CN118522154B - Beidou navigation-based vehicle command management system and method - Google Patents
Beidou navigation-based vehicle command management system and method Download PDFInfo
- Publication number
- CN118522154B CN118522154B CN202410985243.9A CN202410985243A CN118522154B CN 118522154 B CN118522154 B CN 118522154B CN 202410985243 A CN202410985243 A CN 202410985243A CN 118522154 B CN118522154 B CN 118522154B
- Authority
- CN
- China
- Prior art keywords
- data
- time
- real
- vehicle
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 60
- 238000007726 management method Methods 0.000 claims abstract description 58
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 238000009826 distribution Methods 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000013468 resource allocation Methods 0.000 claims abstract description 9
- 230000000007 visual effect Effects 0.000 claims abstract description 9
- 238000013135 deep learning Methods 0.000 claims abstract description 6
- 230000004044 response Effects 0.000 claims description 31
- 238000013439 planning Methods 0.000 claims description 23
- 239000000446 fuel Substances 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 20
- 230000007246 mechanism Effects 0.000 claims description 11
- 230000002068 genetic effect Effects 0.000 claims description 10
- 230000002457 bidirectional effect Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 5
- 238000007667 floating Methods 0.000 claims description 5
- 230000003068 static effect Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 claims 3
- 238000012545 processing Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 10
- 239000003016 pheromone Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 230000019637 foraging behavior Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000009024 positive feedback mechanism Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application provides a Beidou navigation-based vehicle command management system and method, and belongs to the technical field of satellite navigation application. The system comprises a high-precision positioning and Internet of things basic module, wherein the high-precision positioning is realized based on a Beidou positioning terminal installed on a vehicle, vehicle data is uploaded in real time through the Internet of things technology, and real-time human resource monitoring, management and visual display are provided based on GIS; the intelligent prediction and early warning system module is used for establishing a prediction model by utilizing deep learning based on collected historical early warning information data, traffic flow data and meteorological data, automatically identifying potential traffic jam areas and accident high-occurrence areas, generating early warning in advance and scheduling manpower standby; and the self-adaptive scheduling and resource optimizing module is used for analyzing traffic conditions, manpower distribution, staff states and early warning emergency degree in real time, dynamically adjusting scheduling strategies and adopting an optimizing algorithm to ensure resource allocation optimization. The flexibility of manpower use and the processing efficiency of emergency events are greatly improved.
Description
Technical Field
The invention belongs to the technical field of satellite navigation application, and particularly relates to a vehicle command management system and method based on Beidou navigation.
Background
Because the management resources of the city are limited, but the busyness of each road section in the city is different, the manpower resources required to be dispatched by each road section are also different, and the conventional public security traffic management manpower resource allocation mode mainly comprises interphone, telephone and other modes, so that the problems of unbalanced allocation, multiple early warning information transmission levels, multiple command and the like are solved.
The prior art publication No. CN117459900A provides an integrated management system for patrol vehicles, combines intelligent police cars, mobile terminals and command centers, displays the positions and the driving routes of the police cars on a map by utilizing a geographic information system technology through real-time transmission of field information, realizes quick response of alarm information, and improves manpower dispatching efficiency by utilizing GIS, video stream processing and voice recognition technologies, thereby ensuring safety and shortening emergency response time. The prior art improves the allocation efficiency and response speed of human resources to a certain extent, but has some challenges and limitations in practical application, has insufficient dynamic scheduling and real-time optimization of human resources, and cannot flexibly adjust human deployment according to real-time traffic conditions and early warning information changes; meanwhile, the cross-regional collaborative operation and resource sharing lack of effective integration and management mechanisms, and are difficult to cope with complex and changeable public security situations.
In view of the above, we provide a vehicle command management system and method based on Beidou navigation.
Disclosure of Invention
The invention provides a vehicle command management system based on Beidou navigation, which aims to strengthen the integration of Beidou products and services with various equipment and application systems through the combination application of Beidou space-time information, internet of things and big data, and realize real-time, visual and customized management of personnel, vehicles and the like, realize dynamic scheduling of human resources, integrated command and the like, and improve response speed and execution efficiency.
The application provides a Beidou navigation-based vehicle command management system which is connected with a vehicle intelligent management platform and comprises the following components.
High accuracy location and thing networking basic module realizes the high accuracy location of meter level to sub-meter level based on the big dipper positioning terminal of vehicle installation, uploads data such as vehicle position, speed, state in real time through thing networking technology, provides real-time manpower resources control, management and visual show based on GIS.
The intelligent prediction and early warning system module extracts key features based on collected historical early warning information data, traffic flow data and meteorological data, and utilizes a long-short-term memory neural network to establish a prediction model to predict the early warning occurrence probability or traffic jam index ,ht=tanh(Whxxt+Whhht-1+bh),yt=Wyhht+by,, wherein h t is a hidden state, x t is input data, namely the extracted key features, y t is a predicted value, W hx,Whh,Wyh is a weight matrix, b h,by is a bias item, and tanh is an activation function to automatically identify potential traffic jam areas and accident high-occurrence areas, and early warning and manpower standby scheduling are generated in advance.
And the self-adaptive scheduling and resource optimizing module is used for analyzing traffic conditions, manpower distribution, staff states and early warning emergency degree in real time, dynamically adjusting scheduling strategies and adopting an optimizing algorithm to ensure resource allocation optimization.
On the basis of the technical scheme, the vehicle command management system based on Beidou navigation further comprises.
The collaboration operation and cross-regional collaboration module is internally provided with a multi-police-type multi-department collaboration mechanism, and human resources of different regions and different departments are automatically coordinated according to early warning information requirements, so that cross-regional command and dispatch are supported, and rapid response and collaboration operation in an emergency are ensured.
And the path planning and avoiding system module is used for combining real-time traffic data and road condition information, providing accurate road condition information, carrying out path planning, dynamically adjusting a route, providing real-time navigation, prompting road condition change and an optimal driving route and ensuring quick and safe arrival at the site.
And the mobile terminal interaction and real-time feedback module is based on the equipped intelligent mobile terminal, so that bidirectional instant communication is realized, and the intelligent mobile terminal is internally provided with special application for first-line staff.
Preferably, the high-precision positioning and internet of things basic module comprises a Beidou positioning unit, a real-time uploading unit and a GIS integrated unit, wherein the Beidou positioning unit utilizes Beidou high-precision positioning terminals installed on each vehicle to achieve the positioning precision of meter level and even sub-meter level, the dynamic position and the driving state of each vehicle are reflected in real time, the real-time uploading unit adopts the internet of things technology, the real-time position data, the speed data and other state information of the vehicles are uploaded to a vehicle intelligent management platform of the cloud through an encryption channel, and the GIS integrated unit displays the real-time position of the vehicles according to the received real-time data, so that the real-time monitoring of the vehicles is realized, and the driving path of the vehicles is dynamically tracked and replayed.
Preferably, the intelligent prediction and early warning system module comprises a data collection and storage unit, a prediction model construction unit and an early warning trigger unit, wherein the data collection and storage unit collects historical early warning information records, real-time traffic flow data, weather forecast information, holidays, special event schedules and other multi-element data, processes the data to construct a big data warehouse, classifies and stores various original data and processed data, the prediction model construction unit extracts key features from the data to construct a training data set and a testing data set, uses a long-short-term memory neural network to construct a prediction model, carries out rolling prediction on each time point in the future, outputs predicted early warning occurrence probability, traffic jam index and the like, and the early warning trigger unit identifies potential traffic jam areas, accident high-occurrence areas and the like according to prediction results, generates early warning information in advance, sets an early warning threshold according to historical early warning severity and response requirements, and triggers early warning if the model prediction value exceeds a preset threshold.
Preferably, the self-adaptive scheduling and resource optimizing module processes and analyzes the collected data in real time by analyzing multisource data such as traffic conditions, manpower distribution, staff states, early warning emergency degree and the like, extracts key features for decision support, dynamically adjusts a scheduling strategy based on predefined rules and real-time data, preferentially assigns manpower closest to an accident site, considers the fatigue degree of staff and the vehicle fuel level, avoids overuse of a certain staff or vehicle, carries out global optimization by utilizing a genetic algorithm, generates an initial solution group (scheduling scheme), selects an excellent solution according to a fitness function, generates a new solution by cross operation, mutates the new solution, increases the diversity of the solution, and repeatedly selects, crosses and mutates until a preset convergence condition is reached so as to ensure resource allocation optimization.
Preferably, the cooperation operation and cross-regional cooperation module collects real-time early warning information and manpower resource data of each region, acquires cross-regional geographical boundary data and traffic flow data, ensures the feasibility of cross-regional scheduling, considers factors such as the states, positions and equipment of workers, calculates the matching degree of resources and events, establishes cooperation mechanisms among the regions, coordinates the manpower resources of different regions, uses optimization algorithms such as genetic algorithm and the like, synthesizes the matching degree and the cooperation degree, searches for the optimal manpower resources and cooperation scheduling scheme, converts the optimized scheduling scheme into specific task instructions, distributes the specific manpower resources, sends the task instructions in real time through the intelligent mobile terminal, receives feedback, ensures the execution and adjustment of the instructions, and automatically coordinates the manpower resources of different regions and departments to realize cross-regional command scheduling.
Preferably, the path planning and avoidance system module combines real-time traffic data and road condition information to provide accurate path planning and navigation service for vehicles, obtains position information of each vehicle, integrates urban traffic monitoring system, floating vehicle data, predicted traffic flow data and the like to form a real-time traffic condition map, receives early warning information, utilizes static information provided by a GIS system, calculates real-time weight of a road according to the data, aims at minimizing running time and running cost, ensures that the vehicle reaches a destination at the highest speed, simultaneously runs a plurality of path selection algorithms, each algorithm calculates one or more paths according to input data, fuses the results of the path selection algorithms according to the weight, calculates a comprehensive score, selects the path with the highest comprehensive score as a final path, dynamically adjusts the path planning according to real-time data change, periodically recalculates the path, and ensures the real-time property and accuracy of path selection.
Preferably, the bidirectional instant messaging in the mobile terminal interaction and real-time feedback module is as follows: based on the equipped intelligent mobile terminal, the scheduling instruction is received in real time, and the site situation is uploaded.
The application also provides a vehicle command management method based on Beidou navigation, which comprises the following steps of.
S1, a Beidou high-precision positioning terminal installed on a vehicle collects information such as vehicle position and speed in real time, and uploads data to a vehicle intelligent management platform of a command center through an internet of things (IoT) technology.
S2, the uploaded data are stored and processed in a vehicle intelligent management platform, and based on a Geographic Information System (GIS), the positions of the vehicles and the distribution conditions of manpower are displayed in real time, so that visual management of human resources is realized.
And S3, analyzing and predicting potential traffic jam areas and accident high-rise areas by using a deep learning algorithm through integrated historical early warning information data, real-time traffic flow and meteorological data, generating early warning information in advance, and scheduling human resources in advance according to a prediction result.
And S4, when the early warning occurs, determining whether the event is a common event or an event requiring cooperative operation and cross-region cooperation, and when the event is the common event, dynamically adjusting a manpower scheduling strategy by the self-adaptive scheduling and resource optimizing module, preferentially distributing the manpower resources with close distance and good state, and ensuring that the early warning is responded and processed in time.
S5, when the event is an event requiring cooperative operation and cross-regional cooperation, collecting real-time early warning information and human resource data of each region, acquiring cross-regional geographic boundary data and traffic flow data, considering factors including the states, positions and equipment of workers, calculating the matching degree of resources and the event, establishing a cooperation mechanism between regions, coordinating human resources of different regions, using a genetic algorithm to synthesize the matching degree and the cooperation degree, searching an optimal human resource and cooperation scheduling scheme, realizing cooperative operation and cross-regional cooperation between multiple police and multiple departments, ensuring quick response and efficient cooperation in the emergency event, and improving the treatment efficiency.
S6, combining the real-time traffic data and road condition information, acquiring the position information of each vehicle, integrating an urban traffic monitoring system, floating car data and predicted traffic flow data, forming a real-time traffic condition map, receiving early warning information, utilizing static information provided by a GIS system, calculating real-time weight of a road according to the data, enabling an objective function to minimize running time and running cost, simultaneously running a plurality of path selection algorithms, each algorithm calculates one or more paths according to input data, fusing the results of the path selection algorithms according to algorithm weight, calculating a comprehensive score, selecting the path with the highest comprehensive score as a final path, providing accurate path planning and navigation service for the vehicle, and ensuring that the vehicle arrives at the site quickly.
And S7, realizing bidirectional instant communication between the staff and the command center through the intelligent mobile terminal, wherein the staff can receive the scheduling instruction and upload the site situation in real time, and determining the event type again to determine whether to need to be amplified or interrupt excessive resource investment in time.
The vehicle command management system and method based on Beidou navigation have the following advantages.
The system fully utilizes the high-precision positioning capability of the Beidou navigation technology to ensure accurate grasp of the vehicle position, and can collect and upload the vehicle information in real time through the Internet of things technology, so that a command center can know the distribution condition of people at any time, intelligent prediction of potential traffic problems is realized by integrating historical early warning information data, real-time traffic flow and meteorological data and applying a deep learning algorithm, powerful support is provided for pre-dispatching of the people, the prospective and initiative of the system are improved, the use efficiency of the people can be greatly improved by adopting a self-adaptive dispatching mode, the waste of resources is reduced, and the collaborative work and cross-regional collaboration among multiple police and multiple departments are realized. In an emergency event, by automatically coordinating human resources of different areas and departments, quick response and efficient coordination can be ensured, treatment efficiency is improved, a path planning and avoiding function is provided, accurate path planning and navigation service is provided for vehicles, and the running efficiency of the vehicles is improved when the vehicles arrive on site quickly.
The Beidou navigation-based vehicle command management system provided by the invention combines the Beidou navigation technology, the Internet of things technology and the big data technology to realize the functions of accurate positioning, intelligent prediction, self-adaptive scheduling, path planning, collaborative operation and the like of the vehicle, improves the allocation efficiency and response speed of human resources, and provides powerful support for urban management and public safety.
Drawings
Fig. 1 is a diagram of a vehicle command management system based on Beidou navigation.
Fig. 2 is a basic module structure diagram of a high-precision positioning and internet of things in the Beidou navigation-based vehicle command management system.
Fig. 3 is a block diagram of an intelligent prediction and early warning system module in the Beidou navigation-based vehicle command management system.
Fig. 4 is a flow chart of a vehicle command management method based on Beidou navigation.
Fig. 5 is a schematic diagram showing vehicle distribution data information provided by a GIS integrated unit based on a vehicle intelligent management platform according to the present application.
Fig. 6 is a schematic diagram showing information of vehicle tracking data provided by a GIS integrated unit based on a vehicle intelligent management platform according to the present application.
Fig. 7 is a schematic diagram showing vehicle history track data information provided by a GIS integrated unit based on a vehicle intelligent management platform according to the present application.
Fig. 8 is a schematic diagram of command scheduling of the adaptive scheduling and resource optimizing module in the Beidou navigation-based vehicle command management system.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
Referring to fig. 1, a structure diagram of a vehicle command management system based on beidou navigation provided by the application is shown, and the vehicle command management system based on beidou navigation provided by an embodiment of the application is connected with a vehicle intelligent management platform and comprises.
And the high-precision positioning and internet of things basic module is used for installing Beidou positioning terminals on each vehicle, realizing the high-precision positioning from the meter level to the sub-meter level, uploading data such as the position, the speed and the state of the vehicle in real time through the internet of things technology, and providing real-time human resource monitoring, management and visual display functions based on a Geographic Information System (GIS).
And the intelligent prediction and early warning system module is used for collecting historical early warning information data, traffic flow data, meteorological data and the like, storing the historical early warning information data, the traffic flow data, the meteorological data and the like in a data warehouse, establishing a prediction model by utilizing deep learning analysis data, automatically identifying potential traffic jam areas and accident high-occurrence areas, generating early warning in advance and scheduling manpower standby.
And the self-adaptive scheduling and resource optimizing module is used for analyzing traffic conditions, manpower distribution, staff states and early warning emergency degrees in real time, dynamically adjusting scheduling strategies, preferentially assigning manpower with close distance and good state, and adopting an optimizing algorithm to ensure resource allocation optimization.
The collaboration operation and cross-regional collaboration module is internally provided with a multi-police-type multi-department collaboration mechanism, and human resources of different regions and different departments are automatically coordinated according to early warning requirements, so that cross-regional command and dispatch are supported, and rapid response and collaboration operation in an emergency are ensured.
And the path planning and avoiding system module is used for providing accurate road condition information, carrying out path planning, dynamically adjusting a route, providing real-time navigation, prompting road condition change and an optimal driving route and ensuring quick and safe arrival at the site by combining the real-time traffic data and the road condition information.
The mobile terminal interaction and real-time feedback module is provided with a smart phone or a tablet personal computer, and is internally provided with a special application for a first-line staff to realize bidirectional instant messaging, so that the staff can receive the scheduling instruction in real time and upload the site situation in real time, such as pictures, videos, and data of electronic reports reflecting the site situation.
Referring to fig. 2, a structure diagram of a high-precision positioning and internet of things basic module in a vehicle command management system based on Beidou navigation according to an embodiment of the present application is shown, the high-precision positioning and internet of things basic module includes a Beidou positioning unit, a real-time uploading unit and a GIS integrated unit, the Beidou positioning unit includes a Beidou high-precision positioning terminal installed on each vehicle, the vehicles include cars and motorcycles, etc., a Beidou satellite navigation chip is built in the terminals, signals from the Beidou satellite system can be received, accurate position calculation is performed, the Beidou system is used as a global satellite navigation system autonomously researched and developed in China, the provided services not only cover the world, but also have particularly outstanding positioning precision in China and surrounding areas, can achieve the positioning precision of meter level or even sub meter level, the positioning terminal continuously receives satellite signals, and after processing through complex algorithms, information such as precise position, speed, etc. of the vehicles is calculated, and dynamic position and running state of each vehicle are reflected in real time.
The real-time uploading unit adopts the internet of things technology, particularly an internet of things card and a 4G/5G mobile communication network, uploads real-time position data, speed data and other state information of the vehicle to a vehicle intelligent management platform of a cloud through an encryption channel, and the internet of things card is a data transmission card specially designed for internet of things equipment, so that the safety and stability of data transmission can be ensured.
The GIS integrated unit displays the real-time position of the vehicle according to the received real-time data, so that the real-time monitoring of the vehicle is realized, the distribution, tracking and track of the vehicle are respectively shown in fig. 5 to 7, the real-time human resource monitoring, management and visualization information provided by the GIS integrated unit is displayed through the vehicle intelligent management platform, for example, the current positions of all vehicles are checked by utilizing the vehicle distribution function on the vehicle intelligent management platform, the specific vehicle is dynamically tracked by utilizing the vehicle tracking function, and the history track function can play back the vehicle driving path to help analyze the human deployment and action mode.
Referring to fig. 3, a block diagram of an intelligent prediction and early warning system module in a vehicle command management system based on beidou navigation according to an embodiment of the present application is shown, where the intelligent prediction and early warning system module includes a data collection and storage unit, a prediction model construction unit and an early warning trigger unit, where the data collection and storage unit is used for collecting historical early warning information records, traffic flow data, weather forecast information, holidays, special event schedules and other multivariate data, the historical early warning information records include time, place, type, processing time and other information of events such as traffic accidents, violations, congestion and the like occurring in the past, the traffic flow data includes real-time and historical traffic flow information, vehicle speed, vehicle flow density and the like, the weather data includes historical and real-time weather condition data including temperature, rainfall, visibility and the like, and other relevant data such as holidays, important activity information and the like. And processing the collected multi-element data, including cleaning the data, removing abnormal values and missing values, performing standardized processing on the data, ensuring the comparability of the data from different sources, constructing a large data warehouse, and storing various original data and processed data in a classified manner.
The prediction model construction unit extracts key features from the original data and the processed data, such as time (hours, weeks, seasons), place (longitude and latitude, road type), traffic flow, early warning high-rise period, weather condition and the like, constructs a training dataset and a test dataset according to historical data, predicts ,ht=tanh(Whxxt+Whhht-1+bh),yt=Wyhht+by, by using a long-short-period memory neural network, wherein h t is a hidden state, y t is a predicted value, x t is input data, such as the key features extracted from time, place and the like, W hx,Whh,Wyh is a weight matrix, b h,by is a bias term, tanh is an activation function, a historical data training model is used, a loss function uses mean square error, MSE=1/n sigma i=1 n(yi−y^i)2,yi is a true value, y i is a predicted value, n is a sample number, and the performance of the model is evaluated by cross-validation and other technologies, super-parameters are adjusted, rolling prediction is performed on each time point (such as a day and a week) in the future after model training is completed, and early warning occurrence probability or traffic jam index of prediction is output.
The early warning triggering unit identifies potential traffic congestion areas and accident high-occurrence areas according to the prediction results, early warning information is generated in advance, an early warning threshold is set according to historical early warning severity and response requirements, if the model prediction value exceeds the preset threshold, early warning is triggered, if a certain area is predicted to reach a peak of the traffic congestion in one hour in the future, or the accident occurrence probability is obviously increased, the early warning information is automatically pushed to a command center and related staff, an emergency plan is started, manpower is deployed to the potential high-risk areas in advance, or a vehicle patrol route is adjusted.
As an alternative scheme of the application, referring to fig. 8, the adaptive scheduling and resource optimizing module dynamically adjusts the scheduling policy by analyzing the multi-source data such as traffic conditions, manpower distribution, staff status, early warning emergency degree, etc. in real time, so as to optimize the resource allocation and ensure the efficient utilization of manpower. The collected traffic condition data comprise real-time traffic flow, congestion conditions, accident information and the like, the manpower distribution data comprise current vehicle positions, quantity, distribution conditions and the like, the staff status data comprise fatigue degree, duty time, vehicle fuel level and the like of staff, and the early warning emergency degree data comprise the type, emergency degree, processing time limit and the like of current early warning information.
The collected data are processed and analyzed in real time, key features are extracted for decision support, a scheduling strategy is dynamically adjusted based on predefined rules and real-time data, human resources closest to the place of occurrence are preferentially assigned, fatigue of workers and vehicle fuel level are considered, excessive use of a certain worker or vehicle is avoided, scheduling priority is determined according to early warning emergency, an objective function of the scheduling strategy is defined to realize optimization of resource allocation, min Σ i=1 n(wresponseTi+wfatigueFi+wfuelDi), response time T i, Calculating time required for human power to reach an event site from a current position in each scheduling scheme, calculating the fatigue degree F i of the working personnel based on real-time traffic data and a path planning algorithm, evaluating the fatigue state of the working personnel in each scheduling scheme, comprehensively evaluating the fuel consumption D i through factors such as working time length, latest rest time and the like, evaluating the fuel consumption of vehicles in each scheduling scheme, based on the distance traveled by the vehicle and the fuel efficiency calculations of the vehicle, w response、wfatigue and w fuel are weight parameters used to adjust the relative importance of response time, operator fatigue, and fuel consumption in the overall cost, these weight parameters being adjusted according to the specific application scenario and strategy to reflect the priority of the different costs. Constraints include response time constraints, ensuring that human resources arrive at the site in the shortest time, T i≤Tmax,Ti is the response time of the ith human resource, and T max is the maximum allowable response time; the state constraint of the workers avoids the problem that the workers with high dispatching fatigue degree are tired, F j≤Fmax,Fj is the fatigue degree of the jth worker, and F max is the maximum allowed fatigue degree; The fuel level constraints ensure that the vehicle fuel level is sufficient, L k≥Lmin,Lk is the fuel level of the kth vehicle, and L min is the lowest fuel level. And performing global optimization by using a genetic algorithm to generate an initial solution group, namely, a scheduling scheme, selecting excellent solutions according to a fitness function, generating new solutions through crossover operation, mutating the new solutions, increasing the diversity of the solutions, and repeating selection, crossover and mutation until a preset convergence condition is reached.
As an alternative scheme of the application, the collaborative operation and cross-regional collaboration module enables collaborative operation and cross-regional collaboration among multiple police and multiple departments, in an emergency, by automatically coordinating human resources of different areas and different departments, quick response and efficient coordination can be ensured, treatment efficiency is improved, real-time early warning information including event type, position, emergency degree and the like is collected from early warning information systems of all areas, human resource data of all areas including information of positions, states, equipment and the like of workers are collected, geographical boundary data and traffic flow data of the cross-regional are obtained, feasibility of cross-regional scheduling is ensured, and the states of the workers are considered, Position, equipment and other factors, calculate the matching degree ,Match(Rj,Ei)=γProximity(Rj,Ei)+δReadiness(Rj)+ηEquipment(Rj), of the resource and the event, wherein, match (R j,Ei) is the matching degree of the resource R j and the event E i, proximity (R j,Ei) is the distance of the resource from the event, readiness (R j) is the Readiness of the resource, equipment (R j) is the Equipment status of the resource, γ, δ and η are weight coefficients, Establishing a Collaboration mechanism between the areas, coordinating human resources ,Collaboration(Ak,Al)=λResourceAvailability(Ak,Al)+μResponseTime(Ak,Al)+νCoordinationEfficiency(Ak,Al), of different areas, wherein the relationship (A k,Al) is the Collaboration degree between the area A k and the area A l, ResourceAvailability (a k,Al) is availability of inter-area resources, responseTime (a k,Al) is response time, coordinationEfficiency (a k,Al) is collaboration efficiency, λ, μ, and ν are weight coefficients, an optimization algorithm such as a genetic algorithm is used to synthesize the matching degree and the cooperation degree, find the optimal human resources and cooperation schemes, fitness (S) = Σ i=1 n(Match(Ri,Ei)+Collaboration(Ai1,Ai2)), where Fitness (S) represents the adaptation degree of scheme S, match (R i,Ei) is the matching degree of the ith event and the resources, colleration (a i1,Ai2) is the cooperation degree between the ith event-related areas, Generating an initial scheme set, wherein each scheme represents one-time manual scheduling, calculating the fitness of each scheme according to the matching degree and the cooperation degree, selecting a scheme with high fitness to perform the next operation, performing cross operation on the selected scheme, generating a new scheme, performing mutation operation on part of schemes, increasing diversity, repeating the steps until an optimal or near-optimal scheme is found, converting the optimized scheduling scheme into a specific task instruction, distributing the specific task instruction to corresponding human resources, transmitting the task instruction in real time through an intelligent mobile terminal, receiving feedback, and ensuring the execution and adjustment of the instruction.
As an alternative scheme of the application, the path planning and avoidance system module combines real-time traffic data and road condition information to provide accurate path planning and navigation service for vehicles, and can ensure that the vehicles arrive at the scene quickly by avoiding congestion and accident road sections, thereby improving the disposal efficiency. The method comprises the steps of updating the position information of each vehicle to sub-meter precision in real time through a Beidou high-precision positioning terminal, integrating an urban traffic monitoring system, floating vehicle data, predicted traffic flow data and the like to form a real-time traffic condition map, receiving early warning information including early warning occurrence positions and emergency degree assessment, calculating real-time weight z (e) of each road e according to the data by utilizing early warning information such as road network, speed limit, one-way road and the like provided by a GIS system, minimizing running time and running cost by an objective function, ensuring that the vehicle reaches a destination at the fastest speed, taking Min sigma i=1 n(ti+ci),ti as the running time of an i-th road, c i, i-th section, running multiple path selection algorithms simultaneously, each algorithm calculating one or more paths according to input data, such as calculating shortest path distance of each node by Dijkstra algorithm, d [ v ] = min (dist [ u ], dist [ v ] +w (u, v)), dist (u) being shortest distance from source point to vertex u, w (u, v) being weight (running time and running cost) of edge u to v, the algorithm A is based on a heuristic search shortest path algorithm, and combines the current path cost and the estimated cost of reaching the end point to quickly find an optimal path, f (v) =g (v) +h (v), wherein f (v) is the total estimated cost of the vertex v, g (v) is the actual cost from the start point to v, h (v) is the heuristic estimated cost from v to the end point, the ant colony algorithm simulates an optimization algorithm of ant foraging behavior, searches for the optimal path through a positive feedback mechanism of pheromones, τ ij(t+1)=(1-ρ)τij(t)+Δτij, wherein τ ij (t) is the concentration of pheromones on the paths (i, j), ρ is the pheromone volatility coefficient, Δτ ij is the pheromone increment, the results of each algorithm are fused according to the algorithm weight, a composite Score is calculated, score (P) = Σ k=1 mαkPathk (P), where Score (P) is the composite Score of path P, a k is the weight of the kth algorithm, Path k (P) is the Path score of the kth algorithm, the Path with the highest comprehensive score is selected as the final Path, the Path planning is dynamically adjusted according to the real-time data change, the paths are regularly recalculated, and the instantaneity and the accuracy of Path selection are ensured.
The method includes the steps of calculating real-time weight z (e) of each road e according to real-time traffic data, road condition information, early warning information, static information provided by a GIS (geographic information system) and the like, taking running time and running cost as objective functions, adopting a plurality of path selection algorithms to calculate one or more paths respectively, for example, using Dijkstra algorithm to calculate the shortest path distance of each node, A-algorithm is based on heuristic search shortest path algorithm, combining current path cost and estimated arrival end cost, quickly finding out an optimal path, ant colony algorithm simulates optimization algorithm of ant foraging behavior, searching an optimal path through a positive feedback mechanism of a pheromone, calculating the sum of real-time weights of road combinations under each road e based on the real-time weight z (e), calculating the path Score of sum sigma z i (e) of each path through mapping calculation, obtaining the path Score of each path through mapping calculation, obtaining the corresponding optimal path according to different path selection algorithms, searching the optimal path according to different path selection algorithms, finding out the optimal path Score under the combination of the optimal Score of the optimal path calculation algorithms, and comprehensively calculating the optimal Score under the highest Score of the optimal Score according to the algorithm, and finally carrying out the algorithm under the combination of the best Score as the best Score (Score) under the best Score, and finally carrying out the algorithm.
As an alternative scheme of the application, the mobile terminal interaction and real-time feedback module provides a convenient communication means for a first-line staff, and the staff can receive the dispatching instruction of the command center in real time by being provided with the smart phone or the tablet personal computer and upload the field situation, and the two-way instant communication way greatly improves the communication efficiency and the response speed, so that the command center can know the field situation in time and make a correct decision.
In one embodiment of the application, the Beidou high-precision positioning terminal is installed on 52 vehicles of a certain fleet of Guiyang, so that real-time, visual and customized management of the vehicles is realized, dynamic scheduling, integrated command and the like of human resources of the fleet are realized, and the response speed and the execution efficiency are improved.
Referring to fig. 4, a flowchart of a vehicle command management method based on Beidou navigation according to an embodiment of the present application is shown, and the vehicle command management method based on Beidou navigation includes the following steps.
S1, a Beidou high-precision positioning terminal installed on a vehicle collects information such as the position and the speed of the vehicle in real time, and uploads data to an intelligent management platform of a command center through the Internet of things technology.
And S2, after receiving the data, carrying out real-time processing and displaying on the vehicle position by utilizing a Geographic Information System (GIS), realizing visual monitoring of human resources, and developing functions such as vehicle distribution, real-time tracking, historical track playback and the like according to the vehicle state and the position data.
And S3, analyzing and predicting potential traffic jam areas and accident high-rise areas by using a deep learning algorithm through integrated historical early warning information data, real-time traffic flow and meteorological data, generating early warning information in advance, and scheduling human resources in advance according to a prediction result.
And S4, when the early warning occurs, determining whether the event is a common event or an event requiring cooperative operation and cross-region cooperation, and when the event is the common event, dynamically adjusting a manpower scheduling strategy by the self-adaptive scheduling and resource optimizing module, preferentially distributing the manpower resources with close distance and good state, and ensuring that the early warning is responded and processed in time.
S5, when the event is an event requiring cooperative work and cross-regional cooperation, under the support of the cooperative work and cross-regional cooperation module, the cooperative work and cross-regional cooperation among multiple police and multiple departments are realized, the quick response and high-efficiency cooperation in the emergency event are ensured, and the disposal efficiency is improved.
And S6, providing accurate path planning and navigation service for the vehicle by utilizing a path planning and avoidance system module and combining real-time traffic data and road condition information, and ensuring that the vehicle arrives at the scene quickly.
And S7, through the mobile terminal interaction and real-time feedback module, the bidirectional instant communication between the staff and the command center is realized, the staff can receive the scheduling instruction and upload the site situation in real time, the event type is determined again, and whether the need of the rescue is determined or the excessive resource investment is interrupted in time is determined.
Claims (7)
1. A vehicle command management system based on big dipper navigation links to each other with vehicle wisdom management platform, its characterized in that, the system includes:
The high-precision positioning and internet of things basic module is used for realizing high-precision positioning based on a Beidou positioning terminal installed on a vehicle, uploading vehicle data in real time through the internet of things technology and providing real-time human resource monitoring, management and visual display based on GIS;
The intelligent prediction and early warning system module is used for extracting key features based on collected historical early warning information data, traffic flow data and meteorological data, and utilizing a long-short-period memory neural network to establish a prediction model to predict early warning occurrence probability or traffic jam index ,ht＝tanh(Whxxt+Whhht-1+bh),yt＝Wyhht+by,, wherein h t is a hidden state, x t is input data, namely the extracted key features, y t is a predicted value, W hx,Whh,Wyh is a weight matrix, b h,by is a bias item, and tanh is an activation function to automatically identify potential traffic jam areas and accident high-occurrence areas, and early warning is generated in advance and manpower standby is scheduled;
The self-adaptive scheduling and resource optimizing module analyzes traffic conditions, manpower distribution, staff states and early warning emergency degree in real time, dynamically adjusts scheduling strategies, and ensures resource allocation optimization by adopting an optimizing algorithm;
the collaborative operation and cross-regional collaboration module is internally provided with a multi-department collaboration mechanism, and human resources of different regions and different departments are automatically coordinated according to the early warning information requirement, so that cross-regional command scheduling is supported, and rapid response and collaborative operation in an emergency are ensured;
The path planning and avoiding system module is used for providing accurate road condition information by combining real-time traffic data and road condition information, carrying out path planning, dynamically adjusting a route and providing real-time navigation;
the self-adaptive scheduling and resource optimizing module:
Extracting key features for decision support by analyzing multisource data including traffic conditions, manpower distribution, staff states and early warning emergency degree in real time, and dynamically adjusting a scheduling strategy based on predefined rules and real-time data;
Performing global optimization by utilizing a genetic algorithm to generate an initial solution group, selecting excellent solutions according to a fitness function, generating new solutions through crossover operation, mutating the new solutions, increasing the diversity of the solutions, and repeating selection, crossover and mutation until a preset convergence condition is reached so as to ensure resource allocation optimization;
The objective function of the scheduling policy is defined as:
Wherein n is the number of scheduling schemes;
The response time T i is used for calculating the time required for the manpower in each scheduling scheme to reach the event site from the current position based on the real-time traffic data and the path planning algorithm;
The fatigue degree F i of the staff is comprehensively estimated by the working time length and the latest rest time factors;
fuel consumption D i for estimating the fuel consumption of the vehicle in each scheduling on the basis of the distance travelled by the vehicle and the fuel efficiency of the vehicle;
w response、wfatigue and w fuel are weight parameters used for adjusting the relative importance of response time, fatigue of staff and fuel consumption in the total cost, and the weight parameters are adjusted according to specific application scenes and strategies so as to reflect the priorities of different costs;
Constraints include response time constraints, ensuring that human resources arrive at the site in the shortest time, T i≤Tmax,Ti is the response time of the ith human resource, and T max is the maximum allowable response time; staff status constraints: the method comprises the steps that workers with high dispatching fatigue degree are avoided, F j≤Fmax,Fj is the fatigue degree of the jth worker, and F max is the maximum allowed fatigue degree; fuel level constraints, ensuring that the vehicle fuel level is sufficient, L k≥Lmin,Lk is the fuel level of the kth vehicle, and L min is the lowest fuel level;
The collaborative operation and cross-region collaboration module is used for:
collecting real-time early warning information and human resource data of each area, and acquiring geographical boundary data and traffic flow data of the cross-area, so as to ensure the feasibility of cross-area scheduling;
Considering factors including the states, positions and equipment of the staff, calculating the matching degree of resources and events, establishing a collaboration mechanism between areas, and coordinating human resources of different areas;
synthesizing the matching degree and the cooperation degree by using a genetic algorithm, and searching an optimal human resource and a cooperation scheduling scheme;
Converting the optimized scheduling scheme into a specific task instruction, and distributing the specific task instruction to corresponding human resources to automatically coordinate the human resources of different areas and departments, thereby realizing transregional command scheduling;
The consideration includes factors of the states, positions and equipment of the staff, and the matching degree of the resources and the events is calculated, specifically:
Match(Rj,Ei)＝γProximity(Rj,Ei)+δReadiness(Rj)+ηEquipment(Rj), Wherein,
Match (R j,Ei) is the matching degree of resource R j to event E i, proximity (R j,Ei) is the distance of resource to event, readiness (R j) is the Readiness of resource, equipment (R j) is the Equipment condition of resource, and γ, δ and η are weight coefficients;
the cooperation mechanism among the areas is established, and human resources of different areas are coordinated, specifically:
Collaboration(Ak,Al)＝λResourceAvailability(Ak,Al)+μResponseTime(Ak,
A l)+νCoordinationEfficiency(Ak,Al), wherein the relationship (a k,Al) is the degree of Collaboration of the region a k with the region a l, resourceAvailability (a k,Al) is the availability of inter-region resources, res ponseTime (a k,Al) is the response time, coordinationEfficiency (a k,Al) is the Collaboration efficiency, and λ, μ, and ν are weight coefficients;
The genetic algorithm is used for integrating the matching degree and the cooperation degree, and the optimal human resource and cooperation scheduling scheme is found, specifically:
fitness (S) represents the adaptability of the scheme S, n is the number of events to be processed, match (R i,Ei) is the matching degree of the ith event and resources, and collarbonation (A i1,Ai2) is the Collaboration degree between the ith event and the related areas;
When an early warning occurs, judging the event type, and when the event is a common event, dynamically adjusting a human scheduling strategy to preferentially allocate human resources with close distance and good state;
When the event is an event requiring collaborative operation and cross-regional collaboration, collecting real-time early warning information and human resource data of each region, acquiring cross-regional geographic boundary data and traffic flow data, considering factors including the states, positions and equipment of workers, calculating the matching degree of resources and the event, establishing a collaboration mechanism between regions, coordinating human resources of different regions, synthesizing the matching degree and the collaboration degree by using a genetic algorithm, searching an optimal human resource and a scheduling scheme of collaboration, and realizing collaborative operation and cross-regional collaboration among multiple departments;
the path planning and avoidance system module:
combining the real-time traffic data and road condition information, providing accurate path planning and navigation service for the vehicle;
Acquiring position information of each vehicle, integrating an urban traffic monitoring system, floating vehicle data and predicted traffic flow data to form a real-time traffic condition map, receiving early warning information and utilizing static information provided by a GIS system;
Calculating real-time weight of a road, wherein an objective function is to minimize running time and running cost, and ensuring that a vehicle reaches a destination at the fastest speed;
Simultaneously running a plurality of path selection algorithms, each algorithm calculates one or more paths according to input data, fuses the results of the path selection algorithms according to weights, calculates a comprehensive score, and selects a path with the highest comprehensive score as a final path;
and dynamically adjusting path planning according to real-time data change, and periodically recalculating the path.
2. The Beidou navigation based vehicle command management system of claim 1, wherein the system further comprises:
and the mobile terminal interaction and real-time feedback module is based on the equipped intelligent mobile terminal, so that bidirectional instant communication is realized, and the intelligent mobile terminal is internally provided with special application for first-line staff.
3. The Beidou navigation-based vehicle command management system of claim 1, wherein the high-precision positioning and internet of things base module comprises a Beidou positioning unit, a real-time uploading unit and a GIS integrated unit;
The Beidou positioning unit utilizes a Beidou high-precision positioning terminal installed on the vehicle to achieve the positioning precision of the meter level and even the sub-meter level, and reflects the dynamic position and the running state of the vehicle in real time;
the real-time uploading unit adopts the internet of things technology to upload real-time position data, speed data and other state information of the vehicle to a vehicle intelligent management platform of the cloud through an encryption channel;
And the GIS integrated unit displays the real-time position of the vehicle according to the received real-time data, so that the real-time monitoring of the vehicle is realized, and the vehicle driving path is dynamically tracked and replayed.
4. The Beidou navigation based vehicle command management system of claim 1, wherein the intelligent prediction and early warning system module comprises a data collection and storage unit, a prediction model construction unit and an early warning trigger unit;
The data collection and storage unit collects the multi-element data including history early warning information record, real-time traffic flow data, weather forecast information, holidays and special event schedule, processes the data and stores the data in a classified manner;
The prediction model construction unit extracts key features from the data, constructs a training data set and a test data set, constructs a prediction model by using a long-short-period memory neural network, performs rolling prediction on each time point in the future, and outputs predicted early warning occurrence probability or traffic jam index;
The early warning triggering unit identifies potential traffic jam areas and accident high-occurrence areas according to the prediction results, early warning information is generated in advance, an early warning threshold is set according to the historical early warning severity and response requirements, and if the model prediction value exceeds a preset threshold, early warning is triggered.
5. The Beidou navigation-based vehicle command management system of claim 2, wherein the bidirectional instant messaging in the mobile terminal interaction and real-time feedback module is as follows: based on the equipped intelligent mobile terminal, the scheduling instruction is received in real time, and the site situation is uploaded.
6. The vehicle command management method based on Beidou navigation is applied to the vehicle command management system based on Beidou navigation, and is characterized by comprising the following steps:
s1, acquiring vehicle information in real time based on a Beidou positioning terminal installed by a vehicle, and uploading data to a vehicle intelligent management platform through an Internet of things technology;
s2, the uploaded data are stored and processed, and the positions of the vehicles and the distribution conditions of manpower are displayed in real time based on a geographic information system, so that visual management of manpower resources is realized;
S3, analyzing and predicting potential traffic jam areas and accident high-rise areas by using a deep learning algorithm through integrated historical early warning information data, real-time traffic flow and meteorological data, generating early warning information in advance, and scheduling manpower in advance according to a prediction result;
s4, judging the event type when early warning occurs, and dynamically adjusting a manpower scheduling strategy when the event is a common event, and preferentially distributing the manpower resources which are close in distance and good in state;
S5, when the event is an event requiring collaborative operation and cross-regional collaboration, collecting real-time early warning information and human resource data of each region, acquiring cross-regional geographic boundary data and traffic flow data, considering factors including the states, positions and equipment of workers, calculating the matching degree of resources and the event, establishing a collaboration mechanism between regions, coordinating human resources of different regions, synthesizing the matching degree and the collaboration degree by using a genetic algorithm, searching an optimal human resource and a collaborative scheduling scheme, and realizing collaborative operation and cross-regional collaboration among multiple departments.
7. The Beidou navigation-based vehicle command management method of claim 6, further comprising:
S6, combining real-time traffic data and road condition information, acquiring position information of each vehicle, integrating an urban traffic monitoring system, floating car data and predicted traffic flow data, forming a real-time traffic condition map, receiving early warning information, utilizing static information provided by a GIS system, calculating real-time weight of a road according to the data, minimizing running time and running cost by an objective function, simultaneously running a plurality of path selection algorithms, each algorithm calculates one or more paths according to input data, fusing the results of the path selection algorithms according to algorithm weight, calculating a comprehensive score, and selecting the path with the highest comprehensive score as a final path;
And S7, realizing bidirectional instant communication between the staff and the command center through the intelligent mobile terminal, wherein the staff can receive the scheduling instruction and upload the site situation in real time, and determining the event type again to determine whether to need to be amplified or interrupt excessive resource investment in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410985243.9A CN118522154B (en) | 2024-07-23 | 2024-07-23 | Beidou navigation-based vehicle command management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410985243.9A CN118522154B (en) | 2024-07-23 | 2024-07-23 | Beidou navigation-based vehicle command management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118522154A CN118522154A (en) | 2024-08-20 |
| CN118522154B true CN118522154B (en) | 2024-10-11 |
Family
ID=92274551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410985243.9A Active CN118522154B (en) | 2024-07-23 | 2024-07-23 | Beidou navigation-based vehicle command management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118522154B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489042A (en) * | 2013-09-17 | 2014-01-01 | 中国科学院深圳先进技术研究院 | Method for optimizing disaster emergency decision system path |
| CN104408941A (en) * | 2014-11-11 | 2015-03-11 | 四川北斗导航应用技术有限公司 | System and method of vehicle management based on Beidou satellite navigation |
| CN112561341A (en) * | 2020-12-18 | 2021-03-26 | 创意信息技术股份有限公司 | Multi-element dynamic cooperative disposal system for urban disasters |
| CN113807595A (en) * | 2021-09-18 | 2021-12-17 | 武汉朗迈科技有限公司 | Emergency command scheduling method and system based on GIS and Beidou positioning |
| CN118262516A (en) * | 2024-03-16 | 2024-06-28 | 东莞理工学院 | Vehicle traffic prediction method and system based on multiple attention neural networks |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254082B (en) * | 2011-04-22 | 2013-09-18 | 中科怡海高新技术发展江苏股份公司 | Real-time intelligent vehicle and boat scheduling method |
| CN102737499B (en) * | 2012-05-17 | 2014-08-06 | 西安亿力通微波科技有限公司 | Expressway vehicle management and guidance command system and method based on mobile communication |
| CN102682595A (en) * | 2012-05-17 | 2012-09-19 | 西安亿力通微波科技有限公司 | System and method for guiding and commanding urban highway traffic jam based on mobile phone communication |
| US10037689B2 (en) * | 2015-03-24 | 2018-07-31 | Donald Warren Taylor | Apparatus and system to manage monitored vehicular flow rate |
| CN103308073B (en) * | 2013-05-30 | 2015-10-28 | 上海交通大学 | Strap down inertial navigation/combinations of satellites navigation detection system and emulation test method thereof |
| US10551851B2 (en) * | 2013-07-01 | 2020-02-04 | Steven Sounyoung Yu | Autonomous unmanned road vehicle for making deliveries |
| CN103680131B (en) * | 2013-12-11 | 2017-02-08 | 深圳市众鸿科技股份有限公司 | Vehicle monitoring system and method for monitoring vehicle thereof |
| CN111505680A (en) * | 2020-04-21 | 2020-08-07 | 中国人民解放军陆军勤务学院 | Logistics support vehicle monitoring and commanding system |
| CN116502818A (en) * | 2023-02-13 | 2023-07-28 | 深圳天域世界科技有限公司 | Dynamic GIS geographic information monitoring system for emergency command |
| CN117390583A (en) * | 2023-11-02 | 2024-01-12 | 贵州省林业调查规划院 | Forestry and homeland change vector data fusion system |
| CN117459900A (en) * | 2023-12-11 | 2024-01-26 | 福建天创信息科技有限公司 | Patrol police car integrated management system and method |
| CN117894421A (en) * | 2024-02-26 | 2024-04-16 | 浙江中医药大学附属第二医院(浙江省新华医院) | Medical service automation flow optimization method |
| CN118278577A (en) * | 2024-04-19 | 2024-07-02 | 云南沪滇应急装备制造有限公司 | Beidou intelligent emergency rescue command and dispatch system |
-
2024
- 2024-07-23 CN CN202410985243.9A patent/CN118522154B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489042A (en) * | 2013-09-17 | 2014-01-01 | 中国科学院深圳先进技术研究院 | Method for optimizing disaster emergency decision system path |
| CN104408941A (en) * | 2014-11-11 | 2015-03-11 | 四川北斗导航应用技术有限公司 | System and method of vehicle management based on Beidou satellite navigation |
| CN112561341A (en) * | 2020-12-18 | 2021-03-26 | 创意信息技术股份有限公司 | Multi-element dynamic cooperative disposal system for urban disasters |
| CN113807595A (en) * | 2021-09-18 | 2021-12-17 | 武汉朗迈科技有限公司 | Emergency command scheduling method and system based on GIS and Beidou positioning |
| CN118262516A (en) * | 2024-03-16 | 2024-06-28 | 东莞理工学院 | Vehicle traffic prediction method and system based on multiple attention neural networks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118522154A (en) | 2024-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10639995B2 (en) | Methods, circuits, devices, systems and associated computer executable code for driver decision support | |
| Miller-Hooks et al. | Least expected time paths in stochastic, time-varying transportation networks | |
| Maciejewski et al. | Large-scale microscopic simulation of taxi services | |
| US20160334235A1 (en) | Itpa informed traveler program and application | |
| Haghani et al. | Real-time emergency response fleet deployment: concepts, systems, simulation & case studies | |
| MXPA03000171A (en) | Method and system for providing traffic and related information. | |
| Zhang et al. | Battery maintenance of pedelec sharing system: Big data based usage prediction and replenishment scheduling | |
| WO2019003672A1 (en) | Transit demand forecasting device and transit demand forecasting method | |
| CN116046001A (en) | Rescue path planning method and system based on intelligent fire fighting | |
| Li et al. | Trajectory-driven planning of electric taxi charging stations based on cumulative prospect theory | |
| CN115527369A (en) | Large passenger flow early warning and evacuation method under large-area delay condition of airport hub | |
| CN115472011A (en) | Bus intelligent line planning algorithm based on reservation data | |
| CN118134172B (en) | Urban public resource management and allocation system | |
| CN116050581A (en) | Smart city subway driving scheduling optimization method and Internet of things system | |
| CN118095527B (en) | Rail transit operation and maintenance method, device, equipment and storage medium | |
| US20220327483A1 (en) | Processing route information | |
| Krislata et al. | Traffic Flows System Development for Smart City. | |
| CN118522154B (en) | Beidou navigation-based vehicle command management system and method | |
| EP3702980A1 (en) | Method for route plan optimization taking constraint and event into account | |
| Makanadar et al. | Urban Mobility: Leveraging AI, Machine Learning, and Data Analytics for Smart Transportation Planning-A case study on New York City | |
| Rahaman | Context-aware mobility analytics and trip planning | |
| Liu et al. | A Coverage-aware Task Allocation Method for UAV-assisted Mobile Crowd Sensing | |
| Casas et al. | Present and future methodology for the implementation of decision support systems for traffic management | |
| Quadrifoglio et al. | Multi-stage Models for Dynamic Ride-Sharing in Taxi Services and Congestion Analysis | |
| Yu et al. | Multi-cycle optimal taxi routing with e-hailing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |