in industrial parks.

[0005] In the first aspect, to achieve the above-mentioned purpose, the present application provides a park berth management method based on industrial Internet of Things, which is applied to an industrial Internet of Things system. The industrial Internet of Things system includes: an object platform, a management platform and a user platform that interact in sequence. The method is executed by the management platform and includes the following steps:

[0006] In response to the first parking signal, sending to the target vehicle a first request message for requesting parking path planning for the target vehicle;

[0007] According to the first reply information from the target vehicle, the target vehicle is classified to obtain a first vehicle type of the target vehicle, wherein the first reply information at least includes the first vehicle information and the first confirmation information of the target vehicle, and the first vehicle type is configured as a first type of vehicle that can directly perform berth path planning and a second type of vehicle that cannot directly perform berth path planning;

[0008] If the target vehicle is a first type of vehicle, generating a first planned path according to the first park information of the target park and the first vehicle information;

[0009] If the target vehicle is a second type of vehicle, obtaining second vehicle information of the target vehicle;

[0010] Obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, wherein the first prediction result is configured as a behavior prediction result or a time window prediction result of the second type of vehicle;

[0011] Generate first prompt information according to the first park information and the first prediction result;

[0012] Send the first planned path to the target vehicle or send the first prompt information to the target device.

[0013] Optionally, after the step of sending the first planned path to the target vehicle or sending the first prompt information to the target device, the method further includes:

[0014] If the target vehicle is a second type of vehicle, in response to a first preset time, obtaining a first vehicle state of the target vehicle;

[0015] According to the first vehicle state, second request information is sent to the target vehicle to request berth path planning for the target vehicle.

[0016] Optionally, after the step of obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, the method further includes:

[0017] According to the first prediction result, the first park information is updated to obtain the second park information.

[0018] Optionally, after the step of generating a first planned path according to first park information of the target park and the first vehicle information if the target vehicle is a first type of vehicle, the step further includes:

[0019] A second planned path is generated according to the second park information and the first planned path.

[0020] Optionally, if the target vehicle is a first type of vehicle, the step of generating a first planned path according to first park information of the target park and the first vehicle information includes:

[0021] Obtaining a first state space and a first state transition rule according to the first park information and the first vehicle information;

[0022] Initialize according to the first park information and the first vehicle information to obtain the starting node, the target node, the open list and the closed list of the target vehicle;

[0023] Obtaining a first heuristic function according to the first state transition rule, the starting node and the target node;

[0024] Perform a cyclic search according to the first heuristic function, the starting node, the target node, the open list and the closed list to obtain the first node information;

[0025] Perform path backtracking according to the first node information to obtain the first planned path.

[0026] Optionally, the first prediction model is a recurrent neural network model, and the recurrent neural network model is configured to connect the output layer of the recurrent neural network model to a preset softmax layer or a preset linear regression layer according to a target prediction type of the first prediction result, wherein the target prediction type is configured to predict the behavior of the second type of vehicle and the time window of the second type of vehicle.

[0027] Optionally, the step of obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information includes:

[0028] preprocessing the second vehicle information to obtain third vehicle information;

[0029] Obtaining a first feature set according to the third vehicle information;

[0030] According to the target prediction type of this prediction, the first prediction model is set so that the output layer of the first prediction model is connected to the target component corresponding to the target prediction type;

[0031] The first feature set is input into the first prediction model to obtain the first prediction result.

[0032] In a second aspect, the present application further provides a park management system based on industrial Internet of Things, which is applied to an industrial Internet of Things system, wherein the industrial Internet of Things system comprises: an object platform, a management platform and a user platform that interact in sequence;

[0033] The management platform is configured as follows:

[0034] In response to the first parking signal, sending to the target vehicle a first request message for requesting parking path planning for the target vehicle;

[0035] According to the first reply information from the target vehicle, the target vehicle is classified to obtain a first vehicle type of the target vehicle, wherein the first reply information at least includes the first vehicle information and the first confirmation information of the target vehicle, and the first vehicle type is configured as a first type of vehicle that can directly perform berth path planning and a second type of vehicle that cannot directly perform berth path planning;

[0036] If the target vehicle is a first type of vehicle, generating a first planned path according to the first park information of the target park and the first vehicle information;

[0037] If the target vehicle is a second type of vehicle, obtaining second vehicle information of the target vehicle;

[0038] Obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, wherein the first prediction result is configured as a behavior prediction result or a time window prediction result of the second type of vehicle;

[0039] Generate first prompt information according to the first park information and the first prediction result;

[0040] Sending the first planned path to the target vehicle or sending the first prompt information to a target device;

[0041] The user platform is configured to:

[0042] receiving the first request information and the first planned path from the management platform, and sending the first parking signal and the first reply information to the management platform;

[0043] The object platform is configured as follows:

[0044] The first park information is collected, the first prompt information is received from the management platform, and the first parking signal and the first park information are sent to the management platform.

[0045] In a third aspect, the present application also provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a computer program; the processor is used to load and execute the computer program so that the electronic device executes the park berth management method based on the industrial Internet of Things as described in any one of the first aspects.

[0046] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the park berth management method based on the industrial Internet of Things as described in any one of the first aspects.

[0047] The beneficial effects that this application can achieve are as follows:

[0048] The embodiment of the present application proposes a method for park parking space management based on industrial Internet of Things. By sending a first request message to a target vehicle in the industrial park, it is determined whether the target vehicle can directly perform parking path planning. For the first type of vehicles that can directly perform parking path planning, a parking path is planned for them. For the second type of vehicles that cannot directly perform parking path planning, their behavior or subsequent position is first predicted, and then a first prompt message is sent to the target device in its surrounding area to prompt the relevant parking space information around it. The technical problem of low efficiency in finding parking spaces in the industrial park is solved, and efficient management and utilization of parking spaces in the industrial park are realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of an embodiment of a park berth management method based on industrial Internet of Things in this application;

[0050] Figure 2 This is a schematic diagram of the functional modules of an embodiment of an industrial Internet of Things system in the present application.

[0051] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] Example 1

[0054] Reference Figure 1 , an embodiment of a park berth management method based on industrial Internet of Things is applied to an industrial Internet of Things system, the industrial Internet of Things system includes: an object platform, a management platform and a user platform that interact in sequence, the method is executed by the management platform, and includes the following steps:

[0055] S1. In response to a first parking signal, sending a first request message to a target vehicle requesting parking path planning for the target vehicle;

[0056] Specifically, the first parking signal may be a signal actively sent by the target vehicle to the park management party to request parking path planning, or may be a trigger signal generated after the park management party identifies that the target vehicle needs to perform parking path planning after the target vehicle enters a designated area of ​​the target park;

[0057] For example, the first parking signal may be a request sent by the driver of the target vehicle to the management platform through the user platform to perform parking path planning, or it may be an image, driving path and other information of the target vehicle collected by the target platform after the target vehicle enters the information collection range of the object platform, and the management platform analyzes and determines that the target vehicle does not have a fixed parking space in the target park and needs to perform parking path planning for it;

[0058] The first request information may include, in addition to the first vehicle information and the first confirmation information requesting the target vehicle to confirm whether it agrees to plan a berth path for the target vehicle, an application to the target vehicle for relevant permissions required to plan a berth path for the target vehicle. The relevant permissions required for the target vehicle to plan a berth path may include permissions to continuously obtain the target vehicle's location information in order to better plan a path for the target vehicle in the future, or permissions to access the target vehicle's storage space to directly obtain the required first vehicle information and other information.

[0059] S2. Classifying the target vehicle according to the first reply information from the target vehicle to obtain a first vehicle type of the target vehicle, wherein the first reply information at least includes the first vehicle information and the first confirmation information of the target vehicle, and the first vehicle type is configured as a first type of vehicle that can directly perform berth path planning and a second type of vehicle that cannot directly perform berth path planning;

[0060] Specifically, if the target vehicle clearly indicates in the first reply message through the first confirmation message that it can accept the berth path planning, then the target vehicle will be classified as a first-category vehicle; if the target vehicle clearly indicates in the first reply message through the first confirmation message that it does not agree to the berth path planning for itself, then the target vehicle will be classified as a second-category vehicle; if the target vehicle does not reply to the first request message within a specified time or a specified number of requests, that is, does not send the first confirmation message, then the target vehicle is deemed to have sent the first reply message and indicated in the first reply message that it is temporarily unable to accept the berth path planning, then the target vehicle will be classified as a second-category vehicle; of course, a target vehicle that cannot receive the first request message itself will also be deemed to have sent the first reply message and indicated in the first reply message that it is temporarily unable to accept the berth path planning and will be classified as a second-category vehicle;

[0061] Both the first-category and second-category vehicles will be managed. The first-category vehicles will directly receive route planning in the future, while the second-category vehicles can only receive relevant prompts and guidance information;

[0062] At the same time, only when the target vehicle clearly indicates through the first confirmation information that it can accept the berth path planning, the management platform will obtain the first vehicle information and related permissions of the target vehicle. When the first vehicle information is transmitted, it can be encrypted to ensure the security of user data.

[0063] For example, if the target vehicle actively sends a first parking signal to the management platform through a user platform such as a mobile phone APP and explicitly indicates that it can accept the parking path planning through a first reply message and a first confirmation message, then the target vehicle will be classified as a first-category vehicle. However, if the target vehicle actively sends a first parking signal to the management platform through a user platform such as a mobile phone APP but fails to respond to the first request message within a specified time, then the target vehicle will be classified as a second-category vehicle. Alternatively, if the target vehicle actively sends a first parking signal to the management platform through a user platform such as a mobile phone APP but explicitly indicates a refusal through a first confirmation message in a first reply message due to reasons such as not wanting to send its own first vehicle information or grant relevant permissions, then the target vehicle will also be classified as a second-category vehicle.

[0064] The first vehicle information is relevant information required for berth path planning for the target vehicle, and the first vehicle information may include relevant information such as the second vehicle type, destination information, specific size of the target vehicle, color of the target vehicle, license plate number of the target vehicle, type of cargo loaded by the target vehicle, etc.;

[0065] Among them, the second vehicle type is the specific vehicle model of the target vehicle, including new energy vehicles or fuel vehicles, large, medium or small vehicles, and vehicles such as buses or trucks. The management platform will select a suitable parking space for the target vehicle according to the second vehicle type. For a five-seater new energy car, its second vehicle type can be a new energy-small passenger car, and it will give priority to recommending a parking space dedicated to new energy small passenger cars for charging. Of course, more subcategories can be added to the second vehicle type according to the actual situation of the target park;

[0066] The destination information at least includes the place name and coordinates of the final destination of the target vehicle in the target park, and at least one berth with a suitable distance is selected for the target vehicle according to the coordinates of the final destination and the coordinates of each berth;

[0067] The specific dimensions of the target vehicle are the specific overall height, overall width and overall length of the target vehicle;

[0068] The type of cargo loaded on the target vehicle can be classified according to inflammable and explosive goods, hazardous chemicals, high-risk large cargo, etc. For example, steel bars and steel coils are classified as high-risk large cargo.

[0069] S3. If the target vehicle is a first type of vehicle, generating a first planned path according to the first park information and the first vehicle information of the target park;

[0070] The first park information at least includes road information and parking space information in the target park, wherein the road information may include road distribution, road width, road turning radius, building distribution information around the road, obstacle distribution in the park, congestion and other information, and the parking space information may include the location of parking spaces, the number of parking spaces, parking space occupancy, parking space specifications, parking space types and other information;

[0071] Optionally, if the target vehicle is a first type of vehicle, the step of generating a first planned path according to first park information of the target park and the first vehicle information includes:

[0072] Obtaining a first state space and a first state transition rule according to the first park information and the first vehicle information;

[0073] Initialize according to the first park information and the first vehicle information to obtain the starting state, target state, open list and closed list of the target vehicle;

[0074] Obtaining a first heuristic function according to the first state transition rule, the starting state and the target state;

[0075] Perform a cyclic search according to the first heuristic function, the starting state, the target state, the open list and the closed list to obtain first state information;

[0076] Perform path backtracking according to the first state information to obtain the first planned path;

[0077] Specifically, the map of the park can be gridded according to the road information to obtain the first state space. According to the road information, parking space information and the first vehicle information, the movement cost between each state in the first state space is defined to obtain the first state transfer rule. For example, if the distance between states is far, the corresponding movement cost will be higher. For large vehicles, if they pass through narrow roads and roads with difficult turns, the corresponding movement cost between states will be higher. For all vehicles, if they pass through congested roads, the corresponding movement cost between states will be higher. The state corresponding to the obstacle distribution in the park will be configured as an obstacle state and cannot be selected.

[0078] Get the current position of the target vehicle as the starting state (node), and obtain at least one target state, that is, at least one alternative parking space, according to the destination information of the target vehicle. The open list is used to store the states to be explored, and the closed list is used to store the states that have been explored. At the same time, set the initial movement cost for the starting state and add it to the open list;

[0079] Construct the first heuristic function of f(n) = g(n) + h(n), where f(n) is the estimated cost from the initial state via state n to the target state, g(n) is the actual cost from the initial state to state n in the state space, and h(n) is the estimated cost of the best path from state n to the target state, which is used to guide the search towards the target direction;

[0080] The first heuristic function can be constructed by choosing Euclidean distance or Manhattan distance. For example, if there are no obstacles in the current state n and its adjacent states, then the actual cost g(n) from the starting state to state n can usually be determined by calculating the number of grid cells passed through. If each grid cell represents 1 unit of cost, then the path cost from the starting state along the straight line to state n is the Manhattan distance between the two points. Of course, bypassing obstacles will increase the corresponding cost.

[0081] Different weight coefficients can also be set for h(n) and g(n) in the first heuristic function to adjust the bias of the search. For example, if you want to be more inclined to find the shortest path, you can increase the weight of h(n). If you want to be more inclined to consider the actual cost, such as considering matching suitable parking spaces for electric vehicles and large vehicles, you can increase the weight of g(n).

[0082] After constructing the first heuristic function, a loop search is required. In each loop, a state is selected from the open list, and the adjacent states are expanded according to the transition rules between states. Their costs (including the actual cost and the estimated cost of the heuristic function) are calculated. These states are then added to the open list and their costs are updated. This process is repeated until the target state is found or the open list is empty. If the target state is found, the first state information of the parent state corresponding to the target state is obtained. If the open list is empty and the target state is not found, it means that there is no path to reach it.

[0083] After finding the target state, the optimal path, i.e. the route of the target vehicle from its current position to the target berth, can be reconstructed by backtracking the parent state of each state;

[0084] The first planned path can be to guide the target vehicle to the parking lot where the target parking space is located. Furthermore, the first planned path can also guide the target vehicle to the target parking space. For example, after the target vehicle arrives at the underground parking lot where the target parking space is located, the target vehicle is guided to the target parking space through indoor positioning technology. The selection of the target parking space can be further subdivided. For example, image data of multiple alternative parking spaces can be obtained, the distance between vehicles on both sides of each alternative parking space is analyzed, and parking spaces with large distances are recommended for the target vehicle first.

[0085] S4. If the target vehicle is a second type of vehicle, obtaining second vehicle information of the target vehicle;

[0086] Specifically, the second vehicle information includes at least relevant data of the second type of vehicle traveling collected by the object platform, such as speed, acceleration, position, direction and other information, and may also include image information of the second type of vehicle collected by the object platform;

[0087] Of course, by performing image recognition on the image information of the second category of vehicles, it is also possible to obtain information such as the second vehicle type, specific size, vehicle color, vehicle license plate number, and type of cargo loaded on the vehicle corresponding to the second category of vehicles.

[0088] S5. Obtain a first prediction result according to the pre-trained first prediction model and the second vehicle information, wherein the first prediction result is configured as a behavior prediction result or a time window prediction result of the second type of vehicle;

[0089] Optionally, the first prediction model is a recurrent neural network model, and the recurrent neural network model is configured to connect an output layer of the recurrent neural network model to a preset softmax layer or a preset linear regression layer according to a target prediction type of the first prediction result, wherein the target prediction type is configured to predict the behavior of the second type of vehicle and predict the time window of the second type of vehicle;

[0090] Optionally, the step of obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information includes:

[0091] preprocessing the second vehicle information to obtain third vehicle information;

[0092] Obtaining the target prediction type;

[0093] Obtaining a first feature set according to the third vehicle information;

[0094] Inputting the first feature set into the first prediction model, and obtaining the first prediction result according to the target prediction type;

[0095] The behavior prediction result of the second type of vehicle may include whether the target vehicle is looking for a parking space, and the time window prediction result of the second type of vehicle may include the location that the target vehicle will arrive at in a subsequent time window;

[0096] Specifically, the first prediction model can be an LSTM long short-term memory network model or a GRU gated recurrent unit model, which can be selected according to actual needs. If faster computing efficiency is required, the GRU gated recurrent unit model can be selected as the first prediction model. If long sequences and long-term dependencies need to be processed, the LSTM long short-term memory network model can be selected.

[0097] By modifying the output layer of the first prediction model, it can dynamically switch its output layer to the softmax layer or the linear regression layer according to the prediction type without changing the model structure. When the behavior prediction result of the second type of vehicle needs to be output, the output layer of the first prediction model is switched to the softmax layer. When the time window prediction result of the second type of vehicle needs to be output, the output layer of the first prediction model is switched to the linear regression layer.

[0098] Preprocessing can include cleaning the data, removing noise and outliers, and standardizing or normalizing the data;

[0099] The features in the first feature set may be features such as the type of the second vehicle, specific dimensions, speed change, acceleration change, distance to the preceding vehicle, road curvature, etc.;

[0100] When training the first model, two evaluations can be performed. When predicting the behavior of the second type of vehicles, evaluation indicators such as accuracy, recall, and F1 score can be used. When predicting the time window of the second type of vehicles, indicators such as mean square error (MSE) and mean absolute error (MAE) can be used;

[0101] Optionally, after the step of obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, the method further includes:

[0102] According to the first prediction result, the first park information is updated to obtain second park information;

[0103] Further optionally, after the step of generating a first planned path according to the first park information of the target park and the first vehicle information if the target vehicle is a first type of vehicle, the method further includes:

[0104] Generate a second planned path according to the second park information and the first planned path;

[0105] Specifically, the step of generating the second planned path may refer to the step of generating the first planned path.

[0106] S6. Generate first prompt information according to the first park information and the first prediction result;

[0107] Specifically, for a vehicle whose first prediction result is finding a parking space, the parking space situation around the corresponding position in the time window will also be generated as the first prompt information based on the prediction result of its time window. For example, for a new energy five-seater sedan whose first prediction result is finding a parking space, the first prediction result shows that it will arrive at point A in 5 minutes and point B in 10 minutes. The first prompt information may include the remaining new energy parking spaces at point A in 5 minutes and the remaining new energy parking spaces at point B in 10 minutes.

[0108] S7, sending the first planned path to the target vehicle or sending the first prompt information to the target device;

[0109] Optionally, after the step of sending the first planned path to the target vehicle or sending the first prompt information to the target device, the method further includes:

[0110] If the target vehicle is a second type of vehicle, in response to a first preset time, obtaining a first vehicle state of the target vehicle;

[0111] Sending, according to the first vehicle state, second request information to the target vehicle requesting berth path planning for the target vehicle;

[0112] The first vehicle state may be a behavior prediction result that the second type of vehicle is still continuing to find a parking space. The first preset time may be set according to actual conditions. For example, after 5 minutes, if the first vehicle state of the second type of vehicle is still continuing to find a parking space, a request message for parking path planning for the target vehicle is sent again, i.e., the second request message. The content of the second request message may be the same as the content of the first request message.

[0113] Specifically, the target device may be a display device, an audio-visual device or a drone. For example, the first prompt information is sent to an electronic display screen closest to the target vehicle.

[0114] Example 2

[0115] A park management system based on industrial Internet of Things is applied to an industrial Internet of Things system, wherein the industrial Internet of Things system comprises: an object platform, a management platform and a user platform that interact in sequence;

[0116] The management platform is configured as follows:

[0117] In response to the first parking signal, sending to the target vehicle a first request message for requesting parking path planning for the target vehicle;

[0118] According to the first reply information from the target vehicle, the target vehicle is classified to obtain a first vehicle type of the target vehicle, wherein the first reply information at least includes the first vehicle information and the first confirmation information of the target vehicle, and the first vehicle type is configured as a first type of vehicle that can directly perform berth path planning and a second type of vehicle that cannot directly perform berth path planning;

[0119] If the target vehicle is a first type of vehicle, generating a first planned path according to the first park information of the target park and the first vehicle information;

[0120] If the target vehicle is a second type of vehicle, obtaining second vehicle information of the target vehicle;

[0121] Obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, wherein the first prediction result is configured as a behavior prediction result or a time window prediction result of the second type of vehicle;

[0122] Generate first prompt information according to the first park information and the first prediction result;

[0123] Sending the first planned path to the target vehicle or sending the first prompt information to a target device;

[0124] The user platform is configured to:

[0125] receiving the first request information and the first planned path from the management platform, and sending the first parking signal and the first reply information to the management platform;

[0126] The object platform is configured as follows:

[0127] The first park information is collected, the first prompt information is received from the management platform, and the first parking signal and the first park information are sent to the management platform.

[0128] Example 3

[0129] like Figure 2 As shown, this embodiment provides an industrial Internet of Things system based on Embodiment 2, including a user platform, a service platform, a management platform, a sensor network platform and an object platform that establish communication in sequence;

[0130] The user platform is configured to provide front-end service functions to users; users obtain the required perceived service information through the user platform, process the perceived service information, and convert it into user perceived information; users analyze the user perceived information and make corresponding decisions based on their own wishes, and convert the user perceived information into user control information through the corresponding information system and send it to the service platform, thereby expressing the user's corresponding service demand intention.

[0131] The physical entities of the user platform include various user terminals, such as mobile phones, computers, dedicated terminals, etc., which realize user-side services through integration with user information system software.

[0132] The service platform is configured as an API server or other server used to establish communication between the management platform and the user platform to implement corresponding functions; the physical entity of the service platform includes various servers.

[0133] The management platform is configured to perform at least one of equipment operation status monitoring management, data monitoring management, equipment parameter management, and life cycle management; the management platform is an operational coordination platform for the Internet of Things, which may include various management sub-platforms, and different management sub-platforms perform different management services; the physical entities of the management platform include various servers.

[0134] The sensor network platform is configured to perform at least one of network management, command management, device status management, data protocol management, data analysis, data classification, data transmission monitoring, and data transmission security management. The sensor network platform provides data communication, analysis, identification, classification, and other functions, avoiding the direct aggregation of data from various object platforms on the management platform, resulting in redundant data on the management platform and low data processing efficiency; the physical entities of the object platform include various gateways, edge computing devices, etc.

[0135] The object platform is configured to perform specific control, detection, measurement, display and other tasks; the physical entity of the object includes various image acquisition devices, sensors, display devices and the like.

[0136] Optionally, the service platform includes a service main database that communicates with the user platform, at least one service sub-platform that communicates with the service platform main database and the service sub-database, the management platform includes at least one management sub-platform that communicates with the service sub-database and the sensor network main database, the management sub-platform includes a management sub-database, the sensor network platform includes at least one sensor network sub-platform that communicates with the object sub-platform and the management sub-platform, the sensor network sub-platform includes a sensor network sub-database, and the object platform includes at least one object sub-platform.

[0137] Optionally, each service sub-platform corresponds to an API function or API server.

[0138] Example 4

[0139] This embodiment provides a device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0140] Example 5

[0141] A computer-readable storage medium stores a computer program, wherein when the computer program is loaded and executed by a processor, any of the above methods is implemented.

[0142] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0144] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0145] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0146] If the integrated unit 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 non-volatile storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0147] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A park berth management method based on industrial Internet of Things, It is characterized in that Applied to an industrial Internet of Things system, the industrial Internet of Things system includes: an object platform, a management platform and a user platform that interact in sequence, and the method is executed by the management platform, including the following steps: In response to the first parking signal, sending to the target vehicle a first request message for requesting parking path planning for the target vehicle; According to the first reply information from the target vehicle, the target vehicle is classified to obtain a first vehicle type of the target vehicle, wherein the first reply information at least includes the first vehicle information and the first confirmation information of the target vehicle, and the first vehicle type includes a first type of vehicle that can directly perform berth path planning and a second type of vehicle that cannot directly perform berth path planning; If the target vehicle is a first type of vehicle, generating a first planned path according to the first park information of the target park and the first vehicle information; If the target vehicle is a second type of vehicle, obtaining second vehicle information of the target vehicle; Obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, wherein the first prediction result is configured as a behavior prediction result or a time window prediction result of the second type of vehicle; Generate first prompt information according to the first park information and the first prediction result; Send the first planned path to the target vehicle or send the first prompt information to the target device.

2. The industrial park berth management method based on the industrial Internet of Things as claimed in claim 1, It is characterized in that After the step of sending the first planned path to the target vehicle or sending the first prompt information to the target device, the method further includes: If the target vehicle is a second type of vehicle, in response to a first preset time, obtaining a first vehicle state of the target vehicle; According to the first vehicle state, second request information is sent to the target vehicle to request berth path planning for the target vehicle.

3. The industrial park berth management method based on industrial Internet of Things as claimed in claim 1, It is characterized in that After the step of obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, the method further includes: According to the first prediction result, the first park information is updated to obtain the second park information.

4. The industrial park berth management method based on industrial Internet of Things as claimed in claim 3, It is characterized in that After the step of generating a first planned path according to the first park information of the target park and the first vehicle information if the target vehicle is a first type of vehicle, the method further includes: A second planned path is generated according to the second park information and the first planned path.

5. The industrial park berth management method based on industrial Internet of Things as claimed in claim 1, It is characterized in that If the target vehicle is a first type of vehicle, the step of generating a first planned path according to the first park information of the target park and the first vehicle information includes: Obtaining a first state space and a first state transition rule according to the first park information and the first vehicle information; Initialize according to the first park information and the first vehicle information to obtain the starting node, the target node, the open list and the closed list of the target vehicle; Obtaining a first heuristic function according to the first state transition rule, the starting node and the target node; Perform a cyclic search according to the first heuristic function, the starting node, the target node, the open list and the closed list to obtain the first node information; Perform path backtracking according to the first node information to obtain the first planned path.

6. The industrial park berth management method based on industrial Internet of Things as claimed in claim 1, Features: The first prediction model is a recurrent neural network model, and the recurrent neural network model is configured to connect the output layer of the recurrent neural network model to a preset softmax layer or a preset linear regression layer according to a target prediction type of the first prediction result, wherein the target prediction type is configured to predict the behavior of the second type of vehicle and the time window of the second type of vehicle.

7. The industrial park berth management method based on industrial Internet of Things as claimed in claim 6, It is characterized in that The step of obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information comprises: preprocessing the second vehicle information to obtain third vehicle information; Obtaining a first feature set according to the third vehicle information; According to the target prediction type of this prediction, the first prediction model is set so that the output layer of the first prediction model is connected to the target component corresponding to the target prediction type; The first feature set is input into the first prediction model to obtain the first prediction result.

8. A park management system based on industrial Internet of Things, It is characterized in that Applied to an industrial Internet of Things system, the industrial Internet of Things system comprises: an object platform, a management platform and a user platform that interact in sequence; The management platform is configured as follows: In response to the first parking signal, sending to the target vehicle a first request message for requesting parking path planning for the target vehicle; According to the first reply information from the target vehicle, the target vehicle is classified to obtain a first vehicle type of the target vehicle, wherein the first reply information at least includes the first vehicle information and the first confirmation information of the target vehicle, and the first vehicle type is configured as a first type of vehicle that can directly perform berth path planning and a second type of vehicle that cannot directly perform berth path planning; If the target vehicle is a first type of vehicle, generating a first planned path according to the first park information of the target park and the first vehicle information; If the target vehicle is a second type of vehicle, obtaining second vehicle information of the target vehicle; Obtaining a first prediction result according to the pre-trained first prediction model and the second vehicle information, wherein the first prediction result is configured as a behavior prediction result or a time window prediction result of the second type of vehicle; Generate first prompt information according to the first park information and the first prediction result; Sending the first planned path to the target vehicle or sending the first prompt information to a target device; The user platform is configured to: receiving the first request information and the first planned path from the management platform, and sending the first parking signal and the first reply information to the management platform; The object platform is configured as follows: The first park information is collected, the first prompt information is received from the management platform, and the first parking signal and the first park information are sent to the management platform.

9. An electronic device, It is characterized in that It includes a processor and a memory, wherein the memory is used to store a computer program; the processor is used to load and execute the computer program so that the electronic device executes the park berth management method based on the industrial Internet of Things as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is loaded and executed by the processor, the park berth management method based on the industrial Internet of Things as described in any one of claims 1 to 7 is implemented.