A parking space recognition method and related apparatus

Abstract

The application provides a parking space identification method and related device, through a first vehicle collecting external environment information in a driving process, so as to determine parking space related information based on the external environment information and send it to a cloud platform, the cloud platform can determine a target parking space available for a vehicle to park in a surrounding area of the first vehicle from at least one parking space according to a parking confidence of the at least one parking space contained in the parking space related information and historical parking information of the at least one parking space pre-stored. Thus, when a second vehicle sends a parking space query request, the cloud platform can determine an idle parking space around the second vehicle from a target parking space set according to historical parking information of a target parking space contained in the target parking space set. As can be seen, the application can obtain all idle parking spaces around the second vehicle by using the external environment information collected by the first vehicle, thereby improving the efficiency and accuracy of parking space identification.

Description

Technical Field

[0001] This application relates to the field of parking space recognition technology, and in particular to a parking space recognition method and related apparatus. Background Technology

[0002] With the rapid pace of urbanization, the number of vehicles has exploded, leading to an increasingly prominent imbalance between parking space supply and demand. This is especially true in densely populated areas such as bustling commercial districts, large shopping malls, and residential communities, where parking spaces are often in short supply, causing significant inconvenience for car owners. Drivers often spend considerable time and effort searching for parking spaces, sometimes taking tens of minutes to find a suitable spot.

[0003] Therefore, there is an urgent need for a method that can efficiently and accurately identify available parking spaces around a vehicle, so that car owners can find a suitable parking space in a short time, saving time and effort and improving travel efficiency. Summary of the Invention

[0004] In view of this, this application provides a parking space identification method and related apparatus for efficiently and accurately identifying vacant parking spaces around a vehicle, the technical solution of which is as follows:

[0005] Firstly, a parking space recognition method is provided, applied to a cloud platform, including:

[0006] Receive parking space related information from the first vehicle, wherein the parking space related information is determined based on the external environment information collected during the first vehicle's driving process, and the parking space related information includes the parking confidence of at least one parking space in the surrounding area where the first vehicle is driving.

[0007] Based on the parking confidence of at least one parking space and the historical parking information of at least one parking space stored in advance, a target parking space is determined from at least one parking space, wherein the target parking space is a parking space available for parking in the area surrounding the first vehicle's driving.

[0008] In response to the parking space query request of the second vehicle, based on the historical parking information of the target parking spaces contained in the target parking space set, the available parking spaces around the second vehicle are determined from the target parking space set, wherein the target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle.

[0009] Secondly, a parking space recognition method is provided, applied to a first vehicle, including:

[0010] Acquire external environmental information collected during the driving of the first vehicle;

[0011] Based on the external environment information, determine the parking space related information contained in the area surrounding the first vehicle's driving, wherein the parking space related information includes the parking confidence of at least one parking space.

[0012] The system sends parking space information related to the area surrounding the first vehicle to the cloud platform. The cloud platform then determines a target parking space from at least one parking space based on the parking confidence level of at least one parking space and the historical parking information of at least one pre-stored parking space. Upon receiving a parking space query request from the second vehicle, the system determines available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set. The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle. The target parking spaces are parking spaces available for vehicles within the area surrounding the first vehicle.

[0013] Thirdly, a parking space recognition device is provided for use on a cloud platform, including:

[0014] The information receiving unit is used to receive parking space related information from the first vehicle, wherein the parking space related information includes the parking confidence of at least one parking space in the surrounding area of ​​the first vehicle, and the parking confidence is determined based on the external environment information collected during the first vehicle's driving process.

[0015] A parking space determination unit is used to determine a target parking space from at least one parking space based on the parking confidence of at least one parking space and the historical parking information of at least one parking space stored in advance, wherein the target parking space refers to a parking space available for vehicles to park.

[0016] The vacant parking space identification unit is used to respond to the parking space query request of the second vehicle and determine the vacant parking spaces around the second vehicle from the target parking space set according to the historical parking information of the target parking spaces contained in the target parking space set. The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle.

[0017] Fourthly, a parking space recognition device is provided, applied to a first vehicle, comprising:

[0018] The information acquisition unit is used to acquire external environmental information collected during the driving process of the first vehicle;

[0019] The information determination unit is used to determine, based on external environmental information, the parking space related information contained in the area surrounding the first vehicle's driving, wherein the parking space related information includes the parking confidence level of at least one parking space.

[0020] The information sending unit is used to send parking space-related information contained in the area surrounding the first vehicle to the cloud platform, so that the cloud platform can determine the target parking space from the at least one parking space based on the parking confidence of at least one parking space and the historical parking information of at least one parking space stored in advance. When receiving a parking space query request from the second vehicle, the cloud platform can determine the available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set. The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle. The target parking spaces are parking spaces available for vehicles to park in the area surrounding the first vehicle.

[0021] Fifthly, an electronic device is provided, including a memory and a processor;

[0022] Memory, used to store programs;

[0023] A processor is used to execute programs that implement the various steps of any of the parking space recognition methods described above.

[0024] In a sixth aspect, a storage medium is provided having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the various steps of the parking space recognition method as described in any of the above claims.

[0025] As can be seen from the above technical solution, the parking space identification method provided in this application, in order to fully utilize all available vacant parking spaces in the external environment, can collect external environment information during the first vehicle's operation. Based on this information, parking space-related information is determined and sent to a cloud platform. The cloud platform can then determine target parking spaces available for parking within the area surrounding the first vehicle's location based on the parking confidence level of at least one parking space included in the parking space-related information, and on pre-stored historical parking information of at least one parking space. Therefore, when the second vehicle sends a parking space query request, the cloud platform can determine available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces. Thus, this application can utilize the external environment information collected by the first vehicle to obtain all available parking spaces around the second vehicle, improving the efficiency and accuracy of parking space identification. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0027] Figure 1 A flowchart illustrating a parking space recognition method applied to a cloud platform, provided as an embodiment of this application;

[0028] Figure 2 A schematic diagram of multiple parking space clusters provided in an embodiment of this application;

[0029] Figure 3 A flowchart illustrating a parking space identification method for a first vehicle provided in an embodiment of this application;

[0030] Figure 4 This is a schematic diagram illustrating the collection of external environmental information by the first vehicle during its operation.

[0031] Figure 5 A schematic diagram showing the road width and road height for a parking space with a slope;

[0032] Figure 6 A schematic diagram of the structure of a parking space recognition device applied to a cloud platform, provided in an embodiment of this application;

[0033] Figure 7 A schematic diagram of a parking space recognition device applied to a first vehicle, provided in an embodiment of this application;

[0034] Figure 8 This is a hardware structure block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0036] In existing technologies, the method for identifying vacant parking spaces around a vehicle is to identify vacant parking spaces within a small area managed by a management system, such as identifying vacant parking spaces in a parking lot with a supporting management system or identifying private parking spaces. However, the parking resources that can be provided are limited and cannot meet the needs of many scenarios.

[0037] In view of the problems existing in the prior art, the inventors of this case conducted in-depth research and finally proposed a parking space identification method that can be applied to the scenario of identifying vacant parking spaces.

[0038] Optionally, the above-mentioned vacant parking space recognition scenario can be a small-scale scenario with manageable parking spaces, such as a parking lot, or a roadside scenario, etc. This application does not impose specific limitations.

[0039] The parking space recognition method provided in this application is a parking space recognition method in the scenario of interaction between a first vehicle and a data analysis platform. Optionally, the data analysis platform can be a cloud platform.

[0040] To enable those skilled in the art to better understand this application, the following section uses a cloud platform as an example to provide a detailed description of the parking space recognition method applied to a cloud platform provided in this application.

[0041] Please see Figure 1 The diagram illustrates a flowchart of a parking space recognition method applied to a cloud platform, as provided in an embodiment of this application. This parking space recognition method applied to a cloud platform may include:

[0042] Step S101: Receive parking space related information from the first vehicle, including parking confidence of at least one parking space in the surrounding area where the first vehicle is traveling.

[0043] Traditional parking space recognition methods are designed for small-scale scenarios with management systems. They often fail to identify available parking spaces in unmanaged non-parking areas or even unmanaged parking areas. If drivers cannot find available spaces, it can lead to a waste of parking resources, and drivers will have to spend a lot of time and energy searching for other spaces, resulting in a poor parking experience.

[0044] To fully utilize various types of parking spaces and provide drivers with a better parking experience, the inventors of this invention conceived of fully leveraging the capabilities of all available vehicles by collecting external environmental information during vehicle operation. This information is then used to determine parking space-related information. For clarity, any vehicle collecting external environmental information is defined as the first vehicle. In this embodiment, the first vehicle can collect external environmental information during its own operation, generate parking space-related information based on this information, and then send it to a cloud platform.

[0045] In this embodiment of the application, the parking space related information includes at least the parking confidence of at least one parking space in the area surrounding the first vehicle. Here, the parking confidence of a parking space can characterize the reliability of the area where the parking space is located as a parking space available for vehicles. The higher the parking confidence of a parking space, the higher the reliability of the parking space. Conversely, the lower the parking confidence, the lower the reliability of the parking space.

[0046] It should be noted that the "parking space" in this step refers to the identification of the vehicle's external environment information as a parking space based on the information collected from the first vehicle. However, whether it is indeed a real parking space needs to be determined in subsequent steps.

[0047] Step S102: Determine the target parking space from the at least one parking space based on the parking confidence level of at least one parking space and the historical parking information of at least one parking space stored in advance.

[0048] Here, the target parking space is a parking space available for vehicles within the area surrounding the first vehicle's route; that is, the target parking space is indeed a real, available parking space.

[0049] Specifically, in this embodiment, for each parking space in at least one parking space, if the parking confidence level of the parking space is 1, it means that it is indeed a real parking space that can be used, and then it is determined as the target parking space; if the parking confidence level of the parking space is not 1, it means that it cannot be determined with 100% certainty that it is a parking space, and then it is necessary to combine the pre-stored historical parking information of the parking space to determine whether the parking space is the target parking space.

[0050] Optionally, in this embodiment, "historical parking information of at least one parking space" can be determined based on parking space-related information. Specifically, it can be determined based on the discrimination elements of at least one parking space included in the parking space-related information. Here, the discrimination elements can be used to calculate parking confidence. Optionally, the discrimination elements include: a vehicle is parked, there are parking lines, and there are no-parking signs.

[0051] More specifically, the process of determining the historical parking information of at least one parking space may include: determining, from the parking space-related information received from multiple first vehicles in the past, the discrimination element of each of at least one parking space within a preset time period is the target parking space-related information where a vehicle is parked; and determining the target parking space-related information where the discrimination element of each of at least one parking space within the preset time period is the target parking space-related information where a vehicle is parked, and the receiving timestamp of the target parking space-related information, as the historical parking information of at least one parking space.

[0052] Here, "preset time period" refers to the time period at the current time. Considering that the external environment may change over time, the reliability of parking space information received earlier is lower. Setting a preset time period can avoid errors in the historical parking information determined in this embodiment due to referencing parking space information from a long time ago.

[0053] In this embodiment, the cloud platform can record the timestamp of each time it receives parking space-related information. Therefore, it can determine whether the relevant information of each parking space is within a preset time period based on the timestamp.

[0054] It should be understood that when the parking confidence level of a parking space is not 1, if the determining factor of the parking space is that a vehicle is parked there, then the parking space can accommodate one vehicle, and the probability that the parking space is indeed a real and reliable parking space is relatively high. Based on this, taking any one of at least one parking spaces as an example, this embodiment can determine the target parking space information where the determining factor of the parking space is that a vehicle is parked within a preset time period from the parking space information received from multiple first vehicles in the past. Then, the target parking space information and the receiving timestamp of the target parking space information can be determined as the historical parking information of the parking space.

[0055] Based on the aforementioned historical parking information, the specific implementation process of this step may include: identifying parking spaces with a parking confidence level not equal to 1 that are included in at least one parking space as parking spaces to be screened; for each parking space included in the parking spaces to be screened, determining the number of times the parking space has a parking time interval greater than a preset time threshold within a preset time period based on the historical parking information of that parking space; identifying parking spaces in the parking spaces to be screened with a parking time interval greater than or equal to a preset number threshold as filtered parking spaces; and identifying the filtered parking spaces and parking spaces with a parking confidence level of 1 included in at least one parking space as target parking spaces.

[0056] For example, if the preset time period is one month, and a parking space with a parking confidence level of not 1 is found to be parked 5 times within one month under the condition of every 5 hours (preset time threshold less than 5) (preset number threshold less than 5), then the parking space is identified as the target parking space.

[0057] Generally, the overall time from the first vehicle collecting external environmental information to analyzing and sending parking space-related information to the cloud platform is relatively short. Therefore, the receiving timestamp of the parking space-related information can be used as the parking time of those vehicles parked in the parking spaces included in the parking space-related information. In other words, this embodiment can determine the parking time interval of the parking space based on the receiving timestamp.

[0058] It should be noted that the parking time interval in this embodiment refers to the difference between two adjacent receiving timestamps when the judgment element is that a vehicle is parked in the same parking space. The reason for setting the parking time interval in this embodiment is that in some scenarios, some locations are not penalized for short-term parking, but will be penalized for long-term parking. By setting the parking time interval, it is possible to avoid recommending these locations as target parking spaces to car owners, which would result in car owners being penalized for exceeding the prescribed parking time.

[0059] Step S103: Respond to the parking space query request of the second vehicle, and determine the available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set.

[0060] The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle.

[0061] Specifically, the cloud platform can aggregate the target parking spaces obtained from each of the first vehicles to obtain a target parking space set. Then, when the second vehicle sends a parking space query request to the cloud platform, it can determine the available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set.

[0062] In this embodiment, after the cloud platform identifies an available parking space, it can push the available parking space to the second vehicle so that the second vehicle can quickly and accurately find an available parking space.

[0063] The parking space identification method provided in this application, in order to fully utilize all available vacant parking spaces in the external environment of a vehicle, can collect external environmental information during the driving of a first vehicle. Based on this information, parking space-related information is determined and sent to a cloud platform. The cloud platform can then determine target parking spaces available for parking within the area surrounding the first vehicle, based on the parking confidence level of at least one parking space included in the parking space-related information and pre-stored historical parking information of at least one parking space. Therefore, when a second vehicle sends a parking space query request, the cloud platform can determine available parking spaces around the second vehicle from the target parking space set, based on the historical parking information of the target parking spaces. Thus, this application can utilize the external environmental information collected by the first vehicle to obtain all available parking spaces around the second vehicle, improving the efficiency and accuracy of parking space identification.

[0064] In some embodiments of this application, the process of "determining available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set" in step S103 above is described.

[0065] Considering that the area of ​​a single target parking space is small, it is difficult to achieve accurate positioning. However, if multiple target parking spaces that are close together are grouped together, the location of the cluster is relatively more accurate. Based on this, optionally, this embodiment can cluster the set of target parking spaces into multiple parking space clusters according to the location information of the target parking spaces. Here, the location information of the target parking spaces can be obtained based on the vehicle-mounted radar sensors on the first vehicle.

[0066] Generally, the distances to the second vehicle vary across multiple parking space clusters. To improve the parking experience for the second vehicle's owner, it is preferable to identify a target parking space cluster whose distance to the second vehicle is less than a preset distance threshold. Here, the location of the second vehicle can be obtained by parsing the second vehicle's parking space query request.

[0067] For example, see Figure 2 The multiple parking space clusters shown are as follows: the target parking space clusters corresponding to the second vehicle A are cluster A and cluster B; the target parking space cluster corresponding to the second vehicle B is cluster C; the target parking space clusters corresponding to the second vehicle C are cluster D and cluster E; and the target parking space clusters corresponding to the second vehicle D are cluster E and cluster F.

[0068] Furthermore, in this embodiment, available parking spaces can be determined from the target parking space cluster based on the historical parking information of the target parking spaces contained in the target parking space cluster.

[0069] As mentioned earlier, the location of a single parking space is generally not very accurate, but the location of a cluster of parking spaces is highly accurate. Based on this, this embodiment can push the location of the target parking space cluster to the owner of the second vehicle only, and push the number of available parking spaces contained in the target parking space cluster.

[0070] Optionally, it can also push driving routes to the target parking space cluster.

[0071] Here, the number of available parking spaces in the target parking space cluster = the number of target parking spaces in the target parking space cluster - the number of parking spaces in the target parking space cluster at the current time.

[0072] Based on this, the process of "determining available parking spaces from the target parking space cluster based on the historical parking information of the target parking spaces contained in the target parking space cluster" in this embodiment includes: determining the total number of parking spaces contained in the target parking space cluster; determining the number of parking spaces in the target parking space cluster at the current time point based on the historical parking information of the target parking spaces contained in the target parking space cluster; and calculating the number of available parking spaces based on the total number and the number of parking spaces in the target parking space cluster at the current time point.

[0073] Optionally, the process of “determining the total number of parking spaces contained in the target parking space cluster” can be based on the number of parking spaces in the target parking space cluster that are identified by the criteria of having a vehicle parked and having parking lines.

[0074] In this embodiment, the process of "determining the number of parking spaces in the target parking space cluster at the current time point based on the historical parking information of the target parking spaces contained in the target parking space cluster" can be implemented in multiple ways. The following two implementation methods are provided here, but are not limited to.

[0075] It should be noted that, in order to distinguish between the two implementation methods, the first implementation method defines the "number of cars parked in the target parking space cluster at the current time" as the first number of cars, while the second implementation method defines the "number of cars parked in the target parking space cluster at the current time" as the second number of cars.

[0076] The first implementation method is to analyze the historical parking situation of the target parking space cluster at the same time point under a preset time period.

[0077] Specifically, based on the objective fact that the number of cars parked in a parking space cluster is roughly the same at the same time every day, this embodiment can determine the number of cars parked in the target parking space cluster at each historical time point within a preset time period based on the historical parking information of the target parking spaces contained in the target parking space cluster. Here, a historical time point refers to a time point within a unit of time within the preset time period that is the same as the current time point. Then, based on the number of cars parked in the target parking space cluster at each historical time point within the preset time period, the first number of cars parked in the target parking space cluster at the current time point is estimated.

[0078] For example, if the preset time period is one week and the current time is 12 noon, then each historical time point includes 12 noon of each day within the most recent week. In this embodiment of the application, the number of parking spaces in the target parking space cluster at 12 noon of each day within the most recent week can be determined based on the historical parking information received at 12 noon of each day within the most recent week (i.e., the received timestamp).

[0079] Optionally, the process of "estimating the first number of parking spaces in the target parking space cluster at the current time point based on the number of parking spaces in the target parking space cluster at each historical time point within a preset time period" may include: determining the number of units of time within the preset time period as the base number; generating a base weight based on the base number and a preset increment coefficient; determining a target weight for the number of parking spaces in the target parking space cluster at each historical time point within the preset time period based on the base weight; and performing a weighted average of the number of parking spaces in the target parking space cluster at each historical time point within the preset time period based on the determined target weight to obtain the first number of parking spaces in the target parking space cluster at the current time point.

[0080] For example, assuming the preset time period is one week and the unit of time is one day, the base number is 7.

[0081] In this embodiment, the basic weight can be generated according to the following formula (1), the target weight of the number of parking spaces in the target parking space cluster at each historical time point included in the preset time period can be determined according to the following formula (2), and the first number of parking spaces in the target parking space cluster at the current time point can be determined according to the following formula (3).

[0082]

[0083] wi=(i-1)w formula (2)

[0084]

[0085] In the formula, p represents the preset increment coefficient, n represents the base number, w represents the base weight, wi represents the target weight of the number of parking spaces in the target parking space cluster at the i-th historical time point included in the preset time period, Nt represents the first number of parking spaces in the target parking space cluster at the current time point, and Ni represents the number of parking spaces in the target parking space cluster at the i-th historical time point included in the preset time period.

[0086] Optionally, the preset increment coefficient can be a date-based increment coefficient.

[0087] In this embodiment, after determining the first number of parking spaces, the number of available parking spaces can be calculated based on the total number and the first number of parking spaces in the target parking space cluster at the current time.

[0088] The second implementation method: The first implementation method combines the analysis of the most recent record of the day.

[0089] Specifically, in this embodiment, the most recent parking time of the target parking spaces in the target parking space cluster can be determined based on the historical parking information of the target parking spaces in the target parking space cluster; a parking number weight value can be generated based on the most recent parking time of the target parking spaces in the target parking space cluster; and a second parking number of the target parking space cluster at the current time point can be determined based on the parking number weight value and the first parking number of the target parking space cluster at the current time point.

[0090] Here, the most recent parking time refers to the timestamp of the most recent reception of parking space information related to the target parking space in the target parking space cluster. For example, the target parking space cluster includes target parking spaces 1 to 3. The most recent timestamp of the reception of parking space information related to target parking space 1 (where the discrimination element for target parking space 1 is that a vehicle is parked) is 10:00 AM on the same day. The most recent timestamp of the reception of parking space information related to target parking space 2 (where the discrimination element for target parking space 2 is that a vehicle is parked) is 11:00 AM on the same day. The most recent timestamp of the reception of parking space information related to target parking space 3 (where the discrimination element for target parking space 3 is that a vehicle is parked) is 12:00 PM on the same day. Therefore, the most recent parking time in this embodiment is 12:00 PM on the same day.

[0091] Optionally, the process of "generating a parking number weight value based on the most recent parking time of the target parking spaces contained in the target parking space cluster" in this embodiment can be as follows: generating a parking number weight value based on the distance between the most recent parking time of the target parking spaces contained in the target parking space cluster and the current time point.

[0092] For example, if the most recent parking time is within 10 minutes of the current time, the weight of the number of parking spaces is 90%, and the weight of the first parking space is 10%; if the most recent parking time is within 30 minutes of the current time, the weight of the number of parking spaces is 80%, and the weight of the first parking space is 20%, and so on.

[0093] After determining the weight value of the number of parking spaces, this embodiment can determine the second number of parking spaces in the target parking space cluster at the current time point based on the weight value of the number of parking spaces and the first number of parking spaces in the target parking space cluster at the current time point. Then, the number of available parking spaces can be calculated based on the total number and the second number of parking spaces in the target parking space cluster at the current time point.

[0094] In summary, this embodiment provides two methods for calculating the number of available parking spaces in a target parking space cluster based on the objective fact that the number of parking spaces in a parking space cluster is roughly the same at the same time every day, thereby improving the accuracy of the calculated number of available parking spaces.

[0095] This application also provides a parking space identification method for a first vehicle, see [link to relevant documentation]. Figure 3 The diagram shown is a flowchart illustrating a parking space identification method for a first vehicle provided in an embodiment of this application.

[0096] like Figure 3 As shown, the parking space recognition method for a first vehicle provided in this application embodiment may include:

[0097] Step S201: Obtain the external environment information collected during the driving process of the first vehicle.

[0098] Specifically, in this embodiment of the application, each vehicle can be used as the first vehicle, that is, the information collector in this embodiment of the application.

[0099] The first vehicle can collect information about the external environment while in motion. For example, see... Figure 4 The image shown is a schematic diagram illustrating the collection of external environmental information by the first vehicle during its operation. Figure 4 In the above scenario, the first vehicle A in the lane can collect external environmental information A while driving, the first vehicle B in the lane can collect external environmental information B while driving, and the first vehicle C in the lane can collect external environmental information C while driving.

[0100] Optionally, the external environment information includes images of the external environment and radar scan information.

[0101] Optionally, images of the external environment can be obtained by an onboard camera installed on the first vehicle; radar scan images can be obtained by an onboard radar sensor installed on the first vehicle.

[0102] Optionally, the radar scan information includes information such as the distance and angle between the first vehicle and surrounding objects.

[0103] Step S202: Based on the external environment information, determine the parking space related information contained in the area surrounding the first vehicle's driving, wherein the parking space related information includes the parking confidence of at least one parking space.

[0104] Specifically, this step can determine at least one parking space in the area surrounding the first vehicle based on the external environment information, and further determine the parking space information of at least one parking space based on the external environment information.

[0105] Optionally, this step can determine at least one parking space in the area surrounding the first vehicle's travel location based on external environmental information and preset parking space screening rules.

[0106] Optionally, the initial screening rules for parking spaces may include at least one of the following: there is parking space available outside the lane, there are no no-parking signs, and there are parked vehicles.

[0107] Step S203: Send the parking space information of the area surrounding the first vehicle to the cloud platform so that the cloud platform can determine the target parking space from the at least one parking space based on the parking confidence of at least one parking space and the historical parking information of at least one parking space stored in advance. When receiving a parking space query request from the second vehicle, the cloud platform can determine the available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set. The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle. The target parking spaces are the parking spaces available for vehicles to park in the area surrounding the first vehicle.

[0108] Optionally, in this embodiment, the process of the first vehicle sending parking space-related information to the cloud platform can be a periodic behavior or a timed behavior.

[0109] In one optional embodiment, this embodiment can draw a regional map based on the external environment information of the vehicle, mark the parking space-related information on the regional map, and then send the regional map to the cloud platform.

[0110] For example, mark at least one parking space with a parking confidence greater than 0 on the regional map, and identify the discrimination elements and parking confidence of at least one parking space on the regional map, and then send the regional map to the cloud platform.

[0111] Optionally, the location information of the first vehicle can be included when sending the regional map to the cloud platform.

[0112] The process of determining available parking spaces on the cloud platform in this step can be referred to the section on parking space identification methods applied to the cloud platform provided above, and will not be repeated here.

[0113] The parking space identification method provided in this application involves collecting external environmental information from a first vehicle while it is in motion, determining parking space-related information based on this information, and sending it to a cloud platform. The cloud platform can then determine target parking spaces available for parking within the area surrounding the first vehicle, based on the parking confidence level of at least one parking space included in the parking space-related information and pre-stored historical parking information of at least one parking space. Consequently, when a second vehicle sends a parking space query request, the cloud platform can determine available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces. Therefore, this application can utilize the external environmental information collected by the first vehicle to obtain all available parking spaces around the second vehicle, improving the efficiency and accuracy of parking space identification.

[0114] In some embodiments of this application, the process of determining the parking confidence of at least one parking space in step S202 above is described.

[0115] Taking the external environment information, including external environment images and radar scan information, as an example, the process of determining the parking confidence of at least one parking space based on the external environment images in this embodiment may include: parsing the external environment images contained in the external environment information to determine the parking discrimination conditions satisfied by each of the at least one parking space, wherein the parking discrimination conditions include multiple sub-conditions; determining the occupied space information and road slope information of each of the at least one parking space based on the radar scan information contained in the external environment information; for each of the at least one parking space, obtaining the first confidence of the parking space based on the sub-conditions satisfied by the parking space, determining the second confidence of the parking space based on the occupied space information and road slope information of the parking space, and determining the parking confidence of the parking space based on the first confidence and the second confidence.

[0116] Specifically, image processing and machine learning algorithms can be used to analyze the images of the external environment contained in the vehicle's external environment information to determine the parking discrimination conditions that at least one parking space must meet.

[0117] Optionally, each sub-condition included in the parking discrimination condition consists of a discrimination element; for example, the multiple sub-conditions included in the parking discrimination condition are: the first sub-condition that the parking space has a no-parking sign, the second sub-condition that the parking space is a marked parking space, and the third sub-condition that the parking space is a parking space with a vehicle parked.

[0118] Of course, the above sub-conditions are merely examples and are not intended to limit this application. For example, this embodiment may also include a fourth sub-condition that the parking space is a parking space in a parking lot, and so on.

[0119] For each parking space in at least one parking space, this embodiment can obtain the first confidence level of the parking space based on the sub-conditions satisfied by the parking space.

[0120] Optionally, the process of "obtaining the first confidence level of the parking space based on the sub-conditions satisfied by the parking space" may include: determining the initial value of the parking space under the satisfied sub-conditions as a preset value, wherein the multiple sub-conditions include a first sub-condition that the parking space has a no-parking sign, the initial value of the parking space under the satisfied first sub-condition is the first preset value, and the preset value of the same parking space is different under different sub-conditions; if the initial value of the parking space under the satisfied first sub-condition is not the first preset value, then the first confidence level of the parking space is determined based on the initial value of the parking space under the satisfied sub-conditions.

[0121] Optionally, the process of “determining the first confidence level of the parking space based on the initial values ​​of the parking space under the satisfied sub-conditions” may include: determining the maximum value among the initial values ​​of the parking space under the satisfied sub-conditions as the first confidence level of the parking space.

[0122] For example, the first confidence level is denoted by cr; if the parking space meets the first sub-condition, the initial value is set to the first preset value -1; if the parking space meets the second sub-condition, the initial value is set to the second preset value cr1; if the parking space meets the third sub-condition, the initial value is set to the third preset value cr2; and so on.

[0123] So, when the parking space meets the first sub-condition, the initial value is equal to -1, making the first confidence level cr = 0; when the parking space does not meet the first sub-condition, but meets m sub-conditions that are not the first sub-condition, the first confidence level cr = max(cr1, cr2, cr3, ..., crm).

[0124] Furthermore, this embodiment can determine the occupied space information and road slope information of at least one parking space based on the radar scanning information included in the external environment information.

[0125] Optional, road slope information includes road width and road height. See also Figure 5The diagram shown illustrates the road width and height for a sloping parking space. Figure 5 The parking space shown is located on a slope, which gives the parking space a corresponding road width B and road height H.

[0126] It should be noted that radar scans can usually obtain the road width and height, but there may be cases where the road width cannot be identified. In such cases, a preset reference width can be used as the road width.

[0127] For each parking space in at least one parking space, this embodiment can determine the second confidence level of the parking space based on the occupancy information and road slope information of the parking space.

[0128] Optionally, the process of "determining the second confidence level of the parking space based on the occupied space information and the road slope information" may include: determining the first reliability of the parking space on the road slope information based on the road slope information; determining the second reliability of the parking space on the space size information based on the occupied space information; and determining the second confidence level of the parking space based on the first reliability and the second reliability.

[0129] For example, the longitudinal slope value of the slope where the parking space is located is calculated using the following formula (4), and then the first reliability is determined based on the calculated longitudinal slope value.

[0130]

[0131] In the formula, tanα represents the longitudinal slope of the slope where the parking space is located.

[0132] The process of "determining the first reliability based on the calculated longitudinal slope value" can be as follows: when the longitudinal slope value is less than 10%, the first reliability re1 is 1; when the longitudinal slope value is less than 20%, the first reliability re1 is 90%; when the longitudinal slope value is less than 30%, the first reliability re1 is 70%; and when the longitudinal slope value is greater than 30%, the first reliability re1 is 0.

[0133] In this embodiment, a second reliability re2 can be determined based on the occupancy information of the parking space compared to the size of a normal parking space. For example, when the length or width of the occupancy information of the parking space is smaller than that of a normal parking space, re2 is 0; when both the length and width are greater than 10% of that of a normal parking space, re2 is 70%.

[0134] Optionally, the second confidence level of the parking space can be determined using formula (5).

[0135] re=re1*re2 formula (5)

[0136] In the formula, re represents the second confidence level of the parking space.

[0137] In an optional embodiment, the process of "determining the parking confidence of the parking space based on the first confidence and the second confidence of the parking space" may include: performing a weighted summation of the first confidence and the second confidence of the parking space to obtain the parking confidence of the parking space, wherein the weights used for the weighted summation are preset values.

[0138] That is, the parking confidence level of the parking space is obtained by using formula (6).

[0139] T=Wcr*cr+Wre*re formula (6)

[0140] In the formula, T represents the parking confidence level of the parking space, Wcr represents the weight of the first confidence level, and Wre represents the weight of the second confidence level.

[0141] The embodiments of this application can determine the parking confidence of a parking space based on three aspects: discrimination elements, occupied space information, and road slope information. Therefore, based on the parking confidence, it can more accurately determine whether a parking space is indeed a real and reliable parking space, greatly reducing the situation where car owners cannot find a vacant parking space when traveling, and improving the car owner experience.

[0142] This application also provides a parking space recognition device for a cloud platform. The parking space recognition device for a cloud platform provided in this application is described below. The parking space recognition device for a cloud platform described below can be referred to in correspondence with the parking space recognition method for a cloud platform described above.

[0143] Please see Figure 6 This illustration shows a schematic diagram of the structure of a parking space recognition device applied to a cloud platform, as provided in an embodiment of this application. Figure 6 As shown, the parking space recognition device applied to the cloud platform may include: an information receiving unit 601, a parking space determination unit 602, and an vacant parking space recognition unit 603.

[0144] The information receiving unit 601 is used to receive parking space related information from the first vehicle. The parking space related information includes the parking confidence level of at least one parking space in the surrounding area of ​​the first vehicle. The parking confidence level is determined based on the external environment information collected during the driving of the first vehicle.

[0145] The parking space determination unit 602 is used to determine a target parking space from at least one parking space based on the parking confidence of at least one parking space and the historical parking information of at least one parking space stored in advance, wherein the target parking space refers to a parking space available for vehicle parking.

[0146] The vacant parking space identification unit 603 is used to respond to the parking space query request of the second vehicle and determine the vacant parking spaces around the second vehicle from the target parking space set according to the historical parking information of the target parking spaces contained in the target parking space set. The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle.

[0147] In one possible implementation, the parking space determination unit described above may include:

[0148] The parking space to be screened sub-unit is used to identify at least one parking space containing a parking confidence level not equal to 1 as a parking space to be screened.

[0149] The parking frequency determination subunit is used to determine, for each parking space included in the parking spaces to be screened, the number of times the parking time interval of the parking space is greater than a preset time threshold within a preset time period, based on the historical parking information of the parking space.

[0150] The parking space filtering subunit is used to identify parking spaces that have been parked more than or equal to a preset threshold number of times as filtered parking spaces.

[0151] The target parking space determination subunit is used to determine the filtered parking spaces and at least one parking space containing a parking confidence level of 1 as the target parking spaces.

[0152] In one possible implementation, the aforementioned parking space-related information also includes at least one parking space discrimination element.

[0153] Based on this, the process of determining the historical parking information of at least one parking space in the above parking space determination unit may include:

[0154] From the parking space information received from multiple first vehicles in the past, determine the discrimination elements of at least one parking space within a preset time period as the target parking space information where a vehicle is parked.

[0155] The historical parking information of at least one parking space is determined by the following criteria within a preset time period: the identification elements of the target parking space where a vehicle is parked and the receiving timestamp of the target parking space information. The receiving timestamp is used to determine the parking time interval.

[0156] In one possible implementation, the aforementioned vacant parking space identification unit may include:

[0157] The parking space clustering subunit is used to cluster the target parking space set into multiple parking space clusters according to the location information of the target parking spaces.

[0158] The target parking space cluster determination subunit is used to determine the target parking space cluster from multiple parking space clusters whose position distance from the second vehicle is less than a preset distance threshold.

[0159] The vacant parking space determination subunit is used to determine vacant parking spaces from the target parking space cluster based on the historical parking information of the target parking spaces contained in the target parking space cluster.

[0160] In one possible implementation, the process by which the aforementioned vacant parking space determination subunit determines vacant parking spaces from the target parking space cluster based on the historical parking information of the target parking spaces contained in the target parking space cluster may include:

[0161] Based on the historical parking information of the target parking spaces contained in the target parking space cluster, determine the number of parking spaces in the target parking space cluster at each historical time point within the preset time period. The historical time point refers to the time point that is the same as the current time point within a unit of time within the preset time period.

[0162] Based on the number of cars parked in the target parking space cluster at each historical time point within a preset time period, estimate the first number of cars parked in the target parking space cluster at the current time point.

[0163] Determine the total number of parking spaces contained in the target parking space cluster;

[0164] The number of available parking spaces is calculated based on the total number and the number of the first parking spaces in the target parking space cluster at the current time.

[0165] In one possible implementation, the process by which the aforementioned vacant parking space determination subunit estimates the first number of vehicles parked in the target parking space cluster at the current time point based on the number of vehicles parked at each historical time point within a preset time period may include:

[0166] Determine the number of units of time included in the preset time period as the base number;

[0167] Generate basic weights based on the base number and the preset increment coefficient;

[0168] Based on the basic weight, determine the target weight of the number of parking spaces in the target parking space cluster at each historical time point within the preset time period.

[0169] The number of cars parked in the target parking space cluster at each historical time point within a preset time period is weighted and averaged according to the determined target weights to obtain the first number of cars parked in the target parking space cluster at the current time point.

[0170] In one possible implementation, the process by which the aforementioned vacant parking space determination subunit determines vacant parking spaces from the target parking space cluster based on the historical parking information of the target parking spaces contained in the target parking space cluster may include:

[0171] Based on the historical parking information of the target parking spaces contained in the target parking space cluster, determine the number of parking spaces in the target parking space cluster at each historical time point within the preset time period. The historical time point refers to the time point that is the same as the current time point within a unit of time within the preset time period.

[0172] Based on the number of cars parked in the target parking space cluster at each historical time point within a preset time period, estimate the first number of cars parked in the target parking space cluster at the current time point.

[0173] Based on the historical parking information of the target parking spaces contained in the target parking space cluster, determine the most recent parking time of the target parking spaces contained in the target parking space cluster;

[0174] The number of parking spaces is weighted based on the most recent parking time of the target parking spaces contained in the target parking space cluster.

[0175] The second number of parking spaces in the target parking space cluster at the current time point is determined based on the weight value of the number of parking spaces and the first number of parking spaces in the target parking space cluster at the current time point.

[0176] Determine the total number of parking spaces contained in the target parking space cluster;

[0177] The number of available parking spaces is calculated based on the total number and the number of the second parking spaces in the target parking cluster at the current time.

[0178] This application also provides a parking space recognition device for a first vehicle. The parking space recognition device for a first vehicle provided in this application is described below. The parking space recognition device for a first vehicle described below can be referred to in correspondence with the parking space recognition method for a first vehicle described above.

[0179] Please see Figure 7 This illustration shows a schematic diagram of the structure of a parking space recognition device applied to a first vehicle, as provided in an embodiment of this application. Figure 7 As shown, the parking space recognition device applied to the first vehicle may include: an information acquisition unit 701, an information determination unit 702, and an information sending unit 703.

[0180] The information acquisition unit 701 is used to acquire external environmental information collected during the driving process of the first vehicle;

[0181] Information determination unit 702 is used to determine parking space related information contained in the area surrounding the first vehicle's driving based on external environment information, wherein the parking space related information includes parking confidence of at least one parking space.

[0182] The information sending unit 703 is used to send parking space-related information contained in the area surrounding the first vehicle to the cloud platform, so that the cloud platform can determine the target parking space from the at least one parking space based on the parking confidence of at least one parking space and the historical parking information of at least one parking space stored in advance. When receiving a parking space query request from the second vehicle, the cloud platform can determine the available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set. The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle. The target parking spaces are parking spaces available for vehicles to park in the area surrounding the first vehicle.

[0183] In one possible implementation, the process of determining the parking confidence level of at least one parking space in the aforementioned information determination unit may include:

[0184] The vehicle exterior environment information includes images of the vehicle exterior environment to determine the parking discrimination conditions that each parking space meets, wherein the parking discrimination conditions include multiple sub-conditions;

[0185] Based on the radar scan information included in the external environment information, determine the occupied space information and road slope information of at least one parking space;

[0186] For each parking space in at least one parking space, a first confidence level for the parking space is obtained based on the sub-conditions satisfied by the parking space. A first reliability level for the parking space based on the road slope information is determined based on the road slope information of the parking space. A second reliability level for the parking space based on the space occupied information is determined based on the space size information of the parking space. A second confidence level for the parking space is determined based on the first reliability level and the second reliability level. The first confidence level and the second confidence level of the parking space are weighted and summed to obtain the parking confidence level of the parking space. The weights used in the weighted summation are preset values.

[0187] In one possible implementation, the process by which the information determining unit obtains the first confidence level of the parking space based on the sub-conditions satisfied by the parking space may include:

[0188] The initial value of the parking space under the sub-conditions is determined as the preset value. Among the multiple sub-conditions, there is a first sub-condition that the parking space has a no-parking sign. The initial value of the parking space under the first sub-condition is the first preset value. The preset value of the same parking space is different under different sub-conditions.

[0189] If the initial value of the parking space under the first sub-condition is not the first preset value, then the maximum value of the initial value of the parking space under the satisfied sub-condition is determined as the first confidence level of the parking space.

[0190] This application also provides an electronic device. Optionally, Figure 8 A hardware block diagram of the electronic device is shown, with reference to... Figure 8 The hardware structure of the electronic device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0191] In this embodiment of the application, the number of processor 1, communication interface 2, memory 3, and communication bus 4 is at least one, and processor 1, communication interface 2, and memory 3 communicate with each other through communication bus 4;

[0192] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0193] Memory 3 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device;

[0194] The memory 403 stores a program, and the processor 1 can call the program stored in the memory 3. The program is used to implement the various steps of the parking space recognition method applied to the cloud platform as described above, or to implement the various steps of the parking space recognition method applied to the first vehicle as described above.

[0195] Optionally, the refined and extended functions of the program can be found in the description above.

[0196] This application embodiment also provides a readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the various steps of the parking space recognition method applied to the cloud platform as described above, or implements the various steps of the parking space recognition method applied to the first vehicle as described above.

[0197] Optionally, the refined and extended functions of the program can be found in the description above.

[0198] Finally, it should be noted that in this document, relational terms such as "second" and "etc." are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0199] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0200] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A parking space identification method, characterized in that, Applied to cloud platforms, including: Receive parking space related information from the first vehicle, wherein the parking space related information is determined based on the external environment information collected during the driving of the first vehicle, and the parking space related information includes the parking confidence of at least one parking space in the surrounding area of ​​the first vehicle. Based on the parking confidence level of the at least one parking space and the historical parking information of the at least one parking space stored in advance, a target parking space is determined from the at least one parking space, wherein the target parking space is a parking space available for vehicles in the surrounding area where the first vehicle is traveling. In response to the parking space query request of the second vehicle, based on the historical parking information of the target parking spaces contained in the target parking space set, determine the available parking spaces around the second vehicle from the target parking space set, wherein the target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle; The step of determining a target parking space from the at least one parking space based on the parking confidence level of the at least one parking space and the pre-stored historical parking information of the at least one parking space includes: Parking spaces with a parking confidence level not equal to 1 that are included in the at least one parking space are identified as parking spaces to be screened; For each parking space included in the parking spaces to be screened, based on the historical parking information of that parking space, determine the number of times that parking space has a parking time interval greater than a preset time threshold within a preset time period; Parking spaces that have been parked more than or equal to a preset threshold number of times among the parking spaces to be screened are identified as the screened parking spaces; The filtered parking spaces and the parking spaces containing at least one parking space with a parking confidence level of 1 are determined as the target parking spaces.

2. The parking space identification method according to claim 1, characterized in that, The parking space-related information also includes the discrimination element for the at least one parking space, and the process for determining the historical parking information of the at least one parking space includes: From the parking space related information received from multiple first vehicles in the past, determine the discrimination elements of each of the at least one parking space within the preset time period as target parking space related information where a vehicle is parked. The historical parking information of the at least one parking space is determined by the following criteria within the preset time period: the discrimination element of the at least one parking space is the target parking space information where a vehicle is parked, and the receiving timestamp of the target parking space information. The receiving timestamp is used to determine the parking time interval.

3. The parking space identification method according to claim 1, characterized in that, The step of determining available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces included in the target parking space set includes: The target parking space set is clustered into multiple parking space clusters according to the location information of the target parking spaces; From the plurality of parking space clusters, determine the target parking space cluster whose position distance from the second vehicle is less than a preset distance threshold; The available parking space is determined from the target parking space cluster based on the historical parking information of the target parking space cluster.

4. The parking space identification method according to claim 3, characterized in that, The step of determining the available parking space from the target parking space cluster based on the historical parking information of the target parking spaces included in the target parking space cluster includes: Based on the historical parking information of the target parking spaces contained in the target parking space cluster, determine the number of parking spaces in the target parking space cluster at each historical time point within a preset time period. The historical time point refers to the time point that is the same as the current time point within a unit of time contained in the preset time period. Based on the number of cars parked in the target parking space cluster at each historical time point within a preset time period, estimate the first number of cars parked in the target parking space cluster at the current time point. Determine the total number of parking spaces contained in the target parking space cluster; The number of available parking spaces is calculated based on the total number and the first number of parking spaces in the target parking space cluster at the current time.

5. The parking space identification method according to claim 4, characterized in that, The step of estimating the first number of cars parked in the target parking space cluster at the current time point based on the number of cars parked at each historical time point within a preset time period includes: The number of unit times contained in the preset time period is determined as the base number; Based on the aforementioned base number and a preset increment coefficient, a base weight is generated; Based on the aforementioned basic weights, the target weights for the number of parking spaces in the target parking space cluster at each historical time point within a preset time period are determined. The number of cars parked in the target parking space cluster at each historical time point within a preset time period is weighted and averaged according to the determined target weights to obtain the first number of cars parked in the target parking space cluster at the current time point.

6. The parking space identification method according to claim 3, characterized in that, The step of determining the available parking space from the target parking space cluster based on the historical parking information of the target parking spaces included in the target parking space cluster includes: Based on the historical parking information of the target parking spaces contained in the target parking space cluster, determine the number of parking spaces in the target parking space cluster at each historical time point within a preset time period. The historical time point refers to the time point that is the same as the current time point within a unit of time contained in the preset time period. Based on the number of cars parked in the target parking space cluster at each historical time point within a preset time period, estimate the first number of cars parked in the target parking space cluster at the current time point. Based on the historical parking information of the target parking spaces contained in the target parking space cluster, determine the most recent parking time of the target parking spaces contained in the target parking space cluster; A parking number weight value is generated based on the most recent parking time of the target parking spaces contained in the target parking space cluster; Based on the weight value of the number of parking spaces and the first number of parking spaces in the target parking space cluster at the current time point, determine the second number of parking spaces in the target parking space cluster at the current time point; Determine the total number of parking spaces contained in the target parking space cluster; The number of available parking spaces is calculated based on the total number and the second number of parking spaces in the target parking space cluster at the current time.

7. A parking space identification method, characterized in that, Applied to the first vehicle, including: Obtain external environmental information collected during the driving process of the first vehicle; Based on the external environment information, determine the parking space related information contained in the area surrounding the first vehicle's driving, wherein the parking space related information includes the parking confidence level of at least one parking space. The cloud platform sends parking space information related to the area surrounding the first vehicle to the cloud platform. The cloud platform determines a target parking space from the at least one parking space based on the parking confidence of the at least one parking space and the historical parking information of the at least one parking space stored in advance. When a parking space query request is received from the second vehicle, the cloud platform determines the available parking spaces around the second vehicle from the target parking space set based on the historical parking information of the target parking spaces contained in the target parking space set. The target parking space set refers to the set of target parking spaces obtained based on at least one first vehicle. The target parking spaces are parking spaces available for vehicles in the area surrounding the first vehicle. The step of determining a target parking space from the at least one parking space based on the parking confidence level of the at least one parking space and the pre-stored historical parking information of the at least one parking space includes: Parking spaces with a parking confidence level not equal to 1 that are included in the at least one parking space are identified as parking spaces to be screened; For each parking space included in the parking spaces to be screened, based on the historical parking information of that parking space, determine the number of times that parking space has a parking time interval greater than a preset time threshold within a preset time period; Parking spaces that have been parked more than or equal to a preset threshold number of times among the parking spaces to be screened are identified as the screened parking spaces; The filtered parking spaces and the parking spaces containing at least one parking space with a parking confidence level of 1 are determined as the target parking spaces.

8. The parking space identification method according to claim 7, characterized in that, The process of determining the parking confidence level of the at least one parking space includes: The vehicle exterior environment information includes images of the vehicle exterior environment to determine the parking discrimination conditions satisfied by each of the at least one parking space, wherein the parking discrimination conditions include multiple sub-conditions; Based on the radar scan information included in the external environment information, the occupied space information and road slope information of each of the at least one parking space are determined; For each of the at least one parking space, a first confidence level is obtained based on the sub-conditions satisfied by the parking space. A first reliability level of the parking space on the road slope information is determined based on the road slope information of the parking space. A second reliability level of the parking space on the space size information is determined based on the occupied space information of the parking space. A second confidence level of the parking space is determined based on the first reliability level and the second reliability level. The first confidence level and the second confidence level of the parking space are weighted and summed to obtain the parking confidence level of the parking space. The weights used in the weighted summation are preset values.

9. The parking space identification method according to claim 8, characterized in that, The step of obtaining the first confidence level of the parking space based on the sub-conditions satisfied by the parking space includes: The initial value of the parking space under the sub-conditions is determined as the preset value. The multiple sub-conditions include the first sub-condition that the parking space has a no-parking sign. The initial value of the parking space under the first sub-condition is the first preset value. The preset value of the same parking space is different under different sub-conditions. If the initial value of the parking space under the first sub-condition is not the first preset value, then the maximum value among the initial values ​​of the parking space under the satisfied sub-conditions is determined as the first confidence level of the parking space.

10. An electronic device, characterized in that, Including memory and processor; The memory is used to store programs; The processor is configured to execute the program to implement the various steps of the parking space identification method as described in any one of claims 1 to 6, or claims 7 to 9.

11. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the various steps of the parking space identification method as described in any one of claims 1 to 6, or claims 7 to 9.

Images