Parking lot parking recommendation method

Abstract

The invention discloses a parking lot parking recommendation method comprising the steps that all parking record information of a user in a preset historical time period is acquired, and each piece of parking record information comprises position information of a parking lot and a parking time period type corresponding to parking time; when a user triggers a parking demand signal, traversing the parking record information for matching according to the parking time period type to which the triggering time belongs to obtain a plurality of key parking lots; determining a maximum circumcircle of an area formed by connecting all the key parking lots as a core parking area, and determining all the parking lots with idle parking spaces as target parking lots; determining a parking recommendation value of the target parking lot according to the vehicle flow rate, the number of idle parking spaces, the charging unit price and the distance value of the target parking lot; and selecting a preset number of target parking lots with high parking recommendation values to form a recommended parking lot list, and pushing the recommended parking lot list to the user side. Therefore, the parking lot can be individually recommended according to the parking time period type of the user, and the parking efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of parking recommendation, and particularly to a parking recommendation method for a parking lot. Background Art

[0002] With the development of society, cars have become more and more popular and gradually entered every family. While cars bring a lot of convenience to people's lives, they also bring a series of problems. Especially in bustling cities, on the one hand, there are many vehicles and few parking spaces. People can only drive to the scene to confirm whether there is a parking space. When the parking lot is full, it brings inconvenience to parking, and at the same time leads to the phenomenon of random parking, which is likely to cause traffic congestion and traffic accidents. Summary of the Invention

[0003] This application provides a parking recommendation method for a parking lot, which can recommend parking lots personalized according to the type of user's parking time period, and improve parking efficiency.

[0004] This application provides a parking recommendation method for a parking lot, including: S101, obtaining all parking record information of the user within a preset historical time period. Each parking record information includes the location information of the parking lot and the type of parking time period corresponding to the parking time. The types of parking time periods include weekday morning rush hour, weekday evening rush hour, weekday regular, and weekend regular; S102, when the user triggers a parking demand signal, traverse the parking record information for matching according to the type of parking time period to which the trigger time belongs, and obtain several key parking lots; S103, determining the largest circumscribed circle of the area formed by connecting all the key parking lots as the core parking area, and obtaining all the parking lots with available parking spaces within the core parking area and determining them as target parking lots; S104, determining the parking recommendation value of the target parking lot according to the vehicle flow rate, the number of available parking spaces, the charging unit price, and the distance value of the target parking lot; S105, sorting the parking recommendation values of all the target parking lots in descending order, and selecting the top preset number of target parking lots to form a recommended parking lot list and push it to the user terminal.

[0005] Preferably, the traversing the parking record information for matching according to the type of parking time period to which the trigger time belongs and obtaining several key parking lots specifically includes: A1. Matching the parking lots with the same type of parking time period in all the parking record information corresponding to the user according to the type of parking time period to which the trigger time belongs, and recording them as the first parking lots; A2. Calculating the density value of the user's parking in each first parking lot within the preset historical time period according to the following formula: , where is the density value of the i-th first parking lot, is the number of times a user parks at the i-th first parking lot within a preset historical time period, and N is the total number of first parking lots, is the total number of times a user parks at all first parking lots within a preset historical time period; A3. Determine all first parking lots with density values greater than a preset threshold as key parking lots.

[0006] Preferably, the vehicle flow rate of the target parking lot is calculated according to the following formula: , where is the vehicle flow rate of the target parking lot within the current time window, is the vehicle flow rate of the target parking lot within the previous time window, are the numbers of vehicles entering and leaving the target parking lot within the current time window respectively, L is the length of the time window, is the smoothing index, which ranges from 0 to 1 and is used to balance the influence of the current time window and the historical time window on the vehicle flow rate.

[0007] Preferably, in S104, the parking recommendation value of the target parking lot is calculated according to the following formula: , where S is the parking recommendation value of the target parking lot, is the vehicle flow rate of the target parking lot within the current time window, y is the current number of available parking spaces in the target parking lot, Y is the total number of parking spaces in the target parking lot, Mmax is the maximum value of the charging unit price in the corresponding parking area, M is the charging unit price of the target parking lot, D is the distance value between the target parking lot and the user's current location, , , , θ are the influence weight factors of the vehicle flow rate, the number of available parking spaces, the distance value, and the charging unit price on the parking recommendation value respectively.

[0008] Preferably, the method further includes: S201. Taking each key parking lot as the center, delineate an alternative parking area according to a preset radius, and each key parking lot corresponds to an alternative parking area; S202. Determine the parking lots with available parking spaces in all alternative parking areas as target parking lots, and assign a regional label to each target parking lot to distinguish the parking area it belongs to; among them, the parking area includes a core parking area and several alternative parking areas; S203. Obtain the regional dynamic parking index of each parking area based on the total number of parking times of the user in all parking lots in each parking area within a preset historical time period and the vehicle flow rate of each parking area within the current time window.

[0009] Preferably, the regional dynamic parking index of each said parking area is calculated according to the following formula: , where is the vehicle flow rate of vehicles entering and leaving at the boundary of each parking area, T0 is the total number of parking times of the user in all parking lots in this parking area within the preset historical time period, t1 is the length of the preset historical time period, is the preset influence weight value.

[0010] Preferably, after the S104, the method further includes: Determine the regional dynamic parking index of the parking area to which the target parking lot belongs according to the area label of the target parking lot, multiply the parking recommendation value of the target parking lot by its corresponding regional dynamic parking index, and obtain a new parking recommendation value to replace the original parking recommendation value.

[0011] Preferably, after the S105, the method further includes: S301. Periodically obtain the real-time position of the user based on a preset unit time period; S302. Obtain the distance ratio between the user and each parking area according to the distance relationship between the real-time position of the user and the center points of each parking area, specifically: , where r is the distance ratio between the current user and each parking area, d1 is the actual distance value between the current user and the center point of the corresponding parking area, and R is the radius value of the corresponding parking area; S303. Obtain the tendency value between the user and each parking area based on the distance ratio between the user and each parking area; S304. Execute step S203 to obtain the current regional dynamic parking index of each parking area, multiply it by its corresponding tendency value respectively, and update and replace the original regional dynamic parking index; S305. Execute steps S104 to S105, update the recommended parking lot list every unit time period, and periodically update and push the recommended parking lot list for the user until it is detected that the user drives into a certain target parking lot, and then stop pushing.

[0012] Preferably, obtaining the tendency value between the user and each parking area based on the distance ratio between the user and each parking area is specifically as follows: TV = 1 / (1 + r), where TV is the tendency value between the user and each parking area, and r is the distance ratio between the current user and each parking area.

[0013] Preferably, in S303, it further includes: C1. Obtaining the change index of the tendency value between the user and each parking area according to the following formula: , where is the change index of the tendency value between the user and each parking area at present, and j is the serial number of the current corresponding unit time period; C2. Summing the tendency value between the user and each parking area and its corresponding change index respectively, and replacing the original tendency value.

[0014] One or more technical solutions provided in this application have at least the following technical effects or advantages: Matching the core parking area in the historical parking record information by using the type of parking time period to which the time when the user triggers the parking signal belongs, so as to realize personalized search for the target parking lot, improve the parking efficiency and success rate, greatly reduce the time for the user to search for a parking space, and enhance the user experience; by obtaining the vehicle flow rate, the number of available parking spaces, the charging unit price of the target parking lot and the distance value from the user's current location, and calculating the parking recommendation value by combining these parameters, it can provide the user with a comprehensive and objective parking lot recommendation list, which is not only based on the user's personal historical parking habits, but also takes into account the real-time situation of the parking lot, helping the user quickly make the best choice range among many parking lots, meeting the personalized needs, and ensuring the parking efficiency and cost-effectiveness; Not limited to the core parking area determined by the time period type and parking records, it also determines the alternative parking areas centered on each key parking lot, thus forming multiple different parking areas, expanding the range of parking areas that can be recommended to the user. Based on the key parking lots determined by the historical parking records, it improves the diversity and selectivity of the parking lots; by introducing the regional dynamic parking index of the parking area to which the target parking lot belongs to adjust the parking recommendation value of the target parking lot, it not only considers the characteristics of the parking lot itself, but also combines the dynamic situation of the parking area where it is located; By periodically monitoring the real-time location of the user, the dynamic relationship between the user and each parking area can be reflected in real time; by introducing the distance ratio and the tendency value, the regional dynamic parking index of the parking area is dynamically adjusted, and the dynamic relationship between the user and the parking area is quantified, so that the recommended parking lot list strategy can be flexibly adjusted according to the actual driving situation of the user; the dynamically updated parking lot recommended list can more accurately meet the actual needs of the user during driving and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 FIG. is a schematic flow chart of a parking recommendation method for a parking lot according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] To facilitate the understanding of the present invention, the present application will be described more comprehensively with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, however, the present invention may be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0017] It should be noted that the terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only embodiments.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs; the terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0019] Embodiment 1: Figure 1 FIG. is a schematic flow chart of a parking recommendation method for a parking lot according to an embodiment of the present invention.

[0020] As Figure 1 shown, a parking recommendation method for a parking lot includes the following steps: S101, obtaining all parking record information of the user within a preset historical time period, and each parking record information includes the location information of the parking lot and the parking time period type corresponding to the parking time.

[0021] Among them, the parking time period type is set according to expert experience or the personal time law of the user, and specifically includes the early peak of weekdays, the late peak of weekdays, the regular of weekdays, and the regular of weekends. The preset historical time period is set to the past year and can be adjusted according to the actual situation.

[0022] Specifically, all parking record information of the user within a preset historical time period is stored in the user's client. Through big data analysis, the user's personal time pattern can be analyzed. For example, if the working hours of user A on weekdays are from 7:00 to 9:00, then the parking record information during this period corresponds to the morning rush hour of user A on weekdays; if the working hours of user A on weekdays are from 17:00 to 19:00, then the parking record information during this period corresponds to the evening rush hour of user A on weekdays; and the parking record information during the remaining time period on weekdays corresponds to the regular workday of user A.

[0023] S102. When the user triggers a parking demand signal, according to the type of parking time period to which the trigger time belongs, traverse the parking record information for matching to obtain a number of key parking lots.

[0024] Specifically, according to the type of parking time period to which the trigger time belongs, traverse the parking record information for matching to obtain a number of key parking lots, including: A1. According to the type of parking time period to which the trigger time belongs, match the parking lots with the same type of parking time period in all the parking record information corresponding to the user, and record them as the first parking lots.

[0025] A2. Calculate the density value of the user's parking in each first parking lot within the preset historical time period according to the following formula: , where is the density value of the i-th first parking lot, is the number of times the user parks in the i-th first parking lot within the preset historical time period, N is the total number of first parking lots, is the total number of times the user parks in all first parking lots within the preset historical time period.

[0026] A3. Determine the first parking lots with all density values greater than the preset threshold as key parking lots.

[0027] In other embodiments of the present invention, the parking record information further includes attribute label information of the parking lot. The attribute label information is set according to the electronic map. Specifically: obtain all key environmental information within 3KM of the parking lot in the electronic map, and set the attribute label information according to the business type to which the key environmental information belongs. For example, if the key environmental information includes XX Building and XX Hospital, then the corresponding business types of the key environmental information are office building and hospital respectively. Among them, the business type to which the key environmental information belongs is defined according to the actual situation, and the present invention does not limit this.

[0028] Specifically, the user side is also set with a voice recognition function, and step S102 further includes: when the user voice information is recognized, traverse the attribute tag information in the parking record information for text matching to obtain several key parking lots. For example, when "hospital" is recognized, based on all the attribute tag information in the parking record information, text matching can be performed, and a large language model can be used for recognition. The parking lots corresponding to all the attribute tag information that is semantically similar or the same as "hospital" are recorded as the first parking lots, and then the content of A2 to A3 is executed to obtain the key parking lots.

[0029] S103. Determine the largest circumscribed circle of the area formed by connecting all the key parking lots as the core parking area, and obtain all the parking lots with available parking spaces within the core parking area and determine them as the target parking lots.

[0030] S104. Determine the parking recommendation value of the target parking lot according to the vehicle flow rate, the number of available parking spaces, the charging unit price, and the distance value of the target parking lot.

[0031] Specifically, step S104 specifically includes: B1. Calculate the vehicle flow rate of the target parking lot according to the following formula: , where is the vehicle flow rate of the target parking lot within the current time window, is the vehicle flow rate of the target parking lot within the previous time window, are the number of vehicles entering and leaving the target parking lot within the current time window respectively, L is the length of the time window, for example, it can be set to 30 minutes, is the smoothing exponent, which ranges from 0 to 1 and is used to balance the influence of the current time window and the historical time window on the vehicle flow rate.

[0032] Among them, the time window is set to 30 minutes, and the current time window is set to the 30 minutes closest to the current time. It should be noted that for the first time window (t = 1), since there is no vehicle flow rate R(t - 1) of the previous time window, the vehicle flow rate of the corresponding first time window yesterday can be determined as R(t - 1).

[0033] By combining the vehicle flow rate of the previous time window, the data fluctuation of the current time window can be smoothed. The traffic flow often has certain fluctuations, especially large changes may occur in a short period of time. By introducing the data of the previous time window, the influence of this short-term fluctuation on the calculation result can be reduced. Considering the data of the previous time window can provide more context information, thereby improving the prediction accuracy and making the estimation of the vehicle flow rate more stable and reliable.

[0034] A high vehicle flow rate usually means that a large number of vehicles enter and exit the target parking lot in a short period of time, which may indicate that the target parking lot is very busy. For users looking for parking spaces, a parking lot with a high vehicle flow rate may mean that it is more difficult to find an empty parking space, or that vehicles need to be moved more frequently to avoid blocking other vehicles, thus affecting the convenience and efficiency of parking.

[0035] B2. Obtain the total number of parking spaces, the current number of available parking spaces, the hourly charging unit price, and the distance value from the user's current location in the target parking lot. Combine the vehicle flow rate of the target parking lot and calculate the parking recommendation value of the target parking lot according to the following formula: , where S is the parking recommendation value of the target parking lot, is the vehicle flow rate of the target parking lot within the current time window, y is the current number of available parking spaces in the target parking lot, Y is the total number of parking spaces in the target parking lot, Mmax is the maximum value of the charging unit price in the corresponding parking area, M is the charging unit price of the target parking lot, D is the distance value between the target parking lot and the user's current location, 、 、 、θ are the influence weight factors of the vehicle flow rate, the number of available parking spaces, the distance value, and the charging unit price on the parking recommendation value, which are set according to the actual situation and expert experience, and the present invention does not limit and elaborate on this.

[0036] It should be noted that Specifically: By dividing the vehicle flow rate by the number of available parking spaces plus 1 (to avoid division by zero), in fact, it is considering the vehicle flow rate relative to the available parking spaces. The fewer the available parking spaces, the greater the impact of the vehicle flow rate, which is reflected in the decrease of the exponential term, thus reducing the parking recommendation value. Connecting the vehicle flow rate of the target parking lot with its number of available parking spaces, it can be understood that can be used as a dynamic parameter factor to adjust the size, making the parking recommendation value more in line with the actual situation.

[0037] S105. Sort the parking recommendation values of all target parking lots in descending order, and select the top preset number of target parking lots to form a recommended parking lot list and push it to the user terminal.

[0038] The technical solutions in the embodiments of the present application above have at least the following technical effects or advantages: By matching the core parking area in the historical parking record information according to the type of the parking time period to which the time when the user triggers the parking signal belongs, it is possible to circle the core parking area that conforms to the current time period type for the user by analyzing the user's personalized historical parking habits, thereby realizing personalized search for the target parking lot, improving the parking efficiency and success rate, greatly reducing the time for the user to search for a parking space, and enhancing the user experience; By obtaining the vehicle flow rate, the number of available parking spaces, the charging unit price of the target parking lot, and the distance value from the user's current location, and calculating the parking recommendation value by combining these parameters, it comprehensively considers the convenience (distance), cost (charging unit price), availability (number of available parking spaces), and the busyness (vehicle flow rate) of the parking lot, and can provide the user with a comprehensive and objective list of parking lot recommendations. This list is not only based on the user's personal historical parking habits, but also takes into account the real-time situation of the parking lot, helping the user quickly make the best selection range among many parking lots, meeting the personalized needs, and ensuring the parking efficiency and cost-effectiveness.

[0039] Embodiment 2: Embodiment 1 only recommends the parking lot list based on the core parking area composed of the key parking lots determined by relying on the historical parking records. However, there are certain limitations in the range selection of the core parking area. The area is too limited, resulting in fewer choices of parking lots. If there are too few target parking lots that meet the conditions, then calculating and sorting the parking recommendation value is not very meaningful, resulting in waste of resources and affecting the parking recommendation efficiency. With the continuous change of the urban traffic situation, a single parking lot recommendation method can no longer meet the parking needs of modern cities.

[0040] Therefore, the embodiment of the present application is optimized on the basis of the above embodiment.

[0041] In some embodiments, before step S104, it further includes: S201, taking each key parking lot as the center, defining an alternative parking area according to a preset radius, and each key parking lot corresponds to an alternative parking area.

[0042] Among them, the alternative parking areas need to be de-duplicated with the core parking area, and the de-duplicated alternative parking areas are determined as the new alternative parking areas to replace the original alternative parking areas, so as to ensure the independence of each alternative parking area and avoid the intersection of the alternative parking areas and the core parking area.

[0043] S202, determining the parking lots with available parking spaces in all alternative parking areas as target parking lots, and assigning a regional label to each target parking lot to distinguish the parking area to which it belongs (collectively referring to the core parking area and several alternative parking areas as the parking area).

[0044] S203. Obtain the regional dynamic parking index of each parking area based on the total number of parking times of the user in all parking lots in each parking area within a preset historical time period and the vehicle flow rate in each parking area within the current time window.

[0045] Specifically, the regional dynamic parking index of each parking area is calculated according to the following formula: , where is the vehicle flow rate of vehicles entering and leaving at the boundary of each parking area within the current time window. Specifically, the calculation method in step B1 can be referred to, and the target parking lot is replaced with the parking area. This embodiment will not be elaborated. T0 is the total number of parking times of the user in all parking lots within the preset historical time period in this parking area, and t1 is the length of the preset historical time period. is the preset influence weight value, which is used to adjust the influence degree of the vehicle flow rate on the regional dynamic parking index.

[0046] Thus, the lower the vehicle flow rate of the parking area and the more the total number of parking times, the higher the regional dynamic parking index of this parking area.

[0047] In some embodiments, after step S104, it further includes: Determine the regional dynamic parking index of the parking area to which the target parking lot belongs according to the regional label of the target parking lot, and multiply the parking recommendation value of the target parking lot by its corresponding regional dynamic parking index to obtain a new parking recommendation value to replace the original parking recommendation value.

[0048] The technical solutions in the embodiments of the present application at least have the following technical effects or advantages: It is no longer limited to the core parking areas determined by the time period type and parking records, but also determines alternative parking areas centered on each key parking lot, thus forming multiple different parking areas, expanding the scope of parking recommendations for users, and improving the diversity and selectivity of parking lots based on the key parking lots determined by historical parking records; By introducing the regional dynamic parking index of the parking area to which the target parking lot belongs, and considering the vehicle busyness (parking convenience) between different parking areas and the user's preference degree for this parking area, when calculating the parking recommendation value of the target parking lot, not only the characteristics of the parking lot itself are considered, but also the dynamic situation of the parking area where it is located is combined to adapt to the changing urban road environment, further improving the accuracy, dynamics and comprehensiveness of parking recommendations.

[0049] Embodiment 3: The foregoing embodiments are intended to recommend a list of parking lots once when the user triggers a parking demand signal. However, it does not take into account that the complex and changeable nature of the actual traffic may cause unexpected changes in the user's driving route. When the user deviates from some of the delineated parking areas, the calculation of the parking recommendation values for all target parking lots in these parking areas may result in the final recommended parking lot list being unable to adapt to the dynamic change relationship between the user and the parking areas. The original recommendation strategy only makes one recommendation when the user triggers a parking demand signal and cannot adapt to the real-time change relationship between the user and each parking area during the driving process.

[0050] Therefore, the embodiment of the present application makes certain optimizations on the basis of the above embodiments.

[0051] In some embodiments, after step S105, that is, after successfully pushing the recommended parking lot list when the user triggers a parking demand signal, the method further includes: S301, Based on a preset unit time period, periodically obtain the user's real-time position. The preset unit time period is set to 5 minutes, that is, the user's real-time position is obtained every 5 minutes.

[0052] S302, According to the distance relationship between the user's real-time position and the center points of each parking area, obtain the distance ratio between the user and each parking area currently, specifically: r = , where r is the distance ratio between the current user and each parking area, d1 is the actual distance value between the current user and the center point of the corresponding parking area, and R is the radius value of the corresponding parking area.

[0053] It should be noted that the center point of each parking area is the center of the corresponding circle.

[0054] S303, Based on the distance ratio between the user and each parking area currently, obtain the tendency value between the user and each parking area currently, specifically: TV = 1 / (1 + r), TV is the tendency value between the user and each parking area currently, r is the distance ratio between the user and each parking area currently, so that when the user is closer to or approaching a certain parking area, the tendency value of this parking area is larger.

[0055] S304, Execute step S203 to obtain the current regional dynamic parking index of each parking area, and multiply it by its corresponding tendency value respectively to update and replace the original regional dynamic parking index.

[0056] Among them, the real-time trend value is multiplied by the periodically calculated regional dynamic parking index to achieve dynamic adjustment of the original regional dynamic parking index. Based on the adjusted regional dynamic parking index, the parking lot recommendation algorithm is periodically executed to obtain and update the recommended parking lot list corresponding to each unit time period. This adjustment method makes the parking lot recommendation more flexible, can adapt to the real-time changes during the user's driving process, and ensures the timeliness and accuracy of the recommendation list.

[0057] S305: Execute steps S104 to S105, update the recommended parking lot list every unit time period, so as to periodically update and push the recommended parking lot list to the user until it is detected that the user drives into a certain target parking lot and the push stops.

[0058] To better understand the parking lot parking recommendation method of the embodiments of the present invention, as an example, the method flow specifically includes: S401: User Zhang triggers a parking demand signal at 8 o'clock on Monday morning. This time belongs to the morning rush hour on weekdays. Obtain the parking record information of the past year on Zhang's user side, and traverse the parking record information according to the morning rush hour on weekdays to obtain the key parking lots: Parking Lot A, Parking Lot B, and Parking Lot C. Take the largest circumscribed circle of the area connected by the three parking lots as the core parking area, and demarcate a preparatory parking area centered on each key parking lot to obtain three preparatory parking areas. Finally, it is determined that there are four parking areas.

[0059] S402: Obtain all parking lots with available parking spaces in the four parking areas as target parking lots, obtain the regional dynamic parking index of the parking area to which the target parking lot belongs, multiply the parking recommendation value of the target parking lot by its corresponding regional dynamic parking index to obtain the parking recommendation value of the target parking lot, sort all target parking lots in descending order, and select the top 3 parking lots to form a recommended parking lot list and push it to Zhang's user side.

[0060] S403: Real-time obtain Zhang's real-time position, the regional dynamic parking index of each parking area, and the parking recommendation value of each target parking lot every 5 minutes, obtain the real-time distance ratio and trend value between Zhang and each parking area, multiply the trend value by the regional dynamic parking index of the corresponding parking area to update the regional dynamic parking index of each parking area, and at the same time update the parking recommendation value of each target parking lot, regenerate the recommended parking lot list and push it to the user side. Zhang periodically receives the recommended parking lot list during driving and finally decides to drive into Parking Lot D and stops the periodic push.

[0061] Therefore, the parking recommendation method for this parking lot can combine Zhang's parking habits and the dynamic relationship changes with each parking area during driving, efficiently and accurately match and recommend the parking lot list, save Zhang's time in finding a parking space, and improve the commuting efficiency.

[0062] The technical solutions in the above embodiments of the present application at least have the following technical effects or advantages: By periodically monitoring the user's real-time location, the dynamic relationship between the user and each parking area can be reflected in real time; by introducing the distance ratio and the trend value, the regional dynamic parking index of the parking area is dynamically adjusted, and the dynamic relationship between the user and the parking area is quantified, and the recommendation parking lot list strategy can be flexibly adjusted according to the user's actual driving situation; the dynamically updated parking lot recommendation list can more accurately meet the actual needs of the user during driving and improve the user experience.

[0063] Embodiment 4: In Embodiment 3, determining the trend value between the user and the corresponding parking area based on the distance ratio between the parking area and the user in a single current unit time period has certain limitations and cannot adapt to the dynamically changing driving trend of the user.

[0064] Therefore, the embodiment of the present application is optimized on the basis of the above embodiment.

[0065] In some embodiments, in step S303, it further includes: C1. Obtain the change index of the trend value between the user and each parking area according to the following formula: , where is the change index of the trend value between the user and each parking area at present, and j is the serial number of the current corresponding unit time period. For example, if the current corresponding unit time period is the 3rd unit time period, that is, the user's real-time location is obtained in real time for the 3rd time, then is the change index of the trend value between the user and each parking area at present, and 3 is the serial number of the current corresponding unit time period.

[0066] This formula takes into account the trend changes between the user and each parking area in the current unit time period j, and this change index is used to quantify the change in the degree of approach of the user to each parking area in consecutive unit time periods.

[0067] C2. Sum the trend values between the user and each parking area with their corresponding change indexes respectively to replace the original trend values.

[0068] For example, at the current moment, if a tendency value a between the user and a certain preparatory parking area is obtained based on the distance ratio between the user and the preparatory parking area, and the change index of the tendency value a between the user and the preparatory parking area is b, the value of a + b is used to replace the original tendency value a.

[0069] Specifically, the corresponding tendency value is adjusted by using the change index. The change situation of the distance ratio in multiple unit time periods is integrated and quantified into the change index. The larger the change index, the greater the possibility that the user is approaching the corresponding parking area at this time, so that the tendency value is larger. Thus, the tendency value is not only based on the static distance ratio, but also incorporates the dynamic change trend, which can accurately capture the user's real-time approaching intention, thereby improving the differentiation between parking areas and improving the accuracy and real-time performance of the recommendation.

[0070] The above is only the preferred embodiment of the present invention and is not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A parking lot recommendation method, characterized in that: include: S101, obtaining all parking record information of the user within a preset historical time period, each parking record information includes the location information of the parking lot and the parking time period type corresponding to the parking time, and the parking time period types include weekday morning peak, weekday evening peak, weekday regular, and weekend regular; S102, when a user triggers a parking demand signal, the parking record information is traversed and matched according to the parking time period type to which the triggering time belongs, to obtain several key parking lots; S103: determining the largest circumscribed circle of the area formed by connecting all key parking lots as the core parking area, obtaining all parking lots with vacant parking spaces in the core parking area and determining them as target parking lots; S104, determining a parking recommendation value of the target parking lot according to the vehicle turnover rate, the number of vacant parking spaces, the charging unit price, and the distance value of the target parking lot; S105, sorting the parking recommendation values ​​of all target parking lots in descending order, selecting a preset number of target parking lots at the front to form a recommended parking lot list and pushing it to the user end.

2. The parking lot recommendation method according to claim 1, characterized in that: According to the parking time period type to which the trigger time belongs, the parking record information is traversed for matching to obtain several key parking lots, specifically including: A1. According to the parking time period type to which the trigger time belongs, a parking lot with the same parking time period type is matched in all parking record information corresponding to the user, and the parking lot is recorded as the first parking lot; A2. Calculate the density of users parking in each first parking lot during a preset historical time period according to the following formula: ,in, is the density value of the i-th first parking lot, is the number of times the user parks in the i-th first parking lot during the preset historical time period, N is the total number of first parking lots, The total number of times the user has parked in all first parking lots within a preset historical time period; A3. The first parking lot whose density value is greater than a preset threshold is determined as a key parking lot.

3. The parking lot recommendation method according to claim 1, characterized in that: The vehicle turnover rate of the target parking lot is calculated according to the following formula: ,in, is the vehicle turnover rate of the target parking lot in the current time window, is the vehicle turnover rate of the target parking lot in the previous time window, are the number of vehicles entering and leaving the target parking lot in the current time window, L is the length of the time window, It is a smoothing index between 0 and 1, which is used to balance the impact of the current time window and the historical time window on the vehicle flow rate.

4. The parking lot recommendation method according to claim 3, characterized in that: In S104, the parking recommendation value of the target parking lot is calculated according to the following formula: , where S is the parking recommendation value of the target parking lot, is the vehicle turnover rate of the target parking lot in the current time window, y is the current number of free parking spaces in the target parking lot, Y is the total number of parking spaces in the target parking lot, Mmax is the maximum charging unit price in the corresponding parking area, M is the charging unit price of the target parking lot, D is the distance between the target parking lot and the user's current location, , , , θ are the weight factors affecting the parking recommendation value, namely, vehicle turnover rate, number of vacant parking spaces, distance value, and charging unit price.

5. The parking lot recommendation method according to claim 1, characterized in that: Before S104, the method further includes: S201, taking each key parking lot as the center, defining an alternative parking area according to a preset radius, and each key parking lot corresponds to an alternative parking area; S202, all parking lots with vacant parking spaces in the candidate parking areas are also determined as target parking lots, and each target parking lot is given an area label to distinguish the parking area to which it belongs; wherein the parking area includes a core parking area and a plurality of candidate parking areas; S203, obtaining a regional dynamic parking index for each parking area according to the total number of parking times of users in all parking lots in each parking area within a preset historical time period and the vehicle turnover rate of each parking area within a current time window.

6. The parking lot recommendation method according to claim 5, characterized in that: The regional dynamic parking index of each parking area is calculated according to the following formula: ,in, is the vehicle flow rate entering and exiting the boundary of each parking area, T0 is the total number of times users park in all parking lots in the parking area within the preset historical time period, t1 is the length of the preset historical time period, is the preset influence weight value.

7. The parking lot recommendation method according to claim 6, characterized in that: After S104, the method further includes: The regional dynamic parking index of the parking area to which the target parking lot belongs is determined according to the regional label of the target parking lot, and the parking recommendation value of the target parking lot is multiplied by the regional dynamic parking index corresponding to the target parking lot to obtain a new parking recommendation value to replace the original parking recommendation value.

8. The parking lot recommendation method according to claim 5, characterized in that: After S105, the method further includes: S301, periodically obtaining a user's real-time location based on a preset unit time period; S302, according to the distance relationship between the user's real-time location and the center point of each parking area, obtain the distance ratio between the user and each parking area, specifically: , where r is the distance ratio between the current user and each parking area, d1 is the actual distance between the current user and the center point of the corresponding parking area, and R is the radius value of the corresponding parking area; S303, obtaining a trend value between the user and each parking area based on a distance ratio between the user and each parking area; S304, executing step S203 to obtain the current regional dynamic parking index of each parking area, and multiplying it by its corresponding trend value respectively, to update and replace the original regional dynamic parking index; S305, executing step S104 to step S105, updating the recommended parking lot list every unit time period, and periodically updating the recommended parking lot list pushed to the user until it is detected that the user drives into a target parking lot, and then stopping the push.

9. The parking lot recommendation method according to claim 8, characterized in that: Based on the distance ratio between the user and each parking area, the trend value between the user and each parking area is obtained, specifically: TV = 1 / (1 + r), TV is the trend value between the user and each parking area, and r is the distance ratio between the current user and each parking area.

10. The parking lot recommendation method according to claim 9, characterized in that: In the S303, it also includes: C1. Obtain the change index of the trend value between the user and each parking area according to the following formula: ,in, is the change index of the trend value between the user and each parking area, and j is the serial number of the current corresponding unit time period; C2. Sum the trend values ​​between the user and each parking area and their corresponding change indexes to replace the original trend values.

Images