WO2022237277A1 - 停车区域推荐方法、装置、电子设备和介质 - Google Patents

停车区域推荐方法、装置、电子设备和介质 Download PDF

Info

Publication number
WO2022237277A1
WO2022237277A1 PCT/CN2022/078157 CN2022078157W WO2022237277A1 WO 2022237277 A1 WO2022237277 A1 WO 2022237277A1 CN 2022078157 W CN2022078157 W CN 2022078157W WO 2022237277 A1 WO2022237277 A1 WO 2022237277A1
Authority
WO
WIPO (PCT)
Prior art keywords
parking
occupancy
spaces
parking space
historical
Prior art date
Application number
PCT/CN2022/078157
Other languages
English (en)
French (fr)
Inventor
张一鸣
谭雄飞
葛婷婷
Original Assignee
北京百度网讯科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京百度网讯科技有限公司 filed Critical 北京百度网讯科技有限公司
Priority to JP2022551580A priority Critical patent/JP7422890B2/ja
Priority to EP22806254.3A priority patent/EP4202888A1/en
Publication of WO2022237277A1 publication Critical patent/WO2022237277A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
    • G08G1/144—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces on portable or mobile units, e.g. personal digital assistant [PDA]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
    • G08G1/146—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is a limited parking space, e.g. parking garage, restricted space

Definitions

  • the present disclosure relates to the field of computer technology, to the field of machine learning technology, cloud computing and cloud service technology, for example, to a parking area recommendation method, device, electronic equipment and media.
  • Most of the parking space recommendations are based on the distance between each parking space and the entrance, exit and elevator entrance to recommend the optimal parking space to the user.
  • the present disclosure provides a method, device, electronic device and medium for improving the accuracy of parking area recommendation.
  • a method for recommending a parking area including:
  • each candidate parking area includes at least two parking spaces.
  • a device for recommending a parking area including:
  • the parking space occupancy data determination module is configured to determine the parking space occupancy data of the target parking lot
  • the target parking area selection module is configured to select a target parking area from a plurality of candidate parking areas in the target parking lot according to the parking space occupancy data; wherein each candidate parking area includes at least two parking spaces.
  • an electronic device including:
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the above-mentioned parking area recommendation method.
  • a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the above parking area recommendation method.
  • a computer program product including a computer program, the computer program implements the above parking area recommendation method when executed by a processor.
  • FIG. 1 is a flowchart of a method for recommending a parking area according to an embodiment of the present disclosure
  • Fig. 2 is a flow chart of a parking area recommendation method according to an embodiment of the present disclosure
  • Fig. 3 is a schematic structural diagram of a parking area recommendation device according to an embodiment of the present disclosure.
  • Fig. 4 is a block diagram of an electronic device used to implement the method for recommending a parking area disclosed in an embodiment of the present disclosure.
  • the user When a user goes to the parking lot to park, the user must analyze and judge which parking space to choose based on the occupied parking spaces in the parking lot. For example, when entering a parking lot and finding that the parking space is very tight, the user may choose a nearby parking space while driving forward. For another example, after entering the parking lot, you find that there are enough parking spaces, and you may choose a parking space closer to the elevator entrance or entrance. Therefore, the parking space occupancy of the parking lot plays an important role in which parking area the user chooses to park.
  • Fig. 1 is a flow chart of a method for recommending a parking area according to an embodiment of the present disclosure. This embodiment may be applicable to recommending a parking area of a target parking lot to a user.
  • the method of this embodiment can be executed by the device for recommending a parking area disclosed in the embodiment of the present disclosure.
  • the device can be implemented by software and/or hardware, and can be integrated on any electronic device with computing capability.
  • the parking area recommendation method disclosed in this embodiment may include:
  • the type of target parking lot includes but is not limited to open-air parking lot, underground parking lot or three-dimensional parking lot etc., the number of floors of target parking lot can be one floor or multi-layer, present embodiment does not set the type and number of floors of target parking lot Make any restrictions.
  • the parking space occupancy data reflects the occupancy of parking spaces in the target parking lot.
  • the parking space occupancy data can be expressed by the number of parking spaces occupied, or by the occupancy rate of parking spaces, or by the combination of the number of occupied spaces and the occupancy rate of parking spaces. , this embodiment does not limit the data type of the parking space occupancy data, and any data that can reflect the occupancy of parking spaces in the target parking lot can be used as the parking space occupancy data.
  • the user before entering the target parking lot, accesses the parking area recommendation interface in the client installed on the smart terminal, and implements the operation of generating the parking area recommendation instruction in the parking area recommendation interface, wherein the smart terminal includes But not limited to smart phones, smart tablets, smart watches or laptops and other electronic devices installed with smart operating systems; the operation of generating parking area recommendation instructions includes but is not limited to, the user clicks on a preset control in the parking area recommendation interface, for example "Parking area recommendation" button control to generate parking area recommendation instructions.
  • the parking area recommendation server obtains the parking area recommendation instruction sent by the client, correspondingly obtains the occupancy of parking spaces in the target parking lot, and then performs statistical analysis according to the occupancy of parking spaces according to preset rules to obtain the target parking lot parking space occupancy data.
  • the occupied situation of the parking space includes two situations: occupied and unoccupied.
  • the way of determining whether the parking space is occupied includes but not limited to at least one of the following: 1) detecting whether the parking space is occupied by a sensor installed on each parking space, for example, if the light sensor detects that the light is blocked, then determine the The parking space is already occupied; and for example, the pressure sensor detects that the pressure increases, then it is determined that the parking space is occupied. 2) Determine whether the parking space is occupied through the image of the parking space captured by the camera. For example, if a vehicle is detected in the image of the parking space based on the target detection algorithm, it is determined that the parking space is occupied.
  • the parking space occupancy data includes at least one of the total parking space occupancy rate, the parking space occupancy rate of each floor, the parking space occupancy rate of each candidate parking area and the parking space occupancy rate of the key parking area; wherein, the key parking area is Determined according to the identification information of each candidate parking area.
  • the candidate parking areas are pre-divided by relevant personnel on multiple parking spaces in the target parking lot.
  • the key parking area is a candidate parking area with a high degree of importance set by relevant personnel in advance, such as the candidate parking area near the elevator entrance, the candidate parking area near the entrance of the target parking lot, the candidate parking area near the exit of the target parking lot, and the floor Candidate parking areas near the entrance and candidate parking areas near the exit of the floor, etc.
  • Different candidate parking areas correspond to different identification information
  • key parking areas are determined according to the identification information of the candidate parking areas. For example, the candidate parking areas whose identification information is preset as “0001", “0005" and “0010" are key parking areas, then the identification information of the candidate parking areas will be traversed, and the identification information will be "0001", "0005" and "0010". " as the key parking area, and the occupancy rates of the candidate parking areas whose identification information is "0001", "0005" and “0010” are used as the occupancy rates of the corresponding key parking areas.
  • the data of the occupancy data of parking spaces is expanded dimension, which indirectly improves the accuracy of the final parking area recommendation.
  • the parking space occupancy data includes at least one of the total number of occupied parking spaces, the number of occupied parking spaces on each floor, the number of occupied parking spaces in each candidate parking area, and the number of occupied parking spaces in key parking areas.
  • the total number of occupied parking spaces represents the total number of occupied parking spaces in the target parking lot.
  • the number of occupied parking spaces on each floor indicates the number of occupied parking spaces on each floor in the target parking lot.
  • the number of occupied parking spaces in the candidate parking area is the number of occupied parking spaces in the candidate parking area.
  • the number of occupied parking spaces in the key parking area that is, the number of occupied parking spaces in the candidate parking areas with higher importance set by relevant personnel.
  • the data foundation is laid for the subsequent selection of the target parking area according to the parking space occupancy data.
  • each candidate parking area includes at least two parking spaces.
  • the parking space occupancy rates of the plurality of candidate parking areas are sorted, and the target parking area is selected from the plurality of candidate parking areas in order of the parking space occupancy rates from low to high.
  • the candidate parking area with the lowest parking space occupancy rate is selected as the target parking area.
  • the parking area recommendation server After selecting the target parking area, the parking area recommendation server generates a display instruction according to the target parking area, and sends the display instruction to the client, so that the client displays the target parking area to the user according to the display instruction.
  • the target parking area is selected from multiple candidate parking areas in the target parking lot according to the parking space occupancy data.
  • the parking area recommendation model is trained based on the user's historical parking behavior, which includes historical parking areas and historical parking space occupancy data.
  • the machine learning method is used to train the parking area recommendation model. Input the current parking space occupancy data corresponding to the user's current parking moment into the parking area recommendation model, and then output the target parking area.
  • the technical effect of recommending the target parking area to the user is realized.
  • the disclosure determines the parking space occupancy data of the target parking lot, and selects the target parking area from multiple candidate parking areas in the target parking lot according to the parking space occupancy data.
  • the parking space occupancy data plays a role in which parking area the user chooses to park in. Therefore, the disclosure achieves the effect of improving the accuracy of parking area recommendation and improves the parking experience of users.
  • the target parking space is selected from the unoccupied parking spaces in the target parking area.
  • the parking space recommendation rules include but are not limited to the following four types: A, B, C and D:
  • the parking space located in the middle of the three continuous unoccupied parking spaces is taken as the target parking space.
  • any one of the two continuous unoccupied parking spaces is taken as the target parking space.
  • the target parking area does not include continuous unoccupied parking spaces, take the parking spaces at the edge of the target parking area as the target parking spaces.
  • any unoccupied parking space is taken as the target parking space.
  • the priority of the above four parking space recommendation rules from high to low is parking space recommendation rule A, parking space recommendation rule B, parking space recommendation rule C, and parking space recommendation rule D.
  • the effect of recommending parking spaces for users is achieved, which further meets the parking needs of users and improves the parking efficiency of users. experience.
  • the parking area recommendation model is based on the parking space occupancy data and the target parking area is selected from multiple candidate parking areas in the target parking lot, if the occupancy of each parking space is used as a feature field to establish the parking area recommendation model, then The parking area recommendation model is very complex and difficult to fit.
  • Fig. 2 is a flow chart of a method for recommending a parking area according to an embodiment of the present disclosure, which is extended based on the above technical solution and can be combined with the above optional implementation.
  • S201 Determine the historical occupancy time and location information of each of the multiple parking spaces in the target parking lot.
  • the location information of any parking space indicates the relative position of the parking space in the target parking lot, and the location coordinates can be used to represent the location information of the parking space.
  • the historical occupancy time of any parking space indicates the average time that the parking space was occupied in the historical time period, where the historical time period can be a time period, such as 12:00 to 13:00, and the historical time period can also be days or weeks. The embodiment does not limit the historical time period.
  • S202 According to the historical occupancy time and location information of each parking space, perform area division on the multiple parking spaces to obtain multiple candidate parking areas of the target parking lot.
  • multiple parking spaces are clustered according to the historical occupancy time and location information of each parking space, and the multiple parking spaces are divided into regions according to the clustering results to obtain multiple parking spaces of the target parking lot.
  • Candidate parking area are clustered according to the historical occupancy time and location information of each parking space, and the multiple parking spaces are divided into regions according to the clustering results to obtain multiple parking spaces of the target parking lot.
  • S202 includes the following A1 and B1:
  • A1 Clustering the multiple parking spaces according to the historical occupancy time of each parking space to obtain a clustering result of the occupancy time of the multiple parking spaces.
  • a clustering algorithm is used to cluster the historical occupancy duration of multiple parking spaces to obtain the clustering result of the occupancy duration of multiple parking spaces, wherein the clustering algorithm includes but is not limited to the K-means clustering algorithm , mean shift clustering algorithm, density-based clustering algorithm or agglomerative hierarchical clustering algorithm, etc.
  • A1 includes A11, A12 and A13:
  • A11. Determine the historical average occupancy time of each parking space in each of the multiple time periods.
  • the occupancy time of each parking space on any day is divided into 24 time periods for statistics, that is, 0 o'clock to 1 o'clock, 1 o'clock to 2 o'clock, 2 o'clock to 3 o'clock, 3 o'clock to 4 o'clock, 4 o'clock 1:00-5:00, 5:00-6:00, 6:00-7:00, 7:00-8:00, 8:00-9:00, 9:00-10:00, 10:00-11:00, 11:00-12:00, 12:00- 13:00, 13:00-14:00, 14:00-15:00, 15:00-16:00, 16:00-17:00, 17:00-18:00, 18:00-19:00, 19:00-20:00, 20:00-21:00 , 21 o'clock to 22 o'clock, 22 o'clock to 23 o'clock, and 23 o'clock to 24 o'clock, a total of 24 hours of occupation time. Then calculate the historical average occupation time of each period in the preset historical time interval, for example, 30 days.
  • A12. Construct the occupancy duration vector of each parking space according to the historical average occupancy duration in each time period.
  • a preset vector assignment rule is adopted, and the vector is assigned correspondingly according to the historical average occupancy duration in each time period, so as to construct the occupancy duration vector of each parking space.
  • the vector assignment rule can be: Divide the historical average occupancy time of each time period into three situations, 1. Occupied for a short time, that is, the historical average occupancy time is 0-10 minutes; 2. Occupied for a long time , that is, the historical average occupancy time is 10-40 minutes; three, long-time occupation, that is, the historical average occupancy time is 40-60 minutes.
  • the vector is assigned a value of "0"; for the second case, the vector is assigned a value of "1"; for the third case, the vector is assigned a value of "2", thereby constructing a 1*24-dimensional occupancy time vector.
  • the vector of this time period is assigned a value of "1".
  • A13 Clustering the plurality of parking spaces according to the occupancy duration vector of each parking space to obtain the occupancy duration clustering result of the plurality of parking spaces.
  • a clustering algorithm is used to cluster the 1*24-dimensional occupancy duration vectors corresponding to the multiple parking spaces to obtain the occupancy duration clustering results of the multiple parking spaces.
  • the number of categories of the occupancy time clustering results can be set according to requirements, for example, three types of occupancy time clustering results.
  • the occupancy time clustering results and location information of multiple parking spaces are fused, and a clustering algorithm is used to cluster the fusion results again, and the multiple parking spaces are divided into regions according to the clustering results , to get multiple candidate parking areas.
  • B1 includes B11, B12 and B13:
  • the occupancy duration category of each parking space is determined according to the occupancy duration clustering result, and the occupancy duration category of the parking space is fused with location information to construct a spatial location vector of the parking space.
  • the location information of the 10 parking spaces are (x1, y1), (x2, y2), (x3,y3), (x4,y4), (x5,y5), (x6,y6), (x7,y7), (x8,y8), (x9,y9) and (x10,y10) .
  • the occupancy time clustering results include three types of occupancy time categories: Type 1, Type 2, and Type 3. Type 1 includes A01, A05, and A08, Type 2 includes A02, A03, and A10, and Type 3 includes A04, A06, A07, and A09.
  • each parking space corresponds to a 1*3-dimensional spatial position vector.
  • a clustering algorithm is used to cluster the 1*3-dimensional spatial position vectors of the multiple parking spaces to obtain the spatial position clustering results of the multiple parking spaces.
  • the parking spaces of the same type are divided into the same candidate parking area.
  • the spatial location clustering results include three categories: category 1, category 2, and category 3, then the parking spaces belonging to category 1 are divided into a candidate parking area, and the parking spaces belonging to category 2 are divided into a candidate parking area, which belongs to Class 3 parking spaces are divided into a candidate parking area.
  • the number of parking spaces is obtained. Spatial location clustering results, and then according to the spatial location clustering results of multiple parking spaces, multiple parking spaces are divided into regions, and multiple candidate parking areas are obtained, and multiple parking spaces are clustered based on location information, ensuring The obtained multiple parking spaces in each candidate parking area have similar location information, so that the multiple parking spaces in each candidate parking area are similar in spatial location.
  • the occupancy time clustering results of multiple parking spaces are obtained, and according to the occupancy time clustering results and the location information of each parking space, multiple The parking space is divided into areas to obtain multiple candidate parking areas, and multiple candidate parking areas are obtained based on the historical occupancy time and location information of each parking space, ensuring that multiple parking spaces in each candidate parking area have Similar historical occupancy time and location information make multiple parking spaces in each candidate parking area similar in occupancy and spatial location.
  • the parking area recommendation model is trained in the following manner:
  • the historical parking area where the user parked at any historical moment is used as the training label, and the historical parking space occupancy data of the target parking lot corresponding to the historical moment is used as the training data, and the model training is performed to obtain the parking area recommendation model .
  • model training is performed according to the historical parking space occupancy data and the historical parking area, and the parking area recommendation model is obtained.
  • the learning method learns the user's parking behavior, so that the target parking area obtained through the training parking area recommendation model is more in line with the user's actual parking needs.
  • the types of parking area recommendation models include but are not limited to Random Forest models, Extreme Gradient Boost (XGBOOST) models, Light Gradient Boosting Machine (Light Gradient Boosting Machine, LightGBM) models or CatBoost models.
  • This disclosure determines the historical occupancy time and location information of each parking space in the target parking lot, and divides the multiple parking spaces according to the historical occupancy time and location information of each parking space to obtain multiple parking spaces in the target parking lot.
  • Candidate parking areas so that multiple parking spaces in the same candidate parking area are similar in terms of occupancy and spatial location, so it is only necessary to use the occupancy of candidate parking areas as a feature field to establish a parking area recommendation model without using
  • the occupancy of each parking space is used as a feature field to establish a parking area recommendation model, which greatly reduces the complexity of the parking area recommendation model and ensures that the model can be fitted normally; based on the parking area recommendation model, according to the parking space occupancy data, from The target parking area is selected from multiple candidate parking areas in the target parking lot, and the effect of quickly recommending the target parking area to the user based on the recommendation model is realized.
  • the current time information includes at least one of month, week, day and time period; according to the current time information and the parking space occupancy data, from the target parking lot A target parking area is selected from multiple candidate parking areas.
  • “Month” means the month of the current moment, such as January or February; “Week” means the current moment is the week of the month; That is to say the current moment is what time of the day.
  • the target parking area is selected from multiple candidate parking areas in the target parking lot according to current time information and parking space occupancy data.
  • the parking area recommendation model is trained in the following way: determine the historical parking area where the user parked at any historical moment, and the historical parking space occupancy data of the target parking lot corresponding to the historical moment, according to the historical time information of the historical moment, Model training is performed on the historical parking space occupancy data and the historical parking area to obtain the parking area recommendation model.
  • the training process of the parking area recommendation model is similar to the model training process in S204 of this embodiment, and will not be repeated here.
  • the target parking area realizes the joint determination of the target parking area based on two data dimensions of current time information and parking space occupancy data, which further improves the accuracy of parking area recommendation and improves the user's parking experience.
  • the acquisition, storage and application of the user's personal information involved are in compliance with relevant laws and regulations, and do not violate public order and good customs.
  • Fig. 3 is a schematic structural diagram of an apparatus for recommending a parking area according to an embodiment of the present disclosure, which can be applied to recommending a parking area of a target parking lot to a user.
  • the apparatus in this embodiment can be implemented by software and/or hardware, and can be integrated on any electronic device with computing capability.
  • the parking area recommendation device 30 disclosed in this embodiment may include a parking space occupancy data determination module 31 and a target parking area selection module 32, wherein:
  • the parking space occupancy data determining module 31 is configured to determine the parking space occupancy data of the target parking lot; the target parking area selection module 32 is configured to select the target parking area from a plurality of candidate parking areas of the target parking lot according to the parking space occupancy data area; wherein, each candidate parking area includes at least two parking spaces.
  • the target parking area selection module 32 is set to:
  • a target parking area is selected from a plurality of candidate parking areas in the target parking lot; the parking area recommendation model is trained in the following manner:
  • the device also includes a candidate parking area determination module, which is set to:
  • the candidate parking area determining module is configured to divide the plurality of parking spaces according to the historical occupancy time and location information of each parking space in the following manner to obtain the plurality of candidate parking areas:
  • the candidate parking area determination module is configured to cluster the multiple parking spaces according to the historical occupancy time of each parking space in the following manner to obtain the occupancy time clustering result of the multiple parking spaces:
  • the candidate parking area determination module is configured to perform area division on the multiple parking spaces according to the occupancy time clustering result and the location information of each parking space in the following manner to obtain the multiple candidate parking spaces.
  • Parking area :
  • the clustering result of the occupation time and the position information of each parking space construct the spatial position vector of each parking space; cluster the plurality of parking spaces according to the spatial position vector of each parking space to obtain The spatial position clustering results of the plurality of parking spaces; according to the spatial position clustering results of the plurality of parking spaces, the plurality of parking spaces are divided into areas to obtain the plurality of candidate parking areas.
  • the parking space occupancy data includes at least one of the total parking space occupancy rate, the parking space occupancy rate of each floor, the parking space occupancy rate of each candidate parking area, and the parking space occupancy rate of key parking areas; wherein, the The key parking area is determined according to the identification information of each candidate parking area.
  • the current time information determination module is also included, which is set to:
  • the current time information includes at least one of month, week, day and time period; according to the current time information and the parking space occupancy data, from the target parking lot A target parking area is selected from multiple candidate parking areas.
  • the parking area recommendation device 30 disclosed in the embodiment of the present disclosure can execute the parking area recommendation method disclosed in the embodiment of the present disclosure, and has corresponding functional modules and effects for executing the method.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • FIG. 4 shows a schematic block diagram of an example electronic device 400 that may be used to implement embodiments of the present disclosure.
  • Electronic device 400 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic device 400 may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 400 includes a computing unit 401 that can be loaded into a random access memory (Random Access Memory, RAM) according to a computer program stored in a read-only memory (Read-Only Memory, ROM) 402 or from a storage unit 408. ) 403 to perform various appropriate actions and processes. In the RAM 403, various programs and data necessary for the operation of the device 400 can also be stored.
  • the computing unit 401, ROM 402, and RAM 403 are connected to each other through a bus 404.
  • An input/output (Input/Output, I/O) interface 405 is also connected to the bus 404 .
  • the I/O interface 405 includes: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a magnetic disk, an optical disk, etc. ; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 409 allows the device 400 to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.
  • Computing unit 401 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), a variety of dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, a variety of operating Computing units of machine learning model algorithms, digital signal processors (Digital Signal Processing, DSP), and any appropriate processors, controllers, microcontrollers, etc.
  • the calculation unit 401 executes the methods and processes described above, such as the parking area recommendation method.
  • the parking area recommendation method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 408 .
  • part or all of the computer program may be loaded and/or installed on the device 400 via the ROM 402 and/or the communication unit 409 .
  • the computing unit 401 may be configured in any other appropriate way (for example, by means of firmware) to execute the parking area recommendation method.
  • Various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that can is a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • a programmable processor that can is a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media examples include one or more wire-based electrical connections, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM, or Flash memory) ), fiber optics, Compact Disc Read-Only Memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • wire-based electrical connections portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM, or Flash memory)
  • fiber optics Compact Disc Read-Only Memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • CD-ROM Compact Disc Read-Only Memory
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display ( Liquid Crystal Display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the computer.
  • a display device e.g., a cathode ray tube (CRT) or a liquid crystal display ( Liquid Crystal Display (LCD) monitor
  • a keyboard and pointing device e.g., a mouse or trackball
  • Other types of devices may also be configured to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (Wide Area Network, WAN), blockchain networks, and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problems existing in traditional physical host and virtual private server (Virtual Private Server, VPS) services.
  • VPS Virtual Private Server
  • the defects of difficult management and weak business expansion can also be a server of a distributed system, or a server combined with a blockchain.
  • Steps can be reordered, added, or removed using the various forms of flow shown above.
  • steps described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Abstract

提供了一种停车区域推荐方法、装置、电子设备和介质。停车区域推荐方法包括：确定目标停车场的车位占用数据（S101）；根据车位占用数据，从目标停车场的多个候选停车区域中选取目标停车区域；其中，每个候选停车区域中包括至少两个停车位（S102）。

Description

停车区域推荐方法、装置、电子设备和介质
本申请要求在2021年05月12日提交中国专利局、申请号为202110518142.7的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及计算机技术领域，涉及机器学习技术、云计算及云服务技术领域，例如涉及一种停车区域推荐方法、装置、电子设备和介质。
背景技术
随着汽车保有量的不断增加，导致停车位资源十分紧张，停车位的合理推荐变得越来越有意义。
停车位推荐大多是基于每个停车位与出入口及电梯口的距离，来向用户推荐最优停车位。
发明内容
本公开提供了一种用于提高停车区域推荐精准度的方法、装置、电子设备和介质。
根据本公开的一方面，提供了一种停车区域推荐方法，包括：
确定目标停车场的车位占用数据；
根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；其中，每个候选停车区域中包括至少两个停车位。
根据本公开的另一方面，提供了一种停车区域推荐装置，包括：
车位占用数据确定模块，设置为确定目标停车场的车位占用数据；
目标停车区域选取模块，设置为根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；其中，每个候选停车区域中包括至少两个停车位。
根据本公开的另一方面，提供了一种电子设备，包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述 至少一个处理器执行，以使所述至少一个处理器能够执行上述的停车区域推荐方法。
根据本公开的另一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行上述的停车区域推荐方法。
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现上述的停车区域推荐方法。
附图说明
图1是根据本公开实施例公开的一种停车区域推荐方法的流程图；
图2是根据本公开实施例公开的一种停车区域推荐方法的流程图；
图3是根据本公开实施例公开的一种停车区域推荐装置的结构示意图；
图4是用来实现本公开实施例公开的停车区域推荐方法的电子设备的框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的多种细节以助于理解，应当将它们认为仅仅是示范性的。为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
停车区域推荐大多是基于每个停车位与出入口的距离，和/或用户下车后到电梯口或楼梯口的距离来向用户推荐最优停车位。但是这种方法仅考虑了用户主观关心的路径距离维度，考虑比较单一，从而导致无法准确地为用户推荐当前最优的停车区域，导致用户的停车体验较差。
当一个用户去停车场停车的时候，用户一定是根据停车场中车位被占用的情况，去分析判断选择停到哪个停车位的。例如说当进入停车场后，发现车位非常紧张，用户可能会在往前行驶的过程中，就近的选择一个停车位。又例如，当进入停车场后，发现车位非常充足，可能会选择离电梯口或出入口更近一些的车位。因此停车场的车位占用情况对用户选择在哪个停车区域进行停车，起到了重要作用。
图1是根据本公开实施例公开的一种停车区域推荐方法的流程图，本实施例可以适用于向用户推荐目标停车场的停车区域的情况。本实施例方法可以由本公开实施例公开的停车区域推荐装置来执行，所述装置可采用软件和/或硬件实现，并可集成在任意的具有计算能力的电子设备上。
如图1所示，本实施例公开的停车区域推荐方法可以包括：
S101、确定目标停车场的车位占用数据。
目标停车场的类型包括但不限于露天停车场、地下停车场或者立体停车场等，目标停车场的层数可以是一层也可以多层，本实施例并不对目标停车场的类型和层数进行任何限定。车位占用数据体现了目标停车场中车位的被占用情况，车位占用数据可以用车位占用数量来表示，也可以用车位占用率来表示，还可以用车位占用数量和车位占用率两者共同来表示，本实施例并不对车位占用数据的数据类型做限定，凡是能够体现目标停车场中车位被占用情况的数据，都可以作为车位占用数据。
在一种实施方式中，用户在进入目标停车场之前，在智能终端安装的客户端中访问停车区域推荐界面，并在停车区域推荐界面中实施生成停车区域推荐指令的操作，其中，智能终端包括但不限于智能手机、智能平板、智能手表或笔记本电脑等任意安装有智能操作系统的电子设备；生成停车区域推荐指令的操作包括但不限于，用户在停车区域推荐界面中点击预设控件，例如“停车区域推荐”按钮控件，从而生成停车区域推荐指令。停车区域推荐服务器获取到客户端发送来的停车区域推荐指令，相应的获取目标停车场中停车位的被占用情况，进而根据停车位的被占用情况按预设规则进行统计分析，得到目标停车场的车位占用数据。其中，停车位的被占用情况包括已被占用和未被占用两种情况。确定停车位是否被占用的方式包括但不限于以下至少一种：1)通过每个停车位上安装的传感器检测该停车位是否被占用，例如若通过光线传感器检测到光线被遮挡，则确定该停车位已被占用；又例如通过压力传感器检测到压力增大，则确定该停车位已被占用。2)通过摄像头拍摄的停车位图像确定停车位是否被占用，例如基于目标检测算法在停车位图像中检测到车辆，则确定停车位已被占用。
可选的，车位占用数据包括车位总占用率、每个楼层的车位占用率、每个候选停车区域的车位占用率和重点停车区域的车位占用率中的至少一种；其中，重点停车区域是根据每个候选停车区域的标识信息确定的。
车位总占用率表示目标停车场的停车位总占用率，通过停车位总占用数量与停车位总数量之间的比值表示，例如停车位总占用数量为500，停车位总数量为1000，则车位总占用率为500/1000×100％＝50％。
每个楼层的车位占用率表示目标停车场的每个楼层的停车位占用率，通过该楼层的停车位占用数量，与该楼层的停车位总数量之间的比值表示，例如目标停车场一楼的停车位占用数量为100，目标停车场一楼的停车位总数量为150，则目标停车场一楼的车位占用率为100/150×100％＝66％。
候选停车区域是预先由相关人员对目标停车场的多个停车位进行区域划分得到的。每个候选停车区域的车位占用率通过该候选停车区域的停车位占用数量，与该候选停车区域的停车位总数量之间的比值表示，例如候选停车区域A的停车位占用数量为10，候选停车区域A的停车位总数量为50，则候选停车区域A的车位占用率为10/50×100％＝20％。
重点停车区域是预先由相关人员设定的重要程度较高的候选停车区域，例如电梯口附近的候选停车区域、目标停车场入口附近的候选停车区域、目标停车场出口附近的候选停车区域、楼层入口附近的候选停车区域和楼层出口附近的候选停车区域等。不同候选停车区域对应不同的标识信息，而重点停车区域是根据候选停车区域的标识信息确定的。例如预先设定标识信息为“0001”、“0005”和“0010”的候选停车区域为重点停车区域，则遍历候选停车区域的标识信息，将标识信息为“0001”、“0005”和“0010”的候选停车区域作为重点停车区域，且将标识信息为“0001”、“0005”和“0010”的候选停车区域的车位占用率作为对应重点停车区域的车位占用率。
通过将车位总占用率、每个楼层的车位占用率、每个候选停车区域的车位占用率和重点停车区域的车位占用率中的至少一种，作为车位占用数据，扩充了车位占用数据的数据维度，间接提高了最终停车区域推荐的精准度。
可选的，车位占用数据包括车位总占用数量、每个楼层的车位占用数量、每个候选停车区域的车位占用数量和重点停车区域的车位占用数量中的至少一种。
车位总占用数量表示目标停车场的停车位总占用数量。每个楼层的车位占用数量表示目标停车场中每个楼层的停车位占用数量。候选停车区域的车位占用数量即该候选停车区域中被占用的停车位数量。重点停车区域的车位占用数量，即相关人员设定的重要程度较高的候选停车区域中被占用的停车位数量。
通过确定目标停车场的车位占用数据，为后续根据车位占用数据选取目标停车区域奠定了数据基础。
S102、根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；其中，每个候选停车区域中包括至少两个停车位。
在一种实施方式中，将多个候选停车区域的车位占用率进行排序，且按照车位占用率由低到高的顺序，从多个候选停车区域中选取目标停车区域。可选的，选取车位占用率最低的候选停车区域作为目标停车区域。在选取目标停车区域后，停车区域推荐服务器根据目标停车区域生成展示指令，并将 展示指令发送给客户端，以使得客户端根据展示指令向用户展示目标停车区域。
在另一种实施方式中，基于停车区域推荐模型，根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域。
停车区域推荐模型是基于用户的历史停车行为训练得到的，历史停车行为包括历史停车区域以及历史车位占用数据等。
根据海量用户的历史停车行为中的历史停车区域以及历史车位占用数据，采用机器学习的方法训练得到停车区域推荐模型。将用户当前停车时刻对应的当前车位占用数据输入到停车区域推荐模型中，则输出目标停车区域。
通过根据车位占用数据，从目标停车场的多个候选停车区域中选取目标停车区域，实现了向用户推荐目标停车区域的技术效果。
本公开通过确定目标停车场的车位占用数据，并根据车位占用数据，从目标停车场的多个候选停车区域中选取目标停车区域，由于车位占用数据对用户选择在哪个停车区域进行停车，起到了重要作用，因此本公开实现了提高停车区域推荐精准度的效果，改善了用户的停车体验。
在上述实施例的基础上，S102之后，还包括：
基于预先设定的车位推荐规则，从目标停车区域中未被占用的停车位中选择目标停车位。
可选的，车位推荐规则包括但不限于以下A、B、C和D四种：
A、若目标停车区域包括三个连续的未被占用的停车位，则将位于三个连续的未被占用的停车位中间的停车位作为目标停车位。
B、若目标停车区域包括两个连续的未被占用的停车位，则将两个连续的未被占用的停车位中的任一停车位作为目标停车位。
C、若目标停车区域不包括连续的未被占用的停车位，则将位于目标停车区域边缘的停车位，作为目标停车位。
D、若目标停车区域不包括连续的未被占用的停车位，则将任一未被占用的停车位作为目标停车位。
以上四种车位推荐规则的优先级从高到低依次为车位推荐规则A、车位推荐规则B、车位推荐规则C、车位推荐规则D。
通过基于预先设定的车位推荐规则，从目标停车区域中未被占用的停车位中选择目标停车位，实现了为用户推荐停车位的效果，进一步满足了用户的停车需求，提高了用户的停车体验。
当基于停车区域推荐模型，根据车位占用数据，从目标停车场的多个候选停车区域中选取目标停车区域时，若把每个停车位的占用情况作为特征字段来建立停车区域推荐模型，则会导致停车区域推荐模型非常复杂，难以拟合。
图2是根据本公开实施例公开的一种停车区域推荐方法的流程图，基于上述技术方案进行扩展，并可以与上述可选实施方式进行结合。
S201、确定所述目标停车场中多个停车位中每个停车位的历史占用时长以及位置信息。
任一停车位的位置信息表示该停车位位于目标停车场的相对位置，可以用位置坐标来表示停车位的位置信息。任一停车位的历史占用时长表示该停车位在历史时间段中被占用的平均时长，其中历史时间段可以是时段，例如12点～13点，历史时间段还可以是天或者是周，本实施例并不对历史时间段进行限定。
S202、根据每个停车位的历史占用时长以及位置信息，对所述多个停车位进行区域划分，得到目标停车场的多个候选停车区域。
在一种实施方式中，根据每个停车位的历史占用时长以及位置信息，对多个停车位进行聚类，并根据聚类结果对多个停车位进行区域划分，得到目标停车场的多个候选停车区域。
可选的，S202包括以下A1和B1：
A1、根据每个停车位的历史占用时长对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果。
在一种实施方式中，采用聚类算法对多个停车位的历史占用时长进行聚类，得到多个停车位的占用时长聚类结果，其中，聚类算法包括但不限于K均值聚类算法、均值漂移聚类算法、基于密度的聚类算法或凝聚层次聚类算法等。
可选的，A1包括A11、A12和A13：
A11、确定每个停车位在多个时段中每个时段的历史平均占用时长。
示例性的，将每个停车位在任一天的占用时长分为24个时段进行统计，即分别统计0点～1点、1点～2点、2点～3点、3点～4点、4点～5点、5点～6点、6点～7点、7点～8点、8点～9点、9点～10点、10点～11点、11点～12点、12点～13点、13点～14点、14点～15点、15点～16点、16点～17点、17 点～18点、18点～19点、19点～20点、20点～21点、21点～22点、22点～23点、以及23点～24点共24个时段的占用时长。进而计算在预设历史时间区间中，例如30天，每个时段的历史平均占用时长。
A12、根据每个时段中的历史平均占用时长，构建所述每个停车位的占用时长向量。
在一种实施方式中，采用预设的向量赋值规则，根据每个时段中的历史平均占用时长，相应的进行向量赋值，构建每个停车位的占用时长向量。
可选的，向量赋值规则可以是：把每个时段的历史平均占用时长分为三种情况，一、短时间被占用，即历史平均占用时长为0-10分钟；二、较长时间被占用，即历史平均占用时长为10-40分钟；三、长时间被占用，即历史平均占用时长为40-60分钟。对于第一种情况，向量赋值“0”；对于第二种情况，向量赋值“1”；对于第三种情况，向量赋值“2”，从而构建一个1*24维的占用时长向量。
示例性的，假设任一停车位在5点～6点的历史平均占用时长为24分钟，则将该时段的向量赋值为“1”。
A13、根据每个停车位的占用时长向量对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果。
在一种实施方式中，采用聚类算法对多个停车位对应的1*24维的占用时长向量进行聚类，得到多个停车位的占用时长聚类结果。其中，占用时长聚类结果的类别数量可根据需求进行设置，例如为三类占用时长聚类结果。
通过确定每个停车位在每个时段中的历史平均占用时长，并根据每个时段中的历史平均占用时长，构建该停车位的占用时长向量，进而根据每个停车位的占用时长向量对多个停车位进行聚类，得到多个停车位的占用时长聚类结果，实现了基于历史平均占用时长对多个停车位进行聚类，保证后续划分得到的每个候选停车区域中的多个停车位都具有相似的历史平均占用时长，使得每个候选停车区域中的多个停车位在占用情况上是相似的。
B1、根据所述占用时长聚类结果以及每个停车位的位置信息，对所述多个停车位进行区域划分，得到多个候选停车区域。
在一种实施方式中，将多个停车位的占用时长聚类结果以及位置信息进行融合，并采用聚类算法对融合结果再次进行聚类，并根据聚类结果对多个停车位进行区域划分，得到多个候选停车区域。
可选的，B1包括B11、B12和B13：
B11、根据所述占用时长聚类结果以及每个停车位的位置信息，构建所述每个停车位的空间位置向量。
在一种实施方式中，根据占用时长聚类结果确定每个停车位的占用时长类别，且将该停车位的占用时长类别与位置信息进行融合，构建该停车位的空间位置向量。
示例性的，假设一共有10个停车位：A01、A02、A03、A04、A05、A06、A07、A08、A09和A10。10个停车位的位置信息分别为(x1,y1)、(x2,y2)、(x3,y3)、(x4,y4)、(x5,y5)、(x6,y6)、(x7,y7)、(x8,y8)、(x9,y9)和(x10,y10)。占用时长聚类结果包括三类占用时长类别：1类、2类和3类，1类包括A01、A05和A08，2类包括A02、A03和A10，3类包括A04、A06、A07和A09。则10个停车位的空间位置向量分别为：A01(1,x1,y1)、A02(2,x2,y2)、A03(2,x3,y3)、A04(3,x4,y4)、A05(1,x5,y5)、A06(3,x6,y6)、A07(3,x7,y7)、A08(1,x8,y8)、A09(3,x9,y9)和A10(2,x10,y10)。即每个停车位对应一个1*3维的空间位置向量。
B12、根据每个停车位的空间位置向量对所述多个停车位进行聚类，得到所述多个停车位的空间位置聚类结果。
在一种实施方式中，采用聚类算法对多个停车位的1*3维的空间位置向量进行聚类，得到多个停车位的空间位置聚类结果。
B13、根据所述多个停车位的空间位置聚类结果，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
在一种实施方式中，根据空间位置聚类结果，将同一类的停车位划分为同一个候选停车区域。例如空间位置聚类结果包括三类：1类、2类和3类，则属于将1类的停车位划分为一个候选停车区域，将属于2类的停车位划分为一个候选停车区域，将属于3类的停车位划分为一个候选停车区域。
通过根据占用时长聚类结果以及每个停车位的位置信息，构建该停车位的空间位置向量，并根据每个停车位的空间位置向量对多个停车位进行聚类，得到多个停车位的空间位置聚类结果，进而根据多个停车位的空间位置聚类结果，对多个停车位进行区域划分，得到多个候选停车区域，实现了基于位置信息对多个停车位进行聚类，保证得到的每个候选停车区域中的多个停车位都具有相似的位置信息，使得每个候选停车区域中的多个停车位在空间位置上是相似的。
通过根据每个停车位的历史占用时长对多个停车位进行聚类，得到多个停车位的占用时长聚类结果，并根据占用时长聚类结果以及每个停车位的位 置信息，对多个停车位进行区域划分，得到多个候选停车区域，实现了基于每个停车位的历史占用时长和位置信息得到多个候选停车区域，保证得到的每个候选停车区域中的多个停车位都具有相似的历史占用时长和位置信息，使得每个候选停车区域中的多个停车位在占用情况和空间位置上都是相似的。
S203、确定目标停车场的车位占用数据。
S204、基于停车区域推荐模型，根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域。
可选的，停车区域推荐模型采用以下方式训练得到：
确定用户在任意历史时刻停车的历史停车区域，以及所述历史时刻对应的所述目标停车场的历史车位占用数据；根据所述历史车位占用数据和所述历史停车区域进行模型训练，得到所述停车区域推荐模型。
在一种实施方式中，将用户在任意历史时刻停车的历史停车区域作为训练标签，且将所述历史时刻对应的目标停车场的历史车位占用数据作为训练数据，进行模型训练得到停车区域推荐模型。
示例性的，假设用户A在B时刻将车停到了停车区域C，B时刻对应的车位占用数据为D，则将D作为训练数据，且将C作为D的训练标签进行模型训练，得到停车区域推荐模型。
通过确定用户在任意历史时刻停车的历史停车区域，以及历史时刻对应的目标停车场的历史车位占用数据；根据历史车位占用数据和历史停车区域进行模型训练，得到停车区域推荐模型，实现了通过机器学习的方式学习用户的停车行为，使得通过训练得到的停车区域推荐模型得到的目标停车区域，更加符合用户实际的停车需求。
可选的，停车区域推荐模型的类型包括但不限于Random Forest模型、极端梯度提升(Extreme Gradient Boost，XGBOOST)模型、轻量级梯度提升机(Light Gradient Boosting Machine，LightGBM)模型或CatBoost模型等。
本公开通过确定目标停车场中每个停车位的历史占用时长以及位置信息，并根据每个停车位的历史占用时长以及位置信息，对多个停车位进行区域划分，得到目标停车场的多个候选停车区域，使得同一个候选停车区域的多个停车位在占用情况和空间位置上都是相似的，因此仅需要将候选停车区域的占用情况作为特征字段来建立停车区域推荐模型，而无需把每个停车位的占用情况作为特征字段来建立停车区域推荐模型，从而大大降低了停车区域推荐模型的复杂度，保证模型能够正常进行拟合；通过基于停车区域推荐模型，根据车位占用数据，从目标停车场的多个候选停车区域中选取目标停车区域， 实现了基于推荐模型的方式快速向用户推荐目标停车区域的效果。
在上述实施例的基础上，还包括：
确定当前时刻对应的当前时间信息；其中，所述当前时间信息包括月、周、日和时段中的至少一种；根据所述当前时间信息和所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域。
“月”即表示当前时刻的月份，例如一月份或二月份等；“周”即表示当前时刻为月份中的第几周；“日”即表示当前时刻为一周中的周几；“时段”即表示当前时刻为一天中的几点。
在一种实施方式中，基于停车区域推荐模型，根据当前时间信息和车位占用数据，从目标停车场的多个候选停车区域中选取目标停车区域。
停车区域推荐模型采用以下方式训练得到：确定用户在任意历史时刻停车的历史停车区域，以及所述历史时刻对应的所述目标停车场的历史车位占用数据，根据所述历史时刻的历史时间信息、所述历史车位占用数据和所述历史停车区域进行模型训练，得到所述停车区域推荐模型。停车区域推荐模型的训练过程与本实施例S204中的模型训练过程类似，在本处不再赘述。
通过确定当前时刻对应的当前时间信息；其中，当前时间信息包括月、周、日和时段中的至少一种；根据当前时间信息和车位占用数据，从目标停车场的多个候选停车区域中选取目标停车区域，实现了基于当前时间信息和车位占用数据两个数据维度，共同确定目标停车区域，进一步提高了停车区域推荐的精准度，改善了用户的停车体验。
本公开的技术方案中，所涉及的用户个人信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。
图3是根据本公开实施例公开的一种停车区域推荐装置的结构示意图，可以适用于向用户推荐目标停车场的停车区域的情况。本实施例装置可采用软件和/或硬件实现，并可集成在任意的具有计算能力的电子设备上。
如图3所示，本实施例公开的停车区域推荐装置30可以包括车位占用数据确定模块31和目标停车区域选取模块32，其中：
车位占用数据确定模块31，设置为确定目标停车场的车位占用数据；目标停车区域选取模块32，设置为根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；其中，每个候选停车区域中包括至少两个停车位。
可选的，所述目标停车区域选取模块32，设置为：
基于停车区域推荐模型，根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；所述停车区域推荐模型采用以下方式训练得到：
确定用户在任意历史时刻停车的历史停车区域，以及所述历史时刻对应的所述目标停车场的历史车位占用数据；根据所述历史车位占用数据和所述历史停车区域进行模型训练，得到所述停车区域推荐模型。
可选的，所述装置还包括候选停车区域确定模块，设置为：
确定所述目标停车场中多个停车位中每个停车位的历史占用时长以及位置信息；根据每个停车位的历史占用时长以及位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
可选的，所述候选停车区域确定模块设置为通过如下方式根据每个停车位的历史占用时长以及位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域：
根据每个停车位的历史占用时长对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果；根据所述占用时长聚类结果以及每个停车位的位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
可选的，所述候选停车区域确定模块设置为通过如下方式根据每个停车位的历史占用时长对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果：
确定每个停车位在多个时段中每个时段的历史平均占用时长；根据每个时段中的历史平均占用时长，构建所述每个停车位的占用时长向量；根据每个停车位的占用时长向量对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果。
可选的，所述候选停车区域确定模块设置为通过如下方式根据所述占用时长聚类结果以及每个停车位的位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域：
根据所述占用时长聚类结果以及每个停车位的位置信息，构建所述每个停车位的空间位置向量；根据每个停车位的空间位置向量对所述多个停车位进行聚类，得到所述多个停车位的空间位置聚类结果；根据所述多个停车位的空间位置聚类结果，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
可选的，所述车位占用数据包括车位总占用率、每个楼层的车位占用率、每个候选停车区域的车位占用率和重点停车区域的车位占用率中的至少一种；其中，所述重点停车区域是根据每个候选停车区域的标识信息确定的。
可选的，还包括当前时间信息确定模块，设置为：
确定当前时刻对应的当前时间信息；其中，所述当前时间信息包括月、周、日和时段中的至少一种；根据所述当前时间信息和所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域。
本公开实施例所公开的停车区域推荐装置30可执行本公开实施例所公开的停车区域推荐方法，具备执行方法相应的功能模块和效果。本实施例中未详尽描述的内容可以参考本公开任意方法实施例中的描述。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
图4示出了可以用来实施本公开的实施例的示例电子设备400的示意性框图。电子设备400旨在表示多种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备400还可以表示多种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图4所示，设备400包括计算单元401，其可以根据存储在只读存储器(Read-Only Memory，ROM)402中的计算机程序或者从存储单元408加载到随机访问存储器(Random Access Memory，RAM)403中的计算机程序，来执行多种适当的动作和处理。在RAM 403中，还可存储设备400操作所需的多种程序和数据。计算单元401、ROM 402以及RAM 403通过总线404彼此相连。输入/输出(Input/Output，I/O)接口405也连接至总线404。
设备400中的多个部件连接至I/O接口405，包括：输入单元406，例如键盘、鼠标等；输出单元407，例如多种类型的显示器、扬声器等；存储单元408，例如磁盘、光盘等；以及通信单元409，例如网卡、调制解调器、无线通信收发机等。通信单元409允许设备400通过诸如因特网的计算机网络和/或多种电信网络与其他设备交换信息/数据。
计算单元401可以是多种具有处理和计算能力的通用和/或专用处理组件。计算单元401的一些示例包括但不限于中央处理单元(Central Processing  Unit，CPU)、图形处理单元(Graphics Processing Unit，GPU)、多种专用的人工智能(Artificial Intelligence，AI)计算芯片、多种运行机器学习模型算法的计算单元、数字信号处理器(Digital Signal Processing，DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元401执行上文所描述的方法和处理，例如停车区域推荐方法。例如，在一些实施例中，停车区域推荐方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元408。在一些实施例中，计算机程序的部分或者全部可以经由ROM402和/或通信单元409而被载入和/或安装到设备400上。当计算机程序加载到RAM 403并由计算单元401执行时，可以执行上文描述的停车区域推荐方法的一个或多个步骤。备选地，在其他实施例中，计算单元401可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行停车区域推荐方法。
本文中以上描述的系统和技术的多种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、芯片上的系统(System on Chip，SoC)、复杂可编程逻辑设备(Complex Programmable Logic Device，CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。多种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的示例会包括基于一个或多个线的电气连接、便携式计算机盘、 硬盘、RAM、ROM、可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：设置为向用户显示信息的显示装置(例如，阴极射线管(Cathode Ray Tube，CRT)或者液晶显示器(Liquid Crystal Display，LCD)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以设置为提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(Local Area Network，LAN)、广域网(Wide Area Network，WAN)、区块链网络和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，以解决了传统物理主机与虚拟专用服务器(Virtual Private Server，VPS)服务中，存在的管理难度大，业务扩展性弱的缺陷。服务器也可以为分布式系统的服务器，或者是结合了区块链的服务器。
可以使用上面所示的多种形式的流程，重新排序、增加或删除步骤。例如，本公开中记载的多个步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。

Claims (19)

  1. 一种停车区域推荐方法，包括：
    确定目标停车场的车位占用数据；
    根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；其中，每个候选停车区域中包括至少两个停车位。
  2. 根据权利要求1所述的方法，其中，所述根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域，包括：
    基于停车区域推荐模型，根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；
    所述停车区域推荐模型采用以下方式训练得到：
    确定用户在一历史时刻停车的历史停车区域，以及所述历史时刻对应的所述目标停车场的历史车位占用数据；
    根据所述历史车位占用数据和所述历史停车区域进行模型训练，得到所述停车区域推荐模型。
  3. 根据权利要求1所述的方法，其中，所述多个候选停车区域是通过如下方式确定的：
    确定所述目标停车场中多个停车位中每个停车位的历史占用时长以及位置信息；
    根据每个停车位的历史占用时长以及位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
  4. 根据权利要求3所述的方法，其中，所述根据每个停车位的历史占用时长以及位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域，包括：
    根据每个停车位的历史占用时长对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果；
    根据所述占用时长聚类结果以及每个停车位的位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
  5. 根据权利要求4所述的方法，其中，所述根据每个停车位的历史占用时长对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果，包括：
    确定每个停车位在多个时段中每个时段的历史平均占用时长；
    根据每个时段中的历史平均占用时长，构建所述每个停车位的占用时长向量；
    根据每个停车位的占用时长向量对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果。
  6. 根据权利要求4所述的方法，其中，所述根据所述占用时长聚类结果以及每个停车位的位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域，包括：
    根据所述占用时长聚类结果以及每个停车位的位置信息，构建所述每个停车位的空间位置向量；
    根据每个停车位的空间位置向量对所述多个停车位进行聚类，得到所述多个停车位的空间位置聚类结果；
    根据所述多个停车位的空间位置聚类结果，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
  7. 根据权利要求1所述的方法，其中，所述车位占用数据包括车位总占用率、每个楼层的车位占用率、每个候选停车区域的车位占用率和重点停车区域的车位占用率中的至少一种；其中，所述重点停车区域是根据每个候选停车区域的标识信息确定的。
  8. 根据权利要求1所述的方法，还包括：
    确定当前时刻对应的当前时间信息；其中，所述当前时间信息包括月、周、日和时段中的至少一种；
    根据所述当前时间信息和所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域。
  9. 一种停车区域推荐装置，包括：
    车位占用数据确定模块，设置为确定目标停车场的车位占用数据；
    目标停车区域选取模块，设置为根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；其中，每个候选停车区域中包括至少两个停车位。
  10. 根据权利要求9所述的装置，其中，所述目标停车区域选取模块，设置为：
    基于停车区域推荐模型，根据所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域；
    所述停车区域推荐模型采用以下方式训练得到：
    确定用户在一历史时刻停车的历史停车区域，以及所述历史时刻对应的所述目标停车场的历史车位占用数据；
    根据所述历史车位占用数据和所述历史停车区域进行模型训练，得到所述停车区域推荐模型。
  11. 根据权利要求9所述的装置，其中，所述装置还包括候选停车区域确定模块，设置为：
    确定所述目标停车场中多个停车位中每个停车位的历史占用时长以及位置信息；
    根据每个停车位的历史占用时长以及位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
  12. 根据权利要求11所述的装置，其中，所述候选停车区域确定模块设置为通过如下方式根据每个停车位的历史占用时长以及位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域：
    根据每个停车位的历史占用时长对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果；
    根据所述占用时长聚类结果以及每个停车位的位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
  13. 根据权利要求12所述的装置，其中，所述候选停车区域确定模块设置为通过如下方式根据每个停车位的历史占用时长对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果：
    确定每个停车位在多个时段中每个时段的历史平均占用时长；
    根据每个时段中的历史平均占用时长，构建所述每个停车位的占用时长向量；
    根据每个停车位的占用时长向量对所述多个停车位进行聚类，得到所述多个停车位的占用时长聚类结果。
  14. 根据权利要求12所述的装置，其中，所述候选停车区域确定模块设置为通过如下方式根据所述占用时长聚类结果以及每个停车位的位置信息，对所述多个停车位进行区域划分，得到所述多个候选停车区域：
    根据所述占用时长聚类结果以及每个停车位的位置信息，构建所述每个停车位的空间位置向量；
    根据每个停车位的空间位置向量对所述多个停车位进行聚类，得到所述多个停车位的空间位置聚类结果；
    根据所述多个停车位的空间位置聚类结果，对所述多个停车位进行区域划分，得到所述多个候选停车区域。
  15. 根据权利要求9所述的装置，其中，所述车位占用数据包括车位总占用率、每个楼层的车位占用率、每个候选停车区域的车位占用率和重点停车区域的车位占用率中的至少一种；其中，所述重点停车区域是根据每个候选停车区域的标识信息确定的。
  16. 根据权利要求9所述的装置，还包括当前时间信息确定模块，设置为：
    确定当前时刻对应的当前时间信息；其中，所述当前时间信息包括月、周、日和时段中的至少一种；
    根据所述当前时间信息和所述车位占用数据，从所述目标停车场的多个候选停车区域中选取目标停车区域。
  17. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-8中任一项所述的停车区域推荐方法。
  18. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行根据权利要求1-8中任一项所述的停车区域推荐方法。
  19. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-8中任一项所述的停车区域推荐方法。
PCT/CN2022/078157 2021-05-12 2022-02-28 停车区域推荐方法、装置、电子设备和介质 WO2022237277A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022551580A JP7422890B2 (ja) 2021-05-12 2022-02-28 駐車エリア推薦方法、装置、電子機器および媒体
EP22806254.3A EP4202888A1 (en) 2021-05-12 2022-02-28 Parking area recommendation method and apparatus, electronic device, and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110518142.7A CN113240936B (zh) 2021-05-12 2021-05-12 停车区域推荐方法、装置、电子设备和介质
CN202110518142.7 2021-05-12

Publications (1)

Publication Number Publication Date
WO2022237277A1 true WO2022237277A1 (zh) 2022-11-17

Family

ID=77133664

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/078157 WO2022237277A1 (zh) 2021-05-12 2022-02-28 停车区域推荐方法、装置、电子设备和介质

Country Status (4)

Country Link
EP (1) EP4202888A1 (zh)
JP (1) JP7422890B2 (zh)
CN (1) CN113240936B (zh)
WO (1) WO2022237277A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113240936B (zh) * 2021-05-12 2024-03-08 北京百度网讯科技有限公司 停车区域推荐方法、装置、电子设备和介质
CN113781826A (zh) * 2021-09-03 2021-12-10 中通服和信科技有限公司 一种基于5g的智慧园区人工智能停车管理系统
CN114664112B (zh) * 2022-03-16 2023-09-12 广州小鹏汽车科技有限公司 面向车库的车位推荐方法、服务器和存储介质
CN114882729B (zh) * 2022-04-22 2023-12-08 超级视线科技有限公司 停车管理方法以及系统
CN114691758B (zh) * 2022-06-01 2022-09-06 城云科技（中国）有限公司 一种盲点停车场库问题诊断方法、装置和应用
CN115691206B (zh) * 2022-10-19 2024-03-01 北京百度网讯科技有限公司 车位推荐方法、装置、设备以及存储介质
CN115410411A (zh) * 2022-10-31 2022-11-29 宜宾腾卓智能科技有限公司 一种大型停车场停车规划方法
CN117912293A (zh) * 2024-03-20 2024-04-19 鲁东大学 一种停车场智能管理系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107784856A (zh) * 2016-08-31 2018-03-09 上海勤易机电科技有限公司 一种停车场自动引导分配车位系统及方法
US20180313660A1 (en) * 2017-04-27 2018-11-01 International Business Machines Corporation Finding available parking spaces using cognitive algorithms
CN109191896A (zh) * 2018-10-17 2019-01-11 南京邮电大学 个性化停车位推荐方法和系统
EP3462389A1 (en) * 2017-09-27 2019-04-03 Deutsche Telekom AG Parking system that meets a second objective and method thereof
CN112396862A (zh) * 2021-01-19 2021-02-23 武汉中科通达高新技术股份有限公司 停车管理方法及装置
CN113240936A (zh) * 2021-05-12 2021-08-10 北京百度网讯科技有限公司 停车区域推荐方法、装置、电子设备和介质

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4817015B2 (ja) 2006-10-13 2011-11-16 株式会社デンソー 車載用ナビゲーション装置およびナビゲーションプログラム
CN105723433B (zh) * 2013-07-26 2018-06-22 艾纳高格有限公司 停车泊位占用率估计
CN106971604B (zh) * 2017-04-12 2019-12-20 青岛海信网络科技股份有限公司 一种停车位资源配置方法和装置
JP7020098B2 (ja) 2017-12-13 2022-02-16 トヨタ自動車株式会社 駐車場評価装置、駐車場情報提供方法およびプログラム
JP2019158354A (ja) 2018-03-07 2019-09-19 アイシン・エィ・ダブリュ株式会社 駐車支援システム及び駐車支援装置
CN110610250B (zh) * 2018-06-15 2023-07-07 阿里巴巴集团控股有限公司 推荐及提示空闲车位、寻车路线提示的方法、装置及设备
CN109949606A (zh) * 2019-04-18 2019-06-28 佛山市百宇行智能科技有限公司 一种智能停车的大数据分析方法
US11958475B2 (en) 2019-09-06 2024-04-16 Nissan Motor Co., Ltd. Parking assist method and parking assist device
CN110675651B (zh) * 2019-09-29 2021-08-17 百度在线网络技术（北京）有限公司 停车场推荐方法和装置
CN111081058A (zh) * 2019-12-23 2020-04-28 北京首钢自动化信息技术有限公司 一种基于大数据的停车场管理方法和装置
CN111190942B (zh) * 2020-01-06 2022-04-19 浙江大学城市学院 一种基于数据挖掘技术的城市道路停车点统筹分析方法
CN112037577A (zh) * 2020-09-23 2020-12-04 建信金融科技有限责任公司 停车场车位导航方法及系统
CN116682280A (zh) * 2020-11-05 2023-09-01 杨龙 基于区块链的闲置车位共享出租系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107784856A (zh) * 2016-08-31 2018-03-09 上海勤易机电科技有限公司 一种停车场自动引导分配车位系统及方法
US20180313660A1 (en) * 2017-04-27 2018-11-01 International Business Machines Corporation Finding available parking spaces using cognitive algorithms
EP3462389A1 (en) * 2017-09-27 2019-04-03 Deutsche Telekom AG Parking system that meets a second objective and method thereof
CN109191896A (zh) * 2018-10-17 2019-01-11 南京邮电大学 个性化停车位推荐方法和系统
CN112396862A (zh) * 2021-01-19 2021-02-23 武汉中科通达高新技术股份有限公司 停车管理方法及装置
CN113240936A (zh) * 2021-05-12 2021-08-10 北京百度网讯科技有限公司 停车区域推荐方法、装置、电子设备和介质

Also Published As

Publication number Publication date
EP4202888A1 (en) 2023-06-28
JP7422890B2 (ja) 2024-01-26
CN113240936A (zh) 2021-08-10
CN113240936B (zh) 2024-03-08
JP2023528714A (ja) 2023-07-06

Similar Documents

Publication Publication Date Title
WO2022237277A1 (zh) 停车区域推荐方法、装置、电子设备和介质
CN103377293B (zh) 多源输入、信息智能优化处理的全息触摸交互展示系统
CN104750768B (zh) 用于从社交媒体中识别、监控和排名事件的方法和系统
US9275392B2 (en) Parking facility resource management
US11315056B2 (en) Resource planning having improved visualization
CN112565804B (zh) 一种直播互动方法、设备、存储介质及系统
WO2019130003A1 (fr) Systeme et procede de gestion de rassemblement de masse
CN109152061A (zh) 通道调配方法、装置、服务器及存储介质
US11682047B2 (en) Cognitive elevator advertisements
CN110472599A (zh) 对象数量确定方法、装置、存储介质与电子设备
CN110659427A (zh) 基于多源数据的城市功能划分方法、装置和电子设备
WO2022257357A1 (zh) 网约车信息处理方法、装置、设备和计算机存储介质
CN117561517A (zh) 用于在路线规划应用中预测交通状况的计算机实现的设备和方法
CN107832365A (zh) 多类旅行产品推送方法、装置、电子设备、存储介质
CN112561371B (zh) 一种调度确定方法、装置、电子设备及存储介质
CN110223435A (zh) 对象随机分配方法、装置、计算机存储介质和电子设备
JP2022006166A (ja) 地図上の目的地の決定方法、機器、及び記憶媒体
CN104272770A (zh) 物理位置信息的自动化检索
US20070291914A1 (en) Network mapping and bidding system
CN114066505A (zh) 一种电梯广告播放效果数据的分析方法、系统及电子设备
CN111735441B (zh) 一种终端定位方法、装置及存储介质
US20210406557A1 (en) Machine perception using video/image sensors in an edge/service computing system architecture
CN110874737A (zh) 支付方式推荐方法、装置、电子设备、存储介质
CN115691206B (zh) 车位推荐方法、装置、设备以及存储介质
US11561667B2 (en) Semi-virtualized portable command center

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022551580

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 17908789

Country of ref document: US

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22806254

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022806254

Country of ref document: EP

Effective date: 20230321

NENP Non-entry into the national phase

Ref country code: DE