An unmanned garage system and management method based on intelligent identification

Abstract

The present invention relates to the field of unmanned garages, and discloses an unmanned garage system and management method based on intelligent identification, comprising a perception module, a decision module, an execution module, a user experience module, and a management and optimization module. The perception module is used to monitor vehicles, pedestrians and environmental conditions in a garage in real time, including vehicle positions, vehicle models, driving speeds, and parking space occupancy conditions. The decision module is used to determine vehicle parking positions, path planning schemes, and parking space allocation strategies. The execution module is used to control vehicle navigation to a designated parking space. The user experience module is used to reserve parking spaces, query vehicle positions, and pay parking fees. The management and optimization module is responsible for the management of garage operation data and the optimization of system performance. The perception module comprises a vehicle identification module, a parking space monitoring module, and a pedestrian identification module. The present invention has more convenient and efficient parking services, and improves the operation efficiency and management characteristics of the garage.

Description

Technical Field

[0001] The present invention relates to the field of unmanned garages, and in particular to an unmanned garage system and management method based on intelligent identification. Background Art

[0002] With the rapid development of the national economy, more and more motor vehicles are entering cities, and the number of motor vehicles is growing rapidly. However, due to the lack of understanding of urban static traffic problems, the construction of parking lots and facilities in my country has grown slowly, and the number of parking facilities is far from meeting the parking needs. The resulting parking difficulties also plague people's daily lives. At the same time, the phenomenon of vehicles occupying roads, residential green spaces and other public spaces due to parking difficulties is becoming more and more serious, further aggravating urban traffic congestion, which in turn leads to increased environmental pollution. This phenomenon not only seriously damages the overall image of the city, but also has a bad impact on people's lives.

[0003] Therefore, it is necessary to design a convenient and efficient unmanned garage system and management method based on intelligent recognition. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides an unmanned garage system and management method based on intelligent identification, which has more convenient and efficient parking services, improves the operational efficiency and management of the garage, and solves the problems in the above-mentioned background technology.

[0006] (II) Technical solution

[0007] In order to achieve the above-mentioned more convenient and efficient parking service and improve the operation efficiency and management of the garage, the present invention provides the following technical solutions: an unmanned garage system and management method based on intelligent identification, including a perception module, a decision module, an execution module, a user experience module, a management and optimization module, the perception module is used to monitor the vehicles, pedestrians and environmental conditions in the garage in real time, including the vehicle position, vehicle model, driving speed, and the occupancy of parking spaces, the decision module is used to determine the vehicle parking position, path planning scheme and parking space allocation strategy, the execution module is used to control the vehicle to navigate to the designated parking space, the user experience module is used to reserve parking spaces, query vehicle positions, and pay parking fees, the management and optimization module is responsible for the management of garage operation data and the optimization of system performance, the perception module includes a vehicle identification module, a parking space monitoring module, and a pedestrian identification module, the vehicle identification module is used to identify vehicles entering the garage and obtain relevant information of the vehicle, the parking space monitoring module is used to detect the occupancy of parking spaces in the garage and determine whether parking spaces are available, and the pedestrian identification module is used to identify pedestrians in the garage to ensure pedestrian safety and provide personalized services.

[0008] According to the above technical solution, the decision module includes a parking space allocation module and an entry and exit control module. The parking space allocation module is used to allocate parking spaces to vehicles entering the garage and determine the parking space allocation strategy. The entry and exit control module is used to control the order and time of vehicles entering and exiting the garage to ensure the safety and order of vehicles entering and exiting.

[0009] According to the above technical solution, the execution module includes a path planning module and a trajectory generation module. The path planning module is responsible for calculating a path for the vehicle to follow based on the current vehicle position, the target parking space position and the environmental map information. The trajectory generation module is used to further generate the trajectory that the vehicle should travel on the basis of path planning. It is usually necessary to consider the dynamic characteristics of the vehicle and how to smoothly achieve turning and speed changes on the path. First, the dynamic characteristics of the vehicle need to be considered, including factors such as mass, inertia, and tire grip. Then, advanced control algorithms, such as model pre-control or PID controller, can be used to achieve precise and smooth turning and speed changes, and adjust the steering angle and acceleration to ensure that there will be no violent swaying or loss of control during turning and speed changes.

[0010] According to the above technical solution, the user experience module includes a mobile application module, a voice interaction module, and an augmented reality module. The mobile application module is used to allow users to use garage services anytime and anywhere. The voice interaction module is used to realize voice interaction between users and the system through voice recognition technology. The augmented reality module is used to provide users with parking lot navigation and parking space identification services.

[0011] According to the above technical scheme, the management and optimization module includes a data management module, a data analysis module, a system monitoring module, a system optimization module, and a user feedback management module. The data management module is responsible for the collection, storage and management of garage operation data, including vehicle entry and exit records, parking space occupancy, and user information, to ensure the integrity, security and reliability of the data. The data analysis module is used to analyze the garage operation data, discover potential problems and optimization space, and provide decision support for system optimization. The system monitoring module is used to monitor the operating status of the garage system, promptly discover and solve potential faults and problems, and ensure the stable operation of the system. The system optimization module is used to optimize and improve the system performance according to the discovered problems and optimization space, including algorithm optimization, equipment upgrades, and software updates. The user feedback management module is used to collect, analyze and process user feedback, continuously improve the system's user experience and service quality, and take timely measures to solve problems.

[0012] According to the above technical solution, the unmanned garage system and management method based on intelligent recognition comprises the following steps:

[0013] S1: Use cameras and sensors inside the garage to collect data on vehicle flow, parking space occupancy, and user dwell time in real time, and identify information on traffic patterns, peak hours, and parking demand;

[0014] S2: Based on the internal data of the garage and the external environment data, predict the future traffic flow, peak hours and parking demand, and provide a basis for parking space allocation and scheduling;

[0015] S3: Formulate parking space allocation plans and vehicle dispatch strategies, optimize parking space utilization and vehicle parking locations, adjust parking space allocation plans in real time, and dynamically adjust the opening and closing of parking spaces;

[0016] S4: Provides users with real-time parking navigation and route planning, intelligently guiding vehicles to vacant parking spaces based on the real-time location information of vehicles and users;

[0017] S5: Establish a real-time monitoring system to monitor the traffic dynamics, parking space occupancy and equipment operating status in the garage.

[0018] According to the above technical solution, step S1 further includes dividing the historical traffic flow data into time, counting the traffic flow in each time period, obtaining a traffic flow time series, smoothing the traffic flow time series, and using a clustering algorithm to identify different traffic flow patterns, each cluster cluster represents a different traffic flow pattern, and according to the clustering results, selecting cluster clusters with high traffic flow, which represent peak hours, for the selected high traffic flow cluster clusters, calculating the average traffic flow or traffic flow peak value of the corresponding time period, and performing threshold processing, marking the time period when the traffic flow exceeds the threshold as the peak period, and calculating the change coefficient of the traffic flow pattern as an evaluation index of the traffic flow pattern, which can be expressed by the following formula:

[0019] CV = standard deviation / mean

[0020] Among them, the standard deviation represents the degree of fluctuation of the traffic flow time series, and the mean represents the average level of the traffic flow time series. The larger the CV, the greater the degree of change in the traffic flow pattern. For the identification of peak hours, the peak degree of traffic flow (Peakiness) can be calculated using the following formula as an evaluation index for peak hours:

[0021] Peakiness=peak traffic flow / average traffic flow

[0022] The peak traffic flow represents the maximum traffic flow in the selected time period, and the mean traffic flow represents the average traffic flow in the selected time period. The larger the Peakiness, the more concentrated the traffic flow in the time period, which is the peak period.

[0023] According to the above technical solution, step S2 further includes using a neural network model to combine time series data and external factors such as weather and holidays to predict future traffic flow, and the formula is:

[0024] Y t =f(X t ,W)+∈ t

[0025] Y t : Traffic flow at time t, X t : Input factors including time, weather, etc., W: Weight parameter of neural network, f: Neural network model, ∈ t : error term;

[0026] Use the recurrent neural network model to learn the time series pattern from historical data to predict future peak hours. The formula is:

[0027] P t =g(Y t-1 ,Y t-2 ,...,Y t-n )+∈t

[0028] P t : predicted probability of the peak period at time t, g: a function that learns the time series pattern, ∈ t : error term;

[0029] Using a convolutional neural network model, the spatial distribution and temporal pattern of vehicle demand are learned from historical data to predict future parking demand. The formula is:

[0030] D t =h(Z t ,V)+∈ t

[0031] D t : Parking demand at time t, Z t : Input vector including vehicle flow and traffic conditions, V: Model parameters, h: A function to learn parking demand patterns, ∈ t : Error term.

[0032] According to the above scheme, step S3 further includes determining the opening and closing strategy of parking spaces based on the predicted vehicle arrival situation and dwell time distribution to ensure the rational use of parking space resources, dynamically adjusting the allocation of parking spaces in combination with the real-time monitored parking space occupancy situation and vehicle arrival information, providing the best parking space selection and route planning for vehicles about to arrive, so as to alleviate parking congestion and optimize traffic flow, and continuously adjusting and optimizing the parking space allocation plan and vehicle scheduling strategy based on actual conditions and user feedback.

[0033] According to the above scheme, step S4 further includes the system obtaining real-time location information of the vehicle and the user, analyzing the real-time vacancy of the surrounding parking spaces, and using real-time data updates to provide users with personalized parking space selection and route planning, guiding the vehicle to reach the vacant parking space quickly and accurately. The system continuously updates the parking space information and navigation routes through real-time monitoring and dynamic adjustment.

[0034] (III) Beneficial effects

[0035] Compared with the prior art, the present invention provides an unmanned garage system and management method based on intelligent recognition, which has the following beneficial effects:

[0036] The unmanned garage system and management method based on intelligent recognition uses a neural network model, combines time series data and external factors such as weather and holidays to predict future traffic flow, uses a recurrent neural network model to learn time series patterns from historical data to predict future peak hours, and uses a convolutional neural network model to learn the spatial distribution and time patterns of vehicle demand from historical data to predict future parking demand, thereby enabling the unmanned garage to have more convenient and efficient parking services and improving the operational efficiency and management of the garage. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0038] Figure 1 It is a schematic diagram of the system module composition of the present invention;

[0039] Figure 2 It is a schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1 The present invention provides a technical solution: an unmanned garage system based on intelligent identification, including a perception module, a decision module, an execution module, a user experience module, and a management and optimization module, characterized in that: the perception module is used to monitor vehicles, pedestrians and environmental conditions in the garage in real time, including vehicle position, vehicle model, driving speed, and parking space occupancy; the decision module is used to determine the vehicle parking position, path planning scheme and parking space allocation strategy; the execution module is used to control the vehicle to navigate to the designated parking space; the user experience module is used to reserve parking spaces, query vehicle positions, and pay parking fees; the management and optimization module is responsible for the management of garage operation data and the optimization of system performance; the perception module includes a vehicle identification module, a parking space monitoring module, and a pedestrian identification module; the vehicle identification module is used to identify vehicles entering the garage and obtain relevant information about the vehicle; the parking space monitoring module is used to detect the occupancy of parking spaces in the garage and determine whether parking spaces are available; the pedestrian identification module is used to identify pedestrians in the garage, ensure pedestrian safety and provide personalized services.

[0042] The decision module includes a parking space allocation module and an entry and exit control module. The parking space allocation module is used to allocate parking spaces to vehicles entering the garage and determine the parking space allocation strategy. The entry and exit control module is used to control the order and time of vehicles entering and exiting the garage to ensure the safety and order of vehicles entering and exiting.

[0043] The execution module includes a path planning module and a trajectory generation module. The path planning module is responsible for calculating a path for the vehicle to follow based on the current vehicle position, the target parking space position and the environmental map information. The trajectory generation module is used to further generate the trajectory that the vehicle should travel on the basis of the path planning. It is usually necessary to consider the dynamic characteristics of the vehicle and how to smoothly achieve turning and speed change on the path. First, it is necessary to consider the dynamic characteristics of the vehicle, including factors such as mass, inertia, and tire grip. Then, advanced control algorithms such as model pre-control or PID controller can be used to achieve accurate and smooth turning and speed change, and adjust the steering angle and acceleration to ensure that there will be no violent swaying or loss of control during turning and speed change. The user experience module includes a mobile application module, a voice interaction module, and an augmented reality module. The mobile application module is used to allow users to use garage services anytime and anywhere. The voice interaction module is used to realize voice interaction between users and the system through voice recognition technology. The augmented reality module is used to provide users with parking lot navigation and parking space identification services.

[0044] The management and optimization module includes a data management module, a data analysis module, a system monitoring module, a system optimization module, and a user feedback management module. The data management module is responsible for the collection, storage, and management of garage operation data, including vehicle entry and exit records, parking space occupancy, and user information, to ensure the integrity, security, and reliability of the data. The data analysis module is used to analyze the garage operation data, discover potential problems and optimization space, and provide decision support for system optimization. The system monitoring module is used to monitor the operating status of the garage system, promptly discover and resolve potential faults and problems, and ensure the stable operation of the system. The system optimization module is used to optimize and improve system performance based on the discovered problems and optimization space, including algorithm optimization, equipment upgrades, and software updates. The user feedback management module is used to collect, analyze, and process user feedback, continuously improve the system's user experience and service quality, and take timely measures to solve problems.

[0045] An unmanned garage management method based on intelligent recognition includes the following steps:

[0046] S1: Use cameras and sensors inside the garage to collect data on vehicle flow, parking space occupancy, and user dwell time in real time, and identify information on traffic patterns, peak hours, and parking demand;

[0047] S2: Based on the internal data of the garage and the external environment data, predict the future traffic flow, peak hours and parking demand, and provide a basis for parking space allocation and scheduling;

[0048] S3: Formulate parking space allocation plans and vehicle dispatch strategies, optimize parking space utilization and vehicle parking locations, adjust parking space allocation plans in real time, and dynamically adjust the opening and closing of parking spaces;

[0049] S4: Provides users with real-time parking navigation and route planning, intelligently guiding vehicles to vacant parking spaces based on the real-time location information of vehicles and users;

[0050] S5: Establish a real-time monitoring system to monitor the traffic dynamics, parking space occupancy and equipment operating status in the garage.

[0051] Step S1 further includes dividing the historical traffic flow data into time periods, counting the traffic flow in each time period to obtain a traffic flow time series, smoothing the traffic flow time series, and using a clustering algorithm to identify different traffic flow patterns. Each cluster cluster represents a different traffic flow pattern. According to the clustering results, cluster clusters with high traffic flow are selected. These clusters represent peak hours. For the selected high traffic flow cluster clusters, the average traffic flow or traffic flow peak value of the corresponding time period is calculated, and threshold processing is performed. The time period when the traffic flow exceeds the threshold is marked as the peak period. The change coefficient of the traffic flow pattern is calculated as an evaluation index of the traffic flow pattern, which can be expressed by the following formula:

[0052] CV = standard deviation / mean

[0053] Among them, the standard deviation represents the degree of fluctuation of the traffic flow time series, and the mean represents the average level of the traffic flow time series. The larger the CV, the greater the degree of change in the traffic flow pattern. For the identification of peak hours, the peak degree of traffic flow (Peakiness) can be calculated using the following formula as an evaluation index for peak hours:

[0054] Peakiness=peak traffic flow / average traffic flow

[0055] The peak traffic flow represents the maximum traffic flow in the selected time period, and the mean traffic flow represents the average traffic flow in the selected time period. The larger the Peakiness, the more concentrated the traffic flow in the time period, which is the peak period.

[0056] Step S2 further includes using a neural network model to combine time series data and external factors such as weather and holidays to predict future traffic flow, as expressed by the formula:

[0057] Y t =f(X t ,W)+∈ t

[0058] Y t : Traffic flow at time t, X t : Input vector including time and weather factors, W: Weight parameter of neural network, f: Neural network model, ∈ t : error term;

[0059] Use the recurrent neural network model to learn the time series pattern from historical data to predict future peak hours. The formula is:

[0060] P t =g(Y t-1 , Y t-2 , …, Y t-n )+∈ t

[0061] P t : predicted probability of the peak period at time t, g: a function that learns the time series pattern, ∈ t : error term;

[0062] Using a convolutional neural network model, the spatial distribution and temporal pattern of vehicle demand are learned from historical data to predict future parking demand. The formula is:

[0063] D t =h(Z t ,V)+∈ t

[0064] D t : Parking demand at time t, Z t : Input vector including vehicle flow and traffic conditions, V: Model parameters, h: A function to learn parking demand patterns, ∈ t : Error term.

[0065] Step S3 further includes determining the opening and closing strategies of parking spaces according to the predicted vehicle arrival and dwell time distribution to ensure the rational use of parking space resources, dynamically adjusting the allocation of parking spaces in combination with the real-time monitored parking space occupancy and vehicle arrival information, providing the best parking space selection and route planning for the vehicles that are about to arrive, so as to alleviate parking congestion and optimize traffic flow, and continuously adjusting and optimizing the parking space allocation plan and vehicle dispatching strategy according to the actual situation and user feedback.

[0066] Step S4 further includes the system acquiring real-time location information of the vehicle and the user, analyzing the real-time vacancy of surrounding parking spaces, and using real-time data updates to provide users with personalized parking space selection and route planning, guiding the vehicle to reach the vacant parking space quickly and accurately. The system continuously updates the parking space information and navigation routes through real-time monitoring and dynamic adjustment.

[0067] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0068] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An unmanned garage system based on intelligent recognition, including a perception module, a decision module, an execution module, a user experience module and a management and optimization module, characterized in that: The sensing module is used to monitor the vehicles, pedestrians and environment in the garage in real time, including the vehicle location, vehicle model, driving speed, and parking space occupancy; The decision module is used to determine the vehicle parking location, path planning scheme and parking space allocation strategy; The execution module is used to guide the vehicle to a designated parking space; The user experience module is used to reserve parking spaces, query vehicle locations, and pay parking fees; The management and optimization module is responsible for the management of garage operation data and the optimization of system performance; the perception module includes a vehicle recognition module, a parking space monitoring module and a pedestrian recognition module. The vehicle recognition module is used to recognize vehicles entering the garage and obtain relevant information about the vehicles. The parking space monitoring module is used to detect the occupancy of parking spaces in the garage and determine whether parking spaces are available. The pedestrian recognition module is used to recognize pedestrians in the garage to ensure pedestrian safety and provide personalized services. The unmanned garage system adopts an unmanned garage management method based on intelligent identification, and the unmanned garage management method comprises the following steps: S1: Use cameras and sensors inside the garage to collect data on vehicle flow, parking space occupancy, and user dwell time in real time, and identify information on traffic patterns, peak hours, and parking demand; S2: Based on the internal data of the garage and the external environment data, predict the future traffic flow, peak hours and parking demand, and provide a basis for parking space allocation and scheduling; S3: Formulate parking space allocation plans and vehicle dispatch strategies, optimize parking space utilization and vehicle parking locations, adjust parking space allocation plans in real time, and dynamically adjust the opening and closing of parking spaces; S4: Provides users with real-time parking navigation and route planning, intelligently guiding vehicles to vacant parking spaces based on the real-time location information of vehicles and users; S5: Establish a real-time monitoring system to monitor the traffic dynamics, parking space occupancy and equipment operation status in the garage; The step S1 further includes dividing the historical traffic flow data into time periods, counting the traffic flow in each time period to obtain a traffic flow time series, smoothing the traffic flow time series, identifying different traffic flow patterns using a clustering algorithm, each clustering cluster represents a different traffic flow pattern, selecting clustering clusters with high traffic flow according to the clustering results, these clusters represent peak hours, calculating the average traffic flow or traffic flow peak value of the corresponding time period for the selected high traffic flow clusters, and performing threshold processing, marking the time period when the traffic flow exceeds the threshold as the peak period, and calculating the change coefficient of the traffic flow pattern as an evaluation index of the traffic flow pattern, which can be expressed by the following formula: CV = standard deviation / mean Among them, the standard deviation represents the degree of fluctuation of the traffic flow time series, and the mean represents the average level of the traffic flow time series. The larger the CV, the greater the degree of change in the traffic flow pattern. For the identification of peak hours, the peak degree of traffic flow (Peakiness) can be calculated using the following formula as an evaluation index for peak hours: Peakiness=peak traffic flow / average traffic flow The peak traffic flow indicates the maximum traffic flow in the selected time period, and the mean traffic flow indicates the average traffic flow in the selected time period. The larger the Peakiness, the more concentrated the traffic flow in the time period, which is the peak period. The step S2 further includes using a neural network model to combine time series data and external factors such as weather and holidays to predict future traffic flow, as expressed by the formula: Y t =f(X t ,W)+∈ t ) Y t : Traffic flow at time t, X t : Input vector including time and weather factors, W: Weight parameter of neural network, f: Neural network model, ∈ t : error term; Use the recurrent neural network model to learn the time series pattern from historical data to predict future peak hours. The formula is: P t =g(Y t-1 ,AND t-2 ,...,AND t-n )+∈ t P t : predicted probability of the peak period at time t, g: a function that learns the time series pattern, ∈ t : error term; Using a convolutional neural network model, the spatial distribution and temporal pattern of vehicle demand are learned from historical data to predict future parking demand. The formula is: D t =h(Z t ,V)+∈ t D t : Parking demand at time t, Z t : Input vector including vehicle flow and traffic conditions, V: Model parameters, h: A function to learn parking demand patterns, ∈ t : Error term.

2. The unmanned garage system based on intelligent recognition according to claim 1 is characterized in that: The decision-making module includes a parking space allocation module and an entry and exit control module; The parking space allocation module is used to allocate parking spaces to vehicles entering the garage and determine the parking space allocation strategy; The in-and-out control module is used to control the order and time of vehicles entering and exiting the garage to ensure the safety and order of vehicles entering and exiting.

3. The unmanned garage system based on intelligent recognition according to claim 1 is characterized in that: The execution module includes a path planning module and a trajectory generation module; The path planning module is responsible for calculating a path for the vehicle to follow based on the current vehicle position, the target parking space position and the environmental map information; The trajectory generation module is used to further generate a trajectory that the vehicle should travel based on the path planning of the path planning module.

4. The unmanned garage system based on intelligent recognition according to claim 1 is characterized in that: The user experience module includes a mobile application module, a voice interaction module and an augmented reality module; The mobile application module is used to allow users to use the garage service anytime and anywhere; The voice interaction module realizes voice interaction between the user and the system through voice recognition technology; The augmented reality module is used to provide parking lot navigation and parking space identification services for users.

5. The unmanned garage system based on intelligent recognition according to claim 1 is characterized in that: The management and optimization module includes a data management module, a data analysis module, a system monitoring module, a system optimization module, and a user feedback management module; The data management module is used to collect, store and manage garage operation data, including vehicle entry and exit records, parking space occupancy status and user information; The data analysis module is used to analyze the garage operation data, find potential problems and optimization space, and provide decision support for system optimization; The system monitoring module is used to monitor the operating status of the garage system, so as to timely discover and solve potential faults and problems and ensure the stable operation of the system; The system optimization module is used to solve the problems found by the system monitoring module and optimize and improve the system performance. The system optimization module includes algorithm optimization, equipment upgrade and software update; The user feedback management module is used to collect, analyze and process user feedback, continuously improve the user experience and service quality of the system, and take timely measures to solve problems.

6. The unmanned garage system based on intelligent recognition according to claim 1 is characterized in that: The step S3 further includes determining the opening and closing strategies of parking spaces according to the predicted vehicle arrival and dwell time distribution to ensure the rational use of parking space resources, dynamically adjusting the allocation of parking spaces in combination with the real-time monitored parking space occupancy and vehicle arrival information, providing the best parking space selection and route planning for the vehicles about to arrive, so as to alleviate parking congestion and optimize traffic flow, and continuously adjusting and optimizing the parking space allocation plan and vehicle dispatching strategy according to the actual situation and user feedback.

7. The unmanned garage system based on intelligent recognition according to claim 1 is characterized in that: The step S4 further includes the system acquiring real-time location information of the vehicle and the user, analyzing the real-time vacancy of surrounding parking spaces, and using real-time data updates to provide users with personalized parking space selection and route planning, guiding the vehicle to reach the vacant parking space quickly and accurately. The system continuously updates the parking space information and navigation routes through real-time monitoring and dynamic adjustment.

Images