Intelligent parking reservation control adjustment method and system

Abstract

This invention proposes an intelligent parking reservation control and adjustment method and system. The method includes: acquiring user information with parking space reservation needs, including the user's license plate number, vehicle model, and current location; recommending parking spaces to the user based on a scoring model; acquiring user feedback on the recommended parking spaces; updating the weights in the scoring model based on the user's feedback; and updating the weights again by applying collaborative filtering enhancement to each user at preset time intervals. This method and system not only enhance the user's personalized experience but also improve the overall system efficiency and recommendation accuracy through continuous learning and optimization.

Description

Technical Field

[0001] This invention proposes an intelligent parking reservation control and adjustment method and system, belonging to the field of intelligent parking technology. Background Technology

[0002] With rapid urbanization and a surge in vehicle ownership, urban parking problems are becoming increasingly severe, leading to traffic congestion and environmental pollution. Traditional parking methods often rely on drivers searching for available parking spaces, which is not only time-consuming and laborious but also exacerbates the burden on urban traffic. To address this, intelligent parking systems have emerged, aiming to optimize the allocation of parking resources and reduce vehicle idle time while searching for parking spaces through efficient technological means. Most existing intelligent parking systems employ centralized control, processing all parking information and requests centrally and then scheduling them uniformly. These systems typically operate based on fixed rules, such as distance priority and price priority, but often neglect users' personalized needs and preferences. With the rise of personalized services and the development of artificial intelligence technology, providing customized parking solutions for users has become possible. However, achieving this requires processing and analyzing large amounts of user data and updating the system in real time to respond to changes in user preferences. Furthermore, the addition of new users also brings the cold start problem—how to effectively provide services without sufficient user information. Therefore, there is an urgent need to develop an intelligent parking reservation control method and system that can effectively integrate and utilize user preferences, learn user behavior dynamically in real time, and use collaborative filtering technology to solve the cold start problem. Summary of the Invention

[0003] This invention provides an intelligent parking reservation control and adjustment method and system to solve the problems mentioned above:

[0004] This invention proposes an intelligent parking reservation control and adjustment method, the method comprising:

[0005] The system obtains information about users who need to reserve parking spaces, including the user's license plate number, vehicle model, and current location, and recommends parking spaces to users based on a rating model.

[0006] Obtain user feedback on recommended parking spaces and update the weights in the rating model based on the user feedback;

[0007] At preset intervals, the weights for collaborative filtering enhancement are updated again for each user application.

[0008] Furthermore, information on users who need to reserve parking spaces is obtained, including the user's license plate number and current location. Parking spaces are then selected for the user based on a scoring model, including:

[0009] Obtain user information that requires parking space reservations, including: user license plate number, user vehicle size, and user current location;

[0010] The system retrieves all available parking spaces within a distance of the user's current location that does not exceed a preset distance threshold. It also retrieves the weather forecast for the user's reserved parking time period via API. Finally, it recommends parking spaces based on a rating calculated using a rating model. Specifically, the rating model is as follows:

[0011]

[0012] in, This indicates the rating of the parking space. , , , , and Representing the weight of each sub-rating,

[0013] Indicates the distance adjustment factor. Indicates the difficulty level of parking. This indicates the weather adjustment factor. This indicates the coverage facility bonus factor. This represents the time sensitivity coefficient. Indicates the safety factor;

[0014]

[0015] in, This represents the driving distance from the user's current location to the parking space p. This is the distance sensitivity coefficient;

[0016]

[0017] in, The parking difficulty index can be represented by the average historical parking time for that parking space, with θ representing the difficulty sensitivity coefficient.

[0018]

[0019] in, This indicates the impact of weather on the availability of the parking space. Indicates the weather sensitivity coefficient;

[0020]

[0021] Where s(p) represents the safety index of the parking space, and μ represents the safety weighting coefficient;

[0022]

[0023] Where λ represents the time sensitivity coefficient, T is the period (24 hours in a day), and t is the current time, which needs to be converted to a decimal form in hours. C represents the phase shift, adjusted according to the specific time when the demand peak begins; C represents the vertical shift.

[0024] Furthermore, obtaining user feedback on recommended parking spaces and updating the weights in the rating model based on user feedback includes:

[0025] Initialize each user's preference vector P u ;

[0026] For each parking request, the user's feedback rating for the recommended parking space is obtained, and the user preference weights are updated based on a dynamic weight learning model. Specifically, the dynamic weight learning model is as follows:

[0027]

[0028] in, It is the weight of user u on factor i at time step t. It's the learning rate. It is the user's feedback rating for the current recommendation. It is the average feedback score. This is the score of the currently recommended parking space on factor i. It is the average score of factor i.

[0029] Furthermore, at preset intervals, the weights for collaborative filtering enhancement are updated again for each user application, including:

[0030] Find the k most similar users to the user whose weight has been updated;

[0031] The updated weights of users are calculated based on a collaborative filtering model. Specifically, the collaborative filtering model is as follows:

[0032]

[0033] in, η is the weight of user u to factor i, and η is the learning rate. The weights, incorporating collaborative information, represent a balance between individual and group preferences. Let be the k most similar users of user u, and sim(u,v) be the similarity between users u and v.

[0034] This invention proposes an intelligent parking reservation control and adjustment system, the system comprising:

[0035] The recommended parking space module is used to obtain user information that requires a parking space reservation. The user information includes: user license plate number, user vehicle model and user current location. Based on a scoring model, parking spaces are recommended to the user.

[0036] The weight update module is used to obtain user feedback on recommended parking spaces and update the weights in the rating model based on the user feedback.

[0037] The enhanced weight update module is used to update the weights of each user again at preset intervals by applying collaborative filtering enhancements.

[0038] Furthermore, the recommended parking space module includes:

[0039] The user information acquisition module is used to acquire user information who have a parking space reservation requirement. The user information includes: user license plate number, user vehicle size, and user current location.

[0040] The rating module is used to obtain all available parking spaces within a distance of the user's current location that does not exceed a preset distance threshold. It also retrieves the weather forecast for the user's reserved parking time period via API. Based on a rating model, it calculates a rating to recommend parking spaces to the user. Specifically, the rating model is as follows:

[0041]

[0042] in, This indicates the rating of the parking space. , , , , and Representing the weight of each sub-rating, Indicates the distance adjustment factor. Indicates the difficulty level of parking. This represents the weather adjustment factor. This indicates the coverage facility bonus factor. This represents the time sensitivity coefficient. Indicates the safety factor;

[0043]

[0044] in, This represents the driving distance from the user's current location to the parking space p. This is the distance sensitivity coefficient;

[0045]

[0046] in, The parking difficulty index can be represented by the average historical parking time for that parking space, with θ representing the difficulty sensitivity coefficient.

[0047]

[0048] in, This indicates the impact of weather on the availability of the parking space. Indicates the weather sensitivity coefficient;

[0049]

[0050] Where s(p) represents the safety index of the parking space, and μ represents the safety weighting coefficient;

[0051]

[0052] Where λ represents the time sensitivity coefficient, T is the period (24 hours in a day), and t is the current time, which needs to be converted to a decimal form in hours. C represents the phase shift, adjusted according to the specific time when the demand peak begins; C represents the vertical shift.

[0053] Furthermore, the weight update module includes:

[0054] The preference vector initialization module is used to initialize the preference vector P for each user. u ;

[0055] The weight calculation and update module is used to obtain the user's feedback rating for the recommended parking space for each parking request, and update the user preference weights based on a dynamic weight learning model. Specifically, the dynamic weight learning model is as follows:

[0056]

[0057] in, It is the weight of user u on factor i at time step t. It's the learning rate. It is the user's feedback rating for the current recommendation. It is the average feedback score. This is the score of the currently recommended parking space on factor i. The average score of factor i

[0058] Furthermore, the enhanced update weight module includes:

[0059] The module for obtaining similar users is used to obtain the k most similar users to the user whose weight has been updated.

[0060] The filter weight calculation module is used to calculate the updated weights of users based on a collaborative filtering model. Specifically, the collaborative filtering model is:

[0061]

[0062] in, η is the weight of user u to factor i, and η is the learning rate. The weights, incorporating collaborative information, represent a balance between individual and group preferences. Let be the k most similar users of user u, and sim(u,v) be the similarity between users u and v.

[0063] The beneficial effects of this invention are as follows: Enhanced personalized service: By comprehensively considering users' personal information and preferences when recommending parking spaces, the user experience becomes more personalized and satisfaction is higher; Improved recommendation accuracy: Dynamically updated scoring models and regular collaborative filtering enhancements ensure the system continuously learns and optimizes, improving the accuracy and adaptability of recommendations; Enhanced user satisfaction: Timely responses to user feedback and adjustments to recommendation strategies strengthen user trust and satisfaction; Optimized resource allocation: More accurate parking recommendations reduce the time users spend searching for parking spaces, helping to alleviate urban traffic pressure and improve the efficiency of parking resource utilization; Solving the new user problem: Collaborative filtering technology helps solve the cold start problem for new users or users with limited data, providing them with reasonable parking recommendations more quickly; This technical solution not only enhances the user's personalized experience but also improves the overall operating efficiency and recommendation accuracy of the system through continuous learning and optimization. Attached Figure Description

[0064] Figure 1 This is a schematic diagram of an intelligent parking reservation control and adjustment method according to the present invention. Detailed Implementation

[0065] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0066] Numerous specific details are set forth in the following description to provide a thorough understanding of the invention. The described embodiments are only a part of, and not all, of the embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0068] One embodiment of the present invention provides an intelligent parking reservation control adjustment method, the method comprising:

[0069] The system obtains information about users who need to reserve parking spaces, including the user's license plate number, vehicle model, and current location, and recommends parking spaces to users based on a rating model.

[0070] Obtain user feedback on recommended parking spaces and update the weights in the rating model based on the user feedback;

[0071] At preset intervals, the weights for collaborative filtering enhancement are updated again for each user application.

[0072] The working principle and effect of the above technical solution are as follows: To obtain user information, the system first captures the license plate number, vehicle model and current location input by the user. This step is the beginning of collecting necessary information to ensure the accuracy of subsequent parking space recommendations. The user's vehicle model can be used to determine the required parking space size, and the current location is used to optimize distance calculation. Based on the information provided by the user, the system uses the established scoring model to calculate the score of each parking space. The scoring model integrates personalized user preferences (such as distance, price, and safety) with specific parking space conditions (such as location, cost, and space size). Based on the calculated score, the system recommends the optimal parking space to the user. User feedback is collected; users can accept or reject the recommendations, or evaluate their parking experience after parking. This feedback is a crucial data source for adjusting the scoring model. Dynamic weight updates are implemented; based on actual user feedback, the system automatically adjusts the weights in the scoring model. This step uses an online learning algorithm to ensure the model reflects the latest user preferences and needs in real time. Every preset time (e.g., weekly or monthly), the system uses collaborative filtering technology to comprehensively analyze and optimize the preferences of all users. This step improves the recommendation quality for new users or users with limited data by considering the preferences of similar users, and also recalibrates the preference model for all users. Personalized service enhancements are achieved by comprehensively considering users' personal information and preferences when recommending parking spaces, resulting in a more personalized and satisfying user experience. Recommendation accuracy is improved through dynamic updates to the scoring model and regular collaborative filtering enhancements, ensuring continuous learning and optimization to improve the accuracy and adaptability of recommendations. User satisfaction is enhanced by timely responses to user feedback and adjustments to recommendation strategies, strengthening user trust and satisfaction. Resource allocation is optimized; more accurate parking recommendations reduce the time users spend searching for parking spaces, helping to alleviate urban traffic pressure and improve the efficiency of parking resource utilization. The collaborative filtering technology addresses the cold start problem for new users or those with limited data, providing them with suitable parking recommendations more quickly. This technical solution not only enhances the personalized user experience but also improves the overall system efficiency and recommendation accuracy through continuous learning and optimization.

[0073] One embodiment of the present invention provides an intelligent parking reservation control and adjustment method, which acquires user information with a parking space reservation requirement, the user information including: the user's license plate number and the user's current location, and selects a parking space for the user based on a scoring model, including:

[0074] Obtain user information that requires parking space reservations, including: user license plate number, user vehicle size, and user current location;

[0075] The system retrieves all available parking spaces within a distance of the user's current location that does not exceed a preset distance threshold. It also retrieves the weather forecast for the user's reserved parking time period via API. Finally, it recommends parking spaces based on a rating calculated using a rating model. Specifically, the rating model is as follows:

[0076]

[0077] in, This indicates the rating of the parking space. , , , , and Representing the weight of each sub-rating, Indicates the distance adjustment factor. Indicates the difficulty level of parking. This represents the weather adjustment factor. This indicates the coverage facility bonus factor. This represents the time sensitivity coefficient. Indicates the safety factor;

[0078]

[0079] in, This represents the driving distance from the user's current location to the parking space p. This is the distance sensitivity coefficient;

[0080]

[0081] in, The parking difficulty index can be represented by the average historical parking time for that parking space, with θ representing the difficulty sensitivity coefficient.

[0082]

[0083] in, This indicates the impact of weather on the availability of the parking space. Indicates the weather sensitivity coefficient;

[0084]

[0085] Where s(p) represents the safety index of the parking space, and μ represents the safety weighting coefficient;

[0086]

[0087] Where λ represents the time sensitivity coefficient, T is the period (24 hours in a day), and t is the current time, which needs to be converted to a decimal form in hours. C represents the phase shift, adjusted according to the specific time when the demand peak begins; C represents the vertical shift.

[0088] In one embodiment of the present invention, obtaining user feedback on recommended parking spaces and updating the weights in the rating model based on user feedback includes:

[0089] Initialize each user's preference vector P u ;

[0090] For each parking request, the user's feedback rating for the recommended parking space is obtained, and the user preference weights are updated based on a dynamic weight learning model. Specifically, the dynamic weight learning model is as follows:

[0091]

[0092] in, It is the weight of user u on factor i at time step t. It's the learning rate. It is the user's feedback rating for the current recommendation. It is the average feedback score. This is the score of the currently recommended parking space on factor i. It is the average score of factor i.

[0093] In one embodiment of the present invention, the weights of each user application collaborative filtering enhancement are updated again at preset time intervals, including:

[0094] Find the k most similar users to the user whose weight has been updated;

[0095] The updated weights of users are calculated based on a collaborative filtering model. Specifically, the collaborative filtering model is as follows:

[0096]

[0097] in, η is the weight of user u to factor i, and η is the learning rate. The weights, incorporating collaborative information, represent a balance between individual and group preferences. Let be the k most similar users of user u, and sim(u,v) be the similarity between users u and v.

[0098] One embodiment of the present invention provides an intelligent parking reservation control and adjustment system, the system comprising:

[0099] The recommended parking space module is used to obtain user information that requires a parking space reservation. The user information includes: user license plate number, user vehicle model and user current location. Based on a scoring model, parking spaces are recommended to the user.

[0100] The weight update module is used to obtain user feedback on recommended parking spaces and update the weights in the rating model based on the user feedback.

[0101] The enhanced weight update module is used to update the weights of each user again at preset intervals by applying collaborative filtering enhancements.

[0102] In one embodiment of the present invention, an intelligent parking reservation control and adjustment system is provided, wherein the parking space recommendation module includes:

[0103] The user information acquisition module is used to acquire user information who have a parking space reservation requirement. The user information includes: user license plate number, user vehicle size, and user current location.

[0104] The rating module is used to obtain all available parking spaces within a distance of the user's current location that does not exceed a preset distance threshold. It also retrieves the weather forecast for the user's reserved parking time period via API. Based on a rating model, it calculates a rating to recommend parking spaces to the user. Specifically, the rating model is as follows:

[0105]

[0106] in, This indicates the rating of the parking space. , , , , and Representing the weight of each sub-rating, Indicates the distance adjustment factor. Indicates the difficulty level of parking. This represents the weather adjustment factor. This indicates the coverage facility bonus factor. This represents the time sensitivity coefficient. Indicates the safety factor;

[0107]

[0108] in, This represents the driving distance from the user's current location to the parking space p. This is the distance sensitivity coefficient;

[0109]

[0110] in, The parking difficulty index can be represented by the average historical parking time for that parking space, with θ representing the difficulty sensitivity coefficient.

[0111]

[0112] in, This indicates the impact of weather on the availability of the parking space. Indicates the weather sensitivity coefficient;

[0113]

[0114] Where s(p) represents the safety index of the parking space, and μ represents the safety weighting coefficient;

[0115]

[0116] Where λ represents the time sensitivity coefficient, T is the period (24 hours in a day), t is the current time (which needs to be converted to a decimal form in hours), ϕ is the phase offset (adjusted according to the specific time when the demand peak begins), and C is the vertical offset.

[0117] In one embodiment of the present invention, an intelligent parking reservation control and adjustment system is provided, wherein the weight update module includes:

[0118] The preference vector initialization module is used to initialize the preference vector P for each user. u ;

[0119] The weight calculation and update module is used to obtain the user's feedback rating for the recommended parking space for each parking request, and update the user preference weights based on a dynamic weight learning model. Specifically, the dynamic weight learning model is as follows:

[0120]

[0121] in, It is the weight of user u on factor i at time step t. It's the learning rate. It is the user's feedback rating for the current recommendation. It is the average feedback score. This is the score of the currently recommended parking space on factor i. The average score of factor i

[0122] In one embodiment of the present invention, an intelligent parking reservation control and adjustment system includes an enhanced update weight module comprising:

[0123] The module for obtaining similar users is used to obtain the k most similar users to the user whose weight has been updated.

[0124] The filter weight calculation module is used to calculate the updated weights of users based on a collaborative filtering model. Specifically, the collaborative filtering model is:

[0125]

[0126] in, η is the weight of user u to factor i, and η is the learning rate. The weights, incorporating collaborative information, represent a balance between individual and group preferences. Let be the k most similar users of user u, and sim(u,v) be the similarity between users u and v.

[0127] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for intelligent parking reservation control and adjustment, characterized in that, The method includes: The system retrieves user information that indicates a need to reserve a parking space, including the user's license plate number, vehicle model size, and current location. Based on a rating model, it then recommends parking spaces to the user. Obtain information on users who need to reserve parking spaces; The system retrieves all available parking spaces within a distance of the user's current location that does not exceed a preset distance threshold. It also retrieves the weather forecast for the user's reserved parking time period via API. Finally, it recommends parking spaces based on a rating calculated using a rating model. Specifically, the rating model is as follows: ， in, This indicates the rating of the parking space. , , , , Representing the weight of each sub-rating, Indicates the distance adjustment factor. Indicates the difficulty level of parking. This indicates the weather adjustment factor. This represents the time sensitivity coefficient. Indicates the safety factor; ， in, This represents the driving distance from the user's current location to the parking space p. This is the distance sensitivity coefficient; ， in, The parking difficulty index is represented by the average time spent parking in that space historically, with θ representing the difficulty sensitivity coefficient. ， in, This indicates the impact of weather on the availability of the parking space. Indicates the weather sensitivity coefficient; ， Where s(p) represents the safety index of the parking space, and μ represents the safety weighting coefficient; ， Where λ represents the time sensitivity coefficient, T is the period (24 hours in a day), and t is the current time, which needs to be converted to a decimal form in hours. C represents the phase shift, which is adjusted according to the specific time when the demand peak begins; C represents the vertical shift. Obtain user feedback on recommended parking spaces, and update the weights in the rating model based on the user feedback; including: Initialize each user's preference vector P u ; For each parking request, the user's feedback rating for the recommended parking space is obtained, and the user preference weights are updated based on a dynamic weight learning model. Specifically, the dynamic weight learning model is as follows: ， in, It is the weight of user u on factor i at time step t. It's the learning rate. It is the user's feedback rating for the current recommendation. It is the average feedback score. This is the score of the currently recommended parking space on factor i. The average score of factor i; At preset intervals, the weights for collaborative filtering enhancement for each user application are updated again; including: Find the k most similar users to the user whose weight has been updated; The updated weights of users are calculated based on a collaborative filtering model. Specifically, the collaborative filtering model is as follows: ， in, η is the weight of user u to factor i, and η is the learning rate. The weights, incorporating collaborative information, represent a balance between individual and group preferences. Let be the k most similar users of user u, and sim(u,v) be the similarity between users u and v.

2. An intelligent parking reservation control and adjustment system, characterized in that, The system includes: The parking space recommendation module is used to obtain user information that requires a reserved parking space. This user information includes: the user's license plate number, vehicle size, and current location. Based on a rating model, the module recommends parking spaces to the user. The parking space recommendation module includes: The user information acquisition module is used to acquire user information who have a need to reserve parking spaces; The rating module is used to obtain all available parking spaces within a distance of the user's current location that does not exceed a preset distance threshold. It retrieves the weather forecast for the user's reserved parking time period via API. Based on a rating model, it recommends parking spaces to the user. Specifically, the rating model is as follows: ， in, This indicates the rating of the parking space. , , , , Representing the weight of each sub-rating, Indicates the distance adjustment factor. Indicates the difficulty level of parking. This indicates the weather adjustment factor. This represents the time sensitivity coefficient. Indicates the safety factor; ， in, This represents the driving distance from the user's current location to the parking space p. This is the distance sensitivity coefficient; ， in, The parking difficulty index is represented by the average time spent parking in that space historically, with θ representing the difficulty sensitivity coefficient. ， in, This indicates the impact of weather on the availability of the parking space. Indicates the weather sensitivity coefficient; ， Where s(p) represents the safety index of the parking space, and μ represents the safety weighting coefficient; ， Where λ represents the time sensitivity coefficient, T is the period (24 hours in a day), and t is the current time, which needs to be converted to a decimal form in hours. C represents the phase shift, which is adjusted according to the specific time when the demand peak begins; C represents the vertical shift. A weight update module is used to obtain user feedback on recommended parking spaces and update the weights in the rating model based on the user feedback; the weight update module includes: The preference vector initialization module is used to initialize the preference vector P for each user. u ; The weight calculation and update module is used to obtain the user's feedback rating for the recommended parking space for each parking request, and update the user preference weights based on a dynamic weight learning model. Specifically, the dynamic weight learning model is as follows: ， in, It is the weight of user u on factor i at time step t. It's the learning rate. It is the user's feedback rating for the current recommendation. It is the average feedback score. This is the score of the currently recommended parking space on factor i. It is the average score of factor i; The enhanced weight update module is used to update the weight of each user again at preset time intervals by applying collaborative filtering enhancement; the enhanced weight update module includes: The module for obtaining similar users is used to obtain the k most similar users to the user whose weight has been updated. The filter weight calculation module is used to calculate the updated weights of users based on a collaborative filtering model. Specifically, the collaborative filtering model is: ， in, η is the weight of user u to factor i, and η is the learning rate. The weights, incorporating collaborative information, represent a balance between individual and group preferences. Let be the k most similar users of user u, and sim(u,v) be the similarity between users u and v.

Images