Intelligent roadside parking scheduling method and system assisted by berth robot

Abstract

The invention provides a roadside parking intelligent scheduling method and system assisted by a parking robot, and relates to the technical field of intelligent parking, and the method comprises the steps: obtaining a plurality of parking spaces, and carrying out the classification marking according to the sizes and types of the parking spaces. And performing parking complexity analysis in combination with the multiple pieces of parking space type marking information, the parking space gradient information and the parking space neighborhood road information, performing parking level prediction on the first driver, and generating a first recommended parking space in combination with the multiple pieces of parking space size marking information, the first parking level prediction index and the multiple complexity indexes. And generating a first navigation route according to the first recommended parking space, and performing parking guidance according to the first navigation route through the parking robot. The technical problems that in the prior art, a parking robot does not consider the parking level difference of drivers, so that the difficulty of parking space recommendation is too high, and the user experience is poor are solved. The technical effect of improving the parking success rate and the user experience according to matching of the parking level of the driver and the parking space complexity is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent parking, and in particular to a method and system for intelligent dispatching of roadside parking assisted by a berth robot. Background Art

[0002] In the field of smart parking, parking robots, as an important tool to improve parking efficiency, usually rely on parking space availability information to recommend parking spaces. The advantage of this method is that it can provide information about available parking spaces in real time, helping drivers find parking spaces quickly. However, existing technologies mainly focus on the availability of parking spaces, but fail to fully consider the individual differences and parking abilities of drivers, resulting in excessive difficulty in recommending parking spaces and poor user parking experience.

[0003] The existing technology has a technical problem that the parking robot does not take into account the differences in parking skills of drivers, resulting in excessive difficulty in recommending parking spaces and poor user experience. Summary of the invention

[0004] The present application provides a method and system for intelligent dispatching of roadside parking assisted by a parking robot, which is used to solve the technical problem in the prior art that the parking robot does not take into account the differences in parking levels of drivers, resulting in excessive difficulty in recommending parking spaces and poor user experience.

[0005] In view of the above problems, the present application provides a method and system for intelligent scheduling of roadside parking assisted by a berth robot.

[0006] In a first aspect of the present application, a parking robot-assisted roadside parking intelligent scheduling method is provided, the method comprising: a parking robot connected to a first roadside parking area obtains a plurality of parking spaces, and classifies and marks them according to parking space size and parking space type, generating a plurality of parking space size marking information and a plurality of parking space type marking information; obtains a regional digital map of the first roadside parking area, wherein the regional digital map is marked with parking space slope information and parking space neighborhood road information; performs parking complexity analysis on the plurality of parking spaces in combination with the plurality of parking space type marking information, the parking space slope information and the parking space neighborhood road information, generating a plurality of complexity indicators; when a first vehicle enters the first roadside parking area, performs parking level prediction on the first driver, generating a first parking level prediction indicator; performs parking space matching in combination with the plurality of parking space size marking information, the first parking level prediction indicator and the plurality of complexity indicators, generating a first recommended parking space; generates a first navigation route according to the first recommended parking space, and performs parking guidance according to the first navigation route by the parking robot.

[0007] In a second aspect of the present application, a parking robot-assisted roadside parking intelligent scheduling system is provided, the system comprising: a parking space classification module, the parking space classification module is used to connect to a parking robot in a first roadside parking area to obtain multiple parking spaces, and classify and mark them according to parking space size and parking space type, and generate multiple parking space size marking information and multiple parking space type marking information; a digital map acquisition module, the digital map acquisition module is used to obtain a regional digital map of the first roadside parking area, wherein the regional digital map is marked with parking space slope information and parking space neighborhood road information; a parking complexity analysis module, the parking complexity analysis module is used to combine the multiple parking space type marking information, the parking space slope information and the parking space neighborhood road information to perform parking complexity analysis on the multiple parking spaces to generate multiple complexity indicators; a parking level prediction module, the parking level prediction module is used to predict the parking level of the first driver when the first vehicle enters the first roadside parking area, and generate a first parking level prediction indicator; a parking space matching module, the parking space matching module is used to match the parking spaces in combination with the multiple parking space size marking information, the first parking level prediction indicator and the multiple complexity indicators to generate a first recommended parking space; a navigation route generation module, the navigation route generation module is used to generate a first navigation route according to the first recommended parking space, and guide the parking robot to park according to the first navigation route.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The method provided in the embodiment of the present application obtains multiple parking spaces by connecting to a parking robot in a first roadside parking area, and classifies and marks them according to the parking space size and parking space type, generates multiple parking space size marking information and multiple parking space type marking information, and obtains a regional digital map of the first roadside parking area, wherein the regional digital map is marked with parking space slope information and parking space neighborhood road information. The parking complexity analysis of the multiple parking spaces is performed in combination with the multiple parking space type marking information, the parking space slope information and the parking space neighborhood road information, and multiple complexity indicators are generated. When the first vehicle enters the first roadside parking area, the parking level of the first driver is predicted to generate a first parking level prediction index, and the parking space is matched with the multiple parking space size marking information, the first parking level prediction index and the multiple complexity indicators to generate a first recommended parking space. A first navigation route is generated according to the first recommended parking space, and parking guidance is performed by the parking robot according to the first navigation route. The technical effect of matching the driver's parking level with the parking space complexity is achieved, thereby improving the parking success rate and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a process flow of a berth robot-assisted roadside parking intelligent scheduling method provided in this application;

[0012] Figure 2 A schematic diagram of the structure of a berth robot-assisted roadside parking intelligent scheduling system provided in this application.

[0013] Explanation of the reference numerals: parking space classification module 11 , digital map acquisition module 12 , parking complexity analysis module 13 , parking level prediction module 14 , parking space matching module 15 , navigation route generation module 16 . DETAILED DESCRIPTION

[0014] The present application provides a method and system for intelligent dispatching of roadside parking assisted by a parking robot, which is used to solve the technical problem in the prior art that the parking robot does not consider the differences in parking skills of drivers, resulting in excessive difficulty in recommending parking spaces and poor user experience. The method achieves the technical effect of matching the parking skills of drivers with the complexity of parking spaces, thereby improving the parking success rate and user experience.

[0015] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a berth robot-assisted roadside parking intelligent scheduling method, the method comprising:

[0017] The parking robot connected to the first roadside parking area obtains a plurality of parking spaces, and classifies and marks the parking spaces according to their sizes and types, thereby generating a plurality of parking space size marking information and a plurality of parking space type marking information.

[0018] Specifically, the parking robot is an intelligent automated device with advanced sensors, cameras and image recognition technology, which can monitor the parking space information of the parking area in real time. Through a wireless network or other communication methods, it is connected to the parking robot in the first roadside parking area to obtain the information of multiple available parking spaces in the area in real time. The parking robot classifies and marks multiple available parking spaces based on two key features: parking space size and parking space type. The parking space size refers to the actual size of each parking space, including parameters such as length, width and height, which are used to determine whether the parking space is suitable for different types of vehicles, such as small cars or large SUVs. The parking space types include vertical parking spaces, parallel parking spaces and diagonal parking spaces. Vertical parking spaces are usually arranged on both sides of the parking lot. It is relatively simple to enter and exit, and it is relatively easy to park, which is suitable for novice drivers. Parallel parking spaces require higher driving skills, especially on narrow streets, and require drivers to make multiple fine adjustments in a small space, which is relatively more difficult. While diagonal parking spaces are easier to park than parallel parking spaces, you still need to pay attention to the size of the surrounding space to ensure that the vehicle can enter smoothly. By classifying and marking the size and type of each parking space in detail, the parking robot generates multiple parking space size marking information and multiple parking space type marking information. By classifying and marking the parking spaces, it is possible to accurately evaluate the characteristics of each parking space, provide users with more accurate parking suggestions, and enhance the user's parking experience.

[0019] A regional digital map of the first roadside parking area is obtained, wherein the regional digital map is marked with parking space slope information and parking space neighborhood road information.

[0020] Specifically, the first roadside parking area is scanned by sensors such as GPS and laser radar, and a regional digital map of the first roadside parking area is obtained in combination with a reliable data source, such as a professional map service provider. The regional digital map is marked with parking space slope information and parking space neighborhood road information. The parking space slope information refers to the degree of inclination of each parking space relative to the horizontal plane, and the parking space area road information includes the road conditions around the parking space, such as the width of the road, traffic flow, and whether there are obstacles, etc., which can evaluate the difficulty of parking near a specific parking space. By obtaining the regional digital map, the parking robot's ability to understand the parking environment is improved, and it also provides drivers with safer and more convenient parking recommendations.

[0021] The parking space type marking information, the parking space slope information and the parking space neighborhood road information are combined to perform parking complexity analysis on the multiple parking spaces to generate multiple complexity indicators.

[0022] Specifically, the information of multiple parking space type markings is used as basic data to evaluate the initial parking difficulty, and then the parking space slope information is analyzed. In combination with the road information in the parking space area, factors such as the width of the adjacent roads, traffic flow and visibility are evaluated, and the parking complexity of multiple parking spaces is comprehensively analyzed to generate multiple complexity indicators. By obtaining the complexity index of the parking space, the parking difficulty of each parking space can be reflected, which provides a basis for subsequent parking space recommendations, so that the parking robot can provide more accurate and personalized parking suggestions based on the skill levels of different drivers, thereby improving the user's parking experience.

[0023] Furthermore, a parking complexity analysis is performed on the multiple parking spaces in combination with the multiple parking space type marking information, the parking space slope information and the parking space neighborhood road information to generate multiple complexity indices, including: initializing parking complexity according to the multiple parking space type marking information to generate multiple initialization difficulty indices; performing a parking impact analysis on the parking space slope information to establish a slope impact weight; performing a parking impact analysis on the parking space neighborhood road information to establish a neighborhood road impact weight; and performing weighted compensation on the multiple initialization difficulty indices using the slope impact weight and the neighborhood road impact weight to generate the multiple complexity indices.

[0024] Specifically, first, the parking complexity of each parking space is initialized according to the marking information of multiple parking space types. For example, vertical parking spaces are assigned a lower difficulty, while parallel parking spaces are marked as high difficulty and diagonal parking spaces are marked as medium difficulty to reflect the driving skills required, and obtain multiple initialization difficulty indicators. Then, the slope information of the parking space is analyzed to evaluate the inclination of each parking space, quantify the impact of the slope on the parking difficulty, and establish the slope impact weight. The larger the inclination angle of the parking space slope, the higher the impact weight. The parking impact analysis is performed on the parking space domain road information, which includes the domain road environment and domain road flow. The domain road environment refers to the environmental information near the parking space. For example, when there are obstacles near the parking space (such as other vehicles, street lights, etc.), it will limit the parking space, increase the difficulty of parking, and have a large impact weight. The domain road flow includes the traffic and pedestrian flow around the parking space. When the traffic and pedestrian flow are large, it will also directly affect the safety and convenience of parking. Based on the analysis results of the domain road environment and domain road flow, the neighborhood road impact weight is established to ensure that the complexity of the parking environment can be fully reflected. Finally, the obtained slope influence weight and domain road influence weight are applied to the initialization difficulty index, and multiple initialization difficulty indicators are processed by weighted compensation to generate multiple complexity indicators. The multiple complexity indicators can provide the parking robot with a comprehensive and accurate parking difficulty assessment, optimize parking space recommendations, and improve users' parking experience and satisfaction.

[0025] Furthermore, a parking impact analysis is performed on the parking space slope information to establish a slope impact weight, including: collecting multiple historical parking record data sets corresponding to parking spaces of the same type, wherein any historical parking record data set includes multiple parking records corresponding to the same parking space slope mark; calculating the average parking time of multiple parking records in the multiple historical parking record data sets, counting the proportion of data that exceeds the average parking time and has a deviation greater than a preset deviation, generating multiple proportion coefficients, and establishing a first mapping relationship table between the multiple proportion coefficients and parking space slope marks; inputting the parking space slope information into the first mapping relationship table, obtaining the proportion coefficient corresponding to the parking space slope mark with the greatest similarity to the parking space slope information, and generating the slope impact weight.

[0026] Specifically, multiple historical parking record data of the same type of parking spaces are extracted from a parking management system or a cloud database to form multiple historical parking record data sets. Each of the multiple historical parking record data sets contains multiple parking records of different time periods corresponding to the same parking space slope mark. The parking space slope mark refers to a label that identifies and classifies the degree of inclination of each parking space relative to the horizontal plane, which can reflect the slope characteristics of the parking space, such as flat, slightly inclined, medium inclined, and steep. Then, according to the multiple historical parking record data sets, the average parking time of multiple parking records is calculated, that is, the time required for parking vehicles in parking spaces under a specific slope is averaged to obtain the average required parking time. Then, a preset deviation threshold is set, and multiple parking records are compared with the parking time average, and the proportion of parking records that exceed the parking average and are greater than the preset deviation is counted to identify abnormal parking time under the influence of the slope. For example, if the parking time average of a parking space is 10 minutes and the preset deviation is 5 minutes, then any parking time exceeding 15 minutes will be regarded as a deviation greater than the preset deviation. According to the proportion data, multiple proportion coefficients are generated to reflect the actual impact of different slopes on parking time, and according to the proportion coefficients and parking space slope data, a first mapping relationship table of proportion coefficients and parking space slope marks is established to ensure that the abnormal proportion of parking time corresponding to each slope can be quickly queried. Finally, the parking space slope information is input into the first mapping relationship table, and the proportion coefficient corresponding to the slope mark with the greatest similarity to the input slope information is automatically obtained, thereby generating the slope impact weight and accurately quantifying the impact of the parking space slope on the stability of parking time and parking behavior. The same method is also applicable to neighborhood road analysis. By analyzing the historical parking records of neighborhood roads and calculating the impact coefficients related to the road environment and traffic, accurate and reliable neighborhood road impact weights can be obtained. By obtaining accurate slope impact weights and neighborhood road impact weights, the evaluation of parking complexity is further supplemented, providing more accurate and reliable decision support for parking management.

[0027] When the first vehicle enters the first roadside parking area, a parking level prediction is performed on the first driver to generate a first parking level prediction index.

[0028] Furthermore, when the first vehicle enters the first roadside parking area, a parking level prediction is performed on the first driver to generate a first parking level prediction index, including: connecting to a parking record database to extract historical parking records for the first driver; counting the first driver's historical parking success rate, historical parking time, and historical parking space type proportion according to the historical parking records; inputting the historical parking success rate, historical parking time, and historical parking space type proportion into a parking level evaluation model for evaluation and analysis to generate the first parking level prediction index.

[0029] Specifically, when the first vehicle enters the first roadside parking area, the parking robot extracts the historical parking record of the driver of the first vehicle by connecting to the parking record database, and the historical parking record includes the parking performance of the driver in different parking spaces. Then, the historical parking record is statistically analyzed to obtain the historical parking success rate, historical parking time and historical parking space type ratio of the first driver. The historical parking success rate refers to the ratio of the number of successful parking attempts of the first driver to the total number of parking attempts, the historical parking time is the time required for each parking attempt of the first driver, and the historical parking space type ratio refers to the usage ratio of the horizontal parking space, vertical parking space and inclined parking space of the first driver. Finally, the historical parking success rate, historical parking time and historical parking space type ratio are used as input data and input into the parking level evaluation model for comprehensive analysis. The parking level evaluation model uses machine learning or statistical analysis methods to perform weighted calculations on these indicators to generate the required first parking level prediction indicators. The first parking level prediction not only reflects the overall parking level of the first driver, but also provides data support for subsequent parking space recommendations, ensuring that more suitable parking suggestions can be provided to improve parking efficiency and user satisfaction.

[0030] Furthermore, the historical parking success rate, historical parking time and historical parking space type ratio are input into the parking level evaluation model for evaluation and analysis to generate the first parking level prediction index, including: the parking level evaluation model is connected to an evaluation sample library, wherein the evaluation sample library includes multiple groups of evaluation samples, any group of evaluation samples includes parking success rate samples, parking time samples and parking space type ratio samples, and corresponding evaluation identification information marked with parking level prediction indicators; the historical parking success rate, the historical parking time and the historical parking space type ratio are input into the parking level evaluation model, the evaluation sample library is called through the parking level evaluation model, the multiple groups of evaluation samples are traversed for sample matching, and the first parking level prediction index is generated.

[0031] Specifically, the parking level evaluation model is connected to the evaluation sample library, which is a data set containing multiple groups of parking behavior samples, and is used to support the analysis and prediction of the parking level evaluation model. Each group of evaluation samples in the evaluation sample library contains specific parking success rate samples, parking time samples, and parking space type proportion samples. In addition, each group of samples also has a corresponding marked parking level prediction index, that is, corresponding evaluation identification information, which reflects the parking performance and ability of different drivers under specific conditions. When the parking robot receives the historical parking data of the first driver, the historical parking success rate, the historical parking time, and the historical parking space type proportion are integrated as input data and input into the parking level evaluation model. The parking level evaluation model calls the evaluation sample library connected to it, and traverses and matches each group of evaluation samples in the evaluation sample library according to the input data, compares them with each group of samples in the sample library, and identifies samples similar to the historical parking success rate, historical parking time, and historical parking space type proportion. Through sample matching, the parking level evaluation model can find the sample group that is closest to the historical parking behavior of the first driver. Then, according to the matched evaluation sample group, the corresponding parking level prediction index is obtained. The generated first parking level prediction index provides the necessary information for the parking robot, so that it can recommend the most suitable parking space according to the actual parking level of the first driver, thereby improving the parking experience and efficiency.

[0032] The plurality of parking space size marking information, the first parking level prediction index and the plurality of complexity indexes are combined to perform parking space matching to generate a first recommended parking space.

[0033] Specifically, the parking space in which the first driver drives the vehicle is comprehensively matched according to the multiple parking space size marking information including the specific sizes of multiple parking spaces, combined with the first parking level prediction index reflecting the parking ability of the first driver and the multiple complexity indexes reflecting the parking difficulty of each parking space, and the suitability of each parking space is comprehensively evaluated to generate a first recommended parking space. The first recommended parking space can ensure that the recommended parking space matches the vehicle size, and the recommended parking space is not only suitable for the driver's parking level, but also can provide sufficient convenience and safety in the current environment, meet the driver's needs, and improve the user's parking experience and efficiency.

[0034] Furthermore, the multiple parking space size marking information, the first parking level prediction index and the multiple complexity indexes are combined to perform parking space matching to generate a first recommended parking space, including: capturing and identifying an image of the first vehicle through a camera in the first roadside parking area to generate first vehicle size information; comparing the first vehicle size information with the multiple parking space size marking information to locate a first matching parking space set; based on the multiple complexity indexes, obtaining a first matching parking space complexity index set corresponding to the first matching parking space set; performing parking space adaptation analysis and screening in combination with the first matching parking space complexity index set and the first parking level prediction index to generate the first recommended parking space.

[0035] Specifically, firstly, the first vehicle is imaged by a camera in the first roadside parking area, and the shape and size of the first vehicle are automatically identified based on the image recognition technology according to the collected vehicle image, so as to obtain the first vehicle size information. The first vehicle size information includes key size parameters such as vehicle length, width and height. Then, the first vehicle size information is compared with multiple parking space size marking information, and the size marking information of each parking space includes the specific requirements of the vehicle size and the vehicle type suitable for the parking space. Through the comparison, the first matching parking space set that meets the first vehicle size is located and obtained, and the first matching parking space set includes all parking spaces suitable for the vehicle in the first roadside parking area. Based on multiple complexity indicators obtained by analyzing the parking space slope, neighboring road conditions and historical parking records, a corresponding matching parking space complexity indicator is assigned to each matching parking space in the first matching parking space set to form a first matching parking space complexity indicator set, which reflects the parking difficulty of each matching parking space in terms of slope and field road conditions, so as to ensure that the actual parking conditions can be considered when recommending parking spaces. Finally, a parking space adaptation analysis and screening is performed based on the first matching parking space complexity index combined with the first parking level prediction index of the first driver, and the driver's parking ability and the complexity of the matching parking space are comprehensively analyzed to identify the parking space that best suits the first driver and generate a first recommended parking space to ensure that the recommended parking space meets both the vehicle size requirements and is suitable for the driver's parking level, thereby improving parking efficiency and user satisfaction.

[0036] Furthermore, a parking space adaptation analysis and screening is performed in combination with the first matching parking space complexity index set and the first parking level prediction index to generate the first recommended parking space, including: establishing a parking space complexity-parking level mapping relationship; performing an adaptation parking space complexity analysis on the first parking level prediction index according to the parking space complexity-parking level mapping relationship to generate an adaptation complexity interval; connecting the parking robot to obtain the parking space usage status information of the first roadside parking area, and matching the parking space in combination with the adaptation complexity interval to generate the first recommended parking space.

[0037] Specifically, with the help of the technical ability of professional technicians combined with practical experience, a parking space complexity-parking level mapping relationship is established, and the parking space complexity-parking level mapping relationship can effectively associate the complexity of the parking space with the driver's parking ability. By establishing the parking space complexity-parking level mapping relationship, the parking robot can clearly know which parking spaces of different complexity levels are suitable for drivers of different levels. Then the first parking level prediction index is compared with the set parking space complexity-parking level mapping relationship, and the complexity level of the first driver's adapted parking space is analyzed according to the first parking level prediction index of the first driver, that is, according to the user's parking level. The complexity range in which the first driver can park safely and smoothly is clarified by analysis, and an adapted complexity interval is formed. Finally, the parking robot is connected to obtain the parking space usage status information of the first roadside parking area in real time, and the parking space usage status information includes the current occupancy and available status of each parking space. According to the parking space usage status information, the parking space matching is combined with the adapted complexity area to obtain the first recommended parking space. In the matching process, if there are available parking spaces that meet the adapted complexity interval, these parking spaces will be recommended first. If all parking spaces that meet the conditions are occupied, other parking spaces with the smallest difference in the adaptation complexity range are selected as recommended parking spaces to ensure that the driver can find a suitable parking space. Through comprehensive analysis and matching, parking spaces that meet the driver's level are recommended to meet the driver's personalized needs, improve the user's parking experience, and ensure that the recommended parking spaces are both safe and convenient.

[0038] A first navigation route is generated according to the first recommended parking space, and parking guidance is performed by the parking robot according to the first navigation route.

[0039] Specifically, after obtaining the first recommended parking space, the optimal path from the current position of the vehicle to the recommended parking space is determined based on the first recommended parking space information, using map data and positioning information, i.e., the first navigation route. The first navigation route not only takes into account the geographical location of the parking space, but also takes into account road conditions, traffic flow and other potential obstacles to ensure the safety and efficiency of the path. After receiving the first navigation route information, the parking robot provides real-time parking guidance through voice prompts or visual instructions based on the navigation route, including steering prompts, driving speed control and coordination of parking actions, to safely guide the driver to the first recommended parking space, ensure the smooth completion of the parking operation, and improve the user's parking experience and satisfaction.

[0040] Embodiment 2 is based on the same inventive concept as the above-mentioned embodiment of a berth robot-assisted roadside parking intelligent scheduling method. Figure 2 As shown, the present application provides a berth robot-assisted roadside parking intelligent scheduling system, wherein the system includes:

[0041] The parking space classification module 11 is used to connect to the parking robot of the first roadside parking area to obtain multiple parking spaces, and classify and mark them according to the parking space size and parking space type, so as to generate multiple parking space size marking information and multiple parking space type marking information.

[0042] The digital map acquisition module 12 is used to acquire a regional digital map of the first roadside parking area, wherein the regional digital map is marked with parking space slope information and parking space neighborhood road information.

[0043] The parking complexity analysis module 13 is used to perform parking complexity analysis on the multiple parking spaces in combination with the multiple parking space type marking information, the parking space slope information and the parking space neighborhood road information to generate multiple complexity indicators.

[0044] The parking level prediction module 14 is used to predict the parking level of the first driver and generate a first parking level prediction index when the first vehicle enters the first roadside parking area.

[0045] The parking space matching module 15 is used to match parking spaces by combining the plurality of parking space size marking information, the first parking level prediction index and the plurality of complexity indexes to generate a first recommended parking space.

[0046] The navigation route generating module 16 is used to generate a first navigation route according to the first recommended parking space, and to guide the parking robot to park according to the first navigation route.

[0047] Furthermore, the parking complexity analysis module 13 is used to perform the following steps: initialize parking complexity according to the multiple parking space type marking information to generate multiple initialization difficulty indicators; perform parking impact analysis on the parking space slope information to establish slope impact weights; perform parking impact analysis on the parking space neighborhood road information to establish neighborhood road impact weights; perform weighted compensation on the multiple initialization difficulty indicators with the slope impact weights and the neighborhood road impact weights to generate the multiple complexity indicators.

[0048] Furthermore, the parking complexity analysis module 13 is also used to perform the following steps: collecting multiple historical parking record data sets corresponding to parking spaces of the same type, wherein any historical parking record data set includes multiple parking records corresponding to the same parking space slope mark; calculating the average parking time based on multiple parking records in the multiple historical parking record data sets, and counting the proportion of data that exceeds the average parking time and the deviation is greater than a preset deviation, generating multiple proportion coefficients, and establishing a first mapping relationship table between the multiple proportion coefficients and the parking space slope mark; inputting the parking space slope information into the first mapping relationship table, obtaining the proportion coefficient corresponding to the parking space slope mark with the greatest similarity to the parking space slope information, and generating the slope influence weight.

[0049] Furthermore, the parking level prediction module 14 is used to perform the following steps: connect to the parking record database to extract the historical parking records of the first driver; count the historical parking success rate, historical parking time and historical parking space type proportion of the first driver according to the historical parking records; input the historical parking success rate, historical parking time and historical parking space type proportion into the parking level evaluation model for evaluation and analysis, and generate the first parking level prediction index.

[0050] Furthermore, the parking level prediction module 14 is also used to perform the following steps: the parking level evaluation model is connected to an evaluation sample library, wherein the evaluation sample library includes multiple groups of evaluation samples, and any group of evaluation samples includes parking success rate samples, parking time samples and parking space type proportion samples, as well as corresponding evaluation identification information marked with parking level prediction indicators; the historical parking success rate, the historical parking time and the historical parking space type proportion are input into the parking level evaluation model, the evaluation sample library is called through the parking level evaluation model, the multiple groups of evaluation samples are traversed for sample matching, and the first parking level prediction indicator is generated.

[0051] Furthermore, the parking space matching module 15 is used to perform the following steps: capture and identify the image of the first vehicle through a camera in the first roadside parking area to generate first vehicle size information; compare the first vehicle size information with the multiple parking space size mark information to locate a first matching parking space set; based on the multiple complexity indicators, obtain a first matching parking space complexity index set corresponding to the first matching parking space set; perform parking space adaptation analysis and screening in combination with the first matching parking space complexity index set and the first parking level prediction index to generate the first recommended parking space.

[0052] Furthermore, the parking space matching module 15 is also used to perform the following steps: establish a parking space complexity-parking level mapping relationship; according to the parking space complexity-parking level mapping relationship, adapt the parking space complexity analysis to the first parking level prediction index to generate an adaptation complexity interval; connect the parking space robot to obtain the parking space usage status information of the first roadside parking area, and match the parking space in combination with the adaptation complexity interval to generate the first recommended parking space.

[0053] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0054] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A berth robot-assisted roadside parking intelligent scheduling method, characterized in that: include: The parking robot connected to the first roadside parking area obtains a plurality of parking spaces, and classifies and marks the parking spaces according to the parking space sizes and parking space types, thereby generating a plurality of parking space size marking information and a plurality of parking space type marking information; Acquire a regional digital map of the first roadside parking area, wherein the regional digital map is marked with parking space slope information and parking space neighborhood road information; Performing parking complexity analysis on the multiple parking spaces in combination with the multiple parking space type mark information, the parking space slope information, and the parking space neighborhood road information to generate multiple complexity indicators; When the first vehicle enters the first roadside parking area, predicting the parking level of the first driver and generating a first parking level prediction index; Performing parking space matching by combining the plurality of parking space size mark information, the first parking level prediction index and the plurality of complexity indexes to generate a first recommended parking space; A first navigation route is generated according to the first recommended parking space, and parking guidance is performed by the parking robot according to the first navigation route.

2. The method for intelligent roadside parking dispatching assisted by a parking robot according to claim 1, characterized in that: Performing parking complexity analysis on the multiple parking spaces in combination with the multiple parking space type mark information, the parking space slope information, and the parking space neighborhood road information to generate multiple complexity indicators, including: Initialize parking complexity according to the multiple parking space type marking information to generate multiple initialization difficulty indicators; Performing parking impact analysis on the parking space slope information and establishing a slope impact weight; Performing parking impact analysis on the parking space neighborhood road information and establishing neighborhood road impact weights; The plurality of initialization difficulty indicators are weightedly compensated by using the slope influence weight and the neighborhood road influence weight to generate the plurality of complexity indicators.

3. The method for intelligent roadside parking dispatching assisted by a parking robot as claimed in claim 2, characterized in that: Performing parking impact analysis on the parking space slope information and establishing slope impact weights include: Collecting multiple historical parking record data sets corresponding to parking spaces of the same type, wherein any historical parking record data set includes multiple parking records corresponding to the same parking space slope mark; Based on multiple parking records in multiple historical parking record data sets, average parking time is calculated respectively, and the proportion of data exceeding the average parking time and with a deviation greater than a preset deviation is counted to generate multiple proportion coefficients, and a first mapping relationship table between the multiple proportion coefficients and parking space slope marks is established; The parking space slope information is input into the first mapping relationship table, the proportion coefficient corresponding to the parking space slope mark with the greatest similarity to the parking space slope information is obtained, and the slope influence weight is generated.

4. The method for intelligent roadside parking dispatching assisted by a parking robot according to claim 1, characterized in that: When the first vehicle enters the first roadside parking area, a parking level prediction is performed on the first driver to generate a first parking level prediction index, including: Connecting to a parking record database to extract historical parking records for the first driver; According to the historical parking records, the first driver's historical parking success rate, historical parking time, and historical parking space type ratio are counted; The historical parking success rate, historical parking time and historical parking space type ratio are input into the parking level evaluation model for evaluation and analysis to generate the first parking level prediction index.

5. The method for intelligent roadside parking dispatching assisted by a berth robot as claimed in claim 4, characterized in that: The historical parking success rate, historical parking time and historical parking space type ratio are input into the parking level evaluation model for evaluation and analysis to generate the first parking level prediction index, including: The parking level evaluation model is connected to an evaluation sample library, wherein the evaluation sample library includes multiple groups of evaluation samples, and any group of evaluation samples includes parking success rate samples, parking time samples, and parking space type proportion samples, as well as corresponding evaluation identification information marked with parking level prediction indicators; The historical parking success rate, the historical parking time and the historical parking space type ratio are input into a parking level evaluation model, the evaluation sample library is called through the parking level evaluation model, the multiple groups of evaluation samples are traversed for sample matching, and the first parking level prediction index is generated.

6. The method for intelligent roadside parking dispatching assisted by a parking robot as claimed in claim 5, characterized in that: The method of matching the plurality of parking space size mark information, the first parking level prediction index and the plurality of complexity indexes to generate a first recommended parking space includes: Capturing and identifying an image of the first vehicle through a camera in the first roadside parking area to generate first vehicle size information; Comparing the first vehicle size information with the plurality of parking space size mark information to locate a first matching parking space set; Based on the multiple complexity indicators, obtaining a first matching parking space complexity indicator set corresponding to the first matching parking space set; The first matching parking space complexity index set and the first parking level prediction index are combined to perform parking space adaptation analysis and screening to generate the first recommended parking space.

7. The method for intelligent roadside parking dispatching assisted by a parking robot according to claim 6, characterized in that: Performing parking space adaptation analysis and screening in combination with the first matching parking space complexity index set and the first parking level prediction index to generate the first recommended parking space includes: Establish a mapping relationship between parking space complexity and parking level; According to the parking space complexity-parking level mapping relationship, performing an adaptive parking space complexity analysis on the first parking level prediction index to generate an adaptive complexity interval; The parking robot is connected to obtain the parking space usage status information of the first roadside parking area, and the parking space is matched in combination with the adaptation complexity interval to generate the first recommended parking space.

8. A berth robot-assisted roadside parking intelligent dispatching system, characterized in that: The steps for implementing the method according to any one of claims 1 to 7 include: A parking space classification module, wherein the parking space classification module is used to connect to the parking space robot of the first roadside parking area to obtain multiple parking spaces, and classify and mark the parking spaces according to the parking space size and parking space type, thereby generating multiple parking space size marking information and multiple parking space type marking information; A digital map acquisition module, the digital map acquisition module is used to acquire a regional digital map of the first roadside parking area, wherein the regional digital map is marked with parking space slope information and parking space neighborhood road information; A parking complexity analysis module, the parking complexity analysis module is used to perform parking complexity analysis on the multiple parking spaces in combination with the multiple parking space type marking information, the parking space slope information and the parking space neighborhood road information to generate multiple complexity indicators; a parking level prediction module, the parking level prediction module being used to predict the parking level of the first driver and generate a first parking level prediction index when the first vehicle enters the first roadside parking area; A parking space matching module, the parking space matching module is used to match the parking spaces by combining the plurality of parking space size marking information, the first parking level prediction index and the plurality of complexity indexes to generate a first recommended parking space; A navigation route generation module is used to generate a first navigation route according to the first recommended parking space, and to guide the parking robot to park according to the first navigation route.

Images