Parking mode recommendation method and device, electronic equipment and computer readable medium

Abstract

The invention discloses a parking mode recommendation method and device, electronic equipment and a computer readable medium, and belongs to the technical field of intelligent driving, and the method comprises the steps: obtaining a plurality of impact factor data associated with parking mode recommendation, the influence factor data comprises width information of a target parking space, passenger information, parking scratch risk, unloading intention and brightness information of the target parking space, and the target parking space is a to-be-parked parking space; and based on the multiple pieces of influence factor data and the multiple alternative parking modes, through an analytic hierarchy process, determining a target parking mode from the multiple alternative parking modes. According to the method, the target parking mode is determined through the analytic hierarchy process based on the multiple influence factor data and the multiple alternative parking modes, the parking mode closer to the parking intention of a driver can be obtained by integrating the multiple influence factor data, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and more specifically, to a parking method recommendation method, device, electronic device and computer-readable medium. Background Art

[0002] Commonly used parking method recommendation methods include remote control parking recommendation for narrow parking spaces, automatic parking recommendation based on the driver's parking intention, etc. However, the recommendation basis and recommended parking methods of these recommendation methods are relatively simple, and the recommended automatic parking methods are often far from the driver's parking intention and cannot meet the driver's parking needs. Summary of the invention

[0003] The present application proposes a parking method recommendation method, device, electronic device and computer-readable medium to improve the above-mentioned defects.

[0004] In a first aspect, the present application provides a parking method recommendation method, which is applied to a vehicle, and the method includes: obtaining multiple influencing factor data associated with the parking method recommendation, the influencing factor data including width information of a target parking space, occupant information, parking scratch risk, unloading intention, and brightness information of the target parking space, and the target parking space is a parking space to be parked; based on the multiple influencing factor data and multiple alternative parking methods, determining the target parking method from the multiple alternative parking methods through a hierarchical analysis algorithm.

[0005] Optionally, for a possible implementation, the obtaining of the unloading intention includes: obtaining loading information and unloading information of the vehicle within a historical time period; and determining the unloading intention based on the loading information and the unloading information.

[0006] Optionally, for a possible implementation, obtaining the parking scratch risk includes: obtaining obstacle information around a target parking space; determining a parking path according to the current position information of the vehicle and the position information of the target parking space; and determining the parking scratch risk based on the obstacle information and the parking path.

[0007] Optionally, for a possible implementation, the determining a target parking method from the multiple alternative parking methods based on the multiple influencing factor data and the multiple alternative parking methods through a hierarchical analysis algorithm includes: determining a first weight for each of the influencing factor data, the first weight indicating the relative importance of different influencing factors for the parking method recommendation; determining a second weight for each of the alternative parking methods relative to each of the influencing factor data, the second weight indicating the relative superiority or inferiority of different parking methods under each of the influencing factor data; determining a target weight for each of the alternative parking methods based on the first weight and the second weight; and taking the alternative parking method corresponding to the target weight having the largest value as the target parking method.

[0008] Optionally, for a possible implementation, the determining the first weight of each of the influencing factor data includes: constructing a first judgment matrix based on a preset scale table and a plurality of the influencing factor data Where n represents the total number of the impact factor data, a ij Representing the importance index of the i-th influencing factor data compared with the j-th influencing factor data; determining the first weight of each of the influencing factor data based on the first judgment matrix.

[0009] Optionally, for a possible implementation manner, the plurality of alternative parking methods include remote control parking, vehicle-side automatic parking, and user-initiated parking, and the determining of the second weight of each alternative parking method relative to each of the influencing factor data includes: constructing a second judgment matrix for each of the influencing factor data based on a preset scale table, the plurality of influencing factor data, and the plurality of alternative parking methods Wherein, k represents the sequence number of the impact factor data, and the value range of k is [1, n], bk 12 Indicates the importance index of the first alternative parking method and the second alternative parking method compared with the kth influencing factor data; based on the second judgment matrix of each influencing factor data, determines the second weight of each alternative parking method relative to each of the influencing factor data.

[0010] Optionally, for a possible implementation manner, determining the target weight of each alternative parking method according to the first weight and the second weight includes: determining first evaluation data corresponding to the first judgment matrix, the first evaluation data indicating the rationality of the first judgment matrix; determining second evaluation data corresponding to each of the second judgment matrices, the second evaluation data indicating the rationality of the second judgment matrix; if the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices are both within a preset range, determining third evaluation data according to the first weight of each of the influencing factor data, the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices, the third evaluation data indicating the comprehensive rationality of the first judgment matrix and the second judgment matrix; if the third evaluation data is within the preset range, determining the target weight of each alternative parking method according to the first weight and the second weight.

[0011] In the second aspect, the present application also provides a parking method recommendation device, which is applied to a vehicle, and the device includes: a collection unit, which is used to obtain multiple influencing factor data associated with the parking method recommendation, and the influencing factor data include width information of the target parking space, occupant information, parking scratch risk, unloading intention and brightness information of the target parking space, and the target parking space is a parking space to be parked; a calculation unit, which is used to determine the target parking method from the multiple alternative parking methods through a hierarchical analysis algorithm based on the multiple influencing factor data and multiple alternative parking methods.

[0012] In a third aspect, the present application also provides an electronic device comprising: one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory, the one or more applications are configured to be executed by the one or more processors, and the one or more applications are configured to execute the above method.

[0013] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program code executable by a processor, and when the program code is executed by the processor, the processor executes the above method.

[0014] In a fifth aspect, the present application also provides a computer program product, including a computer program / instruction, which implements the above method when executed by a processor.

[0015] The solution provided by the present application first obtains multiple influencing factor data associated with parking method recommendations, the influencing factor data including width information of a target parking space, occupant information, parking scratch risk, unloading intention, and brightness information of the target parking space, and the target parking space is a parking space to be parked; based on the multiple influencing factor data and multiple alternative parking methods, then, a target parking method is determined from the multiple alternative parking methods through a hierarchical analysis algorithm.

[0016] The parking method obtained by considering one factor is far from the driver's parking intention. The present application determines the target parking method through a hierarchical analysis algorithm based on multiple influencing factor data and multiple alternative parking methods. The integration of multiple influencing factor data can obtain a parking method that is closer to the driver's parking intention, thereby improving the user experience. On the one hand, the influencing factor data of the present application includes the unloading intention, which fully considers the user's need to unload after parking, and can provide a more convenient parking method for unloading. On the other hand, the influencing factor data of the present application includes passenger information, which can fully consider the passenger's need for getting off space after parking, and can provide a more convenient parking method for passengers getting off. Finally, the influencing factor data of the present application includes brightness information, which fully considers the accuracy of the width information of the target parking space and the surrounding obstacle information, and can obtain a target parking method with higher accuracy, thereby improving the user experience.

[0017] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A flowchart of a method for recommending a parking method provided in an embodiment of the present application is shown;

[0020] Figure 2 A flowchart of a method for recommending a parking method provided by another embodiment of the present application is shown;

[0021] Figure 3 A schematic diagram of the structure of the hierarchical structure model provided by the present application is shown;

[0022] Figure 4A structural block diagram of a parking method recommendation device provided in an embodiment of the present application is shown;

[0023] Figure 5 A structural block diagram of an electronic device provided in an embodiment of the present application is shown;

[0024] Figure 6 A structural block diagram of a computer-readable storage medium provided in an embodiment of the present application is shown;

[0025] Figure 7 A structural block diagram of a computer program product provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] In order to make those skilled in the art better understand the present application scheme, the technical scheme in the present application embodiment will be clearly and completely described below in conjunction with the drawings in the present application embodiment. Obviously, the described embodiment is only a part of the present application embodiment, rather than all the embodiments. The components of the present application embodiment usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application for protection, but merely represents the selected embodiment of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] Commonly used parking method recommendation methods include remote control parking recommendation for narrow parking spaces, automatic parking recommendation based on the driver's parking intention, etc. However, the recommendation basis and recommended parking methods of these recommendation methods are relatively simple, and the recommended automatic parking methods are often far from the driver's parking intention and cannot meet the driver's parking needs.

[0029] Therefore, in an embodiment of the present application, a parking method recommendation method, device, electronic device and computer-readable medium are provided to solve or partially solve the above-mentioned problems.

[0030] See also Figure 1 , which shows a method flow chart of a parking method recommendation method provided in an embodiment of the present application, which is applied to a vehicle, and the method specifically includes steps S101 to S102.

[0031] Step S101: Acquire multiple influencing factor data associated with parking method recommendation, the influencing factor data including width information of a target parking space, occupant information, parking scratch risk, unloading intention, and brightness information of the target parking space, the target parking space being a parking space to be parked.

[0032] It should be noted that in actual usage scenarios, after determining the target parking space to be parked, the vehicle is first driven to the vicinity of the target parking space, and then the target parking method is determined based on the parking method recommendation method of this application, and finally the vehicle is parked in the target parking space based on the target parking method.

[0033] To this end, a plurality of influencing factor data associated with the parking style recommendation may be acquired, and the target parking style may be determined based on the plurality of influencing factor data.

[0034] It can be known that the target parking space is a parking space to be parked, and the information of the target parking space can be obtained through a vehicle-mounted camera, or based on a distance sensor such as a vehicle-mounted ultrasonic sensor.

[0035] For example, point cloud data and edge features can be determined based on data obtained by the vehicle-mounted camera and the distance sensor. Point cloud data is point data in three-dimensional space collected by sensors such as laser radar and cameras. Each point data contains its coordinates (X, Y, Z) in three-dimensional space. The boundary and position of the target parking space can be obtained based on the point cloud data. Edge features refer to significant change points of the boundary or contour of an object in an image or point cloud data. The boundary and position of the target parking space can be determined based on the edge features.

[0036] It should be noted that in addition to the width of the target parking space, which will affect the choice of parking method, occupant information, parking scratch risk, unloading intention and brightness information of the target parking space will also affect the choice of parking method.

[0037] Specifically, the occupant information may include data such as the gender, age group, and body shape of each occupant. If there are larger occupants, sufficient space must be reserved for the occupants to get off the vehicle. If the occupants include pregnant women or the elderly, sufficient space must also be reserved for the occupants to get off the vehicle. In this case, the vehicle is more inclined to have the occupants get off the vehicle before parking, and parking is performed through remote control. It can be seen that different occupant information may correspond to different parking methods.

[0038] In an optional embodiment, image information of people in the car can be collected by a vehicle-mounted camera device, and the gender and age of each occupant can be determined by performing face recognition on the image information. The body shape of each occupant can be obtained by performing semantic segmentation on the acquired image information.

[0039] Specifically, the parking scratch risk refers to the probability of the vehicle scratching during the parking process. During the parking process, users do not want the vehicle to scratch or rub against surrounding objects. For target parking spaces with a higher scratch risk, users generally choose to change parking spaces. If there is no condition to change parking spaces, they can choose remote control parking or driver-initiated parking to park.

[0040] The parking scratch risk can be determined based on the parking path and obstacle information. Specifically, the obstacle information around the target parking space is obtained; the obstacle information includes wall-mounted fire extinguisher boxes, signboards, and pole-shaped obstacles around the target parking space. The parking path is determined according to the current position information of the vehicle and the position information of the target parking space; the parking scratch risk is determined based on the obstacle information and the parking path.

[0041] Specifically, the unloading intention indicates the user's intention to unload the goods. The unloading intention includes the need to unload the goods and the need not to unload the goods. If the user needs to unload the goods from the vehicle, sufficient space needs to be reserved around the vehicle. Therefore, the unloading intention will affect the choice of parking method.

[0042] In an optional embodiment, the step of obtaining the unloading intention specifically includes: obtaining the loading information and unloading information of the vehicle within a historical time period; and determining the unloading intention based on the loading information and the unloading information. The loading information includes the time when the goods are loaded onto the vehicle and the shape information of the goods, and the unloading information includes the time when the goods are unloaded from the vehicle and the shape information of the unloaded goods. Specifically, images or videos can be obtained based on a vehicle-mounted camera, and loading images and unloading images can be filtered out from the obtained images or videos. The loading information can be determined based on the loading images, and the unloading information can be determined based on the unloading images.

[0043] The historical time period represents a period of time before the current moment. The historical time period is adjacent to the current moment. Based on the loading information and the unloading information, it can be determined whether all the goods on the vehicle are unloaded. If all the goods on the vehicle are unloaded, the unloading intention is that no unloading is required. If not all the goods on the vehicle are unloaded, the unloading intention is that unloading is required.

[0044] In an exemplary embodiment, video information is obtained based on a vehicle-mounted camera, and loading pictures, loading videos, unloading pictures and unloading videos are screened out based on the obtained video information. The categories and information of the goods loaded on the vehicle are determined based on the loading images and loading videos, and the categories and information of the unloaded goods are determined based on the unloading images and unloading videos. The categories and information of the goods loaded on the vehicle and the categories and information of the unloaded goods can be combined to determine the categories and information of the goods remaining in the vehicle. If there is no remaining goods in the vehicle, it means that the user does not need to unload the goods, and the unloading intention is that no unloading is required. If there is remaining goods in the vehicle, it means that the user may still need to unload the goods on the vehicle, and the unloading intention is that unloading is required. If the size of the remaining goods in the vehicle is greater than a preset threshold, sufficient unloading space needs to be reserved. If the size of the remaining goods in the vehicle is less than the preset threshold, it can be approximated that no unloading is required.

[0045] Specifically, the brightness of the target parking space affects the accuracy of the image information of the target parking space and the obstacle information around the target parking space. If the brightness of the target parking space is low or high, the accuracy of the acquired width information of the target parking space and the surrounding obstacle information is low. If the brightness of the target parking space is within a preset range, the accuracy of the acquired width information of the target parking space and the surrounding obstacle information is high. Therefore, the brightness information of the target parking space affects the selection of the parking method.

[0046] Exemplarily, image information of the target parking space may be acquired through a vehicle-mounted camera, and brightness information of the target parking space may be determined based on the acquired image information.

[0047] Step S102: Based on the plurality of influencing factor data and the plurality of alternative parking methods, a target parking method is determined from the plurality of alternative parking methods by using a hierarchy analysis algorithm.

[0048] The plurality of influencing factor data and the plurality of alternative parking methods are used as inputs of a hierarchy analysis algorithm to obtain a target parking method.

[0049] The parking method obtained by considering one factor is far from the driver's parking intention. The present application determines the target parking method through a hierarchical analysis algorithm based on multiple influencing factor data and multiple alternative parking methods. By integrating multiple influencing factor data, a parking method that is closer to the driver's parking intention can be obtained, thereby improving the user experience.

[0050] There is a situation in which the parking method is determined by only one factor. For example, if the width of the target parking space is detected to be a wide parking space, the remote control parking method and the user-initiated parking method can be selected. However, the method of the present application detects the width information of the target parking space, the occupant information, the risk of parking scratches, the unloading intention, and the brightness information of the target parking space, and can determine a safer target parking method based on multiple factors.

[0051] On the one hand, the influencing factor data of the present application includes unloading intention, which fully considers the user's need to unload after parking, and can provide a more convenient parking method for unloading. On the other hand, the influencing factor data of the present application includes passenger information, which fully considers the passenger's need for getting off space after parking, and can provide a more convenient parking method for passengers getting off. Finally, the influencing factor data of the present application includes brightness information, which fully considers the accuracy of the width information of the target parking space and the surrounding obstacle information, and can obtain a more accurate target parking method to enhance the user experience.

[0052] This application integrates multiple influencing factor data associated with parking method recommendations, and uses a hierarchical analysis algorithm to calculate the weight ranking of criteria that affect parking method selection, thereby improving the accuracy of automatic parking method recommendations, improving the matching degree between recommendation results and driving intentions, and improving the safety, convenience, and experience of users using parking assistance driving systems.

[0053] See also Figure 2 , which shows a method flow chart of a parking method recommendation method provided in an embodiment of the present application, which is applied to a vehicle, and the method specifically includes steps S201 to S205.

[0054] Step S201: Acquire multiple influencing factor data associated with parking method recommendations, the influencing factor data including width information of a target parking space, occupant information, parking scratch risk, unloading intention, and brightness information of the target parking space, the target parking space being a parking space to be parked.

[0055] Among them, step S201 has been introduced in detail in the above embodiment and will not be repeated here.

[0056] Step S202: determining a first weight of each of the influencing factor data, wherein the first weight represents the relative importance of different influencing factors for parking method recommendation.

[0057] Please note that Figure 3, the hierarchical structure model corresponding to the hierarchical analysis algorithm includes a target layer, a criterion layer and a scheme layer. The target layer represents the decision-making target, specifically referring to the selection of the target parking method O. The criterion layer represents the criteria or indicators for selecting the parking method. The criterion layer of this application includes 5 indicators, namely, the width information C1 of the target parking space, the occupant information C2, the parking scratch risk C3, the unloading intention C4 and the brightness information C5 of the target parking space. The scheme layer represents the optional schemes. The scheme layer of this application includes 3 parking methods, namely, remote control parking P1, vehicle-side automatic parking P2 and user-initiated parking P3. Among them, the specific method of remote control parking is: the driver and the occupants get off the vehicle before parking, that is, there are no people in the vehicle, and the vehicle realizes automatic parking, or the user realizes automatic parking by remote control. The specific method of vehicle-side automatic parking is: the vehicle automatically parks and the driver sits in the vehicle to supervise the parking. When an emergency occurs, the driver can operate the parking in time. The specific method of user-initiated parking is: the user drives the vehicle to park the vehicle in the target parking space.

[0058] The first weight represents the relative importance of different influencing factors for the parking method recommendation, and the sum of the first weights of each influencing factor data is 1. The specific step of determining the first weight of each influencing factor data is to construct a first judgment matrix based on a preset scale table and a plurality of the influencing factor data. Where n represents the total number of the impact factor data, a ij Representing the importance index of the i-th influencing factor data compared with the j-th influencing factor data; determining the first weight of each of the influencing factor data based on the first judgment matrix.

[0059] The scale table is shown in Table 1.

[0060] Table 1

[0061]

[0062] The scale table includes importance indexes and corresponding meanings. The importance index includes integers from 1 to 9 and their corresponding reciprocals. When the importance index is 1, its corresponding meaning is: compared with the two factors, they have the same importance; when the importance index is 3, its corresponding meaning is: compared with the two factors, one factor is slightly more important than the other; when the importance index is 5, its corresponding meaning is: compared with the two factors, one factor is obviously more important than the other; when the importance index is 7, its corresponding meaning is: compared with the two factors, one factor is strongly more important than the other; when the importance index is 9, its corresponding meaning is: compared with the two factors, one factor is extremely important than the other; the importance index is 1. When the importance index is 2, the corresponding meaning is: compared with the two factors, one factor is between the same importance and slightly important than the other factor; when the importance index is 4, the corresponding meaning is: compared with the two factors, one factor is between slightly important and obviously important than the other factor; when the importance index is 6, the corresponding meaning is: compared with the two factors, one factor is between obviously important and strongly important than the other factor; when the importance index is 8, the corresponding meaning is: compared with the two factors, one factor is between strongly important and extremely important than the other factor; among them, if the importance index corresponding to factor E compared with factor F is H1, then the importance index corresponding to factor F compared with factor E is H2, H1*H2=1. For example, the importance index corresponding to E1 compared with F1 is 3, then the importance index corresponding to F1 compared with E1 is 1 / 3.

[0063] The impact factor data are compared pairwise to construct the first judgment matrix.

[0064] Exemplarily, the five influencing factor data are arranged in order as C1, C2, C3, C4, and C5. If the detected multiple influencing factor data are specifically: the width information C1 of the target parking space is a wide parking space, the occupant information C2 includes the elderly, the parking scratch risk C3 is low, the unloading intention C4 is that unloading is not required, and the brightness information C5 of the target parking space is within a preset range, the importance index of the first influencing factor data compared with the second influencing factor data is compared. The two factors of the width information C1 of the target parking space being a wide parking space and the occupant information C2 including the elderly are compared. If the first factor is significantly more important than the second factor, the importance index of the first influencing factor data compared with the second influencing factor data is 5, then a in the first judgment matrix 12 is 5. Further, a in the first judgment matrix 21 The value of each element in the first judgment matrix can be obtained in the same way, and then the first judgment matrix can be determined.

[0065] It should be noted that the present application compares the importance of two impact factor data based on expert experience. The expert experience is data acquired in advance. The importance of two impact factor data can be compared based on the expert experience data.

[0066] The expert experience includes any two influencing factor data and the corresponding importance comparison results, that is, the expert experience includes a mapping relationship between any two influencing factor data and the corresponding importance comparison results.

[0067] When obtaining expert experience in advance, the expert determines the corresponding importance comparison result based on the specific data of the two influencing factors. For example, the two influencing factors for comparison are the width information C1 of the target parking space as a wide parking space and the occupant information C2 including the elderly. The expert determines that the comparison result is "relatively important" based on the two influencing factors for comparison. Then, a mapping relationship is established between the comparison result of the width information C1 of the target parking space as a wide parking space and the occupant information C2 including the elderly and "relatively important", and the result is saved in the expert database. If it is necessary to compare the importance comparison result of the width information C1 of the target parking space as a wide parking space and the occupant information C2 including the elderly at a later time, the comparison result can be obtained as "relatively important" based on the mapping relationship.

[0068] According to the above method, the importance comparison result of any two influencing factor data in the expert database can be determined in advance and stored in the expert database. When a parking method is to be recommended, the importance comparison result of any two influencing factor data is determined based on the influencing factor data collected in real time and the expert database, and then the importance index of any two influencing factor data is determined based on the importance comparison result of any two influencing factor data, and then the first judgment matrix is ​​determined based on the importance index of any two influencing factor data.

[0069] It should be noted that if the influencing factor data collected in real time are different, the importance comparison results of the two influencing factor data are different, and thus the first judgment matrix obtained is different, and the final first weight may also be different.

[0070] A first weight of each influencing factor data is determined based on the first judgment matrix.

[0071] Specifically, there are 5 influencing factor data, based on the first judgment matrix The specific method for obtaining the first weight of each influencing factor data is to calculate the 1 / 5 power of the product of each row element in the first judgment matrix to obtain a 5-dimensional vector:

[0072] Criterion C1:

[0073] Criterion C2:

[0074] Criterion C3:

[0075] Criterion C4:

[0076] Criterion C5:

[0077] According to the mathematical conversion formula The first weight of each impact factor data can be obtained by standardizing the 5-dimensional vector in, Indicates the first weight of the impact factor data C1.

[0078] After obtaining multiple influencing factor data, a first judgment matrix is ​​constructed based on the scaling table and the multiple influencing factor data. It should be noted that for different target parking spaces, if the collected influencing factor data are different, the constructed first judgment matrix is ​​also different, and thus the first weight of each influencing factor data obtained is also different.

[0079] Exemplarily, if the detected multiple influencing factor data are: the width information C1 of the target parking space is a wide parking space, the occupant information C2 includes the elderly, the parking scratch risk C3 is low, the unloading intention C4 is no need to unload, and the brightness information C5 of the target parking space is within a preset range, then the first judgment matrix A1 of each influencing factor data is determined based on the scale table and the multiple influencing factor data, and the first weight of each influencing factor data is determined based on the first judgment matrix A1. If the detected multiple influencing factor data are specifically: the width information C1 of the target parking space is a narrow parking space, the occupant information C2 includes pregnant women, the parking scratch risk C3 is low, the unloading intention C4 is no need to unload, and the brightness information C5 of the target parking space is within a preset range, then the first judgment matrix A2 of each influencing factor data is determined based on the scale table and the multiple influencing factor data, and the first weight of each influencing factor data is determined based on the first judgment matrix A2.

[0080] Step S203: determining a second weight of each parking alternative method relative to each influencing factor data, wherein the second weight represents a relative superiority or inferiority of different parking methods under each influencing factor data.

[0081] It should be noted that, for different influencing factor data, different parking methods have different relative advantages and disadvantages under each influencing factor data, so it is necessary to determine the second weight of each alternative parking method relative to each of the influencing factor data.

[0082] Specifically, a second judgment matrix for each of the influencing factor data is constructed based on a preset scale table, a plurality of the influencing factor data, and a plurality of the alternative parking modes. Wherein, k represents the sequence number of the impact factor data, and the value range of k is [1, n], bk 12 Indicates the importance index of the first alternative parking method and the second alternative parking method compared with the kth influencing factor data; based on the second judgment matrix of each influencing factor data, determines the second weight of each alternative parking method relative to each of the influencing factor data.

[0083] A second judgment matrix for each of the influencing factor data is constructed based on a preset scale table, a plurality of the influencing factor data, and a plurality of the alternative parking methods. For details of the scale table, please refer to the aforementioned embodiment and will not be described in detail here. It should be noted that the present application compares the importance of two alternative parking methods relative to the influencing factor data based on expert experience. The expert experience is data obtained in advance. The importance index of each of the two alternative parking methods relative to each of the influencing factor data can be determined based on the expert experience data.

[0084] The expert experience includes the comparison results of the importance of any two parking methods relative to the influencing factors.

[0085] When obtaining expert experience in advance, the expert determines the corresponding importance comparison results of the two parking methods based on the specific data of the influencing factors. For example, the importance comparison result of the two parking methods being compared is remote-controlled parking P1 and vehicle-side automatic parking P2 relative to the width information C1 of the target parking space is a wide parking space, which is determined by the expert to be "strongly important". The importance comparison result of the two parking methods being compared is remote-controlled parking P1 and vehicle-side automatic parking P2 relative to the width information C1 of the target parking space is a narrow parking space, which is determined by the expert to be "relatively important". In this case, the two parking methods being remote-controlled parking P1 and vehicle-side automatic parking P2 relative to the width information C1 of the target parking space is a wide parking space and can be stored in the expert database in correspondence with "strongly important". Similarly, the two parking methods being remote-controlled parking P1 and vehicle-side automatic parking P2 relative to the width information C1 of the target parking space is a narrow parking space and can be stored in the expert database in correspondence with "relatively important". If it is necessary to compare the importance of two parking modes, namely remote parking P1 and vehicle-side automatic parking P2, relative to the width information C1 of the target parking space, which is a wide parking space, the comparison result can be obtained as "strongly important" based on the mapping relationship.

[0086] According to the above method, the importance comparison results of any two parking methods in the expert database relative to the influencing factor data can be determined in advance and stored in the expert database. When a parking method recommendation is to be made, the second judgment matrix is ​​determined based on the influencing factor data collected in real time and multiple alternative parking methods.

[0087] It should be noted that if the data of the influencing factors collected in real time are different, the comparison results of the importance of the two parking methods relative to the influencing factor data are different, the importance indexes of the two parking methods relative to the influencing factor data are different, and the second judgment matrix obtained is different, and the second weight obtained in the end may also be different.

[0088] Exemplarily, the three alternative parking methods are arranged in order as remote parking P1, vehicle-side automatic parking P2, and user-initiated parking P3. First, the first influencing factor data C1 is determined. If it is detected that the first influencing factor data is specifically the width information of the target parking space C1, which is a wide parking space, the alternative parking methods are compared in pairs to construct a second judgment matrix of the first influencing factor data. Then, the two factors of remote parking P1 and vehicle-side automatic parking P2 are compared relative to C1, which is a wide parking space. If the first factor is slightly more important than the second factor, the importance index of the first alternative parking method compared to the second alternative parking method is 3, and b1 in the second judgment matrix of C1 is 12 is 3. Furthermore, b1 in the second judgment matrix of C1 21 The value of each element in the second judgment matrix of C1 can be obtained in the same way, and then the second judgment matrix B1 of C1 can be determined. Similarly, the second judgment matrix of each alternative parking method with respect to each of the influencing factor data can be obtained.

[0089] The principle of determining the second weight of each influencing factor data based on the second judgment matrix of each influencing factor data is the same as the principle of determining the first weight of each influencing factor data based on the first judgment matrix, and will not be repeated here. The second weight of each alternative parking method relative to each of the influencing factor data can be obtained. Specifically, the second weight of each alternative parking method relative to the first influencing factor data is The second weight of each alternative parking method relative to the second influencing factor data is The second weight of each alternative parking method relative to the third influencing factor data is The second weight of each alternative parking method relative to the fourth influencing factor data is: The second weight of each alternative parking method relative to the fifth influencing factor data is:

[0090] Step S204: determining a target weight of each alternative parking method according to the first weight and the second weight.

[0091] According to the first weight of each influencing factor data and the second weight of each alternative parking method relative to each influencing factor data, the target weight of each alternative parking method is determined. Specifically, the target weight of remote parking P1 is: The target weight of vehicle-side automatic parking P2 is: The target weight of active parking P3 is: We can further obtain the target weight vector of the alternative parking method as w P ={w P1 , w P2 , w P3}.

[0092] Step S205: the alternative parking method corresponding to the target weight having the largest value is used as the target parking method.

[0093] The target weight vector of each alternative parking method is obtained as w P ={w P1 , w P2 , w P3}After that, the alternative parking method corresponding to the target weight with the largest value is used as the target parking method.

[0094] It should be noted that the correctness of the first judgment matrix and the second judgment matrix determined based on the data obtained from expert experience may be insufficient, so it is necessary to verify the consistency of the first judgment matrix and each second judgment matrix. If the first judgment matrix does not meet the consistency test, the first judgment matrix needs to be reconstructed. If the second judgment matrix does not meet the consistency test, the corresponding second judgment matrix needs to be reconstructed.

[0095] Specifically, first evaluation data corresponding to the first judgment matrix is ​​determined, and the first evaluation data indicates the rationality of the first judgment matrix; second evaluation data corresponding to each of the second judgment matrices is determined, and the second evaluation data indicates the rationality of the second judgment matrix; if the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices are both within a preset range, it indicates that the first judgment matrix and each of the second judgment matrices meet the requirements.

[0096] Specifically, the first evaluation data corresponding to the first judgment matrix is ​​the consistency index of the first judgment matrix A, and the second evaluation data corresponding to the second judgment matrix is ​​the consistency index of the first judgment matrix B.

[0097] For example, taking the consistency of the first judgment matrix as an example, the weight vector w is obtained by solving A After that, the maximum characteristic root of the first judgment matrix A can be calculated Where n is the number of dimensions. Aw is the first judgment matrix A*weight vector w. Substituting in, we can get the maximum eigenvalue of the first judgment matrix A as λ A Similarly, the maximum characteristic roots of the second judgment matrices B1, B2, B3, B4, and B5 are λ B1 , B2 ,B3 , B4 , B5 .

[0098] It should be noted that the consistency index usually includes the consistency index CI, the average random consistency index RI and the consistency ratio CR; according to the solution formula of the consistency index CI The consistency index of the first judgment matrix A can be obtained as CI A Similarly, the consistency indexes of the second judgment matrix B1, B2, B3, B4, and B5 are CI B1 , CI B2 , CI B3 , CI B4 , CI B5 .

[0099] The average random consistency index RI value is usually obtained by looking up a table. The average random consistency index RI value table is shown in Table 2 below.

[0100] Table 2

[0101] n 1 2 3 4 5 6 7 8 9 10 RI 0 0 0.52 0.89 1.12 1.26 1.36 1.41 1.46 1.49

[0102] The first judgment matrix A has n=5, and its average random consistency index RI can be obtained according to Table 2. A is 1.12. According to the consistency ratio CR calculation formula CR = CI / RI, the consistency ratio of the judgment matrix A is CR A .

[0103] Generally speaking, when CR<0.1, it indicates that the consistency of the first judgment matrix A is considered to be within the allowable range, and the eigenvector of A can be used to perform weight vector calculation; if CR≥0.1, it indicates that a logical error occurred when constructing the first judgment matrix, and the first judgment matrix needs to be reconstructed.

[0104] Similarly, it is necessary to calculate the consistency ratio CI of the second judgment matrix B1, B2, B3, B4, and B5 B1 , CI B2 , CI B3 , CI B4 , CI B5 , and ensure that the consistency of the second judgment matrices B1, B2, B3, B4, and B5 is within an allowable range.

[0105] Furthermore, if the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices are both within a preset range, third evaluation data is determined based on the first weight of each of the influencing factor data, the first evaluation data, and the second evaluation data corresponding to each of the second judgment matrices, and the third evaluation data represents the comprehensive rationality of the first judgment matrix and the second judgment matrix; if the third evaluation data is within a preset range, a target weight of each alternative parking method is determined based on the first weight of each of the influencing factor data and the second weight of each alternative parking method relative to each of the influencing factor data.

[0106] Specifically, the third evaluation data is a consistency index of the total hierarchical ranking.

[0107] Similarly, it is necessary to determine whether the total ranking of the hierarchy passes the consistency test to determine whether the weight of the solution level to the overall goal can be used as the final decision basis. Generally, the consistency index of the total ranking of the hierarchy is:

[0108] According to the definition of consistency judgment, when the total ranking of the levels meets the consistency requirements, CRO < 0.1 is required. At this time, the weight of the solution layer to the overall goal can be used as the final decision basis. That is, the weight of the solution layer to the overall goal w P1 、w P2 、w P3 The solution corresponding to the maximum value in is the optimal decision solution.

[0109] This application uses a hierarchical analysis algorithm combined with a variety of criteria factors related to the driver's use of the automatic parking function to provide accurate automatic parking recommendation method detection results; this application can provide an accurate automatic parking method recommendation method for the parking assistance driving system, thereby improving the safety, convenience and experience of users using the parking assistance driving system.

[0110] See also Figure 4 , which shows a structural block diagram of a parking method recommendation device 600 provided in an embodiment of the present application. The testing device 600 includes: a collection unit 610 and a calculation unit 620.

[0111] The acquisition unit 610 is used to obtain multiple influencing factor data associated with the parking method recommendation, the influencing factor data including width information of the target parking space, occupant information, parking scratch risk, unloading intention, and brightness information of the target parking space, where the target parking space is the parking space to be parked.

[0112] Furthermore, the collection unit 610 is also used to obtain the loading information and unloading information of the vehicle in a historical time period; and determine the unloading intention based on the loading information and the unloading information.

[0113] Furthermore, the acquisition unit 610 is also used to obtain obstacle information around the target parking space; determine a parking path according to the current position information of the vehicle and the position information of the target parking space; and determine the risk of parking scratches based on the obstacle information and the parking path.

[0114] The calculation unit 620 is configured to determine a target parking method from the multiple parking alternatives based on the multiple influencing factor data and the multiple parking alternatives by using a hierarchy analysis algorithm.

[0115] Furthermore, the calculation unit 620 can also be used to determine a first weight for each of the influencing factor data, the first weight indicating the relative importance of different influencing factors for the parking method recommendation; determine a second weight for each alternative parking method relative to each of the influencing factor data, the second weight indicating the relative superiority or inferiority of different parking methods under each of the influencing factor data; determine a target weight for each alternative parking method based on the first weight and the second weight; and use the alternative parking method corresponding to the target weight with the largest value as the target parking method.

[0116] Furthermore, the calculation unit 620 can also be used to construct a first judgment matrix based on the preset scale table and the plurality of influencing factor data. Where n represents the total number of the impact factor data, a ij Representing the importance index of the i-th influencing factor data compared with the j-th influencing factor data; determining the first weight of each of the influencing factor data based on the first judgment matrix.

[0117] Furthermore, the calculation unit 620 can also be used to construct a second judgment matrix for each of the influencing factor data based on a preset scale table, the plurality of influencing factor data and the plurality of alternative parking modes. Wherein, k represents the sequence number of the impact factor data, and the value range of k is [1, n], bk 12 Indicates the importance index of the first alternative parking method and the second alternative parking method compared with the kth influencing factor data; based on the second judgment matrix of each influencing factor data, determines the second weight of each alternative parking method relative to each of the influencing factor data.

[0118] Furthermore, the calculation unit 620 can also be used to determine first evaluation data corresponding to the first judgment matrix, the first evaluation data indicating the rationality of the first judgment matrix; determine second evaluation data corresponding to each of the second judgment matrices, the second evaluation data indicating the rationality of the second judgment matrix; if the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices are both within a preset range, then determine third evaluation data based on the first weight of each of the influencing factor data, the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices, the third evaluation data indicating the comprehensive rationality of the first judgment matrix and the second judgment matrix; if the third evaluation data is within the preset range, then determine the target weight of each alternative parking method based on the first weight and the second weight.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0120] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0121] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0122] Please refer to Figure 5 , which shows a structural block diagram of an electronic device 700 provided in an embodiment of the present application. The electronic device 700 may be a vehicle system, which may be arranged in a vehicle. The electronic device 700 in the present application may include one or more of the following components: a processor 711, a memory 712, and one or more application programs, wherein the processor 711 is electrically connected to the memory 712, and the one or more program configurations are used to execute the methods described in the various embodiments of the aforementioned test method.

[0123] The processor 711 may include one or more processing cores. The processor 711 uses various interfaces and lines to connect various parts of the entire electronic device 700, and executes various functions and processes data of the electronic device 700 by running or executing instructions, programs, code sets or instruction sets stored in the memory 712, and calling data stored in the memory 712. Optionally, the processor 711 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 711 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and computer programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 711, and it can be implemented separately through a communication chip. Specifically, the method described in the above embodiment can be executed by one or more processors 711.

[0124] For some embodiments, the memory 712 may include a random access memory (RAM) or a read-only memory (ROM). The memory 712 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 712 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the following various method embodiments, etc. The data storage area may also store data created by the electronic device 700 during use, etc.

[0125] Please refer to Figure 6 , which shows a structural block diagram of a computer-readable medium provided in an embodiment of the present application. The computer-readable medium 800 stores program codes, which can be called by a processor to execute the method described in the above method embodiment.

[0126] The computer readable medium 800 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable medium 800 includes a non-transitory computer-readable storage medium. The computer readable medium 800 has storage space for program code 810 that performs any method step in the above method. These program codes can be read from or written to one or more computer program products. The program code 810 can be compressed, for example, in an appropriate form.

[0127] Please refer to Figure 7 , which shows a structural block diagram 900 of a computer program product provided by an embodiment of the present application. The computer program product 900 includes a computer program / instruction 910, and when the computer program / instruction 910 is executed by a processor, the steps of the above method are implemented.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A parking method recommendation method, characterized in that: Applied to a vehicle, the method comprises: Acquire multiple influencing factor data associated with parking method recommendation, the influencing factor data including width information of a target parking space, occupant information, parking scratch risk, unloading intention, and brightness information of the target parking space, the target parking space being a parking space to be parked; Based on the plurality of influencing factor data and the plurality of alternative parking methods, a target parking method is determined from the plurality of alternative parking methods by using a hierarchy analysis algorithm.

2. The method according to claim 1, characterized in that The obtaining of unloading intention includes: Obtaining loading and unloading information of the vehicle within a historical time period; A discharge intention is determined based on the loading information and the discharge information.

3. The method according to claim 1, characterized in that The obtaining of parking scratch risk includes: Obtain obstacle information around the target parking space; Determining a parking path according to the current position information of the vehicle and the position information of the target parking space; The parking scratch risk is determined based on the obstacle information and the parking path.

4. The method according to claim 1, characterized in that: The step of determining a target parking method from the plurality of alternative parking methods based on the plurality of influencing factor data and the plurality of alternative parking methods by using a hierarchy analysis algorithm includes: Determine a first weight of each of the influencing factor data, wherein the first weight represents the relative importance of different influencing factors for parking method recommendation; Determine a second weight of each alternative parking method relative to each of the influencing factor data, wherein the second weight represents a relative superiority or inferiority of different parking methods under each of the influencing factor data; determining a target weight for each alternative parking method according to the first weight and the second weight; The alternative parking method corresponding to the target weight with the largest value is used as the target parking method.

5. The method according to claim 4, characterized in that The determining of the first weight of each of the influencing factor data comprises: Constructing a first judgment matrix based on a preset scale table and a plurality of said influencing factor data Where n represents the total number of the impact factor data, a ij Indicates the importance index of the i-th impact factor data compared with the j-th impact factor data; A first weight of each of the influencing factor data is determined based on the first judgment matrix.

6. The method according to claim 5, characterized in that The plurality of alternative parking methods include remote control parking, vehicle-side automatic parking, and user-initiated parking. The determining of a second weight of each alternative parking method relative to each of the influencing factor data includes: A second judgment matrix for each of the influencing factor data is constructed based on a preset scale table, the plurality of influencing factor data and the plurality of alternative parking modes. Wherein, k represents the sequence number of the impact factor data, and the value range of k is [1, n], bk 12 represents the importance index of the first alternative parking method and the second alternative parking method relative to the kth influencing factor data; Based on the second judgment matrix of each influencing factor data, a second weight of each alternative parking method relative to each influencing factor data is determined.

7. The method according to claim 6, characterized in that The step of determining a target weight of each alternative parking method according to the first weight and the second weight includes: Determining first evaluation data corresponding to the first judgment matrix, wherein the first evaluation data indicates a rationality of the first judgment matrix; Determining second evaluation data corresponding to each second judgment matrix, wherein the second evaluation data indicates the rationality of the second judgment matrix; If the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices are both within a preset range, determining third evaluation data according to the first weight of each of the influencing factor data, the first evaluation data and the second evaluation data corresponding to each of the second judgment matrices, wherein the third evaluation data represents the comprehensive rationality of the first judgment matrix and the second judgment matrix; If the third evaluation data is within a preset range, a target weight of each alternative parking method is determined according to the first weight and the second weight.

8. A parking method recommendation device, characterized in that: Applied to a vehicle, the device comprises: A collection unit, used to obtain a plurality of influencing factor data associated with the parking method recommendation, wherein the influencing factor data includes width information of a target parking space, occupant information, parking scratch risk, unloading intention, and brightness information of the target parking space, wherein the target parking space is a parking space to be parked; The calculation unit is used to determine a target parking method from the multiple parking alternatives through a hierarchy analysis algorithm based on the multiple influencing factor data and the multiple parking alternatives.

9. An electronic device, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory, the one or more applications are configured to be executed by the one or more processors, and the one or more applications are configured to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images