A parking assistance method and system for intelligent vehicles

Abstract

The present invention provides an assisted parking method for smart cars, including: obtaining a user's destination; determining a target parking lot based on the destination; obtaining the user's location information in real time; determining whether to enter a parking guidance mode based on the location information and the location of the target parking lot; when entering the parking guidance mode, accessing the intelligent management platform of the target parking lot and obtaining the parking situation in the current target parking lot and the vehicle movement situation in the parking lot; planning a parking path based on the parking situation and the vehicle movement situation in the current target parking lot; and outputting the parking path. The assisted parking method for smart cars of the present invention directly plans a parking path based on the parking situation and the vehicle movement situation in the current target parking lot; realizes the path navigation for parking in the parking lot, avoids users wasting time looking for parking spaces in the parking lot when parking spaces are tight during holidays, and enables users to park more quickly and conveniently.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent vehicles, and in particular to an auxiliary parking method and system applied to intelligent vehicles. Background Art

[0002] At present, with the development of science and technology, people's living standards have improved; driving is the first choice for every family to travel during holidays. Due to travel during holidays, parking is often difficult; people need to find parking spaces in the parking lot by themselves, which is extremely inconvenient. Summary of the invention

[0003] One of the purposes of the present invention is to provide an assisted parking method for smart cars, which directly plans a parking route based on the parking situation and vehicle movement situation in the current target parking lot; realizes path navigation in the parking lot, avoids users wasting time looking for parking spaces in the parking lot when parking spaces are tight on holidays, etc., and enables users to park more quickly and conveniently.

[0004] An embodiment of the present invention provides an auxiliary parking method for a smart car, comprising:

[0005] Get the user's destination;

[0006] Based on the destination, determine the target parking lot;

[0007] Obtain user location information in real time;

[0008] Based on the positioning information and the location of the target parking lot, determining whether to enter a parking guidance mode;

[0009] When entering the parking guidance mode, the intelligent management platform of the target parking lot is connected to obtain the current parking situation in the target parking lot and the vehicle movement situation in the parking lot;

[0010] Plan parking routes based on the current parking situation and vehicle movement in the target parking lot;

[0011] Output parking routes.

[0012] Preferably, obtaining the user's destination includes:

[0013] Get the user's navigation information;

[0014] Analyze navigation information and determine the navigation destination;

[0015] Set the navigation end point as the destination;

[0016] and / or,

[0017] Get the destination entered by the user in the destination input interface.

[0018] Preferably, based on the destination, determining the target parking lot includes:

[0019] Get a parking lot distribution map near the destination;

[0020] Based on the parking lot distribution map, the parking lot closest to the destination is determined as the target parking lot.

[0021] Preferably, determining whether to enter the parking guidance mode based on the positioning information and the location of the target parking lot includes:

[0022] Parse positioning information to determine the user's current location;

[0023] Determine a first distance between the user and the target parking lot based on the current location and the location of the target parking lot;

[0024] When the first distance is less than the preset trigger threshold, the trigger determination is entered;

[0025] When entering the trigger judgment, the current position is sampled every preset first time to obtain multiple sampling positions;

[0026] Determine a first distance value between each sampling position and the position of the target parking lot;

[0027] Determine the difference between the first distance values ​​of two adjacent sampling positions; the difference is the first distance value corresponding to the previous sampling position minus the first distance value corresponding to the next sampling position;

[0028] When the number of differences greater than zero is greater than the number of differences less than or equal to zero, entering the parking guidance mode is triggered; otherwise, it is not triggered.

[0029] Preferably, based on the parking situation and vehicle movement situation in the current target parking lot, planning a parking route includes:

[0030] determining at least one target channel;

[0031] Obtain a preset parking space layout map of the target parking lot;

[0032] Analyze the parking situation and determine the first position of each vacant parking space in the target parking lot in the parking space setting map;

[0033] In the parking space setting diagram, determine the second position corresponding to each target channel;

[0034] Based on the first position and the second position, determining a second distance between each vacant parking space and each target channel;

[0035] Based on the second distance, determining a first priority value for each vacant parking space;

[0036] Analyze vehicle movement and determine the vehicles to be parked;

[0037] Mapping the vehicle to be parked into the parking space setting map, and determining the third position and movement direction of the vehicle to be parked;

[0038] Based on the third position and the direction of movement, determine the probability of each free parking space being used;

[0039] Determine a second priority value for each free parking space based on the probability that each free parking space is used;

[0040] Determining a comprehensive priority value based on the first priority value and the second priority value;

[0041] The vacant parking space with the largest comprehensive priority value is taken as the target parking space;

[0042] Get the user's entrance location to the target parking lot;

[0043] Plan parking routes based on entrance locations and target parking spaces.

[0044] Preferably, determining at least one target channel comprises:

[0045] Acquire the fourth position of each passage for people to enter and exit in the target parking lot;

[0046] parsing the destination again, and determining a fifth position when the destination belongs to a preset type of destination;

[0047] Determining at least one target channel based on the fourth position and the fifth position of each channel for personnel to enter and exit;

[0048] When the destination does not belong to the preset type of destination, receiving a prediction analysis of the activity area after the user enters the building corresponding to the destination, sent by the intelligent management platform of the target parking lot, and determining at least one target passage closest to the activity area;

[0049] Among them, the activity area is predicted by the following steps:

[0050] Get the user's profile;

[0051] Based on the user portrait, obtain the user's activity trajectory in the building corresponding to the destination;

[0052] The sixth position of the user when extracting the historical moment corresponding to the current moment;

[0053] Based on the activity trajectory, determine the seventh location of the user's primary goal after entering the building;

[0054] determining an activity area based on the sixth position and the seventh position;

[0055] When the activity track of the user in the building corresponding to the destination is not obtained, the activity area is determined based on a preset time and activity area comparison prediction table.

[0056] Preferably, determining the activity area based on the sixth position and the seventh position includes:

[0057] Obtaining areas divided based on preset area division rules within the building;

[0058] Based on the areas corresponding to the sixth position and the seventh position, determining the number of times each area appears in the activity track;

[0059] The area with the highest number of views is regarded as the active area.

[0060] Preferably, based on the third position and the movement direction, determining the probability of each vacant parking space being used includes:

[0061] Based on the third position and the direction of movement, determine the path information of each to-be-parked vehicle to the vacant parking space and the parking space usage on each path information;

[0062] Extract features of each path information and parking space usage on each path information to determine multiple feature values;

[0063] Multiple feature values ​​are input into the preset neural network model to determine the probability of the vacant parking space being used.

[0064] The present invention also provides an auxiliary parking system for a smart car, comprising:

[0065] A first acquisition module is used to acquire a user's destination;

[0066] A determination module, used to determine a target parking lot based on a destination;

[0067] Positioning module, used to obtain user's position information in real time;

[0068] A trigger module, used to determine whether to enter a parking guidance mode based on the positioning information and the location of the target parking lot;

[0069] The second acquisition module is used to access the intelligent management platform of the target parking lot and obtain the parking situation in the current target parking lot and the vehicle movement situation in the parking lot when entering the parking guidance mode;

[0070] A planning module is used to plan a parking route based on the parking situation and vehicle movement in the current target parking lot;

[0071] The output module is used to output the parking path.

[0072] Preferably, the first acquisition module acquires the user's destination and performs the following operations:

[0073] Get the user's navigation information;

[0074] Analyze navigation information and determine the navigation destination;

[0075] Set the navigation end point as the destination;

[0076] and / or,

[0077] Get the destination entered by the user in the destination input interface.

[0078] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0079] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0081] Figure 1 A schematic diagram of an auxiliary parking method applied to a smart car in an embodiment of the present invention;

[0082] Figure 2 Schematic diagram of an assisted parking system applied to a smart car in an embodiment of the present invention. DETAILED DESCRIPTION

[0083] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0084] The embodiment of the present invention provides an auxiliary parking method applied to a smart car, such as Figure 1 As shown, including:

[0085] Step S1: Get the user's destination;

[0086] Step S2: Determine the target parking lot based on the destination;

[0087] Step S3: Acquire the user's location information in real time;

[0088] Step S4: determining whether to enter parking guidance mode based on the positioning information and the location of the target parking lot;

[0089] Step S5: When entering the parking guidance mode, access the intelligent management platform of the target parking lot and obtain the current parking situation in the target parking lot and the vehicle movement situation in the parking lot;

[0090] Step S6: planning a parking route based on the parking situation and vehicle movement situation in the current target parking lot;

[0091] Step S7: Output the parking path.

[0092] The working principle and beneficial effects of the above technical solution are:

[0093] The parking assistance method of the present invention is mainly applied to smart cars. The target parking lot is determined by analyzing the destination of the user; the parking guidance mode is determined according to the change and relative relationship between the user's position and the position of the target parking lot; after entering the parking guidance mode, the parking situation in the parking lot and the vehicle movement situation in the parking lot are obtained, and the parking path is planned according to the actual situation in the parking lot and the parking path is output; wherein the intelligent management platform is used for the target parking lot, and has the functions of intelligently managing the parking spaces in the parking lot and the images collected by the image acquisition device at each preset position in the parking lot; the output of the parking path can be displayed and output through the display screen in the smart car and / or voice output through the speaker set in the smart car. For example: when the user sets out from home, he inputs the destination, and then determines in real time whether to enter the parking guidance mode according to the user's location. When entering, the display screen outputs the parking guidance. The parking assistance method of the present invention directly plans the parking path according to the parking situation and the vehicle movement situation in the current target parking lot; the path navigation of parking in the parking lot is realized, so as to avoid the user from wasting time looking for parking spaces in the parking lot when the parking spaces in the parking lot are tight during holidays, so that the user can park more quickly and conveniently.

[0094] In one embodiment, obtaining the user's destination includes:

[0095] Get the user's navigation information;

[0096] Analyze navigation information and determine the navigation destination;

[0097] Set the navigation end point as the destination;

[0098] and / or,

[0099] Get the destination entered by the user in the destination input interface.

[0100] The working principle and beneficial effects of the above technical solution are:

[0101] This implementation provides two ways to obtain the user's destination. The first is to obtain the user's navigation information through the in-vehicle navigation or the navigation APP on the smart phone connected to the smart car, and use the navigation end point corresponding to the navigation information as the user's destination; the second is to directly enter the destination through the destination input interface displayed on the display screen of the smart car.

[0102] In order to determine the target parking lot, in one embodiment, the target parking lot is determined based on the destination, including:

[0103] Get a parking lot distribution map near the destination;

[0104] Based on the parking lot distribution map, the parking lot closest to the destination is determined as the target parking lot. Generally, large commercial centers have underground parking lots. When the user navigates to the large commercial center, the nearest parking lot is the underground parking lot. This parking lot is the target parking lot.

[0105] In one embodiment, determining whether to enter the parking guidance mode based on the positioning information and the location of the target parking lot includes:

[0106] Parse positioning information to determine the user's current location;

[0107] Determine a first distance between the user and the target parking lot based on the current location and the location of the target parking lot;

[0108] When the first distance is less than a preset trigger threshold (e.g., 500 meters), the trigger determination is entered;

[0109] When entering the trigger judgment, the current position is sampled every preset first time (for example: 3 seconds) to obtain multiple sampling positions;

[0110] Determine a first distance value between each sampling position and the position of the target parking lot;

[0111] Determine the difference between the first distance values ​​of two adjacent sampling positions; the difference is the first distance value corresponding to the previous sampling position minus the first distance value corresponding to the next sampling position;

[0112] When the number of differences greater than zero is greater than the number of differences less than or equal to zero, the parking guidance mode is triggered, otherwise, it is not triggered. When entering the distance range corresponding to the trigger threshold from the target parking lot, the user's position is sampled, and according to the changing trend of the distance difference between the sampled position and the target parking lot, it is determined whether the user is moving towards the target parking lot, and then it is determined whether to enter the parking guidance mode, which improves intelligence.

[0113] In one embodiment, based on the parking situation and vehicle movement situation in the current target parking lot, planning a parking path includes:

[0114] Determine at least one target channel; the target channel is a channel for people to enter and exit the target parking lot; for example, facilities such as elevators and escalators; a parking lot is often provided with multiple channels for people to enter and exit, and one or more of them is determined as the target channel;

[0115] Obtaining a preset parking space layout diagram of the target parking lot; the parking space layout diagram is pre-constructed according to the internal structure of the target parking lot and the division of parking spaces;

[0116] Analyze the parking situation and determine the first position of each free parking space in the target parking lot in the parking space setting map; the parking situation refers to the use of parking spaces in the parking lot. When there is a vehicle parked in the parking space, it is occupied; if there is no vehicle parked, it is free; whether there is a vehicle in the parking space can be detected by geomagnetic sensors, high-position cameras, and image analysis.

[0117] In the parking space arrangement diagram, determining the second position corresponding to each target channel; that is, marking the target channel in the parking space arrangement diagram;

[0118] Based on the first position and the second position, determining a second distance between each vacant parking space and each target channel;

[0119] Based on the second distance, determine the first priority value of each free parking space; by comparing the second distances between the free parking space and each target channel, determine the shortest distance, query the preset distance and priority value correspondence table, and determine the first priority value;

[0120] Analyze the vehicle movement and determine the vehicle to be parked; when a vehicle drives out of a parking space, the vehicle will not be determined as a vehicle to be parked; only vehicles that enter the parking lot and are looking for parking spaces will be determined as vehicles to be parked; for example, the specific expression of the vehicle movement can be the movement trajectory of each vehicle; determine whether it is a vehicle to be parked by the starting point of the movement trajectory; when the starting point is a parking space, it is determined that it is not a vehicle to be parked, and when the starting point is the entrance or exit of the parking lot, it is determined to be a vehicle to be parked;

[0121] Mapping the vehicle to be parked into the parking space setting map, and determining the third position and movement direction of the vehicle to be parked;

[0122] Based on the third position and the direction of movement, the probability of each free parking space being used is determined; that is, through the probability, it can be marked whether the free parking space has been used after the user enters the target parking lot; when the probability of the free parking space being used is high, it cannot be used as the end point of the parking path planning;

[0123] Based on the probability of each free parking space being used, determine the second priority value of each free parking space; using the probability, and then by querying the probability and priority value correspondence table, determine the second priority value corresponding to the probability;

[0124] Determine a comprehensive priority value based on the first priority value and the second priority value; the comprehensive priority value is the sum of the first priority value and the second priority value;

[0125] The vacant parking space with the largest comprehensive priority value is taken as the target parking space;

[0126] Obtain the entrance location of the user to the target parking lot; plan the path for the user to move into the parking lot based on the user's current location; determine the shortest path for the user to enter the parking lot based on various paths; use the entrance location corresponding to the shortest path as the entrance location for the user to enter the target parking lot;

[0127] The parking path is planned based on the entrance location and the target parking space. The starting point of the parking path is the entrance location and the end point is the target parking space. The path is planned according to the road settings in the parking lot to make the parking path the shortest and most effective.

[0128] In one embodiment, determining at least one target channel includes:

[0129] Acquire the fourth position of each passage for people to enter and exit in the target parking lot;

[0130] parsing the destination again, and determining a fifth position when the destination belongs to a preset type of destination;

[0131] Determining at least one target channel based on the fourth position and the fifth position of each channel for personnel to enter and exit;

[0132] When the destination does not belong to the preset type of destination, receiving a prediction analysis of the activity area after the user enters the building corresponding to the destination, sent by the intelligent management platform of the target parking lot, and determining at least one target passage closest to the activity area;

[0133] Among them, the activity area is predicted by the following steps:

[0134] Get the user's profile;

[0135] Based on the user portrait, obtain the user's activity trajectory in the building corresponding to the destination;

[0136] The sixth position of the user when extracting the historical moment corresponding to the current moment;

[0137] Based on the activity trajectory, determine the seventh position of the primary target of the user after entering the building; the primary target is mainly determined by analyzing the user's trajectory, for example: when the user enters the first store after entering the mall, the primary target is this store;

[0138] determining an activity area based on the sixth position and the seventh position;

[0139] When the activity track of the user in the building corresponding to the destination is not obtained, the activity area is determined based on a preset time and activity area comparison prediction table.

[0140] The working principle and beneficial effects of the above technical solution are:

[0141] Preset type, for example: the name of a specific store in a large commercial center as the destination; the specific store name can be used to determine which area of ​​the large commercial center it belongs to. The area divisions of large commercial centers are generally shopping areas, leisure areas, food areas, etc.; when the destination is a preset type, the nearest channel can be directly determined, for example: elevator A can go directly from the underground parking lot to destination B; when the destination input by the user is just destination B, the target channel can be determined as elevator A; when the type of the user's destination is not a preset type, for example: the name of a large commercial center is directly used as the destination; the target channel is determined by the prediction analysis of the activity area sent by the intelligent management platform of the target parking lot; for specific analysis, the user's user portrait can be used to call out the portraits taken by various video surveillance devices in the large commercial center, and then analyze the user's activity trajectory; then the activity trajectory is analyzed, the user's behavior is predicted, and the activity area corresponding to the primary target of the user is determined; when the activity trajectory is not retrieved through the user portrait, that is, the user has not entered the building corresponding to the destination, the activity area is determined by comparing the preset time with the activity area prediction table; for example: when the user is from 5:00 to 7:00, the user's activity area can be predicted to be the food area. The user portrait is the user's identification information, including: the user's username, face information, image information, etc.

[0142] In one embodiment, determining the activity area based on the sixth position and the seventh position includes:

[0143] Obtaining areas divided based on preset area division rules within the building;

[0144] Based on the areas corresponding to the sixth position and the seventh position, determining the number of times each area appears in the activity track;

[0145] The area with the highest number of views is regarded as the active area.

[0146] The working principle and beneficial effects of the above technical solution are:

[0147] Through statistical analysis of the primary targets that appear in the user's historical activity trajectories and the areas where the historical moments corresponding to the current moment are located, the activity area is determined and the user's activity area is predicted; for example: the user has 10 activity trajectories; 5 of the activity trajectories have primary targets located in the food area, 3 have primary targets located in the leisure area, and 2 have primary targets located in the shopping area; 5 activity trajectories have historical moments (for example: 5:00 p.m.) corresponding to the current moment (for example: 5:00 p.m.); the user's locations are respectively located in the leisure area (3 trajectories) and the shopping area (2 trajectories); the statistical data are: 5 times in the food area, 6 times in the leisure area, and 4 times in the shopping area; therefore, the leisure area is taken as the activity area.

[0148] In one embodiment, based on the third position and the movement direction, determining the probability of each vacant parking space being used includes:

[0149] Based on the third position and the direction of movement, determine the path information of each to-be-parked vehicle to the vacant parking space and the parking space usage on each path information;

[0150] Extract features of each path information and parking space usage on each path information to determine multiple feature values;

[0151] Multiple feature values ​​are input into the preset neural network model to determine the probability of the vacant parking space being used.

[0152] The working principle and beneficial effects of the above technical solution are:

[0153] Through the neural network model, the movement direction and the third position of the vehicle to be parked are analyzed in combination with the parking settings and road settings in the parking lot to determine the probability of the vacant parking space being used; the neural network model is obtained based on a large amount of data training convergence in advance; for example: when the vacant parking space is located at the end of a branch road in the parking lot, there is a vehicle to be parked on the branch road, and there is only one vacant parking space on the branch road in the driving direction of the vehicle, the probability of the vacant parking space being used is 100%; when there are two parking spaces, the probability of the vacant parking space that is closer to the vehicle to be parked being used is higher than the probability of the vacant parking space that is farther away from the vehicle to be parked being used; when two vacant parking spaces are adjacent, the probability of both is 50%; when the distance between the two is greater than 4 parking spaces, the probability of the parking space that is closer being used is 95%, and the probability of the vacant parking space that is farther away being used is 5%.

[0154] In addition, the status of the vacant parking space determined as the end point of the parking path is tracked, and parking guidance is re-performed when the vacant parking space is used.

[0155] The present invention also provides an auxiliary parking system for smart cars, such as Figure 2 As shown, including:

[0156] The first acquisition module 1 is used to acquire the user's destination;

[0157] A determination module 2 is used to determine a target parking lot based on the destination;

[0158] Positioning module 3, used to obtain the user's position information in real time;

[0159] A trigger module 4 is used to determine whether to enter a parking guidance mode based on the positioning information and the location of the target parking lot;

[0160] The second acquisition module 5 is used to access the intelligent management platform of the target parking lot and obtain the parking situation in the current target parking lot and the vehicle movement situation in the parking lot when entering the parking guidance mode;

[0161] Planning module 6, used to plan a parking route based on the parking situation and vehicle movement situation in the current target parking lot;

[0162] The output module 7 is used to output the parking path.

[0163] In one embodiment, the first acquisition module 1 acquires the destination of the user and performs the following operations:

[0164] Get the user's navigation information;

[0165] Analyze navigation information and determine the navigation destination;

[0166] Set the navigation end point as the destination;

[0167] and / or,

[0168] Get the destination entered by the user in the destination input interface.

[0169] In one embodiment, the determination module 2 determines the target parking lot based on the destination and performs the following operations:

[0170] Get a parking lot distribution map near the destination;

[0171] Based on the parking lot distribution map, the parking lot closest to the destination is determined as the target parking lot.

[0172] In one embodiment, the trigger module 4 determines whether to enter the parking guidance mode based on the positioning information and the location of the target parking lot, and performs the following operations:

[0173] Parse positioning information to determine the user's current location;

[0174] Determine a first distance between the user and the target parking lot based on the current location and the location of the target parking lot;

[0175] When the first distance is less than the preset trigger threshold, the trigger determination is entered;

[0176] When entering the trigger judgment, the current position is sampled every preset first time to obtain multiple sampling positions;

[0177] Determine a first distance value between each sampling position and the position of the target parking lot;

[0178] Determine the difference between the first distance values ​​of two adjacent sampling positions; the difference is the first distance value corresponding to the previous sampling position minus the first distance value corresponding to the next sampling position;

[0179] When the number of differences greater than zero is greater than the number of differences less than or equal to zero, entering the parking guidance mode is triggered; otherwise, it is not triggered.

[0180] In one embodiment, the planning module 6 plans a parking path based on the parking situation and vehicle movement situation in the current target parking lot, and performs the following operations:

[0181] determining at least one target channel;

[0182] Obtain a preset parking space layout map of the target parking lot;

[0183] Analyze the parking situation and determine the first position of each vacant parking space in the target parking lot in the parking space setting map;

[0184] In the parking space setting diagram, determine the second position corresponding to each target channel;

[0185] Based on the first position and the second position, determining a second distance between each vacant parking space and each target channel;

[0186] Based on the second distance, determining a first priority value for each vacant parking space;

[0187] Analyze vehicle movement and determine the vehicles to be parked;

[0188] Mapping the vehicle to be parked into the parking space setting map, and determining the third position and movement direction of the vehicle to be parked;

[0189] Based on the third position and the direction of movement, determine the probability of each free parking space being used;

[0190] Determine a second priority value for each free parking space based on the probability that each free parking space is used;

[0191] Determining a comprehensive priority value based on the first priority value and the second priority value;

[0192] The vacant parking space with the largest comprehensive priority value is taken as the target parking space;

[0193] Get the user's entrance location to the target parking lot;

[0194] Plan parking routes based on entrance locations and target parking spaces.

[0195] In one embodiment, the planning module 6 determines at least one target channel and performs the following operations:

[0196] Acquire the fourth position of each passage for people to enter and exit in the target parking lot;

[0197] parsing the destination again, and determining a fifth position when the destination belongs to a preset type of destination;

[0198] Determining at least one target channel based on the fourth position and the fifth position of each channel for personnel to enter and exit;

[0199] When the destination does not belong to the preset type of destination, receiving a prediction analysis of the activity area after the user enters the building corresponding to the destination, sent by the intelligent management platform of the target parking lot, and determining at least one target passage closest to the activity area;

[0200] Among them, the activity area is predicted by the following steps:

[0201] Get the user's profile;

[0202] Based on the user portrait, obtain the user's activity trajectory in the building corresponding to the destination;

[0203] The sixth position of the user when extracting the historical moment corresponding to the current moment;

[0204] Based on the activity trajectory, determine the seventh location of the user's primary goal after entering the building;

[0205] determining an activity area based on the sixth position and the seventh position;

[0206] When the activity track of the user in the building corresponding to the destination is not obtained, the activity area is determined based on a preset time and activity area comparison prediction table.

[0207] In one embodiment, determining the activity area based on the sixth position and the seventh position includes:

[0208] Obtaining areas divided based on preset area division rules within the building;

[0209] Based on the areas corresponding to the sixth position and the seventh position, determining the number of times each area appears in the activity track;

[0210] The area with the highest number of views is regarded as the active area.

[0211] In one embodiment, based on the third position and the movement direction, determining the probability of each vacant parking space being used includes:

[0212] Based on the third position and the direction of movement, determine the path information of each to-be-parked vehicle to the vacant parking space and the parking space usage on each path information;

[0213] Extract features of each path information and parking space usage on each path information to determine multiple feature values;

[0214] Multiple feature values ​​are input into the preset neural network model to determine the probability of the vacant parking space being used.

[0215] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An auxiliary parking method applied to a smart car, characterized in that: include: Get the user's destination; Based on the destination, determining a target parking lot; Acquire the location information of the user in real time; Based on the positioning information and the location of the target parking lot, determining whether to enter a parking guidance mode; When entering the parking guidance mode, accessing the intelligent management platform of the target parking lot and obtaining the current parking situation in the target parking lot and the vehicle movement situation in the parking lot; Planning a parking path based on the current parking situation in the target parking lot and the vehicle movement situation; Outputting the parking path; Wherein, planning a parking route based on the current parking situation in the target parking lot and the vehicle movement situation includes: determining at least one target channel; Obtaining a preset parking space layout diagram of the target parking lot; Analyzing the parking situation, and determining the first position of each vacant parking space in the target parking lot in the parking space arrangement map; In the parking space arrangement diagram, determining a second position corresponding to each of the target channels; Based on the first position and the second position, determining a second distance between each of the vacant parking spaces and each of the target channels; Based on the second distance, determining a first priority value for each of the vacant parking spaces; Analyze the vehicle movement conditions and determine the vehicle to be parked; Mapping the vehicle to be parked into the parking space setting map, and determining a third position and a moving direction of the vehicle to be parked; Based on the third position and the movement direction, determining the probability of each of the vacant parking spaces being used; Determining a second priority value for each of the idle parking spaces based on a probability that each of the idle parking spaces is used; Determining a comprehensive priority value based on the first priority value and the second priority value; Taking the vacant parking space with the largest comprehensive priority value as the target parking space; Obtaining the entrance location of the user into the target parking lot; Planning the parking path based on the entrance location and the target parking space; Wherein, determining the probability of each of the vacant parking spaces being used based on the third position and the movement direction includes: Based on the third position and the movement direction, determining the path information of each of the to-be-parked vehicles to the vacant parking space and the parking space usage on each of the path information; Extracting features from each piece of path information and the parking space usage on each piece of path information to determine a plurality of feature values; The plurality of characteristic values ​​are input into a preset neural network model to determine the probability that the vacant parking space is used.

2. The assisted parking method for a smart car according to claim 1, characterized in that: The obtaining of the user's destination includes: Get the user's navigation information; Analyze the navigation information to determine the navigation destination; Taking the navigation end point as the destination; and / or, The destination input by the user in the destination input interface is obtained.

3. The assisted parking method for a smart car according to claim 1, characterized in that: The step of determining a target parking lot based on the destination includes: Obtaining a parking lot distribution map in an area near the destination; Based on the parking lot distribution map, the parking lot closest to the destination is determined as the target parking lot.

4. The assisted parking method for a smart car according to claim 1, characterized in that: The determining whether to enter a parking guidance mode based on the positioning information and the location of the target parking lot includes: Parsing the positioning information to determine the current location of the user; Determining a first distance between the user and the target parking lot based on the current location and the location of the target parking lot; When the first distance is less than a preset trigger threshold, entering trigger determination; When entering the trigger determination, sampling the current position every preset first time to obtain multiple sampling positions; Determine a first distance value between each of the sampling positions and the position of the target parking lot; Determine a difference between the first distance values ​​of two adjacent sampling positions; the difference is the first distance value corresponding to the previous sampling position minus the first distance value corresponding to the next sampling position; When the number of the differences greater than zero is greater than the number of the differences less than or equal to zero, entering the parking guidance mode is triggered; otherwise, it is not triggered.

5. The assisted parking method for a smart car as claimed in claim 1, characterized in that: The determining of at least one target channel comprises: Acquire a fourth position of each passage for people to enter and exit in the target parking lot; parsing the destination again, and determining a fifth position when the destination belongs to a preset type of destination; Determine at least one target channel based on the fourth position of each channel for personnel to enter and exit and the fifth position; When the destination does not belong to a preset type of destination, receiving a prediction analysis based on the activity area after the user enters the building corresponding to the destination, sent by the intelligent management platform of the target parking lot, and determining at least one target passage closest to the activity area; The activity area is predicted by the following steps: Obtaining a user profile of the user; Based on the user portrait, obtaining the activity track of the user in the building corresponding to the destination; The sixth position of the user when extracting the historical moment corresponding to the current moment; Based on the activity trajectory, determining a seventh position of the primary target of the user after entering the building; determining the activity area based on the sixth position and the seventh position; When the activity track of the user in the building corresponding to the destination is not obtained, the activity area is determined based on a preset time and activity area comparison prediction table.

6. The assisted parking method for a smart car as claimed in claim 5, characterized in that: The determining the activity area based on the sixth position and the seventh position includes: Acquire areas divided based on preset area division rules within the building; Based on the areas corresponding to the sixth position and the seventh position, determining the number of times each area appears in the activity track; The area with the largest number of occurrences is taken as the active area.

7. An auxiliary parking system applied to a smart car, characterized in that: include: A first acquisition module is used to acquire a user's destination; A determination module, configured to determine a target parking lot based on the destination; A positioning module, used to obtain the positioning information of the user in real time; a trigger module, configured to determine whether to enter a parking guidance mode based on the positioning information and the location of the target parking lot; A second acquisition module is used to access the intelligent management platform of the target parking lot and obtain the current parking situation in the target parking lot and the vehicle movement situation in the parking lot when entering the parking guidance mode; A planning module, used to plan a parking path based on the current parking situation in the target parking lot and the vehicle movement situation; An output module, used for outputting the parking path; The planning module plans the parking path based on the parking situation and vehicle movement in the current target parking lot and performs the following operations: determining at least one target channel; Obtain a preset parking space layout map of the target parking lot; Analyze the parking situation and determine the first position of each vacant parking space in the target parking lot in the parking space setting map; In the parking space setting diagram, determine the second position corresponding to each target channel; Based on the first position and the second position, determining a second distance between each vacant parking space and each target channel; Based on the second distance, determining a first priority value for each vacant parking space; Analyze vehicle movement and determine the vehicles to be parked; Mapping the vehicle to be parked into the parking space setting map, and determining the third position and movement direction of the vehicle to be parked; Based on the third position and the direction of movement, determine the probability of each free parking space being used; Determine a second priority value for each free parking space based on the probability that each free parking space is used; Determining a comprehensive priority value based on the first priority value and the second priority value; The vacant parking space with the largest comprehensive priority value is taken as the target parking space; Get the user's entrance location to the target parking lot; Plan parking routes based on entrance locations and target parking spaces; The method of determining the probability of each vacant parking space being used based on the third position and the movement direction includes: Based on the third position and the direction of movement, determine the path information of each to-be-parked vehicle to the vacant parking space and the parking space usage on each path information; Extract features of each path information and parking space usage on each path information to determine multiple feature values; Multiple feature values ​​are input into the preset neural network model to determine the probability of the vacant parking space being used.

8. The assisted parking system for smart cars as claimed in claim 7, characterized in that: The first acquisition module acquires the user's destination and performs the following operations: Get the user's navigation information; Analyze the navigation information to determine the navigation destination; Taking the navigation end point as the destination; and / or, The destination input by the user in the destination input interface is obtained.

Images