Method and device for acquiring state of parking area

Abstract

The invention discloses a state acquisition method and device of a parking area. At least one target parking area is obtained, the target parking area is divided into a first type and a second type according to whether detection equipment exists in the parking area, and the state of the target parking area of the first type is determined according to data obtained by the detection equipment; and determining the state of the second type of target parking area through a pre-trained state detection model. Therefore, the state representing the congestion degree of each parking area can be obtained for the user to check, so that the user can obtain the parking area where parking can be performed in advance, and the timeliness and convenience of vehicle returning of the user are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for acquiring the status of a parking area. Background Art

[0002] At present, traveling by shared vehicles (such as shared bicycles, shared electric vehicles, etc.) has become a new mode of travel in cities, which can effectively meet the travel needs of urban residents. However, with the large-scale use of shared vehicles, random parking and even occupying motor vehicle lanes, it brings challenges and hidden dangers to urban management and traffic safety.

[0003] In the prior art, a common method is to use electronic fences to guide the orderly and standardized return of bicycles at designated locations. However, in some scenarios, it is easy for shared bicycles to be crowded, resulting in users being unable to return the bicycles in time. Summary of the invention

[0004] In view of this, an object of an embodiment of the present invention is to provide a method and device for obtaining the status of a parking area, which can improve the timeliness and convenience of users returning their vehicles.

[0005] In a first aspect, an embodiment of the present invention provides a method for obtaining the status of a parking area, which is applicable to a platform server, and the method includes:

[0006] Acquire at least one target parking area, where the target parking area is a parking area whose status needs to be acquired;

[0007] Determine the type of each target parking area, the type includes a first type and a second type, the first type is a parking area with a detection device, and the second type is a parking area without a detection device;

[0008] In response to the type of the target parking area being the first type, determining the state of the target parking area according to the data acquired by the detection device; and

[0009] In response to the type of the target parking area being the second type, the state of the target parking area is determined by using a pre-trained state detection model.

[0010] In some embodiments, the state of the target parking area is used to represent the congestion level of the parking area.

[0011] In some embodiments, acquiring at least one target parking area includes:

[0012] receiving a query request from a user terminal, the query request including location information; and

[0013] At least one target parking area is acquired according to the position information.

[0014] In some embodiments, the location information is the user's current location point or a query location point selected by the user.

[0015] In some embodiments, acquiring at least one target parking area according to the location information specifically includes:

[0016] A parking area within a predetermined range of the user's current positioning point or the query position point selected by the user is determined as the target parking area.

[0017] In some embodiments, the location information is a parking area selected by a user.

[0018] In some embodiments, acquiring at least one target parking area according to the location information specifically includes:

[0019] The parking area selected by the user is determined as the target parking area.

[0020] In some embodiments, the detection device is a camera.

[0021] In some embodiments, determining the state of the target parking area according to the data acquired by the detection device includes:

[0022] Determining predetermined attribute information of each target parking area, wherein the predetermined attribute information is used to characterize a unique parking area; and

[0023] The state of the target parking area is acquired from a detection server according to the predetermined attribute information, wherein the detection server acquires the state of the target parking area according to the image data or the video data.

[0024] In some embodiments, determining the state of the target parking area according to the data acquired by the detection device includes:

[0025] Acquiring image data or video data captured by the detection device; and

[0026] The state of the target parking area is determined based on the image data or the video data.

[0027] In some embodiments, determining the state of the target parking area according to the image data or the video data includes:

[0028] Obtain the maximum number of parking spaces in the target parking area;

[0029] determining the current number of parking spaces in the target parking area according to the image data or the video data;

[0030] Acquire a first ratio, where the first ratio is a ratio of the current parking quantity to the maximum parking quantity; and

[0031] The congestion degree of the target parking area is determined according to the first ratio.

[0032] In some embodiments, determining the congestion degree of the target parking area according to the first ratio includes at least one of the following:

[0033] Using the first ratio as the congestion degree of the target parking area;

[0034] The congestion degree is determined according to the first ratio and a predetermined corresponding relationship, the predetermined corresponding relationship is a corresponding relationship between a ratio interval and a congestion degree, and the congestion degree is divided into a plurality of levels.

[0035] In some embodiments, determining the state of the target parking area according to the image data or the video data includes:

[0036] acquiring a second ratio according to the image data or the video data, wherein the second ratio is a ratio of an occupied area of ​​the target parking area to a total area of ​​the target parking area; and

[0037] The congestion degree of the target parking area is determined according to the second ratio.

[0038] In some embodiments, determining the congestion degree of the target parking area according to the second ratio includes at least one of the following:

[0039] using the second ratio as the congestion degree of the target parking area;

[0040] The congestion degree is determined according to the second ratio and a predetermined corresponding relationship, the predetermined corresponding relationship is a corresponding relationship between a ratio interval and a congestion degree, and the congestion degree is divided into multiple levels.

[0041] In some embodiments, determining the state of the target parking area by using a pre-trained state detection model includes:

[0042] Acquire input parameters of each target parking area, wherein the input parameters include one or more of time information, date information, weather information, season information, and parking area weight; and

[0043] The state of each of the target parking areas is acquired according to the input parameters through the pre-trained state detection model.

[0044] In some embodiments, determining the state of the target parking area according to the data acquired by the detection device includes:

[0045] Determining a first database according to the data acquired by the detection device, wherein the first database includes the status of each parking area; and

[0046] Determining predetermined attribute information of the target parking area; and

[0047] A state corresponding to the target parking area is acquired in the first database according to predetermined attribute information of the target parking area.

[0048] In some embodiments, determining the first database according to the data acquired by the detection device includes:

[0049] Acquire image data or video data captured by the detection device;

[0050] Determining the state of each of the parking areas according to the image data or the video data; and

[0051] The status of the parking area is stored in the first database.

[0052] In some embodiments, determining the first database according to the data acquired by the detection device is specifically:

[0053] The status of each parking area is obtained from a detection server and stored in a first database. The detection server stores the status of a first type of parking area. The status of the first type of parking area is obtained based on image data or video data captured by the detection device.

[0054] In some embodiments, determining the state of the target parking area by using a pre-trained state detection model includes:

[0055] Acquire a second database through a pre-trained state detection model;

[0056] Determining predetermined attribute information of the target parking area; and

[0057] The state corresponding to the target parking area is acquired in the second database according to the predetermined attribute information of the target parking area.

[0058] In some embodiments, acquiring the second database through a pre-trained state detection model includes:

[0059] Obtaining input parameters of each parking area, wherein the input parameters include one or more of time information, date information, weather information, season information, and parking area weight;

[0060] Acquiring the state of each of the parking areas according to the input parameters by using the pre-trained state detection model; and

[0061] The status of the parking area is stored in the second database.

[0062] In some embodiments, the first database and the second database are the same database or different databases.

[0063] In some embodiments, the method further comprises:

[0064] The status of each target parking area is sent to the user terminal.

[0065] In a second aspect, an embodiment of the present invention provides a parking area status acquisition device, which is applicable to a platform server, and the device includes:

[0066] a target parking area acquisition unit, configured to acquire at least one target parking area, wherein the target parking area is a parking area whose status needs to be acquired;

[0067] a type determination unit, configured to determine a type of each of the target parking areas, the type comprising a first type and a second type, the first type being a parking area with a detection device, and the second type being a parking area without a detection device;

[0068] a first state acquisition unit, configured to determine the state of the target parking area according to the data acquired by the detection device in response to the type of the target parking area being the first type; and

[0069] The second state acquisition unit is configured to determine the state of the target parking area by using a pre-trained state detection model in response to the type of the target parking area being the second type.

[0070] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0071] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer program instructions, wherein the computer program instructions implement the method described in the first aspect when executed by a processor.

[0072] The technical solution of the embodiment of the present invention obtains at least one target parking area, divides the target parking area into a first type and a second type according to whether there is a detection device in the parking area, determines the state of the first type of target parking area according to the data obtained by the detection device, and determines the state of the second type of target parking area through a pre-trained state detection model. In this way, the state representing the congestion degree of each parking area can be obtained for the user to view, so that the user can obtain the parking area that can be parked in advance, and improve the timeliness and convenience of the user's return of the car. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0074] Figure 1 is a schematic diagram of a shared vehicle system according to an embodiment of the present invention;

[0075] Figure 2 is a flow chart of an information interaction method according to an embodiment of the present invention;

[0076] Figure 3 is a schematic diagram of a status display interface of an embodiment of the present invention;

[0077] Figure 4 is a schematic diagram of a status display interface of another embodiment of the present invention;

[0078] Figure 5 is a flow chart of a method for acquiring the state of a parking area according to an embodiment of the present invention;

[0079] Figure 6 is a flow chart of obtaining a target parking area according to an embodiment of the present invention;

[0080] Figure 7 is a flowchart of obtaining a state of a first type of target parking area according to an embodiment of the present invention;

[0081] Figure 8 is a flow chart of a detection server acquiring a state of a parking area according to an embodiment of the present invention;

[0082] Fig. 9 is a flow chart of a detection server acquiring a status of a parking area according to another embodiment of the present invention;

[0083] Fig.10 is a flowchart of obtaining the state of a target parking area of ​​a first type according to another embodiment of the present invention;

[0084] Fig.11 is a flow chart of a platform server acquiring a first database according to an embodiment of the present invention;

[0085] Fig.12 is a flowchart of obtaining the state of a second type of target parking area according to an embodiment of the present invention;

[0086] Fig.13 is a flowchart of obtaining the state of a second type of target parking area according to another embodiment of the present invention;

[0087] Fig.14 is a flow chart of a platform server acquiring a second database according to an embodiment of the present invention;

[0088] Fig.15 is a schematic diagram of a parking area status acquisition device according to an embodiment of the present invention;

[0089] Fig.16 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0090] The present invention is described below based on embodiments, but the present invention is not limited to these embodiments. In the detailed description of the present invention below, some specific details are described in detail. It is possible for a person skilled in the art to fully understand the present invention without the description of these details. In order to avoid confusing the essence of the present invention, known methods, processes, flows, components and circuits are not described in detail.

[0091] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0092] Unless the context clearly requires otherwise, the words "include", "comprising" and the like throughout this application should be interpreted as including rather than exclusive or exhaustive; that is, as meaning "including but not limited to".

[0093] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0094] Figure 1 Schematic diagram of a shared vehicle system according to an embodiment of the present invention. Figure 1 As shown, the shared vehicle system according to the embodiment of the present invention includes at least one platform server 1 , at least one vehicle 2 and at least one user terminal 3 .

[0095] In this embodiment, the platform server 1 may be an independent server or a server cluster composed of multiple servers.

[0096] Furthermore, the platform server 1 is a server of a shared vehicle service platform.

[0097] In this embodiment, the vehicle may be a bicycle, an electric bicycle, a tricycle, a motorcycle, or the like.

[0098] Furthermore, the vehicle can communicate with the platform server 1 wirelessly. For example, communication can be performed through GSM (Global System for Mobile Communications), GPRS (General packet radio service), eMTC (LTE enhanced MTO), NB-IoT (Narrow Band Internet of Things), etc., so as to realize data interaction between the vehicle and the platform server.

[0099] In an optional implementation, a user can borrow a car by scanning a vehicle QR code. Specifically, a QR code is pre-set in each vehicle setting. When a user needs to borrow a car, he opens a pre-installed application, scans the vehicle QR code through the application to obtain the vehicle's Bluetooth communication address, and then establishes a Bluetooth communication connection with the vehicle, and sends an unlocking instruction to the vehicle through Bluetooth communication to borrow the car. Alternatively, when a user needs to borrow a car, he opens a pre-installed application, scans the vehicle QR code through the application to obtain the vehicle's unique identifier, and sends a borrowing request to the platform server, the borrowing request includes the unique identifier. After receiving the borrowing request, the platform server obtains the vehicle's communication address through the unique identifier, and sends an unlocking instruction to the vehicle to borrow the car.

[0100] In another optional implementation, users can borrow a car through NFC (Near Field Communication). Specifically, NFC is a short-range high-frequency wireless communication technology that allows contactless point-to-point data transmission between electronic devices. An NFC module is pre-set in each vehicle setting. When a user needs to borrow a car, the user terminal with NFC function is close to the identification area of ​​the vehicle, and the Bluetooth communication address of the vehicle is obtained through NFC communication, and then a Bluetooth communication connection is established with the vehicle, and an unlocking instruction is sent to the vehicle through Bluetooth communication to borrow the car. Alternatively, an NFC module is pre-set in each vehicle setting. When a user needs to borrow a car, the user terminal with NFC function is close to the identification area of ​​the vehicle, and the unique identifier of the vehicle is obtained through NFC communication, and a borrowing request is sent to the platform server. The borrowing request includes the unique identifier. After receiving the borrowing request, the platform server obtains the communication address of the vehicle through the unique identifier, and sends an unlocking instruction to the vehicle to borrow the car.

[0101] It should be understood that the above two car borrowing methods are only two examples provided by the embodiment of the present invention, and the embodiment of the present invention does not limit this. The user terminal borrowing a car by other methods is also applicable to the technical solution of the embodiment of the present invention.

[0102] It should also be understood that the above description uses the example of a user terminal sending a car borrowing request, but the embodiment of the present invention does not limit this, and the car borrowing request can also be sent by the vehicle. Specifically, when borrowing a car by scanning a vehicle QR code, each vehicle is pre-set with a QR code. When a user needs to borrow a car, he opens a pre-installed application, scans the vehicle QR code through the application to obtain the vehicle's Bluetooth communication address, and then establishes a Bluetooth communication connection with the vehicle, and sends an unlocking instruction to the vehicle through Bluetooth communication. After receiving the unlocking instruction sent by the user terminal, the vehicle generates a car borrowing request and sends it to the platform server. Alternatively, when borrowing a car through NFC, each vehicle is pre-set with an NFC module. When a user needs to borrow a car, he brings a user terminal with NFC function close to the identification area of ​​the vehicle, and then establishes an MFC communication connection with the vehicle, sends an unlocking instruction to the vehicle through NFC communication, and the vehicle sends a car borrowing request to the platform server.

[0103] In order to standardize the return of users' vehicles and avoid random parking, parking areas are planned. When the user finishes riding and needs to return the vehicle, he / she parks the vehicle in the planned parking area and controls the vehicle to lock through the user terminal, or manually closes the lock to trigger the return of the vehicle. The positioning module in the vehicle sends the vehicle's location to the platform server. After receiving the vehicle's location, the platform server detects whether the vehicle's location is within the planned parking area. If the vehicle is within the planned parking area, the user has successfully returned the vehicle. If not, the user has failed to return the vehicle. The platform server sends an unlocking command to the vehicle, the vehicle lock pops open, and the platform server sends a return failure prompt to the user terminal, and prompts the user to park the vehicle within the parking area.

[0104] It should be understood that the above is only an example of returning a vehicle provided in an embodiment of the present invention. The embodiment of the present invention does not limit the vehicle returning process of the user, which can be implemented in various ways.

[0105] However, the problem of shared bicycles crowding has had a negative impact on subsequent management. Bicycles are easily parked in crowds at subway entrances, shopping malls, tourist attractions and other areas. Nowadays, after taking vehicle dispatch management measures, the problem of vehicle crowding can be alleviated to a certain extent; however, users still encounter the problem of being unable to return the bicycle due to untimely dispatch. The fundamental reason is that they cannot perceive the congestion of surrounding parking spots, so they need to manually try to park at surrounding parking spots, resulting in too long parking time. In the existing shared bicycle travel scenarios, when users park in hot spots (shopping malls, subway entrances, etc.), they often encounter the problem of being unable to park normally due to untimely dispatch and overflow of vehicles at parking spots. Users can only continue to choose closer parking spots to park, and the problem of vehicle overflow at the target parking spot will still occur; when users find a suitable parking spot, they have already spent a lot of extra time, which is time-consuming and laborious.

[0106] Therefore, the present invention reasonably monitors the load conditions of parking spots and reports the congestion conditions of the spots through data collection; when a user is unable to return the car due to overflow of parking spots, the user can check the congestion conditions of the spots through a map and navigate to the nearest parking spot with appropriate congestion to park, thus solving the problem of being unable to perceive the congestion of parking spots.

[0107] Figure 2 It is a flow chart of the information interaction method according to an embodiment of the present invention. Figure 2 The data interaction between the platform server and the user terminal is shown, which specifically includes the following steps:

[0108] Step S101: The user terminal obtains a query instruction.

[0109] In an optional implementation, the query instruction is a command input by the user through a user terminal, that is, when the user needs to query the status of the parking position, the query instruction is input through the human-computer interaction interface of the user terminal. The query instruction at least includes location information, wherein the location information is the user's current location point or the query location point selected by the user, or the location information is the parking area selected by the user.

[0110] For example, when a user needs to query the status of a parking area, the status display interface is opened, and the status display interface displays an electronic map, with the user's current location point being the map center by default, and the status of parking areas within a certain range around it is displayed. At this time, the location information is the user's current location point. If there is no parking area that the user needs to view in the currently displayed electronic map, the user can drag the map to change the map center, or the user triggers a point on the interface as the map center, and the user terminal displays the status of parking areas within a certain range around it with the new map center. At this time, the location information is the query location point selected by the user.

[0111] For another example, the electronic map of the user terminal displays various parking areas but does not display the status. When the user clicks on a parking area, the status of the parking area selected by the user is displayed. At this time, the location information is the parking area selected by the user.

[0112] In another optional implementation, the query instruction is automatically generated by the user terminal. For example, when the user enters a destination in the user terminal, the user terminal automatically generates a query instruction for the parking position of the destination.

[0113] It should be noted that the embodiment of the present invention does not limit the manner in which the user terminal obtains the query instruction, and the query instruction can be triggered and generated through various scenarios.

[0114] Step S102: The user terminal sends a query request.

[0115] In this embodiment, the user terminal sends a query request to the platform server, and the query request includes location information.

[0116] The location information is the user's current location point or the query location point selected by the user. Alternatively, the location information is the parking area selected by the user.

[0117] Step S103: The platform server obtains the status of the target parking area.

[0118] In this embodiment, after receiving the query request, the platform server parses the query request to obtain the location information, and obtains at least one target parking area according to the location information. The type of each target parking area is determined, and the type includes a first type and a second type, the first type is a parking area with a detection device, and the second type is a parking area without a detection device. In response to the type of the target parking area being the first type, the state of the target parking area is determined according to the data obtained by the detection device. In response to the type of the target parking area being the second type, the state of the target parking area is determined by a pre-trained state detection model.

[0119] Step S104: The platform server sends the status of the target parking area.

[0120] In this embodiment, the platform server sends the status of each target parking area to the user terminal.

[0121] Step S105: display the status of the target parking area.

[0122] In this embodiment, after receiving the state of the target parking area sent by the platform server, the user terminal displays the state of the target parking area, wherein the state of the target parking area is used to characterize the congestion of the parking area.

[0123] In an optional implementation, the state of the parking area is a ratio, wherein the ratio is the ratio of the current parking quantity to the maximum parking quantity of the parking area. That is, assuming that the parking threshold of a parking area is N and the current parking quantity is M, the congestion degree is M / N.

[0124] Figure 3 FIG. 1 is a schematic diagram of a status display interface of an embodiment of the present invention. Figure 3 In the illustrated embodiment, the status display interface shows roads, parking areas and other areas, wherein the other areas may be building areas, open space areas and the like. Figure 3 Taking six parking areas as an example, the congestion levels of the six parking areas are shown respectively as M1 / N1, M2 / N2, M3 / N3, M4 / N4, M5 / N5, and M6 / N6.

[0125] Thus, the user can intuitively determine the status of each parking area according to the congestion, and then choose a parking area to park in. For example, assuming that the congestion of the fourth parking area M4 / N4 = 75 / 80, and the congestion of the sixth parking area M6 / N6 = 30 / 60. When the user's destination is close to the fourth parking area and the sixth parking area, since the fourth parking area may be full or nearly full, the sixth parking area can be selected for parking in a more timely manner.

[0126] It should be noted that the maximum parking quantity in the embodiment of the present invention is set according to actual conditions and is a reasonable number under normal vehicle parking conditions. However, due to the randomness of bicycle parking, a ratio greater than 1 may occur in actual conditions.

[0127] In another optional implementation, the state of the parking area is a congestion level. The embodiment of the present invention divides the congestion into multiple levels. For example, the congestion level can be divided into four levels: no congestion, light congestion, medium congestion, and high congestion. For another example, the congestion level can be divided into a first level, a second level, a third level, etc., and a higher level indicates more congestion.

[0128] The congestion level may be displayed in different ways, such as directly displaying in the form of text, rendering different levels in different ways (color and / or pattern, etc.), and so on.

[0129] Figure 4 FIG. 1 is a schematic diagram of a status display interface of another embodiment of the present invention. Figure 4 In the illustrated embodiment, the status display interface shows roads, parking areas and other areas, wherein the other areas may be building areas, open space areas and the like. Figure 4 Taking six parking areas as examples, the congestion levels of the six parking areas are shown respectively.

[0130] In this way, users can intuitively determine the status of each parking area according to the degree of congestion, and then choose a parking area to go to.

[0131] at the same time, Figure 3-Figure 4 In the example of directly displaying the congestion degree of each parking area, the present invention is not limited to this, and other methods can also be used for display. For example, only each parking area is displayed on the electronic map, and when the user clicks on a parking area, the congestion degree of the parking area is displayed in the form of bubbles.

[0132] The embodiment of the present invention obtains at least one target parking area, divides the target parking area into a first type and a second type according to whether there is a detection device in the parking area, determines the state of the first type of target parking area according to the data obtained by the detection device, and determines the state of the second type of target parking area through a pre-trained state detection model. In this way, the state representing the congestion degree of each parking area can be obtained for the user to view, so that the user can obtain the parking area that can be parked in advance, and improve the timeliness and convenience of the user's return of the car.

[0133] Figure 5 is a flow chart of a method for acquiring the state of a parking area according to an embodiment of the present invention. Figure 5 In the embodiment shown, the method for obtaining the state of the parking area corresponds to Figure 2 The step S103 shown is applicable to the platform server and specifically includes the following steps:

[0134] Step S200: Acquire at least one target parking area.

[0135] The target parking area is a parking area whose status needs to be obtained.

[0136] In an optional implementation, the acquiring of at least one target parking area is as follows: Figure 6 As shown, the following steps are included:

[0137] Step S210: receiving a query request from a user terminal.

[0138] In this embodiment, the server receives a query request from a user terminal, and the query request includes location information. When the user needs to query the status of the parking location, the user enters a query instruction through the human-computer interaction interface of the user terminal. The query instruction at least includes location information, wherein the location information is the user's current location point or the query location point selected by the user, or the location information is the parking area selected by the user.

[0139] For example, when a user needs to query the status of a parking area, the status display interface is opened. The status display interface displays an electronic map, and the user's current location point is defaulted as the map center, and the status of the parking area within a certain range around it is displayed. At this time, the location information is the user's current location point. If there is no parking area that the user needs to view in the currently displayed electronic map, the user can drag the map to change the map center, or the user triggers a point on the interface as the map center, and the user terminal displays the status of the parking area within a certain range around it with the new map center. At this time, the location information is the query location point selected by the user. The user terminal sends a query request to the platform server.

[0140] For another example, the electronic map of the user terminal displays various parking areas but does not display the status. When the user clicks on a parking area, the status of the parking area selected by the user is displayed. At this time, the location information is the parking area selected by the user. The user terminal sends a query request to the platform server.

[0141] Step S220: Acquire at least one target parking area according to the location information.

[0142] In this embodiment, after receiving the query request, the platform server parses the query request to obtain location information, and obtains at least one target parking area according to the location information.

[0143] In an optional implementation, when the location information is the user's current location point or the query location point selected by the user, the step of acquiring at least one target parking area according to the location information is as follows: determining a parking area within a predetermined range of the user's current location point or the query location point selected by the user as the target parking area. The predetermined range may be set according to actual conditions, such as 100 meters, 500 meters, 1000 meters, 2000 meters, etc.

[0144] In another optional implementation, when the location information is a parking area selected by a user, acquiring at least one target parking area according to the location information specifically includes: determining the parking area selected by the user as the target parking area.

[0145] Step S300: Determine the type of each target parking area.

[0146] In this embodiment, each detection device is marked according to whether there is a detection device in each parking area, and the type of each target parking area is determined according to the marking result. The type includes a first type and a second type. The first type is a parking area with a detection device, and the second type is a parking area without a detection device.

[0147] In some embodiments, the detection device can be implemented by a camera, wherein the camera is installed on a platform with public place monitoring authority.

[0148] Step S400: In response to the type of the target parking area being the first type, determining the state of the target parking area according to the data acquired by the detection device.

[0149] The state of the parking area is used to characterize the congestion degree of the parking area.

[0150] The status of the first type of target parking area can be acquired in real time or in advance.

[0151] Figure 7 FIG. 1 is a flowchart of obtaining the state of a first type of target parking area according to an embodiment of the present invention. Figure 7 In the illustrated embodiment, the state of the first type of target parking area is acquired in real time. Specifically, the step of determining the state of the target parking area according to the data acquired by the detection device comprises the following steps:

[0152] Step S410: Determine predetermined attribute information of each target parking area.

[0153] In this embodiment, the predetermined attribute information is used to characterize a unique parking area.

[0154] The predetermined attribute information includes at least one of a parking area location, a parking area number, a parking area name, and the like.

[0155] Step S420: Acquire the state of the target parking area from the detection server according to the predetermined attribute information.

[0156] In this embodiment, the detection server is a server corresponding to a platform providing a camera. The detection server obtains the state of the target parking area according to the image data or the video data.

[0157] For a parking area with a camera installed, when the platform server detects that the type of the target parking area is the first type, the platform server sends a status acquisition request to the detection server, and the status acquisition request includes the predetermined attribute information. After receiving the status acquisition request, the detection server parses the status acquisition request to determine the predetermined attribute information, determines the corresponding parking area according to the predetermined attribute information, calls the camera installed in the corresponding parking area to collect image data or video data, obtains the image data or video data of the parking area through the camera, and the detection server obtains the status of the parking area through the image recognition algorithm according to the video frame extracted from the image data or video data, and sends the acquired status of the parking area to the platform server. In this way, the platform server can obtain the status of the target parking area through the detection server.

[0158] In an optional implementation, the process of the detection server obtaining the status of the parking area is as follows: Figure 8 As shown, the specific steps include:

[0159] Step S4211, obtaining the maximum number of parking spaces in the target parking area.

[0160] The maximum parking quantity can be preset or determined according to the area of ​​the parking area. The maximum parking quantity determined according to the area of ​​the parking area can be calculated by the formula N=a*S, where N is the maximum parking quantity of the parking area, a is a preset constant and a is greater than 0, and S is the area of ​​the parking area.

[0161] Step S4212 determines the current number of parking spaces in the target parking area according to the image data or video data.

[0162] The detection server calls the camera of the parking area to obtain image data or video data, and obtains the current number of parking lots in the parking area through a pre-trained target detection model according to the video frames of the image data or video data.

[0163] The pre-trained target detection model can be implemented by various existing target detection models, which are not limited in the embodiments of the present invention. For example, the target detection model can be implemented by a one-stage target detection network, such as YOLO (You Only Look Once), Retina-Net (retina network) and FCOS (Fully Convolutional One-Stage Object Detection) and other models.

[0164] YOLO is an object detection algorithm that redefines object detection as a regression problem. Specifically, YOLO applies a single convolutional neural network (CNN) to the entire image, divides the image into grids, and predicts the class probability and bounding box of each grid. Then, for each grid, the network predicts a bounding box and the probability corresponding to each category (such as people, roadblocks, road signs, and text signs, etc.). Each bounding box can be described using four descriptors: the center, height, width, and value of the bounding box are mapped to the class to which the object belongs. In addition, the algorithm can also predict the probability of the existence of an object in the bounding box (that is, the confidence of the embodiment of the present invention). If the center of an object falls in a grid cell, the grid cell is responsible for detecting the object. Finally, the non-maximum suppression method is applied to the objects of each class to filter out the bounding boxes with a confidence less than a threshold. Thus, a sub-image to be classified with a confidence greater than or equal to a predetermined threshold can be obtained.

[0165] Retina-Net is a unified network consisting of a backbone network and two task-specific subnetworks. The backbone network is a self-convolutional network that is responsible for computing convolutional feature maps over the entire input image. The first subnetwork performs convolutional object classification on the output of the backbone, and the second subnetwork performs convolutional bounding box regression. Specifically, the backbone network can be FPN (Feature Pyramid Network), which enhances the standard convolutional network through a top-down path and lateral connections. It takes a single-dimensional image as input, and then it selects features from all layers to process and then combines them as the final feature output combination. The first subnetwork is the classification subnetwork, which is used to predict the probability of the existence of each bounding box and K object classes at each spatial location. The second subnetwork is the box regression subnetwork, which works similarly to the classification subnetwork, except that there is a linear output at the end.

[0166] The core idea of ​​FCOS is to predict the target category and target box to which each point in the input image belongs. The FCOS network structure includes a backbone network and three output layers, which output classification, Center-ness, and regression respectively. The first output of the three output layers is the output of the classification branch, which outputs a feature vector of H*W*C, where H*W represents the size of the feature, C represents the number of categories, and the position (x, y) on the feature can be converted to the position of the input image. In this way, the relationship between the position of the point on the feature map and the position of the point on the input image is established, which facilitates the calculation of the classification and regression targets of each point on the feature map. The second output is Center-ness. This branch is parallel to the classification branch and is used to calculate the distance between each point and the target center point, so as to reduce the predicted points that are far away from the target center point. The third output is the output of the regression branch. The regression part of FCOS predicts 4 values ​​(l, t, r, b), which respectively represent the distance of a point in the target box from the left, top, right, and bottom of the box. Then the category label of each point on the input image can be determined based on whether the point is in the labeled box. The point outside the labeled box is a negative sample, and the category is set to 0; the point (x, y) in the labeled box is a positive sample, and the category target is the category of the labeled box, and the regression target is the above 4 values. From this, it can be seen that the positive and negative samples of FCOS are based on each point. Generally, the area of ​​the target box and the area of ​​the non-target box on an image will not be very different, so there is basically no imbalance between positive and negative samples.

[0167] At the same time, the target detection model can be implemented through a two-stage target detection network, such as Faster R-CNN (Faster Region-Convolutional Neural Networks), Cascade R-CNN (Cascade Region-Convolutional Neural Networks), etc. The implementation methods of each model are as follows:

[0168] Faster R-CNN extracts features through convolutional layers, CNN and other basic networks to obtain feature maps, passes through the RPN (Region Proposal Network) layer, and then uses a slide window on the feature map extracted through the convolutional layer to traverse the entire feature map. During the traversal process, each window generates multiple anchors (anchors, or understood as predefined boxes at a fixed ratio), and then uses full connection to perform binary classification and preliminary box regression on each anchor, and finally outputs multiple relatively accurate ROIs (region of interest). The input dimension of the fully connected layer is fixed with ROI pooling for the feature map that has passed the convolutional layer. Then, the multiple ROIs output by the RPN are mapped to the feature map of the ROI pooling for regression and classification to obtain the classification results.

[0169] Cascade R-CNN is composed of a series of detection models. Each detection model is trained based on positive and negative samples with different IOU (Intersection-over-Union) thresholds. The output of the previous detection model is used as the input of the next detection model. Therefore, it is a staged training method. Moreover, the IOU threshold for defining positive and negative samples continues to rise with each subsequent detection model.

[0170] Step S4213, obtaining a first ratio.

[0171] In this embodiment, the detection server calculates a first ratio, which is a ratio of the current parking quantity to the maximum parking quantity. That is, the calculation formula of the first ratio is: M / N, where M is the current parking quantity and N is the maximum parking quantity.

[0172] Step S4214: Determine the congestion degree of the target parking area according to the first ratio.

[0173] Wherein, determining the congestion degree of the target parking area according to the first ratio includes at least one of the following:

[0174] Using the first ratio as the congestion degree of the target parking area;

[0175] The degree of congestion is determined according to the first ratio and a predetermined correspondence, wherein the predetermined correspondence is a correspondence between a ratio interval and a degree of congestion, and the degree of congestion is divided into a plurality of levels. For example, assuming that in the predetermined correspondence, the degree of congestion is divided into four levels: non-congested, lightly congested, moderately congested, and heavily congested, and the ratio intervals corresponding to the various levels are [0, 30%), [30%, 50%), [50%, 90%), and [90%, +∞). After obtaining the first ratio, the ratio interval in which the first ratio is located is detected, and the congestion level corresponding to the ratio interval in which the first ratio is located is determined as the degree of congestion. Assuming that the first ratio is 82%, and the ratio interval in which it is located is [50%, 90%), the corresponding degree of congestion is moderately congested.

[0176] It should be understood that in the embodiment of the present invention, the first ratio may be used as the congestion degree, the congestion degree level corresponding to the first ratio may be used as the congestion degree, or both the first ratio and the congestion degree level may be used as the congestion degree.

[0177] In another optional implementation, the process of the detection server obtaining the status of the parking area is as follows: Fig. 9 As shown, the specific steps include:

[0178] Step S4221: Obtain a second ratio according to the image data or the video data.

[0179] The second ratio is a ratio of an occupied area of ​​the parking area to a total area of ​​the parking area.

[0180] In a specific implementation, the detection server calls the camera of the parking area to obtain image data or video data, obtains the parking area through an image processing model based on the video frame of the image data or video data, and obtains the occupied area and the blank area in the parking area, wherein the occupied area is the area where the car has been parked, and the blank area is the area where the car has not been parked, and calculates the ratio of the occupied area of ​​the parking area to the total area of ​​the parking area.

[0181] The image processing model can be implemented based on various existing methods, such as RNN (Recurrent Neural Network) or CNN (Convolutional Neural Networks) models. It is easy to understand that the image processing model of this embodiment can also be other types of machine learning models, which are not specifically limited in this embodiment.

[0182] RNN is a type of recursive neural network that takes sequence data as input, recursively in the direction of sequence evolution, and is connected in a chain. Recurrent neural networks have memory, parameter sharing, and Turing completeness (in computability theory, if a series of rules for operating data, such as instruction sets, programming languages, etc., can be used to simulate a single-band Turing machine, then this rule is Turing complete), so it has certain advantages in nonlinear learning of sequences.

[0183] CNN is a type of feedforward neural network with deep structure and convolutional computing. It is one of the representative algorithms of deep learning. CNN has the ability of representation learning (that is, converting raw data into a form that can be effectively developed by machine learning, allowing the computer to learn how to extract features while learning to use features). It can classify input information according to its hierarchical structure in a shift-invariant manner, so it is also called "Shift-Invariant Artificial Neural Networks (SIANN)". With the introduction of deep learning theory and the improvement of numerical computing equipment, convolutional neural networks have developed rapidly and have been applied to computer vision, natural language processing and other fields. CNN is constructed by imitating the visual perception mechanism of organisms. It can perform supervised learning and unsupervised learning. The convolution kernel parameters in its hidden layer are shared. At the same time, the sparsity of inter-layer connections enables CNN to learn grid features such as pixel features and audio with a small amount of calculation.

[0184] Step S4222: Determine the congestion degree of the target parking area according to the second ratio.

[0185] Wherein, determining the congestion degree of the target parking area according to the second ratio includes at least one of the following:

[0186] using the second ratio as the congestion degree of the target parking area;

[0187] The degree of congestion is determined according to the second ratio and a predetermined correspondence, wherein the predetermined correspondence is a correspondence between a ratio interval and a degree of congestion, and the degree of congestion is divided into a plurality of levels. For example, assuming that in the predetermined correspondence, the degree of congestion is divided into four levels: non-congested, lightly congested, moderately congested, and heavily congested, and the ratio intervals corresponding to the various levels are [0, 30%), [30%, 50%), [50%, 90%), and [90%, +∞). After the second ratio is obtained, the ratio interval in which the second ratio is located is detected, and the congestion level corresponding to the ratio interval in which the second ratio is located is determined as the degree of congestion. Assuming that the second ratio is 82%, and the ratio interval in which it is located is [50%, 90%), the corresponding degree of congestion is moderately congested.

[0188] It should be understood that in the embodiment of the present invention, the second ratio may be used as the congestion degree, the congestion degree level corresponding to the second ratio may be used as the congestion degree, or both the second ratio and the congestion degree level may be used as the congestion degree.

[0189] It should be understood that the above steps S4211-S4214 and S4221-S4222 are generated by the detection server after receiving the status acquisition request from the platform server, and the detection server sends the acquired status to the platform server, but the embodiment of the present invention does not limit the specific implementation method.

[0190] For example, for a parking area with a camera installed, when the platform server detects that the type of the target parking area is the first type, the platform server sends an image acquisition request to the detection server, and the image acquisition request includes the predetermined attribute information. After receiving the image acquisition request, the detection server parses the image acquisition request to determine the predetermined attribute information, determines the corresponding parking area according to the predetermined attribute information, calls the camera installed in the corresponding parking area to collect image data or video data, and sends the image data or video data of the parking area obtained by the camera to the platform server. The platform server obtains the state of the parking area through an image recognition algorithm based on the video frame extracted from the image data or video data.

[0191] In an optional implementation, the platform server obtains the status of the parking area including the following steps:

[0192] Step S4231, obtaining the maximum number of parking spaces in the target parking area.

[0193] Step S4232: Determine the current number of parking spaces in the target parking area according to the image data or video data.

[0194] Step S4233: Obtain a first ratio, where the first ratio is the ratio of the current parking quantity to the maximum parking quantity.

[0195] Step S4234: determine the congestion degree of the target parking area according to the first ratio.

[0196] The specific implementation of steps S4231-S4234 can be as follows: Figure 8 The difference between steps S4211-S4214 shown is that in S4211-S4214, the detection server obtains the status of the target parking area based on the image data or video data, while in S4231-S4234, the platform server first obtains the image data or video data from the detection server, and then the platform server obtains the status of the target parking area based on the image data or video data.

[0197] In another optional implementation, the platform server obtains the status of the parking area including the following steps:

[0198] Step S4241: Obtain a second ratio according to the image data or the video data.

[0199] Step S4242: Determine the congestion degree of the target parking area according to the second ratio.

[0200] The specific implementation of steps S4241-S4242 can be as follows: Fig. 9 The difference between steps S4221-S4222 shown is that in S4241-S4242, the detection server obtains the status of the target parking area based on the image data or video data, while in S4241-S4242, the platform server first obtains the image data or video data from the detection server, and then the platform server obtains the status of the target parking area based on the image data or video data.

[0201] It should also be understood that the four methods shown in the above steps S4211-S4214, S4221-S4222, S4231-S4234, and S4241-S4242 are all for obtaining the status of the target parking area in real time. That is, after receiving the query request sent by the user terminal, the platform server obtains the status of the target parking area at the current time according to the query request. Since the status of the parking area changes in real time, the status obtained in this way is more accurate.

[0202] At the same time, in order to reduce the computational difficulty of the platform server or the detection server, the embodiment of the present invention can also be implemented by pre-acquiring the state.

[0203] Specifically, Fig.10 FIG. 1 is a flowchart of obtaining the state of the target parking area of ​​the first type according to another embodiment of the present invention. Fig.10 In the illustrated embodiment, the state of the first type of target parking area is obtained in advance. Specifically, the step of determining the state of the target parking area according to the data obtained by the detection device includes the following steps:

[0204] Step S4251: Determine a first database according to the data acquired by the detection device.

[0205] In this embodiment, the first database includes the status of each parking area. The first database stores the corresponding relationship between the status of each parking area and predetermined attribute information, and the predetermined attribute information includes at least one of the parking area location, parking area number, parking area name, etc.

[0206] In an optional implementation, the platform server determines the process of the first database according to the data acquired by the detection device as follows: Fig.11 As shown, the following steps are included:

[0207] Step S42511, obtaining image data or video data captured by the detection device.

[0208] For parking areas with cameras installed, the platform server sends an image acquisition request to the detection server once in each cycle according to a predetermined time period, and the image acquisition request includes the predetermined attribute information. After receiving the image acquisition request, the detection server parses the image acquisition request to determine the predetermined attribute information, determines the corresponding parking area according to the predetermined attribute information, calls the camera installed in the corresponding parking area to collect image data or video data, and sends the image data or video data of the parking area obtained by the camera to the platform server. In this way, the platform server can obtain the image data or video data captured by the detection device.

[0209] The predetermined time period can be set according to the actual situation. If you want higher accuracy, the time period can be set to a smaller value, such as 5 minutes, 10 minutes or 20 minutes, etc. If you want to reduce the amount of calculation of the platform server, the time period can be set to a larger value, such as 30 minutes, 60 minutes or 90 minutes, etc.

[0210] Step S42512: determine the status of each parking area based on the image data or video data.

[0211] Among them, determining the status of each parking area according to the image data or the video data can refer to S4231-S4234 or steps S4211-S4214, and the embodiments of the present invention will not be repeated here.

[0212] Step S42513: Store the status of the parking area in the first database.

[0213] In this embodiment, the platform server stores the correspondence between the state of the parking area and the predetermined attribute information in the first database.

[0214] In another optional implementation, the platform server determines the first database based on the data acquired by the detection device as follows: the status of each parking area is acquired from the detection server and stored in the first database, the detection server stores the status of the first type of parking area, and the status of the first type of parking area is acquired based on the image data or video data captured by the detection device. The detection server determines the status of each parking area based on the image data or video data, which can be referred to S4211-S4214 or steps S4221-S4222, and the embodiments of the present invention are not repeated here.

[0215] Step S4252: Determine predetermined attribute information of the target parking area.

[0216] In this embodiment, the platform server obtains predetermined attribute information of the target parking area according to the query request, wherein the predetermined attribute information includes at least one of time, parking area location, parking area number, parking area name, etc.

[0217] Step S4253: Acquire a status corresponding to the target parking area in the first database according to the predetermined attribute information of the target parking area.

[0218] In this embodiment, the platform server obtains the status corresponding to the target parking area in the first database according to the predetermined attribute information.

[0219] Thus, the platform server can obtain the status of the first type of target parking area.

[0220] Step S500: In response to the type of the target parking area being the second type, determining the state of the target parking area by using a pre-trained state detection model.

[0221] The status of the second type of target parking area may be acquired in real time or in advance.

[0222] In an optional implementation, Fig.12 FIG. 1 is a flowchart of obtaining the state of the target parking area of ​​the second type according to an embodiment of the present invention. Fig.12 In the illustrated embodiment, the state of the second type of target parking area is acquired in real time. Specifically, the state of the target parking area is determined by a pre-trained state detection model, including the following steps:

[0223] Step S511, obtaining input parameters of each target parking area.

[0224] In this embodiment, a pre-trained state detection model is obtained, the input parameters of the state detection model include one or more of time information, date information, weather information, season information, and parking area weight, and the output parameter is the state of the parking area.

[0225] In parking areas without camera surveillance, the congestion of the current point is deduced through long-term training data. Collect training samples, which include the deployment volume, collection volume, parking volume, usage volume, etc. of shared vehicles, and the parking situation of social vehicles, and calculate the congestion of the current parking point through the training model. The current parking congestion is calculated by input factors such as weekdays, holidays, parking area weights (for example, the weights of the city center and subway stations are high, and vice versa), seasons, weather conditions, peak time periods, etc. The probability of reaching full quota on weekdays is higher. Manually input the geographical location weight, and the higher the weight, the higher the probability of reaching full quota. Similarly, seasons, weather conditions, and peak time periods of a single day will affect the probability of full quota of the parking spot. Through historical data analysis and the current input factors of the parking spot, the congestion of the current parking spot is calculated, and then the actual parking situation of users returning the car is used as a model correction.

[0226] The state detection model can be implemented by RNN (Recurrent Neural Network) or CNN (Convolutional Neural Networks) models. It is easy to understand that the state detection model of this embodiment can also be other types of machine learning models, which are not specifically limited in this embodiment.

[0227] Step S512: obtaining the state of each of the target parking areas according to the input parameters through the pre-trained state detection model.

[0228] In this embodiment, after receiving the input parameters, the pre-trained state detection model outputs the state of the target parking area according to the input parameters.

[0229] Thus, the platform server can obtain the status of the first type of target parking area.

[0230] In another optional implementation, Fig.13 FIG. 1 is a flowchart of obtaining the state of the target parking area of ​​the second type according to another embodiment of the present invention. Fig.13 In the illustrated embodiment, the state of the second type of target parking area is obtained in advance. Specifically, the state of the target parking area is determined by using a pre-trained state detection model, including the following steps:

[0231] Step S521: Acquire a second database through a pre-trained state detection model.

[0232] Specifically, in an optional implementation, the platform server determines the process of the second database according to the data acquired by the detection device as follows: Fig.14 As shown, the following steps are included:

[0233] Step S5211, obtaining input parameters of each parking area.

[0234] In this embodiment, the platform server obtains the state of the second type of parking area once in each period through the pre-trained state detection model according to the predetermined time period, and stores the obtained state of the parking area and the predetermined attribute information in the second database. The predetermined time period can be set according to the actual situation. If higher accuracy is desired, the time period can be set to a shorter period, such as 5 minutes, 10 minutes or 20 minutes. If the amount of calculation of the platform server is to be reduced, the time period can be set to a longer period, such as 30 minutes, 60 minutes or 90 minutes.

[0235] Step S5212: obtaining the state of each parking area according to the input parameters through the pre-trained state detection model.

[0236] In this embodiment, after receiving the input parameters, the pre-trained state detection model outputs the state of the parking area according to the input parameters.

[0237] Step S5213: Store the status of the parking area in the second database.

[0238] In this embodiment, the platform server stores the acquired status and predetermined attribute information of the parking area in the second database.

[0239] Step S522: Determine predetermined attribute information of the target parking area.

[0240] In this embodiment, the platform server obtains predetermined attribute information of the target parking area according to the query request, wherein the predetermined attribute information includes at least one of time, parking area location, parking area number, parking area name, etc.

[0241] Step S523: Acquire a state corresponding to the target parking area in the second database according to the predetermined attribute information of the target parking area.

[0242] In this embodiment, the platform server obtains the status corresponding to the target parking area in the second database according to the predetermined attribute information.

[0243] Thus, the platform server can obtain the status of the second type of target parking area.

[0244] It should be noted that the first database and the second database in the embodiment of the present invention may be two different databases, and the two different databases respectively maintain the status of the parking area with a camera and the status of the parking area without a camera. Alternatively, the first database and the second database may be the same database, and the status of the parking area with a camera and the status of the parking area without a camera are stored in the same database.

[0245] At the same time, it should be noted that when the platform server needs to obtain data from the detection server, firstly, the detection server is a platform with the authority to monitor the parking area and has the authority to grant data to other platforms. Secondly, the platform server obtains data after being authorized by the detection server.

[0246] Furthermore, the platform server sends the acquired status of the target parking area to the user terminal for the user to view.

[0247] The embodiment of the present invention obtains at least one target parking area, divides the target parking area into a first type and a second type according to whether there is a detection device in the parking area, determines the state of the first type of target parking area according to the data obtained by the detection device, and determines the state of the second type of target parking area through a pre-trained state detection model. In this way, the state representing the congestion degree of each parking area can be obtained for the user to view, so that the user can obtain the parking area that can be parked in advance, and improve the timeliness and convenience of the user's return of the car.

[0248] Fig.15 Schematic diagram of a parking area status acquisition device according to an embodiment of the present invention. Fig.15 In the illustrated embodiment, the parking area state acquisition device is applicable to the platform server, and the device includes a target parking area acquisition unit 151, a type determination unit 152, a first state acquisition unit 153, and a second state acquisition unit 154. The target parking area acquisition unit 151 is used to acquire at least one target parking area, and the target parking area is a parking area whose state needs to be acquired. The type determination unit 152 is used to determine the type of each target parking area, and the type includes a first type and a second type. The first type is a parking area with a detection device, and the second type is a parking area without a detection device. The first state acquisition unit 153 is used to determine the state of the target parking area according to the data acquired by the detection device in response to the type of the target parking area being the first type. The second state acquisition unit 154 is used to determine the state of the target parking area through a pre-trained state detection model in response to the type of the target parking area being the second type.

[0249] In some embodiments, the state of the target parking area is used to represent the congestion level of the parking area.

[0250] In some embodiments, the target parking area acquisition unit includes:

[0251] a query request receiving subunit, configured to receive a query request from a user terminal, wherein the query request includes location information; and

[0252] The parking area determination subunit is used to obtain at least one target parking area according to the position information.

[0253] In some embodiments, the location information is the user's current location point or a query location point selected by the user.

[0254] In some embodiments, the parking area determination subunit is specifically used to:

[0255] A parking area within a predetermined range of the user's current positioning point or the query position point selected by the user is determined as the target parking area.

[0256] In some embodiments, the location information is a parking area selected by a user.

[0257] In some embodiments, the parking area determination subunit is specifically used to:

[0258] The parking area selected by the user is determined as the target parking area.

[0259] In some embodiments, the detection device is a camera.

[0260] In some embodiments, the first state acquisition unit includes:

[0261] A first attribute determination subunit, configured to determine predetermined attribute information of each target parking area, wherein the predetermined attribute information is used to characterize a unique parking area; and

[0262] The state acquisition subunit acquires the state of the target parking area from the detection server according to the predetermined attribute information, wherein the detection server acquires the state of the target parking area according to the image data or the video data.

[0263] In some embodiments, the first state acquisition unit includes:

[0264] an image acquisition subunit, used to acquire image data or video data captured by the detection device; and

[0265] The image recognition subunit is used to determine the state of the target parking area according to the image data or the video data.

[0266] In some embodiments, the image recognition subunit includes:

[0267] A first quantity determination module is used to obtain the maximum parking quantity of the target parking area;

[0268] A second quantity determination module, configured to determine the current number of parking spaces in the target parking area according to the image data or the video data;

[0269] A first ratio acquisition module, configured to acquire a first ratio, wherein the first ratio is a ratio of the current parking quantity to the maximum parking quantity; and

[0270] The first congestion determination module is used to determine the congestion of the target parking area according to the first ratio.

[0271] In some embodiments, the congestion determination module is used to:

[0272] Using the first ratio as the congestion degree of the target parking area; and / or

[0273] The congestion degree is determined according to the first ratio and a predetermined corresponding relationship, the predetermined corresponding relationship is a corresponding relationship between a ratio interval and a congestion degree, and the congestion degree is divided into a plurality of levels.

[0274] In some embodiments, the image recognition subunit includes:

[0275] A second ratio acquisition module, configured to acquire a second ratio according to the image data or the video data, wherein the second ratio is a ratio of an occupied area of ​​the target parking area to a total area of ​​the target parking area; and

[0276] The second congestion determination module is used to determine the congestion of the target parking area according to the second ratio.

[0277] In some embodiments, the second congestion determination module is configured to:

[0278] Using the second ratio as the congestion degree of the target parking area; and / or

[0279] The congestion degree is determined according to the second ratio and a predetermined corresponding relationship, the predetermined corresponding relationship is a corresponding relationship between a ratio interval and a congestion degree, and the congestion degree is divided into multiple levels.

[0280] In some embodiments, the second state acquisition unit includes:

[0281] A first parameter acquisition subunit is used to acquire input parameters of each target parking area, wherein the input parameters include one or more of time information, date information, weather information, season information, and parking area weight; and

[0282] The state output subunit is used to obtain the state of each target parking area according to the input parameters through the pre-trained state detection model.

[0283] In some embodiments, the first state acquisition unit includes:

[0284] A first database determining subunit, configured to determine a first database according to the data acquired by the detection device, wherein the first database includes the status of each parking area; and

[0285] A second attribute determination subunit, configured to determine predetermined attribute information of the target parking area; and

[0286] The first database query subunit is used to obtain the state corresponding to the target parking area in the first database according to the predetermined attribute information of the target parking area.

[0287] In some embodiments, the first database determining subunit includes:

[0288] A data acquisition module, used to acquire image data or video data captured by the detection device;

[0289] A first state determination module, configured to determine the state of each parking area according to the image data or the video data; and

[0290] A first state storage module is used to store the state of the parking area in the first database.

[0291] In some embodiments, the first database determination subunit is specifically configured to:

[0292] The status of each parking area is obtained from a detection server and stored in a first database. The detection server stores the status of a first type of parking area. The status of the first type of parking area is obtained based on image data or video data captured by the detection device.

[0293] In some embodiments, the second state acquisition unit includes:

[0294] A second database determination subunit, configured to obtain a second database through a pre-trained state detection model;

[0295] A third attribute determination subunit, configured to determine predetermined attribute information of the target parking area; and

[0296] The second database query subunit is used to obtain the state corresponding to the target parking area in the second database according to the predetermined attribute information of the target parking area.

[0297] In some embodiments, the second database determining subunit includes:

[0298] A second parameter acquisition module, used to acquire input parameters of each parking area, wherein the input parameters include one or more of time information, date information, weather information, season information, and parking area weight;

[0299] A second state determination module, configured to obtain the state of each parking area according to the input parameters through the pre-trained state detection model; and

[0300] A second state storage module is used to store the state of the parking area in the second database.

[0301] In some embodiments, the first database and the second database are the same database or different databases.

[0302] In some embodiments, the apparatus further comprises:

[0303] A status sending unit is used to send the status of each target parking area to the user terminal.

[0304] The embodiment of the present invention obtains at least one target parking area, divides the target parking area into a first type and a second type according to whether there is a detection device in the parking area, determines the state of the first type of target parking area according to the data obtained by the detection device, and determines the state of the second type of target parking area through a pre-trained state detection model. In this way, the state representing the congestion degree of each parking area can be obtained for the user to view, so that the user can obtain the parking area that can be parked in advance, and improve the timeliness and convenience of the user's return of the car.

[0305] Fig.16 is a schematic diagram of an electronic device according to an embodiment of the present invention. Fig.16The electronic device shown is a general data processing device, which includes a general computer hardware structure, which at least includes a processor 161 and a memory 162. The processor 161 and the memory 162 are connected via a bus 163. The memory 162 is suitable for storing instructions or programs executable by the processor 161. The processor 161 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 161 executes the instructions stored in the memory 162, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 163 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 164 and the display device and the input / output (I / O) device 165. The input / output (I / O) device 165 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 165 is connected to the system through an input / output (I / O) controller 166.

[0306] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, devices (equipment) or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0307] The present invention is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0308] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0309] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0310] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0311] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for obtaining the status of a parking area, applicable to a platform server, characterized in that: The method comprises: Acquire at least one target parking area, where the target parking area is a parking area whose status needs to be acquired; Determine the type of each target parking area, the type includes a first type and a second type, the first type is a parking area with a detection device, and the second type is a parking area without a detection device; In response to the type of the target parking area being the first type, determining the state of the target parking area according to the data acquired by the detection device; and In response to the type of the target parking area being the second type, the state of the target parking area is determined by using a pre-trained state detection model.

2. The method according to claim 1, characterized in that The state of the target parking area is used to represent the congestion degree of the parking area.

3. The method according to claim 1, characterized in that The acquiring of at least one target parking area comprises: receiving a query request from a user terminal, the query request including location information; and At least one target parking area is acquired according to the position information.

4. The method according to claim 3, characterized in that The location information is the user's current location point or the query location point selected by the user.

5. The method according to claim 4, characterized in that The acquiring of at least one target parking area according to the position information is specifically: A parking area within a predetermined range of the user's current positioning point or the query position point selected by the user is determined as the target parking area.

6. The method according to claim 3, characterized in that The location information is the parking area selected by the user.

7. The method according to claim 6, characterized in that The acquiring of at least one target parking area according to the position information is specifically: The parking area selected by the user is determined as the target parking area.

8. The method according to claim 1, characterized in that: The detection device is a camera.

9. The method according to claim 8, characterized in that Determining the state of the target parking area according to the data acquired by the detection device includes: Determining predetermined attribute information of each target parking area, wherein the predetermined attribute information is used to characterize a unique parking area; and The state of the target parking area is acquired from a detection server according to the predetermined attribute information, wherein the detection server acquires the state of the target parking area according to image data or video data.

10. The method according to claim 8, characterized in that Determining the state of the target parking area according to the data acquired by the detection device includes: Acquiring image data or video data captured by the detection device; and The state of the target parking area is determined based on the image data or the video data.

11. The method according to claim 10, characterized in that Determining the state of the target parking area according to the image data or the video data includes: Obtain the maximum number of parking spaces in the target parking area; determining the current number of parking spaces in the target parking area according to the image data or the video data; Acquire a first ratio, where the first ratio is a ratio of the current parking quantity to the maximum parking quantity; and The congestion degree of the target parking area is determined according to the first ratio.

12. The method according to claim 11, characterized in that Determining the congestion degree of the target parking area according to the first ratio includes at least one of the following: Using the first ratio as the congestion degree of the target parking area; The congestion degree is determined according to the first ratio and a predetermined corresponding relationship, the predetermined corresponding relationship is a corresponding relationship between a ratio interval and a congestion degree, and the congestion degree is divided into a plurality of levels.

13. The method according to claim 10, characterized in that Determining the state of the target parking area according to the image data or the video data includes: acquiring a second ratio according to the image data or the video data, wherein the second ratio is a ratio of an occupied area of ​​the target parking area to a total area of ​​the target parking area; and The congestion degree of the target parking area is determined according to the second ratio.

14. The method according to claim 13, characterized in that Determining the congestion degree of the target parking area according to the second ratio includes at least one of the following: using the second ratio as the congestion degree of the target parking area; The congestion degree is determined according to the second ratio and a predetermined corresponding relationship, the predetermined corresponding relationship is a corresponding relationship between a ratio interval and a congestion degree, and the congestion degree is divided into multiple levels.

15. The method according to claim 1, characterized in that Determining the state of the target parking area by using a pre-trained state detection model includes: Acquire input parameters of each target parking area, wherein the input parameters include one or more of time information, date information, weather information, season information, and parking area weight; and The state of each of the target parking areas is acquired according to the input parameters through the pre-trained state detection model.

16. The method according to claim 8, characterized in that Determining the state of the target parking area according to the data acquired by the detection device includes: Determining a first database according to the data acquired by the detection device, wherein the first database includes the status of each parking area; and Determining predetermined attribute information of the target parking area; and A state corresponding to the target parking area is acquired in the first database according to predetermined attribute information of the target parking area.

17. The method according to claim 16, characterized in that Determining the first database according to the data acquired by the detection device includes: Acquire image data or video data captured by the detection device; Determining the state of each of the parking areas according to the image data or the video data; and The status of the parking area is stored in the first database.

18. The method according to claim 16, characterized in that The determining of the first database according to the data acquired by the detection device is specifically: The status of each parking area is obtained from a detection server and stored in a first database. The detection server stores the status of a first type of parking area. The status of the first type of parking area is obtained based on image data or video data captured by the detection device.

19. The method according to claim 16, characterized in that Determining the state of the target parking area by using a pre-trained state detection model includes: Acquire a second database through a pre-trained state detection model; Determining predetermined attribute information of the target parking area; and The state corresponding to the target parking area is acquired in the second database according to the predetermined attribute information of the target parking area.

20. The method according to claim 19, characterized in that The acquiring of the second database by using the pre-trained state detection model comprises: Obtaining input parameters of each parking area, wherein the input parameters include one or more of time information, date information, weather information, season information, and parking area weight; Acquiring the state of each of the parking areas according to the input parameters by using the pre-trained state detection model; and The status of the parking area is stored in the second database.

21. The method according to claim 20, characterized in that The first database and the second database are the same database or different databases.

22. The method according to claim 3, characterized in that The method further comprises: The status of each target parking area is sent to the user terminal.

23. A parking area status acquisition device, suitable for a platform server, characterized in that: The device comprises: a target parking area acquisition unit, configured to acquire at least one target parking area, wherein the target parking area is a parking area whose status needs to be acquired; a type determination unit, configured to determine a type of each of the target parking areas, the type comprising a first type and a second type, the first type being a parking area with a detection device, and the second type being a parking area without a detection device; a first state acquisition unit, configured to determine the state of the target parking area according to the data acquired by the detection device in response to the type of the target parking area being the first type; and The second state acquisition unit is configured to determine the state of the target parking area by using a pre-trained state detection model in response to the type of the target parking area being the second type.

24. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-22.

25. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: The computer program instructions, when executed by a processor, implement the method of any one of claims 1-22.

Images