Intelligent monitoring and self-adaptive scheduling management platform for safe operation of parking lot vehicle based on cloud-side collaborative AI (artificial intelligence)

Abstract

The invention provides a parking lot safety operation intelligent monitoring and self-adaptive scheduling management platform based on cloud edge cooperation AI, and the platform comprises a data analysis and alarm module which carries out the analysis of the behaviors of a driver and the surrounding environment of a vehicle based on an AI model disposed on a parking lot intelligent terminal, and carries out the instant alarm when an abnormal driving behavior or a safety risk exists; the global analysis index determination module is used for uploading the behavior recognition result obtained through analysis and the time series data of the environmental risk information to the cloud platform, and aggregating and mining the time series data of each parking lot vehicle in the space region based on the cloud platform to obtain the global analysis index of the working efficiency and the safety situation of the parking lot vehicle; and the scheduling management module dynamically generates a task scheduling instruction and a path planning instruction of each parking lot based on the global analysis index, and issues the task scheduling instruction and the path planning instruction to the parking lot intelligent terminal for cooperative management of operation behaviors. The operation safety and the operation efficiency are remarkably improved, and human errors and resource waste are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of monitoring and data processing, in particular to a field vehicle safety operation intelligent monitoring and self-adaptive scheduling management platform based on cloud edge collaborative AI. BACKGROUND

[0002] At present, with the rapid development of logistics and warehousing, production and manufacturing industries, field vehicles as important field operation tools, their use frequency and density are increasing, however, the field vehicle operation environment is usually complex, and people and vehicles mix, which leads to high risk of safety accidents; The traditional safety management mode mainly relies on manual supervision, fixed monitoring cameras and simple overspeed alarm devices, which has the problems of large monitoring blind area, late warning, dependence on personnel experience, etc., and it is difficult to realize real-time and accurate perception and intervention on the unsafe behavior of the driver and the risk of complex environment; In addition, the existing field vehicle scheduling management mainly focuses on task allocation and path planning to improve logistics efficiency, which is usually a static task list and map information, and lacks deep integration with real-time safety situation, and the scheduling system cannot perceive the driver's state change, surrounding sudden risks and regional overall safety level fluctuations, which leads to the risk of reducing safety and efficiency. Therefore, in order to overcome the above technical problems, the present application provides a field vehicle safety operation intelligent monitoring and self-adaptive scheduling management platform based on cloud edge collaborative AI. SUMMARY

[0003] The present application provides a field vehicle safety operation intelligent monitoring and self-adaptive scheduling management platform based on cloud edge collaborative AI, which realizes the intelligent management of the whole process of field vehicle operation by using cloud edge collaborative AI technology, analyzes the driver's behavior and the surrounding environment in real time by using AI model in the edge terminal, triggers an alarm as soon as an abnormality or risk is found, effectively prevents safety accidents, uploads the time series data analyzed in real time to the cloud for aggregation and deep mining, generates global indicators reflecting the overall operation efficiency and safety situation, and provides decision support, dynamically adjusts the task allocation and driving path of each vehicle according to the global indicators of operation efficiency and safety situation, and issues instructions to the terminal for execution, realizes collaborative operation and self-adaptive scheduling among field vehicles, significantly improves operation safety and operational efficiency, and reduces human errors and resource waste.

[0004] The present application provides a field vehicle safety operation intelligent monitoring and self-adaptive scheduling management platform based on cloud edge collaborative AI, which comprises: a data analysis and alarm module, configured to analyze driver behavior and vehicle surrounding environment in real time based on an AI model deployed on the field vehicle intelligent terminal, and to perform immediate alarm when there is abnormal driving behavior or safety risk; a global analysis index determination module, configured to upload the behavior recognition result and the time series data of the environmental risk information obtained through analysis to a cloud platform, and to aggregate and mine the time series data of each field vehicle in the space region based on the cloud platform to obtain global analysis indexes of work efficiency and safety situation of the field vehicle; a scheduling management module, configured to dynamically generate task scheduling instructions and path planning instructions of each field vehicle based on the global analysis indexes, and to issue the task scheduling instructions and the path planning instructions to the field vehicle intelligent terminal for collaborative management of work behavior.

[0005] Preferably, the field vehicle safety work intelligent monitoring and adaptive scheduling management platform based on cloud-edge collaborative AI comprises: an image acquisition unit, configured to: acquire a sequence of driver face and posture images and a sequence of vehicle surrounding environment images in real time based on a camera device loaded on the field vehicle; extract key frames and locate face regions from the acquired sequence of face and posture images, and perform standardization preprocessing on the sequence of face and posture images and the sequence of environment images based on data input conditions of the AI model; a data analysis unit, configured to: input the preprocessed key frames, face region positioning results and to-be-analyzed data into the AI model deployed on the field vehicle intelligent terminal, and identify and analyze the key frames and the face region positioning results based on a behavior recognition layer in the AI model to determine a behavior recognition result of the driver; Meanwhile, analyze the preprocessed sequence of environment images based on an environment perception layer in the AI model to obtain environmental risk information of the vehicle surrounding environment; an alarm unit, configured to perform alarm management based on the behavior recognition result and the environmental risk information.

[0006] Preferably, the field vehicle safety work intelligent monitoring and adaptive scheduling management platform based on cloud-edge collaborative AI comprises: an alarm judgment subunit, configured to: obtain alarm thresholds corresponding to driving behavior and environmental safety risk based on the management terminal, and compare the obtained behavior recognition result and environmental risk information with the corresponding alarm thresholds; when the recognition result or the environmental risk information is greater than or equal to the corresponding alarm threshold, it is determined that the alarm condition is met; an alarm execution subunit, configured to: Generate a local alarm instruction based on the determination result, and drive the sound and light alarm device on the field vehicle to give an immediate warning based on the local alarm instruction.

[0007] Preferably, a field vehicle safety operation intelligent monitoring and adaptive scheduling management platform based on cloud edge collaborative AI, the data analysis unit comprises: The behavior determination subunit is configured to: The face and posture image frames subjected to the standardized preprocessing are input to a feature extraction sublayer in the behavior recognition layer, and spatial features of the face and posture image frames are extracted layer by layer based on a convolutional neural network; The key point positioning layer in the behavior recognition layer determines the coordinates of the driver's face key points and the Euler angles of the head posture based on the extracted spatial features, and the face key point coordinates and the head posture Euler angles of each image frame are summarized based on a face and posture image sequence, and the summarized results are subjected to time sequence feature analysis based on a time sequence convolution network to determine the dynamic change law of the driver's blink frequency, closed-eye duration and head deflection angle; The continuous time sequence features obtained are mapped to discrete driver state labels based on a preset classification algorithm according to the dynamic change law, and the corresponding behavior recognition results are obtained, wherein the labels include normal, fatigue, looking around and using handheld devices; The environmental risk determination subunit is configured to: The standardized preprocessed environmental image sequence is input to an environment perception layer, and environmental feature maps containing multiple scales are obtained based on a depth separable convolution operation; Pedestrians, fixed obstacles and boundaries of drivable areas and dangerous areas in the image are recognized and framed based on the environmental feature maps, and the relative distance and azimuth angle between the pedestrians or obstacles and the field vehicle are evaluated based on the pixel coordinates of the framed target detection frame, the known camera intrinsic parameters and the preset actual size priori knowledge; The relative distance and azimuth angle are analyzed based on a safety threshold function of a preset distance and speed to obtain the instant risk level of each detected target or region; The target type, relative distance and azimuth angle of the detected target and the instant risk level are summarized to obtain the environmental risk information around the vehicle.

[0008] Preferably, a field vehicle safety operation intelligent monitoring and adaptive scheduling management platform based on cloud edge collaborative AI, the global analysis index determination module comprises: The data transmission unit is configured to: Obtain the vehicle identifiers of the field vehicles, and extract the time stamps corresponding to the behavior recognition results and the environmental risk information of the drivers on the field vehicles; The vehicle identification, behavior recognition result, and environmental risk information of each vehicle are packaged, and the packaged result is uploaded to a cloud platform based on a wireless communication network; The data analysis unit is configured to: The received behavior recognition result and environmental risk information are subjected to format unification and normalization processing based on a standardized rule preset on the cloud platform, and a vehicle time series database is constructed for each vehicle on the cloud platform. The behavior recognition result and environmental risk information subjected to format unification and normalization processing are stored in the corresponding vehicle time series database based on the time stamp and vehicle identification; The vehicle time series database is periodically scanned based on an aggregation computing engine, and the same type of data of all vehicles in a specified time window and a specified spatial region is subjected to statistical operation based on the periodic scanning result, to obtain primary aggregation indexes of each vehicle, wherein the primary aggregation indexes include the total frequency of fatigue driving events, the occurrence rate of high-risk behaviors, and the density of regional risk points. The global index determination unit is configured to: The primary aggregation indexes, the historical operation mode library, and the static environment map information are subjected to fusion analysis based on a deep learning model, to determine the spatio-temporal correlation between safety events and predict the systematic risk evolution trend. The operation task metadata of each vehicle is extracted, and the spatio-temporal correlation, risk evolution trend, and operation task metadata are jointly analyzed based on a multi-objective optimization algorithm, to obtain global analysis indexes of the operation efficiency and safety situation of the vehicles.

[0009] Preferably, a field vehicle safety operation intelligent monitoring and adaptive scheduling management platform based on cloud-edge collaborative AI, the global index determination unit includes: The index analysis subunit is configured to: The specified time window and the specified spatial region corresponding to the primary aggregation indexes are extracted, and the historical operation load and the historical event sequence matching the specified time window and the specified spatial region are retrieved from the historical operation mode library. Meanwhile, the topological structure, key node position, and functional area attribute of each spatial region are extracted from the static environment map information, to obtain multi-source heterogeneous data. The multi-source heterogeneous data is converted into a unified dimension numerical vector, and the numerical vector is spliced based on a preset rule to obtain a fusion feature vector; The fusion feature vector is converted into a region node and edge relationship graph based on the topological structure of each spatial region according to the deep learning model, and the spatial region dependency relationship is determined based on the region node and edge relationship graph. Meanwhile, the time sequence dependency relationship between the historical event sequence and the current situation of the field vehicle is determined based on the spatial region dependency relationship; Determine the correlation weight between different security event features based on spatial region dependence and time sequence dependence, and determine the correlation mode between security events based on the correlation weight, to obtain a security event space-time correlation rule table; Based on the deep learning model, the fusion feature vector and the security event space-time correlation rule table are iteratively analyzed to obtain the risk evolution probability distribution in each spatial region, and based on the risk evolution probability distribution, the prediction of the systematic risk evolution trend is obtained.

[0010] Preferably, a cloud edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform, a global analysis index determination module, comprising: A result acquisition unit is configured to acquire the obtained global analysis index of the field vehicle's operation efficiency and safety situation, and extract the time node corresponding to the global analysis index; A result recording unit is configured to construct an index recording table, and sequentially record different time nodes and corresponding global analysis indexes into the index recording table based on the development order of the time nodes for storage.

[0011] Preferably, a cloud edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform, a scheduling management module, comprising: An optimization target determination unit is configured to acquire the obtained global analysis index, and simultaneously acquire the field vehicle's operation state information and the to-be-executed task queue, and determine the optimization target at the task scheduling based on the global analysis index and the field vehicle's operation state information and the to-be-executed task queue; A task scheduling instruction generation unit is configured to construct a multi-objective decision model based on the optimization target, and analyze the global analysis index and the field vehicle's operation state information and the to-be-executed task queue based on the target decision model to obtain a macro scheduling scheme, and generate a task scheduling instruction based on the macro scheduling scheme; A path planning instruction generation unit is configured to: Acquire the static environment map corresponding to the scene working area, and generate a collision-free path for each field vehicle from the current position to the target point by taking the macro scheduling scheme as a constraint condition; Evaluate the estimated travel time and comprehensive risk value of each path, and obtain the optimal path of each field vehicle based on the evaluation result; Extract the path point sequence, speed suggestion and risk prompt corresponding to the optimal path, and generate the path planning instruction of each field vehicle based on the path point sequence, speed suggestion and risk prompt.

[0012] Preferably, a cloud edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform, a scheduling management module, comprising: The instruction issuing unit is configured to encapsulate the task scheduling instruction and the path planning instruction of the same field vehicle based on the identity tag of each field vehicle, and issue the encapsulation result to the corresponding field vehicle intelligent terminal based on the communication interface of the cloud platform. The cooperative management unit is configured to configure the working parameters of each field vehicle based on the issuing result, and to perform effective management on the tasks and paths of each field vehicle based on the configuration result, and to feed back the effective management result to the cloud platform, thereby completing the cooperative management of the working behavior.

[0013] Preferably, the field vehicle safety working intelligent monitoring and adaptive scheduling management platform based on cloud-edge cooperative AI comprises a cooperative management unit. The tracking subunit is configured to periodically acquire the running state parameters of each field vehicle after performing effective management on the tasks and paths of each field vehicle, and to re-analyze the running state parameters to obtain global analysis indexes of the working efficiency and safety situation of the field vehicle in the current state. The real-time optimization management subunit is configured to compare the global analysis indexes with preset threshold values, and to re-plan the tasks and paths of each field vehicle when the global analysis indexes do not meet the preset threshold values.

[0014] Compared with the prior art, the field vehicle safety working intelligent monitoring and adaptive scheduling management platform based on cloud-edge cooperative AI has the following beneficial effects: Through the cloud-edge cooperative AI technology, the whole-process intelligent management of the field vehicle working is realized. The AI model is used to analyze the driver behavior and the surrounding environment in real time on the edge terminal. Once an abnormality or risk is found, an alarm is triggered immediately to effectively prevent safety accidents. Meanwhile, the time sequence data of real-time analysis is uploaded to the cloud for aggregation and deep mining to generate global indexes reflecting the overall working efficiency and safety situation, thereby providing decision support. According to the global indexes of the working efficiency and safety situation, the platform dynamically adjusts the task allocation and driving path of each vehicle, and issues the instructions to the terminal for execution, thereby realizing the cooperative working and adaptive scheduling among the field vehicles, significantly improving the working safety and operation efficiency, and reducing human errors and resource waste.

[0015] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the application. The objects and other advantages of the present application can be realized and attained by means of the instrumentalities particularly pointed out in the specification.

[0016] The technical solutions of the present application will be further described in detail below with reference to the drawings and embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation on the present application. In the drawings: Figure 1 This is a structural diagram of a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles, as described in an embodiment of the present invention. Figure 2 This is a structural diagram of the data analysis and alarm module in a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles, as described in an embodiment of the present invention. Figure 3 This is a structural diagram of the global analysis index determination module in a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles, as described in an embodiment of the present invention. Detailed Implementation

[0018] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0019] Example 1: This example provides a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles, such as... Figure 1 As shown, it includes: The data analysis and alarm module is used to perform real-time analysis of driver behavior and the surrounding environment of the vehicle based on the AI ​​model deployed on the intelligent terminal of the parking lot, and to issue an immediate alarm when there is abnormal driving behavior or safety risk. The global analysis index determination module is used to upload the time-series data of the behavior recognition results and environmental risk information obtained from the analysis to the cloud platform, and aggregate and mine the time-series data of each vehicle in the spatial area based on the cloud platform to obtain global analysis indexes of the vehicle's operating efficiency and safety status. The scheduling and management module is used to dynamically generate task scheduling instructions and route planning instructions for each vehicle based on global analysis indicators, and to send the task scheduling instructions and route planning instructions to the intelligent terminal of the vehicle for collaborative management of operation behavior.

[0020] In this embodiment, "site vehicle" refers to a vehicle that operates in a specific location (such as a factory, warehouse, port, etc.), such as a forklift, a pallet truck, or a tractor.

[0021] In this embodiment, the AI ​​model refers to the artificial intelligence algorithm model deployed on the intelligent terminal of the parking lot, which is used to identify driver behavior (such as fatigue driving, illegal operation) and risks in the surrounding environment of the vehicle (such as obstacles, pedestrians) in real time.

[0022] In this embodiment, time-series data refers to a data sequence of behavior identification results and environmental risk information recorded in chronological order, which is used to trace and analyze the dynamic changes during the operation of the parking lot vehicle.

[0023] In this embodiment, the cloud platform refers to a cloud computing-based background service platform responsible for receiving, storing and processing time series data from multiple field vehicles, and performing aggregation and mining calculations.

[0024] In this embodiment, the global analysis indicator refers to a quantitative indicator obtained by comprehensively analyzing all field vehicle data in a spatial region through the cloud, used to evaluate overall work efficiency (such as task completion rate, vehicle utilization rate) and safety situation (such as risk event frequency, alarm distribution).

[0025] In this embodiment, the task scheduling instruction refers to a work task allocation command dynamically generated based on the global analysis indicator and issued to the field vehicle, used to coordinate the work order and load of each vehicle.

[0026] In this embodiment, the path planning instruction refers to an optimized driving route command dynamically generated based on the global analysis indicator and issued to the field vehicle, used to avoid collisions, congestion or dangerous areas.

[0027] In this embodiment, the field vehicle intelligent terminal refers to an intelligent device installed on the field vehicle, with AI analysis, data collection and communication functions, used to perform local analysis and receive cloud instructions.

[0028] In this embodiment, the spatial region refers to the physical range of field vehicle work, such as a specific geographic area within a warehouse, factory or logistics park.

[0029] The beneficial effects of the above technical solution are: through cloud-edge collaborative AI technology, the whole process of field vehicle work is intelligently managed; in the edge terminal, AI model is used to analyze driver behavior and surrounding environment in real time, and once abnormality or risk is found, alarm is triggered immediately to effectively prevent safety accidents; at the same time, time series data analyzed in real time is uploaded to the cloud for aggregation and deep mining, and global indicators reflecting overall work efficiency and safety situation are generated to provide decision support; based on the global indicators of work efficiency and safety situation, the platform dynamically adjusts the task allocation and driving path of each vehicle, and issues instructions to the terminal for execution, realizing collaborative work and adaptive scheduling among field vehicles, significantly improving work safety and operational efficiency, and reducing human error and resource waste.

[0030] Embodiment 2: Based on embodiment 1, this embodiment provides a field vehicle safety work intelligent monitoring and adaptive scheduling management platform based on cloud-edge collaborative AI, as shown in Figure 2 The data analysis and alarm module comprises: The image acquisition unit is configured to: acquire real-time facial and posture image sequences of the driver based on the camera device installed on the field vehicle, and simultaneously acquire environmental image sequences around the vehicle; The collected face and posture image sequences are subjected to key frame extraction and face region positioning, and the face and posture image sequences and the environment image sequences are subjected to standardized preprocessing based on the data input conditions of the AI model; a data analysis unit for: inputting the preprocessed key frames, face region positioning results and to-be-analyzed data into the AI model deployed on the field vehicle intelligent terminal, and identifying and analyzing the key frames and face region positioning results based on the behavior recognition layer in the AI model to determine the behavior recognition result of the driver; Meanwhile, the preprocessed environment image sequences are analyzed based on the environment perception layer in the AI model to obtain the environmental risk information of the vehicle surroundings; an alarm unit for alarm management based on the behavior recognition result and the environmental risk information.

[0031] In this embodiment, the environmental risk information includes the proximity of pedestrians, obstacles or dangerous areas in the vehicle surroundings.

[0032] In this embodiment, the behavior recognition layer refers to the part of the AI model that is specifically used to analyze the driver's face and posture images, and determines the driver's behavior state such as fatigue, distraction or illegal operation by identifying key frames and face regions.

[0033] In this embodiment, the environment perception layer refers to the part of the AI model that is specifically used to analyze the vehicle surrounding environment images, which is used to detect pedestrians, obstacles or dangerous areas in the environment and evaluate their proximity to generate environmental risk information.

[0034] In this embodiment, the behavior recognition result refers to the driver state information obtained by analyzing the behavior recognition layer, including the driver's fatigue state, distraction action or illegal operation.

[0035] The beneficial effects of the above technical solution are: by real-time collection of driver's face, posture and vehicle surrounding environment images, and extraction of key frames and face regions for standardized processing, the AI model is used to identify the driver's fatigue, distraction or illegal behavior, and the surrounding pedestrians, obstacles and other risks are perceived, so as to realize immediate alarm; effectively improve the accuracy of driver behavior monitoring and the real-time performance of environmental risk detection, prevent safety accidents, and enhance the overall safety of the work site.

[0036] Embodiment 3. Based on embodiment 2, this embodiment provides a field vehicle safety operation intelligent monitoring and adaptive scheduling management platform based on cloud-edge collaborative AI, and the alarm unit comprises: an alarm judgment subunit for: The management terminal obtains alarm thresholds corresponding to driving behaviors and environmental safety risks respectively, and compares the obtained behavior recognition result and environmental risk information with the corresponding alarm thresholds respectively; When the identification result or the environmental risk information is greater than or equal to the corresponding alarm threshold, it is determined that the alarm condition is met. The alarm execution subunit is configured to: Generate a local alarm instruction based on the determination result, and drive the sound and light alarm device on the field vehicle to perform instant warning based on the local alarm instruction.

[0037] In this embodiment, the alarm threshold refers to a critical value for triggering an alarm, which is set in advance by the management terminal and is used for setting driving behaviors (such as fatigue level) and environmental safety risks (such as obstacle distance).

[0038] In this embodiment, the management terminal refers to a device or system interface used by the management personnel, which is used to configure and issue system parameters such as alarm thresholds.

[0039] In this embodiment, the local alarm instruction refers to a command signal generated by the field vehicle intelligent terminal when the alarm condition is met, which is used to directly control the local alarm device to start.

[0040] In this embodiment, the sound and light alarm device refers to a physical device installed on the field vehicle, which can simultaneously or separately emit sound (such as a buzzer) and light (such as a warning light) signals, and is used for instant warning on site.

[0041] The beneficial effects of the above technical solution are: by comparing the behavior and environmental data obtained by real-time analysis with the pre-set safety threshold which can be flexibly configured, the standardization and objectivity of risk judgment are realized; once the threshold is reached or exceeded, the system will automatically trigger the local sound and light warning, providing instant and explicit on-site reminders for the driver, effectively avoiding the response lag caused by subjective judgment delay or omission, significantly improving the real-time and accuracy of risk warning, thereby intervening in potential dangers in the first time, preventing accidents from happening or expanding, and ensuring the safety of people and vehicles on the work site.

[0042] Embodiment 4: Based on embodiment 2, this embodiment provides a field vehicle safety operation intelligent monitoring and self-adaptive scheduling management platform based on cloud edge collaborative AI, and the data analysis unit comprises: The behavior determination subunit is configured to: Input the standardized preprocessed face and posture image frames into the feature extraction sublayer in the behavior recognition layer, and extract the spatial features of the face and posture image frames layer by layer based on the convolutional neural network. Based on the key point localization layer in the behavior recognition layer, the coordinates of the driver's facial key points and the Euler angles of the head posture are determined according to the extracted spatial features. Based on the facial and posture image sequence, the coordinates of the facial key points and the Euler angles of the head posture of each image frame are summarized. Furthermore, based on the temporal convolutional network, the summarization results are analyzed for temporal features to determine the dynamic changes of the driver's blinking frequency, eye-closing duration and head offset angle. Based on a preset classification algorithm, the continuous temporal features obtained are mapped into discrete driver state labels according to the dynamic change pattern, and the corresponding behavior recognition results are obtained. The labels include normal, fatigued, looking around, and using a handheld device. The environmental risk determination subunit is used for: The standardized preprocessed environmental image sequence is input into the environment perception layer, and based on depthwise separable convolution operation, an environmental feature map containing multiple scales is obtained; Based on the environmental feature map, pedestrians, fixed obstacles, and the boundaries of drivable and dangerous areas in the image are identified and bounded. Based on the pixel coordinates of the bounding target detection box, known camera intrinsic parameters, and preset prior knowledge of actual size, the relative distance and azimuth angle between pedestrians or obstacles and the field vehicle are evaluated. The relative distance and azimuth are analyzed based on a preset safety threshold function for distance and speed to obtain the instantaneous risk level of each detected target or area; The environmental risk information around the vehicle is obtained by summarizing the target type, relative distance and azimuth angle between the detected target and the vehicle.

[0043] In this embodiment, spatial features refer to multidimensional data representations extracted from single-frame facial and pose images through convolutional neural networks, which can characterize key information in the image (such as eye and mouth contours, head orientation).

[0044] In this embodiment, the key point localization layer refers to a specific network layer in the behavior recognition layer. Its function is to output the pixel coordinates of predefined facial key points (such as the corners of the eyes and mouth) and Euler angles representing the head rotation angle based on the input spatial features.

[0045] In this embodiment, Euler angles refer to a mathematical representation of the attitude of an object (in this case, the driver's head) in three-dimensional space using three angles of rotation about an axis (usually yaw, pitch, and roll).

[0046] In this embodiment, temporal convolutional network refers to a convolutional neural network structure specifically designed for processing temporal data (such as feature sequences of consecutive image frames), which can capture the dynamic changes of data in the time dimension.

[0047] In this embodiment, depthwise separable convolution operation refers to a lightweight convolution calculation method that decomposes standard convolution into two steps: depthwise convolution and pointwise convolution, which can significantly reduce the amount of computation while maintaining certain model performance.

[0048] In this embodiment, the environmental feature map refers to the set of feature matrices obtained by performing convolution operations on the environmental image sequence, which contains semantic information at different levels of abstraction (such as edges, shapes, and target components).

[0049] In this embodiment, the target detection box refers to a rectangular area on the environmental feature map or the original image used to frame and locate the identified target (such as a pedestrian or obstacle), which is usually represented by pixel coordinates.

[0050] In this embodiment, the risk level refers to a level index calculated by a preset safety model based on the relative distance, azimuth angle, and speed of movement of the detected target and the vehicle, which is used to quantify the current degree of danger.

[0051] The beneficial effects of the above technical solution are as follows: Firstly, by continuously extracting spatiotemporal features of the face and posture, and using a time-series model to analyze dynamic patterns, it can accurately identify subtle and continuous state changes from normal to fatigued or distracted states, greatly improving the finesse and reliability of behavior recognition. Secondly, by utilizing efficient convolutional networks to extract multi-scale environmental features and combining geometric principles to convert image coordinates into distance and orientation in real space, it achieves a quantitative assessment of the risk level of targets such as pedestrians and obstacles. This provides a high-confidence data foundation for subsequent accurate alarms and dispatching, enabling safety monitoring to move from qualitative perception to quantitative decision-making, effectively preventing safety accidents caused by subtle changes in state or misjudgments of distance.

[0052] Example 5: Based on Example 1, this example provides a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles, such as... Figure 3 As shown, the global analysis indicator determination module includes: Data transmission unit, used for: Obtain the vehicle identification number of each vehicle and extract the timestamps corresponding to the behavioral recognition results of the drivers on each vehicle and the environmental risk information; The vehicle identification, behavior recognition results, environmental risk information, and corresponding timestamps for each vehicle are packaged together and uploaded to the cloud platform via a wireless communication network. Data analysis unit, used for: Based on the standardized rules preset on the cloud platform, the received behavior recognition results and environmental risk information are formatted and normalized. At the same time, a vehicle time series database is built for each vehicle on the cloud platform, and the formatted and normalized behavior recognition results and environmental risk information are stored in the corresponding vehicle time series database based on the timestamp and vehicle identifier. Based on the aggregation computing engine, the vehicle time series database is periodically scanned, and statistical calculations are performed on the same data of all vehicles in the specified time window and specified spatial area based on the periodic scan results to obtain the primary aggregation index of each vehicle. The primary aggregation index includes the total frequency of fatigue driving events, the incidence rate of high-risk behaviors, and the density of regional risk points. The global indicator determination unit is used for: Based on a deep learning model, primary aggregation indicators are integrated with historical operation pattern database and static environment map information to determine the spatiotemporal correlation between safety events and predict the evolution trend of systemic risks. Extract the metadata of the operation tasks of each vehicle in the yard, and perform joint analysis of the spatiotemporal correlation, risk evolution trend and operation task metadata based on a multi-objective optimization algorithm to obtain global analysis indicators of the operation efficiency and safety status of the vehicles in the yard.

[0053] In this embodiment, the timestamp refers to the precise time data that records the moment when each behavior identification result or environmental risk information is generated.

[0054] In this embodiment, packetization refers to the process of packaging vehicle identification, data content, and their timestamps into an independent data unit according to a predetermined format and protocol.

[0055] In this embodiment, the vehicle time-series database refers to a database created independently for each parking vehicle on a cloud platform, which stores all its behavioral and environmental-related structured data in chronological order.

[0056] In this embodiment, the aggregation computing engine refers to a dedicated software module on the cloud platform used to periodically scan time-series databases and perform statistical operations (such as summation, counting, and density calculation) on massive amounts of data within specified dimensions and time windows.

[0057] In this embodiment, the primary aggregation index refers to the intermediate results obtained by performing preliminary statistical calculations on the original time-series data, such as the total frequency of fatigue driving events, the incidence of high-risk behaviors, and the density of regional risk points.

[0058] In this embodiment, the historical operation pattern library refers to a data set stored in the cloud that describes the typical operation patterns of the site vehicle in a specific area or time period (such as high-frequency driving routes and regular task cycles).

[0059] In this embodiment, static environment map information refers to digital information about the site environment that is pre-entered into the system and does not change frequently, including road layout, location of fixed facilities, functional area division, etc.

[0060] In this embodiment, spatiotemporal correlation refers to the inherent connection or pattern between the time of occurrence and the geographical location of security events, as discovered through analysis.

[0061] In this embodiment, the systemic risk evolution trend refers to the direction and pattern of overall change in the safety risks of the entire work area over a future period of time, predicted based on current and historical data.

[0062] In this embodiment, the task metadata refers to data that describes the basic attributes of the task performed by the vehicle, such as task type, start and end point, planned duration, priority, etc.

[0063] In this embodiment, the multi-objective optimization algorithm refers to a mathematical solution method used to find the optimal balance between multiple conflicting objectives (such as maximizing operational efficiency and minimizing safety risks), and to estimate the overall operational efficiency coefficient.

[0064] The beneficial effects of the above technical solution are as follows: By systematically uploading data with precise time stamps from each vehicle to the cloud and performing standardized processing and storage, a complete vehicle operation time-series database is constructed; through periodic aggregation calculations, scattered real-time information is transformed into primary statistical indicators reflecting the overall situation of the region; combining prior knowledge such as historical operation patterns and static maps, deep learning is used to mine the spatiotemporal correlation of safety events and predict risk trends; finally, real-time task data is integrated, and global indicators that balance efficiency and safety are analyzed through multi-objective optimization. This enables management decisions to transcend the immediate risks of individual vehicles, gain insight into potential hazards and predict situations from a systemic perspective, thereby providing accurate data-driven basis for forward-looking collaborative scheduling and resource optimization, and comprehensively improving the safety level and operational efficiency of regional operations.

[0065] Example 6: Based on Example 5, this example provides a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles, including a global indicator determination unit: The indicator analysis subunit is used for: Extract the specified time window and specified spatial area corresponding to the primary aggregation index, and retrieve the historical operation load and historical event sequence that match the specified time window and specified spatial area from the historical operation mode library. At the same time, extract the topology, key node location and functional area attributes of each spatial area from the static environment map information to obtain multi-source heterogeneous data. Multi-source heterogeneous data is converted into numerical vectors of a unified dimension, and the numerical vectors are concatenated according to preset rules to obtain a fused feature vector. Based on the deep learning model, the fused feature vectors are converted into a relationship graph of regional nodes and edges according to the topology of each spatial region. Based on the relationship graph of regional nodes and edges, the spatial region dependencies are determined. At the same time, based on the spatial region dependencies, the temporal dependencies between historical event sequences and the current status of the field vehicle are determined. Based on spatial region dependency and temporal dependency, the association weights between different security event characteristics are determined, and the association patterns between security events are determined based on the association weights, resulting in a spatiotemporal association rule table for security events. Based on a deep learning model, iterative analysis is performed on the fused feature vector and the spatiotemporal correlation rule table of security events to obtain the risk evolution probability distribution in each spatial region, and the predicted systemic risk evolution trend is obtained based on the risk evolution probability distribution.

[0066] In this embodiment, multi-source heterogeneous data refers to a collection of data from different sources, structures, and formats, including primary aggregation indicators, matched historical workloads and historical event sequences, as well as topological structures, node locations, and functional area attributes extracted from map information.

[0067] In this embodiment, the fused feature vector refers to a feature vector that comprehensively represents the overall state of a specified time window and spatial region after multi-source heterogeneous data is converted into a numerical vector of a unified dimension and spliced ​​together according to preset rules.

[0068] In this embodiment, the relationship graph between regional nodes and edges refers to a graph data structure constructed based on the topological structure of spatial regions, where each sub-region or its key nodes are represented as "nodes" and the connections or influence relationships between regions are represented as "edges," which is used to model spatial dependencies.

[0069] In this embodiment, spatial regional dependency refers to the mutual influence or association between different geographical sub-regions in terms of security situation, as revealed by the relationship graph of regional nodes and edges.

[0070] In this embodiment, the temporal dependency relationship refers to the correlation or evolutionary pattern of security events in the time dimension, which is derived from the analysis of historical event sequences and the current situation.

[0071] In this embodiment, the association weight refers to a numerical value determined through model learning, used to quantify the strength of the association between different security event characteristics (such as a certain behavior and a certain type of environmental risk).

[0072] In this embodiment, the security event spatiotemporal association rule table refers to the association pattern between security events recorded in a structured form (such as a table). Its rules usually include elements such as event type, spatial relationship, temporal relationship and association weight.

[0073] In this embodiment, the risk evolution probability distribution refers to the quantitative probability distribution of different levels or types of risks occurring in various spatial regions within a future period, as predicted by the model.

[0074] The beneficial effects of the above technical solution are as follows: By deeply integrating real-time aggregated indicators, historical operational patterns, and static environmental information, a multi-dimensional data feature that comprehensively describes the operational scenario is constructed; by using a deep learning model, these features are transformed into a graph structure that reflects spatial topological relationships, thereby accurately depicting the mutual influence between different regions and the temporal dependence between historical and current situations; intelligently analyzing and quantifying the intrinsic correlation weights between different safety event features, forming clear spatiotemporal correlation rules; finally, through iterative analysis, the future risk probability distribution of each region is predicted, achieving a forward-looking judgment on the evolution trend of systemic risks; and providing in-depth decision-making insights for implementing precise proactive intervention and preventive scheduling, greatly improving the predictability and scientific nature of safety management.

[0075] Example 7: Based on Example 1, this example provides a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles, including a global analysis indicator determination module, comprising: The result acquisition unit is used to acquire global analysis indicators of the operating efficiency and safety status of the field vehicles, and extract the time nodes corresponding to the global analysis indicators. The results recording unit is used to construct the indicator recording table and to sequentially enter different time nodes and their corresponding global analysis indicators into the indicator recording table for storage based on the development order of time nodes.

[0076] In this embodiment, a time node refers to the specific moment or time period corresponding to the generation or acquisition of a set of global analysis indicators.

[0077] In this embodiment, the indicator record table refers to a database table or structured file used to systematically store historical global analysis indicators in chronological order.

[0078] The beneficial effects of the above technical solution are as follows: by retaining global analysis indicators at each time point, a complete historical situation archive is constructed, enabling managers to trace changes in operational efficiency and safety levels over different time periods, clearly understand the actual effects and long-term trends of management measures, provide reliable quantitative basis for continuous optimization of scheduling strategies and evaluation of improvement plans, and the standardized records also provide complete data support for post-event analysis, accountability tracing and compliance audits, thereby improving the scientific nature and traceability of overall management.

[0079] Example 8: Based on Example 1, this example provides a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles. The scheduling management module includes: The system obtains global analysis metrics, as well as the operational status information of each vehicle and the queue of tasks to be executed. Based on the global analysis metrics, the operational status information of each vehicle and the queue of tasks to be executed, the system determines the optimization objectives for task scheduling. A multi-objective decision-making model is constructed based on the optimization objective. Based on the objective decision-making model, global analysis indicators, operational status information of vehicles in each yard, and queue of tasks to be executed are analyzed to obtain a macro-scheduling scheme. Based on the macro-scheduling scheme, task scheduling instructions are generated. Obtain the static environment map corresponding to the scene's working area, and use the macro scheduling scheme as a constraint to generate a collision-free path from the current location to the target point for each vehicle in the field. Assess the estimated travel time and overall risk value of each route, and obtain the optimal route for each vehicle based on the assessment results; Extract the path point sequence, speed suggestions, and risk warnings corresponding to the optimal path, and generate path planning instructions for each vehicle based on the path point sequence, speed suggestions, and risk warnings.

[0080] In this embodiment, the optimization objective is to minimize the total system risk and maximize the overall operational efficiency.

[0081] In this embodiment, the macro scheduling scheme refers to the task execution order of each vehicle, the start time of the operation, and the suggested average operation speed.

[0082] In this embodiment, the multi-objective decision model refers to a mathematical model or algorithmic framework used to weigh and solve multiple conflicting optimization objectives (such as safety and efficiency).

[0083] In this embodiment, the static environment map refers to map information that is pre-digitally entered into the system and reflects the fixed layout within the work area, including the locations of roads, passages, and fixed facilities.

[0084] In this embodiment, a collision-free path refers to a feasible driving route planned in a static environment map, from the starting point to the target point, without conflicting with static obstacles or area boundaries.

[0085] In this embodiment, the estimated travel time refers to the estimated time required for a vehicle to complete a certain route, based on the route length, recommended speed, and historical traffic data.

[0086] In this embodiment, the comprehensive risk value refers to the quantitative value obtained after risk assessment of a certain path. Its calculation comprehensively considers factors such as the density of historical risk points around the path, real-time risk information, and road complexity.

[0087] In this embodiment, the optimal path refers to the best driving route selected from multiple collision-free paths based on preset evaluation criteria (such as balancing the shortest time and the lowest risk).

[0088] In this embodiment, the path point sequence refers to a series of ordered coordinate points that constitute a driving path, used to guide the vehicle from the starting point to the destination.

[0089] In this embodiment, the speed recommendation refers to the recommended driving speed for different road segments in the route planning process to ensure safety or to coordinate with the overall scheduling.

[0090] In this embodiment, risk warning refers to the text or label warning in the route planning instruction for potential risks (such as blind spots or high-frequency accident points) in a specific road segment or area.

[0091] The beneficial effects of the above technical solution are as follows: by integrating real-time global indicators, vehicle status, and pending tasks, it achieves the core objective of balancing system safety and operational efficiency, intelligently generating macro-level task allocation and time plans, and then combining high-precision maps to plan collision-free and optimal driving routes for each vehicle in real time, providing specific speed suggestions and risk warnings; it effectively realizes end-to-end optimization from task allocation to single-vehicle-level path guidance, can dynamically respond to changes on-site, effectively avoid congestion and risk areas, and significantly improve the collaborative operation efficiency and task completion speed of vehicles on site while ensuring overall safety.

[0092] Example 9: Based on Example 1, this example provides a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles. The scheduling management module includes: The instruction issuing unit is used to encapsulate the task scheduling instructions and route planning instructions of the same vehicle based on the identity tags of each vehicle, and to send the encapsulation results to the corresponding intelligent terminal of the vehicle based on the communication interface of the cloud platform. The collaborative management unit is used to configure the working parameters of each vehicle based on the issued results, and to manage the tasks and routes of each vehicle based on the configuration results. The management results are then fed back to the cloud platform to complete the collaborative management of work behavior.

[0093] In this embodiment, the identity tag refers to a code or identifier registered in the cloud platform and used to uniquely identify and distinguish different vehicles. It usually corresponds to the vehicle identifier and is used for the targeted issuance of instructions.

[0094] In this embodiment, the communication interface refers to the specific communication protocol or hardware / software channel used for stable and secure data transmission between the cloud platform and the intelligent terminal of the parking lot.

[0095] In this embodiment, the operating parameters refer to the specific operating parameters that the intelligent terminal of the parking lot needs to configure in order to execute specific task scheduling instructions and path planning instructions, such as target speed, navigation mode, task priority identifier, etc.

[0096] In this embodiment, effective management refers to the process by which the intelligent terminal of the parking lot receives and parses the instruction, applies the instruction to the vehicle control system, enables the new task and path to begin formal execution, and monitors and confirms the status of the new task and path.

[0097] The beneficial effects of the above technical solution are as follows: by accurately binding and encapsulating dispatch instructions with specific vehicle identities, the accurate delivery and parsing of instructions are ensured. The vehicle terminal receiving the instructions will automatically configure relevant operation parameters, so that new tasks and route planning take effect immediately, and the execution status will be fed back to the cloud in real time, thus forming a complete management closed loop from instruction generation, issuance, execution to status feedback; the reliability and execution efficiency of dispatch instructions are improved, precise coordination and unified management of multi-vehicle operations are realized, instruction mismatch or response delay is effectively avoided, and the safe and orderly execution of the overall operation plan is guaranteed.

[0098] Example 10: Based on Example 9, this example provides a cloud-edge collaborative AI-based intelligent monitoring and adaptive scheduling management platform for safe operation of parking vehicles. The collaborative management unit includes: The tracking subunit is used to periodically obtain the operating status parameters of each vehicle after the task and route of each vehicle have been effectively managed, and to re-analyze the operating status parameters to obtain global analysis indicators of the operating efficiency and safety status of the vehicle under the current status. The real-time optimization management subunit is used to compare global analysis indicators with preset thresholds, and to replan the tasks and routes of each vehicle when a global analysis indicator fails to meet the preset threshold.

[0099] In this embodiment, the operating status parameters refer to the data that are periodically obtained from the intelligent terminal of the parking lot during the task execution process, reflecting the real-time status of the vehicle, such as actual location, speed, task completion progress, and current alarm status.

[0100] In this embodiment, the preset threshold refers to the minimum or maximum standard value set for various global analysis indicators (such as the lower limit of overall operation efficiency, the highest acceptable risk level of the system, etc.) to determine whether the overall operating status of the system meets the standard.

[0101] The beneficial effects of the above technical solution are: it can flexibly respond to various sudden changes at the work site, continuously ensure that the work process is carried out in an optimal or safe and controllable state, and effectively avoid the decline in efficiency or the accumulation of risks caused by the disconnect between the initial plan and the actual situation.

[0102] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform, characterized in that, Comprise: A data analysis and alarm module for real-time analysis of driver behavior and vehicle surrounding environment based on AI models deployed on the field vehicle intelligent terminal, and immediate alarm when there is abnormal driving behavior or safety risk; A global analysis index determination module for uploading the behavior recognition results and time series data of environmental risk information obtained by analysis to the cloud platform, and aggregating and mining the time series data of each field vehicle in the space region based on the cloud platform to obtain global analysis indexes of the work efficiency and safety situation of the field vehicle; A scheduling management module for dynamically generating task scheduling instructions and path planning instructions for each field vehicle based on the global analysis indexes, and issuing the task scheduling instructions and path planning instructions to the field vehicle intelligent terminal for work behavior collaborative management.

2. The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform according to claim 1, characterized in that, The data analysis and alarm module comprises: An image acquisition unit for: Real-time acquisition of driver face and posture image sequences based on the camera device loaded on the field vehicle, and simultaneously, acquisition of environmental image sequences around the vehicle; Key frame extraction and face region positioning of the collected face and posture image sequences, and standardization preprocessing of the face and posture image sequences and environmental image sequences based on the data input conditions of the AI model; The data analysis unit is configured to: Input the preprocessed key frames, face region positioning results and to-be-analyzed data into the AI model deployed on the field vehicle intelligent terminal, and identify and analyze the key frames and face region positioning results based on the behavior recognition layer in the AI model to determine the driver behavior recognition result; At the same time, analyze the preprocessed environmental image sequences based on the environment perception layer in the AI model to obtain the environmental risk information around the vehicle; The alarm unit is configured to perform alarm management based on the behavior recognition result and the environmental risk information. 3.The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform of claim 2, characterized in that, The alarm unit comprises: An alarm judgment subunit configured to: Obtain alarm thresholds corresponding to driving behavior and environmental safety risk based on the management terminal, and compare the obtained behavior recognition result and environmental risk information with the corresponding alarm warning thresholds respectively; When there is an identification result or environmental risk information greater than or equal to the corresponding alarm threshold, it is determined that the alarm condition is met; An alarm execution subunit configured to: Generate a local alarm instruction based on the determination result, and drive the sound and light alarm device on the field vehicle to perform immediate warning based on the local alarm instruction.

4. The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform according to claim 2, characterized in that, The data analysis unit comprises: A behavior determination subunit configured to: Input the standardized preprocessed face and posture image frames into the feature extraction sublayer in the behavior recognition layer, and extract the spatial features of the face and posture image frames layer by layer based on the convolutional neural network; Determine the coordinates of the driver face key points and the Euler angles of the head posture based on the key point positioning layer in the behavior recognition layer according to the extracted spatial features, and summarize the face key point coordinates and head posture Euler angles of each image frame based on the face and posture image sequence, and perform time series feature analysis on the summary results based on the time series convolution network to determine the dynamic change law of the driver blink frequency, closed-eye duration and head offset angle; The continuous time sequence features are mapped into discrete driver state labels according to a dynamic change rule based on a preset classification algorithm, and a corresponding behavior recognition result is obtained, wherein the labels include normal, fatigue, looking left and right and using handheld devices; The environment risk determination subunit is used for: The standardized preprocessed environment image sequence is input into the environment perception layer, and environment feature maps containing multiple scales are obtained based on depth separable convolution operation; Pedestrians, fixed obstacles and boundaries of drivable areas and dangerous areas in the image are recognized and framed based on the environment feature maps, and the relative distance and azimuth angle between the pedestrians or obstacles and the field vehicle are evaluated based on the pixel coordinates of the framed target detection frame, the known camera internal parameters and the preset actual size priori knowledge; The relative distance and azimuth angle are analyzed based on a safety threshold function of preset distance and speed, and the instant risk level of each detected target or area is obtained; The target type of the detected target, the relative distance and azimuth angle to the field vehicle and the instant risk level are summarized, and the environment risk information of the vehicle periphery is obtained.

5. The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform according to claim 1, characterized in that, The global analysis index determination module includes: The data transmission unit is used for: Obtaining vehicle identifiers of the field vehicles, and extracting time stamps corresponding to the behavior recognition results and the environment risk information of the drivers on the field vehicles; Packing the vehicle identifiers, the behavior recognition results and the environment risk information and the corresponding time stamps of each field vehicle, and uploading the packing results to the cloud platform based on a wireless communication network; The data analysis unit is used for: Performing format unification and normalization processing on the received behavior recognition results and environment risk information based on preset standardized rules on the cloud platform, simultaneously, constructing a vehicle time sequence database for each field vehicle on the cloud platform, and storing the behavior recognition results and the environment risk information after the format unification and normalization processing into the corresponding vehicle time sequence database based on the time stamps and the vehicle identifiers; Periodically scanning the vehicle time sequence database based on an aggregation calculation engine, and performing statistical operation on the same data of all field vehicles in a specified time window and a specified space region based on the periodic scanning results, to obtain primary aggregation indexes of the field vehicles, wherein the primary aggregation indexes include the total frequency of fatigue driving events, the high-risk behavior occurrence rate and the regional risk point density; The global index determination unit is used for: Fusing and analyzing the primary aggregation indexes, the historical operation mode library and the static environment map information based on a deep learning model, determining the spatio-temporal correlation between safety events, and predicting the systematic risk evolution trend; Extracting operation task metadata of the field vehicles, and jointly analyzing the spatio-temporal correlation, the risk evolution trend and the operation task metadata based on a multi-objective optimization algorithm, to obtain the global analysis indexes of the operation efficiency and the safety situation of the field vehicles.

6. The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform according to claim 5, characterized in that, The global index determination unit includes: The index analysis subunit is used for: extract a specified time window and a specified space region corresponding to the primary polymerization index, and call a historical job load and a historical event sequence matching the specified time window and the specified space region from a historical job mode library, and meanwhile, extract a topology structure, a key node position and a functional area attribute of each space region from static environment map information to obtain multi-source heterogeneous data; convert the multi-source heterogeneous data into a unified dimension numerical vector, and splice the numerical vector based on a preset rule to obtain a fusion feature vector; convert the fusion feature vector into a region node and edge relationship graph based on a deep learning model according to the topology structure of each space region, and determine a space region dependency relationship based on the region node and edge relationship graph, and meanwhile, determine a time sequence dependency relationship between the historical event sequence and the current situation of the field vehicle based on the space region dependency relationship; determine an association weight between different safety event features based on the space region dependency relationship and the time sequence dependency relationship, and determine an association mode between safety events based on the association weight to obtain a safety event space-time association rule table; perform iterative analysis on the fusion feature vector and the safety event space-time association rule table based on a deep learning model to obtain a risk evolution probability distribution in each space region, and obtain a predicted systematic risk evolution trend based on the risk evolution probability distribution.

7. The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform according to claim 1, characterized in that, The global analysis index determination module comprises: a result acquisition unit configured to acquire the obtained global analysis index of the job efficiency and safety situation of the field vehicle, and extract a time node corresponding to the global analysis index; a result recording unit configured to construct an index recording table, and sequentially record different time nodes and corresponding global analysis indexes into the index recording table based on the development order of the time nodes for storage. 8.The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform of claim 1, wherein, The scheduling management module comprises: an optimization target determination unit configured to acquire the obtained global analysis index, simultaneously acquire field vehicle job state information and a to-be-executed task queue, and determine an optimization target at the time of task scheduling based on the global analysis index and the field vehicle job state information and the to-be-executed task queue; a task scheduling instruction generation unit configured to construct a multi-objective decision model based on the optimization target, analyze the global analysis index and the field vehicle job state information and the to-be-executed task queue based on the decision model, obtain a macro scheduling scheme, and generate a task scheduling instruction based on the macro scheduling scheme; a path planning instruction generation unit configured to: acquire a static environment map corresponding to a scene working area, and generate a collision-free path for each field vehicle from a current position to a target point by taking the macro scheduling scheme as a constraint condition; evaluate an estimated passing time and a comprehensive risk value of each path, and obtain an optimal path for each field vehicle based on the evaluation result; extract a path point sequence, a speed suggestion and a risk prompt corresponding to the optimal path, and generate a path planning instruction for each field vehicle based on the path point sequence, the speed suggestion and the risk prompt. 9.The cloud-edge collaborative AI based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform according to claim 1, characterized in that, The scheduling management module comprises: an instruction issuing unit configured to encapsulate the task scheduling instruction and the path planning instruction of the same field vehicle based on an identity tag of each field vehicle, and issue the encapsulation result to a corresponding field vehicle intelligent terminal based on a communication interface of a cloud platform. The cooperative management unit is configured to configure the working parameters of the field vehicles based on the result of the delivery, to perform effective management on the tasks and paths of the field vehicles based on the configuration result, and to feed back the effective management result to the cloud platform, thereby completing the cooperative management of the working behavior.

10. The cloud-edge collaborative AI-based field vehicle safety operation intelligent monitoring and adaptive scheduling management platform according to claim 9, characterized in that, The cooperative management unit comprises: The tracking subunit is configured to periodically acquire the running state parameters of the field vehicles after performing the effective management on the tasks and paths of the field vehicles, to re-analyze the running state parameters, and to obtain global analysis indexes of the working efficiency and the safety situation of the field vehicles in the current state; The real-time optimization management subunit is configured to compare the global analysis indexes with preset threshold values, and to re-plan the tasks and paths of the field vehicles when the global analysis indexes do not meet the preset threshold values.

Images