A smart bus stop parking area vehicle illegal parking status detection method and system

Abstract

The present invention relates to a method and system for detecting the illegal parking status of vehicles in smart bus stop parking areas. The method comprises: Q1. When a vehicle is parked at a smart bus stop, data information of the vehicle's historical parking location is collected, and data information of the vehicle's positioning and the relative position of the vehicle and the center point of the platform parking space are obtained in real time. The matching degree between the vehicle and the parking space is predicted using an improved Hippo optimized least squares support vector machine regression prediction algorithm to obtain data information of the predicted matching degree between the vehicle and the parking space. The present invention not only solves the problems of untimely and inaccurate abnormal state detection and inability to automatically warn in the existing bus stop parking area management, but also improves the management efficiency of the bus stop parking area and ensures the normal operation of public buses.

Description

Technical Field

[0001] The present invention relates to the field of smart public transportation technology, and in particular to a method and system for detecting the illegally parked vehicle status in a smart bus stop parking area. Background Art

[0002] With the rapid development of urban transportation, smart buses, as an important part of urban public transportation, are receiving increasing attention for their operational efficiency and safety. As key locations for buses to dock and passengers to board and disembark, the normal operation of smart bus stops is crucial to the efficient operation of the public transportation system.

[0003] However, in actual operation, various abnormal conditions often occur in bus stop parking areas, such as vehicles occupying parking spaces for a long time and non-bus vehicles parking illegally. These abnormal conditions not only affect the normal parking and departure of buses, causing bus operation delays and reducing bus service quality, but may also cause traffic congestion and affect the overall smoothness of urban traffic.

[0004] Currently, the management of bus stop parking areas primarily relies on manual inspections and traditional monitoring equipment. Manual inspections suffer from low efficiency, limited coverage, and poor real-time performance, making it difficult to promptly detect and address abnormal parking conditions. Traditional monitoring equipment, such as cameras, can provide real-time monitoring of parking areas, but they require manual review of the footage to determine if any anomalies exist. This lacks automated detection and early warning capabilities, and falls short of meeting the demands of modern smart transportation for efficient bus stop management.

[0005] In the prior art, a Chinese patent (Application Number: 201611079213.3, Publication Number: CN 107545723A) discloses a video surveillance system for a bus rapid transit stop. The bus stop is equipped with a monitoring room containing a host computer and a communication module connected to the host computer. The bus stop is divided into multiple parking areas, each with a gate and a camera connected to the host computer. An access control system connected to the host computer is installed at the entrance of the bus stop. The host computer is connected to the camera to collect video information and determine whether to open the gate. While this invention involves bus entry reminders and passenger information displays, its abnormal state detection is insufficiently comprehensive: the solution focuses on bus-passenger collision risk identification, danger zone demarcation, and bus entry reminders. It does not address abnormal conditions that may occur in parking areas, such as vehicle breakdowns and illegal prolonged parking, resulting in incomplete detection coverage.

[0006] In the prior art, a Chinese patent (application number: 201810110095.0, publication number: CN 108222559A) discloses an intelligent bus stop, which includes: an intelligent bus stop announcement module, a rainy night sensor, an anti-slip pad, a base, a top plate, an automatic sliding mechanism and a shielding cover; wherein the rainy night sensor is arranged on the shielding cover, and the top plate is vertically penetrated into the base. When the rainy night sensor senses rain, the automatic sliding mechanism is driven to drive the top plate to rise or fall along the length direction; one side of the shielding cover is hinged to an end of the top plate away from the base, and can form a horizontal shielding state under the support of a support frame; the base is mounted on the upper surface of the anti-slip pad, and the anti-slip pad is arranged at an angle; the intelligent bus stop announcement module is arranged on the top plate to display bus information in real time. This plan only improves the system of bus stops and does not detect illegally parked vehicles in the platform parking area. It will cause delays in bus operations, reduce the quality of bus services, and may also cause traffic congestion. Summary of the Invention

[0007] In view of the above shortcomings of the existing technology, the present invention provides a smart bus stop parking area vehicle illegal parking status detection method and system, which not only solves the problems of untimely and inaccurate abnormal status detection and inability to automatically issue warnings in the existing bus stop parking area management, but also improves the management efficiency of bus stop parking areas and ensures the normal operation of buses.

[0008] In order to achieve the above-mentioned and other related purposes, the present invention provides the following technical solutions:

[0009] A method for detecting the illegally parked vehicle status in a smart bus stop parking area, the method comprising:

[0010] Q1. When a vehicle stops at a smart bus stop, data on the vehicle's historical parking locations is collected, along with real-time data on the vehicle's location and its relative position to the center of the bus stop's parking space.

[0011] Q2. Based on the vehicle's historical parking location data, the vehicle's positioning data, and the relative position of the vehicle and the center point of the platform parking space, a modified Hippo optimized least squares support vector machine regression prediction algorithm is used to predict the matching degree between the vehicle and the parking space, thereby obtaining predicted matching degree data for the vehicle and the parking space.

[0012] Q3. Based on the predicted vehicle-to-parking space matching data, optimize the matching between the vehicle and the parking space using an improved cane rat optimization algorithm based on a decay factor and dynamic learning, obtaining optimized vehicle-to-parking space matching data;

[0013] Q4. Based on the optimized data information on the matching degree between the vehicle and the parking space, establish a parking space abnormal state function W, calculate the abnormal state value of the parking space, and obtain data information on the abnormal state value of the parking space.

[0014] Furthermore, the method further comprises:

[0015] Q5. Based on the data information of the abnormal status value of the parking space, a preset threshold is set. If the abnormal status value of the parking space is greater than the preset threshold, the vehicle is illegally parked and needs to be "driven away" and leave the platform parking space. If the abnormal status value of the parking space is less than the preset threshold, the vehicle is not illegally parked and no processing is required.

[0016] Furthermore, the parking space abnormal state function W is:

[0017] ,

[0018] ,

[0019] Among them, x is the data information of the matching degree between the optimized vehicle and the parking space, and ω1, ω2 and ω3 are weight coefficients.

[0020] Furthermore, in step Q2, the use of the improved Hippo optimized least squares support vector machine regression prediction algorithm to predict the matching degree between the vehicle and the parking space includes:

[0021] Q21. Input the data information of the vehicle's historical parking locations, the vehicle's positioning data, and the data information of the relative position of the vehicle and the center point of the platform parking space into a least squares support vector regression prediction model for training and learning. Reset the width of the model kernel function and the error penalty factor to obtain the data information of the reset model kernel function width and error penalty factor.

[0022] Q22. Based on the data information of the width of the kernel function of the reset model and the error penalty factor, the hippo population is initialized, the population parameters are determined, and the data information of the initialized hippo population is obtained;

[0023] Q23. Based on the data information of the initialized hippopotamus population, establish the objective function W of the population,

[0024] ,

[0025] Among them, x is the data information of the initialized hippo population, α1, α2 and α3 are target optimization factors, and the width of the kernel function and the error penalty factor of the reset model are optimized to obtain the data information of the width of the kernel function and the error penalty factor of the optimized model.

[0026] Furthermore, the use of the improved Hippo optimized least squares support vector machine regression prediction algorithm to predict the matching degree between the vehicle and the parking space also includes:

[0027] Q24. Based on the data information of the width of the kernel function of the optimized model and the error penalty factor, an optimized least squares support vector regression prediction model is obtained, and the data information of the historical parking position points of the vehicle, the data information of the positioning of the vehicle, and the data information of the relative position between the vehicle and the center point of the platform parking space are input to predict the matching degree between the vehicle and the parking space, and obtain the data information of the predicted matching degree between the vehicle and the parking space.

[0028] Furthermore, the target optimization factors α1, α2 and α3 are,

[0029] ,

[0030] ,

[0031] ,

[0032] Among them, x is the data information of the initialized hippo population.

[0033] Furthermore, in step Q3, the optimization of the matching degree between the vehicle and the parking space using the improved cane rat optimization algorithm based on attenuation factor and dynamic learning includes:

[0034] Q31. Based on the predicted data information of the matching degree of the vehicle and the parking space, the large cane rat population is initialized, the population parameters are determined, and the data information of the large cane rat population after the initialization is obtained;

[0035] Q32. Based on the data information of the initialized cane rat population, construct a rat position update function R,

[0036] ,

[0037] Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population, i and j are positive integers, C is any constant parameter between 0 and 1, β is the attenuation factor of the cane rat population, and δ is the dynamic learning factor of the cane rat population;

[0038] Q33. Based on the position update function R of the mouse group, iterate and optimize the matching degree between the vehicle and the parking space to obtain data information of the optimized matching degree between the vehicle and the parking space.

[0039] Furthermore, the attenuation factor β of the greater cane rat population is,

[0040] ,

[0041] Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population;

[0042] The dynamic learning factor δ of the cane rat population is,

[0043] ,

[0044] Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population.

[0045] In order to achieve the above-mentioned and other related objectives, the present invention further provides a system for implementing any of the above-mentioned methods for detecting illegally parked vehicles in a smart bus stop parking area, the system comprising:

[0046] The smart bus stop data acquisition module is used to collect data information on the historical parking locations of vehicles, and obtain data information on the vehicle's positioning and the relative position of the vehicle and the center point of the platform parking space in real time;

[0047] A vehicle-parking space matching prediction module is connected to the smart bus stop data acquisition module and is used to predict the matching degree between the vehicle and the parking space using an improved Hippo optimized least squares support vector machine regression prediction algorithm to obtain data information on the predicted matching degree between the vehicle and the parking space;

[0048] a vehicle-parking-space matching degree optimization module, connected to the vehicle-parking-space matching degree prediction module, for optimizing the matching degree between the vehicle and the parking space using an improved cane rat optimization algorithm based on an attenuation factor and dynamic learning, and obtaining data information on the optimized matching degree between the vehicle and the parking space;

[0049] The parking space abnormal state value module is connected to the vehicle and parking space matching optimization module, and is used to establish a parking space abnormal state function W, calculate the parking space abnormal state value, and obtain data information of the parking space abnormal state value.

[0050] Furthermore, the system also includes a parking space abnormal state judgment module, which is connected to the parking space abnormal state value module and is used to set a preset threshold. If the abnormal state value of the parking space is greater than the preset threshold, the vehicle is illegally parked and needs to be "driven away" and leave the platform parking space. If the abnormal state value of the parking space is less than the preset threshold, the vehicle is not illegally parked and no processing is required.

[0051] The present invention has the following positive effects:

[0052] 1. The present invention predicts the matching degree between vehicles and parking spaces by adopting an improved Hippopotamus optimized least squares support vector machine regression prediction algorithm, and optimizes the matching degree between vehicles and parking spaces by combining an improved cane rat optimization algorithm based on attenuation factor and dynamic learning. Not only does the vehicle illegal parking status model established based on the machine learning algorithm enable the system to have autonomous learning and judgment capabilities, and automatically identify abnormal status of parking areas and trigger early warnings, but this process also does not require manual real-time monitoring and intervention, greatly reducing the workload and management costs of manual inspections, promoting the transformation of bus stop parking area management from the traditional manual mode to the intelligent and automated mode, improving management efficiency and response speed, and adapting to the needs of modern smart transportation development.

[0053] 2. By establishing a parking space abnormal state function W and calculating the abnormal state value of a parking space, the present invention not only solves the problems existing in the management of bus stop parking areas, such as untimely and inaccurate abnormal state detection and inability to automatically issue warnings, but also improves the management efficiency of bus stop parking areas and ensures the normal operation of buses. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of a parking area illegal parking scenario of a social vehicle in the present invention;

[0055] Figure 2 Schematic diagram of the method flow of the present invention;

[0056] Figure 3 Schematic diagram of the process of the improved Hippo optimized least squares support vector machine regression prediction algorithm of the present invention;

[0057] Figure 4 Schematic diagram of the flow of the improved cane rat optimization algorithm based on attenuation factor and dynamic learning of the present invention;

[0058] Figure 5 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0059] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0060] Example 1: Figure 1 or Figure 2 As shown, a method for detecting the illegal parking status of vehicles in a smart bus stop parking area includes:

[0061] Q1. When a vehicle stops at a smart bus stop, data on the vehicle's historical parking locations is collected, along with real-time data on the vehicle's location and its relative position to the center of the bus stop's parking space.

[0062] Q2. Based on the vehicle's historical parking location data, the vehicle's positioning data, and the relative position of the vehicle and the center point of the platform parking space, a modified Hippo optimized least squares support vector machine regression prediction algorithm is used to predict the matching degree between the vehicle and the parking space, thereby obtaining predicted matching degree data for the vehicle and the parking space.

[0063] Q3. Based on the predicted vehicle-to-parking space matching data, optimize the matching between the vehicle and the parking space using an improved cane rat optimization algorithm based on a decay factor and dynamic learning, obtaining optimized vehicle-to-parking space matching data;

[0064] Q4. Based on the optimized data information on the matching degree between the vehicle and the parking space, establish a parking space abnormal state function W, calculate the abnormal state value of the parking space, and obtain data information on the abnormal state value of the parking space.

[0065] In this embodiment, the method further includes:

[0066] Q5. Based on the data information of the abnormal status value of the parking space, a preset threshold is set. If the abnormal status value of the parking space is greater than the preset threshold, the vehicle is illegally parked and needs to be "driven away" and leave the platform parking space. If the abnormal status value of the parking space is less than the preset threshold, the vehicle is not illegally parked and no processing is required.

[0067] In this embodiment, if Figure 3 As shown, in step Q2, the use of the improved Hippo optimized least squares support vector machine regression prediction algorithm to predict the matching degree between the vehicle and the parking space includes:

[0068] Q21. Input the data information of the vehicle's historical parking locations, the vehicle's positioning data, and the data information of the relative position of the vehicle and the center point of the platform parking space into a least squares support vector regression prediction model for training and learning. Reset the width of the model kernel function and the error penalty factor to obtain the data information of the reset model kernel function width and error penalty factor.

[0069] Q22. Based on the data information of the width of the kernel function of the reset model and the error penalty factor, the hippo population is initialized, the population parameters are determined, and the data information of the initialized hippo population is obtained;

[0070] Q23. Based on the data information of the initialized hippopotamus population, establish the objective function W of the population,

[0071] ,

[0072] Among them, x is the data information of the initialized hippo population, α1, α2 and α3 are target optimization factors, and the width of the kernel function and the error penalty factor of the reset model are optimized to obtain the data information of the width of the kernel function and the error penalty factor of the optimized model.

[0073] In this embodiment, the method of predicting the matching degree between the vehicle and the parking space using the improved Hippo optimized least squares support vector machine regression prediction algorithm further includes:

[0074] Q24. Based on the data information of the width of the kernel function of the optimized model and the error penalty factor, an optimized least squares support vector regression prediction model is obtained, and the data information of the historical parking position points of the vehicle, the data information of the positioning of the vehicle, and the data information of the relative position between the vehicle and the center point of the platform parking space are input to predict the matching degree between the vehicle and the parking space, and obtain the data information of the predicted matching degree between the vehicle and the parking space.

[0075] In this embodiment, the target optimization factors α1, α2 and α3 are,

[0076] ,

[0077] ,

[0078] ,

[0079] Among them, x is the data information of the initialized hippo population.

[0080] In this embodiment, if Figure 4As shown, in step Q3, the optimization of the matching degree between the vehicle and the parking space using the improved cane rat optimization algorithm based on attenuation factor and dynamic learning includes:

[0081] Q31. Based on the predicted data information of the matching degree of the vehicle and the parking space, the large cane rat population is initialized, the population parameters are determined, and the data information of the large cane rat population after the initialization is obtained;

[0082] Q32. Based on the data information of the initialized cane rat population, construct a rat position update function R,

[0083] ,

[0084] Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population, i and j are positive integers, C is any constant parameter between 0 and 1, β is the attenuation factor of the cane rat population, and δ is the dynamic learning factor of the cane rat population;

[0085] Q33. Based on the position update function R of the mouse group, iterate and optimize the matching degree between the vehicle and the parking space to obtain data information of the optimized matching degree between the vehicle and the parking space.

[0086] In this embodiment, the attenuation factor β of the cane rat population is,

[0087] ,

[0088] Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population;

[0089] The dynamic learning factor δ of the cane rat population is,

[0090] ,

[0091] Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population.

[0092] In this embodiment, the present invention proposes a smart bus stop parking area vehicle illegal parking status detection method based on an improved Hippo optimized least squares support vector machine regression prediction algorithm and an improved cane rat optimization algorithm. Practical applications have verified that this method performs well in terms of detection accuracy, efficiency, and user satisfaction.

[0093] In this example, we deployed the aforementioned smart parking detection system at Bus Stop A in a certain city. During a month-long test, we collected a large amount of parking data. Data analysis showed that the system accurately predicted over 95% of vehicle-to-parking space matches and successfully identified 80% of illegal parking incidents.

[0094] Example 2: Based on the method for detecting the illegal parking status of vehicles in a smart bus stop parking area in Example 1, the present invention is further illustrated and described below.

[0095] like Figure 1 or Figure 2 As shown, a method for detecting the illegal parking status of vehicles in a smart bus stop parking area includes:

[0096] Q1. When a vehicle stops at a smart bus stop, data on the vehicle's historical parking locations is collected, along with real-time data on the vehicle's location and its relative position to the center of the bus stop's parking space.

[0097] Q2. Based on the vehicle's historical parking location data, the vehicle's positioning data, and the relative position of the vehicle and the center point of the platform parking space, a modified Hippo optimized least squares support vector machine regression prediction algorithm is used to predict the matching degree between the vehicle and the parking space, thereby obtaining predicted matching degree data for the vehicle and the parking space.

[0098] Q3. Based on the predicted vehicle-to-parking space matching data, optimize the matching between the vehicle and the parking space using an improved cane rat optimization algorithm based on a decay factor and dynamic learning, obtaining optimized vehicle-to-parking space matching data;

[0099] Q4. Based on the optimized data information on the matching degree between the vehicle and the parking space, establish a parking space abnormal state function W, calculate the abnormal state value of the parking space, and obtain data information on the abnormal state value of the parking space.

[0100] In this embodiment, the parking space abnormal state function W is:

[0101] ,

[0102] ,

[0103] Among them, x is the data information of the matching degree between the optimized vehicle and the parking space, and ω1, ω2 and ω3 are weight coefficients.

[0104] In this embodiment, the present invention has been successfully applied to bus stops in multiple cities, achieving significant social and economic benefits. For example, in a provincial capital city, after the system was launched, illegal parking incidents at bus stops decreased by 60%, and passenger complaints dropped by 40%. Furthermore, the promotion of the system has driven the development of related industrial chains and promoted the construction of smart cities.

[0105] In this embodiment, if Figure 5 As shown, the present invention provides a system for implementing any of the above methods for detecting illegally parked vehicles in a smart bus stop parking area, the system comprising:

[0106] The smart bus stop data acquisition module is used to collect data information on the historical parking locations of vehicles, and obtain data information on the vehicle's positioning and the relative position of the vehicle and the center point of the platform parking space in real time;

[0107] A vehicle-parking space matching prediction module is connected to the smart bus stop data acquisition module and is used to predict the matching degree between the vehicle and the parking space using an improved Hippo optimized least squares support vector machine regression prediction algorithm to obtain data information on the predicted matching degree between the vehicle and the parking space;

[0108] a vehicle-parking-space matching degree optimization module, connected to the vehicle-parking-space matching degree prediction module, for optimizing the matching degree between the vehicle and the parking space using an improved cane rat optimization algorithm based on an attenuation factor and dynamic learning, and obtaining data information on the optimized matching degree between the vehicle and the parking space;

[0109] The parking space abnormal state value module is connected to the vehicle and parking space matching optimization module, and is used to establish a parking space abnormal state function W, calculate the parking space abnormal state value, and obtain data information of the parking space abnormal state value.

[0110] In this embodiment, the system also includes a parking space abnormal state judgment module, which is connected to the parking space abnormal state value module and is used to set a preset threshold. If the abnormal state value of the parking space is greater than the preset threshold, the vehicle is illegally parked and needs to be "driven away" and leave the platform parking space. If the abnormal state value of the parking space is less than the preset threshold, the vehicle is not illegally parked and no processing is required.

[0111] The present invention provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the methods for detecting the illegal parking status of vehicles in a smart bus stop parking area.

[0112] Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0113] In summary, the present invention not only solves the problems existing in the existing bus stop parking area management, such as untimely and inaccurate abnormal state detection and inability to automatically warn, but also improves the management efficiency of bus stop parking areas and ensures the normal operation of buses.

[0114] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for detecting the illegal parking status of vehicles in a smart bus stop parking area, characterized in that: The method comprises: Q1. When a vehicle stops at a smart bus stop, data on the vehicle's historical parking locations is collected, along with real-time data on the vehicle's location and its relative position to the center of the bus stop's parking space. Q2. Based on the vehicle's historical parking location data, the vehicle's positioning data, and the relative position of the vehicle to the center of the platform parking space, a modified Hippo optimized least squares support vector machine regression prediction algorithm is used to predict the matching degree between the vehicle and the parking space, thereby obtaining predicted matching degree data. Q3. Based on the predicted vehicle-to-parking space matching data, optimize the matching between the vehicle and the parking space using an improved cane rat optimization algorithm based on a decay factor and dynamic learning, obtaining optimized vehicle-to-parking space matching data; Q4. Based on the optimized data information of the matching degree between the vehicle and the parking space, establish a parking space abnormal state function W, calculate the abnormal state value of the parking space, and obtain data information of the abnormal state value of the parking space; In step Q3, the optimization of the matching degree between the vehicle and the parking space using the improved cane rat optimization algorithm based on attenuation factor and dynamic learning includes: Q31. Based on the predicted data information of the matching degree of the vehicle and the parking space, the large cane rat population is initialized, the population parameters are determined, and the data information of the large cane rat population after the initialization is obtained; Q32. Based on the data information of the initialized cane rat population, construct a rat position update function R, ， Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population, i and j are positive integers, C is any constant parameter between 0 and 1, β is the attenuation factor of the cane rat population, and δ is the dynamic learning factor of the cane rat population; Q33. Based on the position update function R of the mouse group, iterate and optimize the matching degree between the vehicle and the parking space to obtain data information of the optimized matching degree between the vehicle and the parking space.

2. The method for detecting illegally parked vehicles in a smart bus stop parking area according to claim 1 is characterized in that: The method further comprises: Q5. Based on the data information of the abnormal status value of the parking space, a preset threshold is set. If the abnormal status value of the parking space is greater than the preset threshold, the vehicle is illegally parked and needs to be "driven away" and leave the platform parking space. If the abnormal status value of the parking space is less than the preset threshold, the vehicle is not illegally parked and no action is required.

3. The method for detecting illegally parked vehicles in a smart bus stop parking area according to claim 1 is characterized by: The parking space abnormal state function W is: ， ， Among them, x is the data information of the matching degree between the optimized vehicle and the parking space, and ω1, ω2 and ω3 are weight coefficients.

4. The method for detecting illegally parked vehicles in a smart bus stop parking area according to claim 1 is characterized in that: In step Q2, the use of the improved Hippo optimized least squares support vector machine regression prediction algorithm to predict the matching degree between the vehicle and the parking space includes: Q21. Input the data information of the vehicle's historical parking locations, the vehicle's positioning data, and the data information of the relative position of the vehicle and the center point of the platform parking space into a least squares support vector regression prediction model for training and learning. Reset the width of the model kernel function and the error penalty factor to obtain the data information of the reset model kernel function width and error penalty factor. Q22. Based on the data information of the width of the kernel function of the reset model and the error penalty factor, the hippo population is initialized, the population parameters are determined, and the data information of the initialized hippo population is obtained; Q23. Based on the data information of the initialized hippopotamus population, establish the objective function W of the population, ， Among them, x is the data information of the initialized hippo population, α1, α2 and α3 are target optimization factors, and the width of the kernel function and the error penalty factor of the reset model are optimized to obtain the data information of the width of the kernel function and the error penalty factor of the optimized model.

5. The method for detecting illegally parked vehicles in a smart bus stop parking area according to claim 4 is characterized in that: The method of using the improved Hippo optimized least squares support vector machine regression prediction algorithm to predict the matching degree between the vehicle and the parking space also includes: Q24. Based on the data information of the width of the kernel function of the optimized model and the error penalty factor, an optimized least squares support vector regression prediction model is obtained, and the data information of the historical parking position points of the vehicle, the data information of the positioning of the vehicle, and the data information of the relative position between the vehicle and the center point of the platform parking space are input to predict the matching degree between the vehicle and the parking space, and obtain the data information of the predicted matching degree between the vehicle and the parking space.

6. The method for detecting illegally parked vehicles in a smart bus stop parking area according to claim 4 is characterized by: The target optimization factors α1, α2 and α3 are, ， ， ， Among them, x is the data information of the initialized hippo population.

7. The method for detecting illegally parked vehicles in a smart bus stop parking area according to claim 1 is characterized by: The decay factor β of the cane rat population is, ， Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population; The dynamic learning factor δ of the cane rat population is, ， Among them, y i is the i-th individual of the initialized cane rat population, y j is the jth individual of the initialized cane rat population.

8. A system for implementing the method for detecting illegally parked vehicles in a smart bus stop parking area according to any one of claims 1 to 7, characterized in that: The system comprises: The smart bus stop data acquisition module is used to collect data information on the historical parking locations of vehicles, and obtain data information on the vehicle's positioning and the relative position of the vehicle and the center point of the platform parking space in real time; A vehicle-parking space matching prediction module is connected to the smart bus stop data acquisition module and is used to predict the matching degree between the vehicle and the parking space using an improved Hippo optimized least squares support vector machine regression prediction algorithm to obtain data information on the predicted matching degree between the vehicle and the parking space; a vehicle-parking-space matching degree optimization module, connected to the vehicle-parking-space matching degree prediction module, for optimizing the matching degree between the vehicle and the parking space using an improved cane rat optimization algorithm based on an attenuation factor and dynamic learning, and obtaining data information on the optimized matching degree between the vehicle and the parking space; The parking space abnormal state value module is connected to the vehicle and parking space matching optimization module, and is used to establish a parking space abnormal state function W, calculate the parking space abnormal state value, and obtain data information of the parking space abnormal state value.

9. The system according to claim 8, characterized in that The system also includes a parking space abnormal state judgment module, which is connected to the parking space abnormal state value module and is used to set a preset threshold. If the parking space abnormal state value is greater than the preset threshold, the vehicle is illegally parked and needs to be "driven away" and leave the platform parking space. If the parking space abnormal state value is less than the preset threshold, the vehicle is not illegally parked and no processing is required.

Images