Method for predicting user driving event, electronic equipment and vehicle

Abstract

The invention provides a user driving event prediction method, electronic equipment and a vehicle, and the method comprises the steps: obtaining the driving habit data of a current user, combining the driving habit data of each historical user, determining a target similar user of the current user from each historical user, and obtaining the current driving information of the current user, and determining a predicted driving event of the current user based on the current driving information and the historical driving information of each historical driving event recorded for the target similar user, thereby realizing risk prediction of the driving event of the user. Therefore, in combination with the historical driving information of the historical driving events of the similar users, targeted prediction of the driving events of the users is realized, the users can be helped to mine potential driving risks, the driving experience and driving safety of the users are improved, and event loss is reduced for the users.

Description

Technical Field

[0001] The present application relates to the field of vehicle safety technology, and in particular to a method for predicting a user driving event, an electronic device, and a vehicle. Background Art

[0002] In actual driving, some drivers' driving habits may lead to certain driving problems. For example, novice drivers may have the habit of misjudging distance and miscontrolling acceleration and deceleration, which may lead to rear-end collisions, vehicle slipping on slopes, and too fast acceleration at the start of the vehicle, affecting the comfort of passengers.

[0003] However, existing solutions usually provide risk warnings based on unified indicators, such as predicting collision risks based on safe collision time or distance. They fail to predict the driving risks of different users in a targeted manner, and the prediction results are inaccurate. Summary of the invention

[0004] In view of this, the purpose of this application is to propose a method, electronic device and vehicle for predicting user driving events, so as to solve the problem that the prior art fails to predict the driving risks of different users separately and specifically, and to improve the accuracy of predicting user driving risks.

[0005] Based on the above purpose, the present application provides a method for predicting a user's driving event, comprising:

[0006] Acquire driving habit data of a current user, and determine a target similar user of the current user from among the historical users based on the driving habit data of the current user and the driving habit data of each historical user;

[0007] The current driving information of the current user is obtained, and the predicted driving event of the current user is determined based on the current driving information and the historical driving information of each historical driving event recorded for the target similar user.

[0008] Optionally, after determining the predicted driving event of the current user, the method further includes:

[0009] Displaying prompt information corresponding to the predicted driving event on the vehicle interface; and / or,

[0010] The prompt information corresponding to the predicted driving event is played through the vehicle's voice playback device.

[0011] Optionally, based on the driving habit data of the current user and the driving habit data of each historical user, determining a target similar user of the current user from each historical user includes:

[0012] Determine a target user class corresponding to the current user based on the driving habit data of the current user and the average driving habit data of each user class, wherein the average driving habit data of the user class is obtained by clustering the driving habit data of all historical users;

[0013] Based on the driving habit data of the current user and the driving habit data of each historical user under the target user class, a target similar user to the current user is determined from each historical user under the target user class.

[0014] Optionally, based on the driving habit data of the current user and the driving habit data of each historical user, determining a target similar user of the current user from each historical user includes:

[0015] Based on the driving habit data of the current user and the driving habit data of each historical user under the current vehicle model, a target similar user of the current user is determined from each historical user under the current vehicle model.

[0016] Optionally, determining the predicted driving event of the current user based on the current driving information and historical driving information of each historical driving event recorded for the target similar user includes:

[0017] For each historical driving event recorded by the target similar user, determining the similarity between the historical driving information of the historical driving event and the current driving information;

[0018] A predicted driving event of the current user is determined based on the similarity.

[0019] Optionally, determining the similarity between the historical driving information of the historical driving event and the current driving information includes:

[0020] Based on the historical environmental data, historical road data, historical climate data and historical driving data in the historical driving information, and the current environmental data, current road data, current climate data and current driving data in the current driving information, the similarity between the historical driving information and the current driving information is determined.

[0021] Optionally, the method further includes:

[0022] Re-acquiring the driving habit data of the current user;

[0023] Based on the new driving habit data and the driving habit data of each historical user, the target similar user of the current user is re-determined to determine the predicted driving event of the current user based on the historical driving information of each historical driving event recorded for the newly determined target similar user.

[0024] Optionally, the method further includes:

[0025] In response to detecting a current driving event of the current user, the current driving event and driving information when the current driving event occurs and within a period of time before the current driving event are recorded.

[0026] Based on the same purpose, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method provided in any embodiment of the present application is implemented.

[0027] Based on the same purpose, an embodiment of the present application also provides a vehicle, which includes the electronic device provided by any embodiment of the present application.

[0028] As can be seen from the above, the method for predicting user driving events provided by the present application obtains the driving habit data of the current user, determines the target similar user of the current user from the historical users according to the driving habit data and the driving habit data of each historical user, and then obtains the current driving information of the current user, and determines the predicted driving event of the current user based on the current driving information and the historical driving information of each historical driving event recorded for the target similar user, thereby realizing risk prediction of the user's driving event. The method can match other users similar to the current user through the driving habit data of the current user, and then combine the historical driving information of the historical driving events of the similar users and the current driving information of the current user to realize targeted prediction of the user's driving event, which can help the user to explore potential driving risks, solve the problem that the prior art fails to predict the risks of users in a targeted manner, improve the prediction accuracy of the user's driving risks, and can also help the user avoid driving events, improve the user's driving experience and driving safety, and reduce the loss caused by the event for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 A flowchart of a method for predicting a user driving event provided in an embodiment of the present application;

[0031] Figure 2 A schematic diagram of the structure of a device for predicting user driving events provided in an embodiment of the present application;

[0032] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0034] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0035] Before introducing in detail the method for predicting user driving events provided in the embodiment of the present application, the technical problem solved by the method is first described.

[0036] In the prior art, predictions of driving risks and risk warnings for users are usually made based on unified risk indicators, such as safe collision time, relative distance between vehicles, etc. However, this method can only predict some collision risks, and cannot specifically predict the potential driving risks of users, resulting in low risk prediction accuracy.

[0037] Therefore, in order to solve the above technical problems, an embodiment of the present application provides a method for predicting user driving events. The method can match other users similar to the current user through the driving habit data of the current user, and then combine the historical driving events of similar users to predict the potential driving events of the current user in advance. This method can achieve targeted prediction of user driving risks and help users avoid potential driving risks.

[0038] Figure 1 A flowchart of a method for predicting a user driving event provided in an embodiment of the present application. The method can be executed by a device for predicting a user driving event. The device for predicting a user driving event can be integrated into an electronic device by means of hardware and / or software, such as, integrated into a vehicle controller of a vehicle.

[0039] like Figure 1 As shown, the method for predicting user driving events provided in the embodiment of the present application includes the following steps:

[0040] S110 , obtaining driving habit data of the current user, and determining target similar users of the current user from among the historical users based on the driving habit data of the current user and the driving habit data of each historical user.

[0041] The current user can be understood as the user who needs to perform driving risk prediction at the current moment, and the historical user can be understood as the user whose driving habit data has been constructed. The driving habit data of each historical user can be sent from a remote server or a cloud.

[0042] For example, the remote server or cloud can receive the historical driving data uploaded by each vehicle, and build the driving habit data of each historical user based on the historical driving data of each vehicle. The remote server or cloud can build a driving profile corresponding to each historical user, and the driving profile includes driving habit data and historical driving information of each historical driving event. The remote server or cloud can send the driving profile corresponding to each historical user to each vehicle through OTA (Over-the-Air Technology) and other methods.

[0043] The driving habit data may be used as a user label to reflect the user's driving habits. For example, the driving habit data may include turning radius under various working conditions, vehicle speed under various working conditions, deceleration under various working conditions, acceleration under various working conditions, and lane change direction.

[0044] In the embodiment of the present application, the historical driving data of the current user can be obtained, and the driving habit data of the current user can be analyzed based on the historical driving data. For example, each historical working condition can be identified based on the historical driving data, and then the average turning radius, average vehicle speed, average deceleration, average acceleration and the most frequent lane change direction under each historical working condition can be determined based on the historical driving data to obtain the driving habit data of the current user.

[0045] Specifically, after the driving habit data of the current user is acquired, users with similar driving habits, ie, target similar users, may be matched for the current user based on the driving habit data of the current user and the driving habit data of each historical user.

[0046] Exemplarily, the similarity between the driving habit data of the current user and the driving habit data of each historical user may be calculated, so that the historical user with the highest similarity is determined as the target similar user.

[0047] For example, a corresponding weight may be set for each data item in the driving habit data, and then the gaps between the corresponding data items may be weighted by each weight, and the weighted result may be used as the similarity; or, the Euclidean distance between the current user's driving habit data and the historical user's driving habit data may be calculated, and the similarity between the two sets of driving habit data may be measured by the Euclidean distance, etc.

[0048] In an embodiment of the present application, in order to further improve the efficiency of matching similar users for the current user, all historical users can be classified in advance to obtain the center of each class, and then the corresponding class is matched for the current user first, and then the target similar users are further accurately matched in the matched class.

[0049] In a specific implementation, based on the driving habit data of the current user and the driving habit data of each historical user, determining a target similar user of the current user from each historical user includes the following steps:

[0050] Step 11: determining a target user class corresponding to the current user based on the driving habit data of the current user and the average driving habit data of each user class, wherein the average driving habit data of the user class is obtained by clustering the driving habit data of all historical users;

[0051] Step 12: Based on the driving habit data of the current user and the driving habit data of each historical user under the target user class, determine a target similar user of the current user from each historical user under the target user class.

[0052] The user class may be each cluster obtained by clustering the driving habit data of all historical users in advance. The average driving habit data of the user class may be understood as the center of the user class, and the average driving habit data of all historical users under the user class may be taken.

[0053] Specifically, in step 11, the distance between the current user and the center of each user class can be determined based on the driving habit data of the current user and the average driving habit data of each user class. For example, the difference between the driving habit data of the current user and the average driving habit data of the user class is calculated, and the calculated difference is used to measure the distance to the center of the user class. Furthermore, the user class with the smallest distance can be selected as the target user class corresponding to the current user.

[0054] After determining the target user class, further, in step 12, similar users can be accurately matched for the current user under the target user class. Specifically, the similarity between the driving habit data of the current user and the driving habit data of each historical user under the target user class can be calculated, and then the historical user with the highest similarity under the target user class is selected as the target similar user.

[0055] Through the above steps 11 and 12, all historical users can be classified in advance to obtain various user classes. Then, in the process of matching similar users for the current user, the user class to which the current user belongs can be determined first, and then the target similar users with similar driving habits to the current user are searched under the user class. Compared with directly calculating the similarity between the driving habit data of the current user and all historical users, the similarity calculation amount can be reduced, thereby improving the efficiency of matching similar users for the current user.

[0056] In addition, in the embodiment of the present application, considering the differences in driving control of different car models, there may be large differences in driving habit data of users with the same driving habits. Therefore, in order to improve the accuracy of matching similar users for the current user and thereby improve the accuracy of predicting subsequent events, historical users can also be distinguished according to car models, thereby matching similar users for the current user among the historical users under the corresponding car models.

[0057] In one example, based on the driving habit data of the current user and the driving habit data of each historical user, determining a target similar user of the current user from each historical user includes:

[0058] Based on the driving habit data of the current user and the driving habit data of each historical user under the current model of the vehicle, a target similar user of the current user is determined from each historical user under the current model.

[0059] Among them, each historical user can be distinguished in advance according to the vehicle model; for example, a corresponding archive library can be constructed for each vehicle model, in which the driving habit data of each historical user under the vehicle model and the historical driving information of each recorded historical driving event are stored.

[0060] Specifically, based on the current model corresponding to the vehicle driven by the current user, the driving habit data of each historical user under the current model can be selected. Furthermore, the similarity between the driving habit data of the current user and the driving habit data of each historical user under the current model can be calculated, so as to select the target similar user from the historical users under the current model according to the similarity.

[0061] Through the above examples, the car model can be combined with the current user to match users with similar driving habits. Taking into account the different driving control methods of different car models, the accuracy of matching similar users for the current user can be further improved, thereby improving the reliability of subsequent risk prediction for the current user.

[0062] It should be noted that the above clustering can also be combined with a solution for matching similar users by vehicle type. For example, clustering processing can be performed in advance on the driving habit data of all historical users under each vehicle type to obtain all user classes under the vehicle type and the average driving habit data of the user classes. Furthermore, according to the current vehicle type corresponding to the vehicle driven by the current user, the target user class can be matched first among all user classes under the current vehicle type, and then the target similar user can be determined from the historical users under the target user class.

[0063] S120: Acquire current driving information of the current user, and determine a predicted driving event of the current user based on the current driving information and historical driving information of each historical driving event recorded for a target similar user.

[0064] The current driving information may be used to describe relevant information of the current user driving the vehicle during driving. Exemplarily, the current driving information may describe the current environment, current road, current climate, and current state of the vehicle. For example, the current driving information may include current environment data, current road data, current climate data, and current driving data.

[0065] Among them, environmental data can be understood as information related to the environment in which the vehicle is located, and may include the light intensity, humidity, longitude and latitude, and altitude of the environment in which the vehicle is located. In the embodiment of the present application, the current environmental data can be collected by sensors (such as light sensors, humidity sensors, altitude sensors, etc.) installed on the vehicle driven by the current user; or, the environmental information can be requested from the cloud to obtain the current environmental data fed back by the cloud; or, based on the current location in the navigation application or the current location located by the sensor, the current environmental data corresponding to the current location can be searched on the Internet.

[0066] Among them, road data can be understood as information related to the road where the vehicle is located, which may include whether there is water on the road where the vehicle is located, whether the road where the vehicle is located is frozen, the road type of the road where the vehicle is located, whether the road where the vehicle is located is uphill or downhill, and the number of lanes on the road where the vehicle is located. In the embodiment of the present application, the current road data can be obtained by visually perceiving the road where the vehicle is located through the sensors and cameras installed on the vehicle currently driven by the user.

[0067] Among them, climate data can be understood as information related to the climate of the environment in which the vehicle is located, and can include the temperature of the environment in which the vehicle is located, and the weather type of the environment in which the vehicle is located. In the embodiment of the present application, the current temperature can be obtained through the temperature sensor installed on the vehicle driven by the current user, and the current weather type can be obtained by requesting the weather type from the cloud, or searching the Internet for the corresponding weather type based on the current location in the navigation application or the current location located by the sensor, and then the current temperature and the current weather type are used as the current climate data.

[0068] The driving data may be understood as information related to the vehicle driving state, including vehicle speed, vehicle acceleration, vehicle speed gear, window opening state, distance to the vehicle in front, and component failure state, etc. In the embodiment of the present application, the current driving data may be obtained by communicating with various systems in the vehicle currently driven by the user.

[0069] In the embodiment of the present application, after obtaining the current driving information of the current user, the driving events that may occur to the current user can be predicted by combining the historical driving information of each historical driving event recorded for the target similar user to obtain the predicted driving event. The historical driving event can be a driving event that has occurred, such as a collision, rear-end collision, violation of traffic rules, etc.

[0070] The historical driving information of each historical driving event recorded by each historical user may be sent together with the driving habit data of each historical user. The cloud or remote server may record the driving events of each user during the driving process of the vehicle, and record the driving information when the driving event occurs and within a period of time before the event occurs, and store it in the driving file.

[0071] Specifically, in the process of predicting the risk of the current user, the current driving information can be compared with the historical driving information of various historical driving events of similar target users to determine whether the current user is likely to have a historical driving event. If so, the possible historical driving event is determined as a predicted driving event.

[0072] In a specific implementation, determining a predicted driving event of the current user based on the current driving information and the historical driving information of each historical driving event recorded for a target similar user includes the following steps:

[0073] Step 21: for each historical driving event recorded by the target similar user, determine the similarity between the historical driving information of the historical driving event and the current driving information;

[0074] Step 22: Determine a predicted driving event of the current user based on the similarity.

[0075] In step 21, for each historical driving event of the target similar user, the similarity between the historical driving information recorded for the historical driving event and the current driving information may be calculated.

[0076] Specifically, for a historical driving event of a target similar user, if the similarity between it and the current driving information is high, it means that the driving condition of the current user is relatively similar to the driving condition of the historical user before the historical driving event occurred; if the similarity between it and the current driving information is low, it means that the driving condition of the current user is quite different from the driving condition of the historical user before the historical driving event occurred.

[0077] In step 22, after determining the similarity between the historical driving information and the current driving information of each historical driving event of the target similar user, the predicted occurrence probability of the historical driving event can be determined based on the similarity. The higher the similarity, the greater the predicted occurrence probability. The predicted driving event of the current user is then determined through the predicted occurrence probabilities of all historical driving events.

[0078] Exemplarily, a mapping function between similarity and predicted probability of occurrence can be pre-constructed, and the predicted probability of occurrence of historical driving events can be determined through similarity and mapping function. For example, the mapping function can be: when the similarity is (0, 0.4), the predicted probability of occurrence is 0, when the similarity is (0.4, 0.6), the predicted probability of occurrence is 0.4, when the similarity is (0.6, 0.8), the predicted probability of occurrence is 0.7, and when the similarity is (0.8, 1), the predicted probability of occurrence is 1. Of course, the mapping function is not limited to the above examples, and the above examples are only for illustration, and the embodiments of the present application do not limit this.

[0079] Furthermore, after the predicted occurrence probabilities of all historical driving events are obtained, historical driving events whose predicted occurrence probabilities are not less than a set probability (such as 0.7) may be determined as predicted driving events for the current user.

[0080] It should be noted that if the predicted probability of occurrence of all historical driving events is lower than the set probability, the predicted driving event of the current user is empty.

[0081] In addition, if there are multiple historical driving events whose predicted probability of occurrence is not less than the set probability, the multiple historical driving events can be simultaneously determined as predicted driving events, so as to subsequently remind the user of the existence of multiple event risks at the same time.

[0082] Alternatively, in order to facilitate subsequent reminders for the user to focus on the driving event with the highest probability of occurrence, the historical driving event with the highest predicted probability of occurrence may be selected as the predicted driving event from among multiple historical driving events with predicted probability of occurrence not less than a set probability. Alternatively, in order to facilitate subsequent reminders for the user to focus on the driving event with the highest degree of danger, the historical driving event with the highest degree of danger may be selected as the predicted driving event from among multiple historical driving events with predicted probability of occurrence not less than a set probability.

[0083] Through the above steps 21 and 22, based on the similarity between the historical driving information of the historical driving events and the current driving information, possible driving events can be matched for the current user from the historical driving events of the target similar users, thereby realizing driving risk prediction. The similarity between the driving information can reflect the overlap between the driving conditions of the current user and the target similar user before the event occurs, thereby ensuring the accuracy of driving risk prediction.

[0084] With respect to the above step 21, optionally, determining the similarity between the historical driving information of the historical driving event and the current driving information includes:

[0085] Based on the historical environment data, historical road data, historical climate data and historical driving data in the historical driving information, and the current environment data, current road data, current climate data and current driving data in the current driving information, the similarity between the historical driving information and the current driving information is determined.

[0086] Specifically, the similarity between the historical driving information and the current driving information may be evaluated through the environmental data, road data, climate data, and driving data in the driving information.

[0087] Exemplarily, the similarity between current environmental data in the current driving information and historical environmental data in the historical driving information can be calculated to obtain a first similarity, the similarity between current road data in the current driving information and historical road data in the historical driving information can be calculated to obtain a second similarity, the similarity between current climate data in the current driving information and historical climate data in the historical driving information can be calculated to obtain a third similarity, and the similarity between current driving data in the current driving information and historical driving data in the historical driving information can be calculated to obtain a fourth similarity.

[0088] Furthermore, the first similarity, the second similarity, the third similarity and the fourth similarity may be fused according to the weights pre-set for the environmental data, the road data, the climate data and the driving data to obtain the final similarity.

[0089] Considering that the occurrence of driving events in some scenarios can be predicted only by partial data in the driving information, for example, some users are accustomed to following the vehicle in front closely in the underground garage, which causes the vehicle to slip on the slope and rear-end collision, which has nothing to do with the climate, environment, etc. Therefore, for some scenarios, the similarity between the historical driving information and the current driving information can also be determined based on the similarity between partial data in the driving information.

[0090] Exemplarily, the current scene can be identified through the current road data and current environmental data in the current driving information. If the current scene is a preset scene (such as flooded roads, driving in underground garages, driving in snowy weather, etc.), then part of the data can be selected from the current driving information and part of the data can be selected from the historical driving information based on the data items corresponding to the preset scene, and the similarity between the historical driving information and the current driving information can be determined through the selected part of the data.

[0091] Through the above implementation, driving event matching based on environmental data, road data, climate data and driving data can be achieved, and the possible risks of the vehicle can be predicted from multiple aspects such as the vehicle's current driving environment, road, climate, and driving status, thereby ensuring the reliability and comprehensiveness of driving risk prediction.

[0092] In the embodiment of the present application, in addition to first determining the user class to which the current user belongs, and then searching for target similar users with similar driving habits to the current user under the user class, and providing driving event warning for the current user through the similarity between the historical driving information of the historical driving events of the target similar users and the current driving information, all historical users can also be classified in advance to obtain various user classes, and the historical driving information of the historical driving events of all historical users contained in the user class can be recorded under the user class, wherein the historical driving information of repeated historical driving events can be averaged. Further, the target user class to which the current user belongs can be determined, and the similarity between the historical driving information of each historical driving event under the target user class and the current driving information is calculated to determine the predicted driving event of the current user.

[0093] In one example, after determining the predicted driving event of the current user, the method further includes:

[0094] Displaying prompt information corresponding to the predicted driving event in the vehicle interface; and / or playing the prompt information corresponding to the predicted driving event through the vehicle's voice playback device.

[0095] In an embodiment of the present application, after the predicted driving event of the current user is determined, the user may be prompted.

[0096] Specifically, prompt information corresponding to the predicted driving event can be displayed in the vehicle computer interface, wherein the prompt information can be displayed in the form of text or animation, or can also be displayed in the form of a combination of text and animation.

[0097] In addition to displaying the prompt information in the vehicle interface, the prompt information corresponding to the predicted driving event can also be played through the vehicle's voice playback device. It should be noted that in order to prevent the user from missing the prompt information, the prompt information can also be played through the voice playback device while displaying the prompt information in the vehicle interface.

[0098] In addition, the number of times the prompt information is displayed can be preset, and the prompt information is displayed cyclically according to the number of times, so as to achieve the purpose of multiple reminders. The number of times the prompt information is displayed can be determined according to the number of times the current user's driving events occur. For example, the more times the driving events occur, the higher the number of times the prompt information is displayed.

[0099] In order to avoid frequent reminders affecting the user's driving, when it is detected that the user triggers the operation of closing the reminder function, the prompt information corresponding to the predicted driving event will no longer be displayed.

[0100] Through the above example, after determining the predicted driving event of the current user, the prompt information can be displayed through the vehicle interface or voice playback device, which can remind the user to avoid driving events and ensure the driving safety of the vehicle.

[0101] It should be noted that in addition to displaying prompt information through the vehicle interface or voice playback device, prompt information corresponding to the predicted driving event can also be projected onto the vehicle window glass through the HUD (Head Up Display) device.

[0102] In addition, after determining the predicted driving event of the current user, in addition to displaying prompt information to remind the user to avoid the driving event, the vehicle's driving can also be controlled according to the predicted driving event, thereby actively helping the user to avoid the driving event.

[0103] For example, the corresponding preset control strategy and preset control component can be determined based on the predicted driving event, and then the preset control component can be controlled according to the preset control strategy. For example, if the preset driving event is a rear-end collision, the corresponding preset control strategy can be to limit the vehicle speed (limit the vehicle speed within a set range) or control the vehicle to slow down, and the corresponding preset control component can be the engine or motor; if the preset driving event is a tire blowout, the corresponding preset control strategy can be to control the vehicle to turn on the double flash lights, and the corresponding preset control component can be the double flash lights.

[0104] In the embodiment of the present application, considering that the user's driving habits may change after driving for a period of time, the driving habit data of the current user may be re-acquired after a period of time to re-match users with similar driving habits to the current user.

[0105] In one example, the method provided in the embodiment of the present application further includes:

[0106] Re-acquire the driving habit data of the current user; re-determine the target similar user of the current user based on the new driving habit data and the driving habit data of each historical user, so as to determine the predicted driving event of the current user based on the historical driving information of each historical driving event recorded for the newly determined target similar user.

[0107] Specifically, the driving habits of the current user may be re-analyzed based on the historical driving data of the current user in a recent period of time to obtain new driving habit data of the current user.

[0108] Furthermore, the new driving habit data can be matched with the driving habit data of each historical user, and the target similar users of the current user can be re-determined from among the historical users. After the target similar users are re-determined, the driving risk prediction of the current user can be achieved based on the historical driving information of each historical driving event of the newly determined target similar users.

[0109] In the embodiment of the present application, the trigger condition of the above example may be that the user's driving time reaches a set time, or the user's driving mileage reaches a set mileage. That is, in response to detecting that the user's driving time reaches a set time or the user's driving mileage reaches a set mileage, the current user's driving habit data can be re-acquired, and the target similar user can be re-determined based on the new driving habit data and the driving habit data of each historical user.

[0110] Through the above example, the current user's driving habit data can be updated, and the target similar users can be re-matched based on the new driving habit data to ensure that the matched similar users are consistent with the current user's recent driving habits, thereby further ensuring the reliability of driving risk prediction.

[0111] It should be noted that in addition to re-acquiring the driving habit data of the current user, the cloud or remote server can also update the driving habit data of each historical user after a period of time, that is, use the historical user's most recent historical driving data to update the driving habit data, and then the cloud or remote server can send the latest driving file.

[0112] In an embodiment of the present application, if a driving event occurs to the current user, the driving event of the current user may also be stored for subsequent use by other users to predict driving risks. In an example, the method provided in the embodiment of the present application further includes:

[0113] In response to detecting a current driving event of the current user, the current driving event and the driving information when the current driving event occurs and within a period of time before the current driving event occurs are recorded.

[0114] Specifically, if a driving event is detected for the current user, the current driving event may be recorded, and at the same time, driving information when the current driving event occurs and within a period of time before the event occurs may also be recorded.

[0115] Among them, the recorded current driving events and driving information can be stored locally in the vehicle, and then the current user's driving habit data, as well as the recorded current driving events and driving information can be uploaded to the cloud or remote server through the on-board communication terminal (T-Box).

[0116] Through the above example, after a driving event occurs to the current user, the driving event and driving information of the current user can be stored, so that other users can use it to predict driving risks. In addition, by recording the driving information when the event occurs and within a period of time before the event, other vehicles can predict the driving event in advance.

[0117] The method for predicting user driving events provided in the embodiment of the present application obtains the driving habit data of the current user, determines the target similar user of the current user from the historical users according to the driving habit data and the driving habit data of each historical user, and then obtains the current driving information of the current user, and determines the predicted driving event of the current user based on the current driving information and the historical driving information of each historical driving event recorded for the target similar user, so as to realize risk prediction of the user's driving event. The method can match other users similar to the current user through the driving habit data of the current user, and then combine the historical driving information of the historical driving events of the similar users and the current driving information of the current user to realize targeted prediction of the user's driving event, which can help the user to explore potential driving risks, solve the problem that the prior art fails to predict the risks of users in a targeted manner, improve the prediction accuracy of the user's driving risks, and can also help the user avoid driving events, improve the user's driving experience and driving safety, and reduce the loss caused by the event for the user.

[0118] In addition, the method for predicting user driving events provided in the embodiment of the present application is different from the driving behavior prediction based on the big data model in that, first, the method provided in the embodiment of the present application does not rely on model training, but first matches similar users for the current user and warns the current user based on driving events that have occurred to similar users; secondly, usually in the scheme of predicting driving behavior with a big data model, the purpose of training the model is to obtain the mapping relationship between the input data and the output driving behavior, which has nothing to do with the user, while the method provided in the embodiment of the present application does not need to obtain the mapping relationship between the input data and the output driving behavior, but warns the current user based on the matched similar users; finally, in the scheme of predicting driving behavior with a big data model, after the model is deployed, behavior prediction can only be performed based on the known mapping relationship, and the applicability is low and the accuracy cannot be guaranteed. However, in the method provided in the embodiment of the present application, each user can be used to warn other users of events. With the storage of driving files of newly added users, the applicability is strong and the accuracy of event prediction can be continuously improved.

[0119] Furthermore, the method for predicting user driving events provided in the embodiment of the present application is different from the method for calculating a single indicator based on driving-related data and then predicting driving events through the calculated indicator in that, firstly, calculating a single indicator can only predict a small part of driving events, such as predicting whether a collision will occur based on distance, collision time, etc., while the method provided in the embodiment of the present application can warn the current user based on driving events that have occurred to similar users, thereby ensuring the comprehensiveness of event warnings; secondly, calculating a single indicator usually relies on a mathematical model, and the higher the calculation rate of the indicator, the stronger the real-time prediction, which places higher requirements on system memory, while the method provided in the embodiment of the present application does not need to use a mathematical model for calculation, has a small burden on system memory, and can be applied to various vehicle configurations.

[0120] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0121] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a device for predicting user driving events. Figure 2 A schematic diagram of a device for predicting a user driving event provided in an embodiment of the present application, referring to Figure 2 The device for predicting user driving events includes a similar user matching module 210 and an event prediction module 220, wherein:

[0123] A similar user matching module 210 is used to obtain driving habit data of the current user, and determine a target similar user of the current user from among the historical users based on the driving habit data of the current user and the driving habit data of each historical user;

[0124] The event prediction module 220 is used to obtain the current driving information of the current user, and determine the predicted driving event of the current user based on the current driving information and the historical driving information of each historical driving event recorded for the target similar user.

[0125] Based on the above implementation, optionally, the device also includes a display module, which is used to display prompt information corresponding to the predicted driving event in the vehicle interface; and / or play the prompt information corresponding to the predicted driving event through the vehicle's voice playback device.

[0126] Based on the above implementation, optionally, the similar user matching module 210 is specifically used for:

[0127] Based on the driving habit data of the current user and the average driving habit data of each user class, a target user class corresponding to the current user is determined, wherein the average driving habit data of the user class is obtained by clustering the driving habit data of all historical users; based on the driving habit data of the current user and the driving habit data of each historical user under the target user class, a target similar user of the current user is determined among each historical user under the target user class.

[0128] Based on the above implementation, optionally, the similar user matching module 210 is specifically used for:

[0129] Based on the driving habit data of the current user and the driving habit data of each historical user under the current vehicle model, a target similar user of the current user is determined from each historical user under the current vehicle model.

[0130] Based on the above implementation, optionally, the event prediction module 220 is specifically used to:

[0131] For each historical driving event recorded by the target similar user, determine the similarity between the historical driving information of the historical driving event and the current driving information; and determine the predicted driving event of the current user based on the similarity.

[0132] Based on the above implementation, optionally, the event prediction module 220 is also used to determine the similarity between the historical driving information and the current driving information based on the historical environmental data, historical road data, historical climate data and historical driving data in the historical driving information, and the current environmental data, current road data, current climate data and current driving data in the current driving information.

[0133] Based on the above implementation, optionally, the similar user matching module 210 is also used to reacquire the driving habit data of the current user; based on the new driving habit data and the driving habit data of each historical user, re-determine the target similar user of the current user, so as to determine the predicted driving event of the current user based on the historical driving information of each historical driving event recorded for the newly determined target similar user.

[0134] Based on the above implementation, optionally, the event prediction module 220 is also used to record the current driving event and the driving information when the current driving event occurs and within a period of time before the current driving event occurs in response to detecting the current driving event of the current user.

[0135] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0136] The device of the above embodiment is used to implement the corresponding method for predicting user driving events in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0137] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for predicting user driving events described in any of the above embodiments is implemented.

[0138] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, Figure 3 A specific electronic device hardware structure is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0139] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0140] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0141] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0142] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0143] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0144] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0145] The electronic device of the above-mentioned embodiment is used to implement the corresponding method for predicting user driving events in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0146] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for predicting user driving events as described in any of the above embodiments.

[0147] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0148] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for predicting user driving events as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0149] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a vehicle, which includes the electronic device provided by any of the embodiments of the present application.

[0150] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0151] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0152] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0153] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for predicting a user driving event, characterized in that: include: Acquire driving habit data of a current user, and determine a target similar user of the current user from among the historical users based on the driving habit data of the current user and the driving habit data of each historical user; The current driving information of the current user is obtained, and the predicted driving event of the current user is determined based on the current driving information and the historical driving information of each historical driving event recorded for the target similar user.

2. The method according to claim 1, characterized in that After determining the predicted driving event of the current user, the method further includes: Displaying prompt information corresponding to the predicted driving event on the vehicle interface; and / or, The prompt information corresponding to the predicted driving event is played through the vehicle's voice playback device.

3. The method according to claim 1, characterized in that Based on the driving habit data of the current user and the driving habit data of each historical user, determining a target similar user of the current user from each historical user includes: Determine a target user class corresponding to the current user based on the driving habit data of the current user and the average driving habit data of each user class, wherein the average driving habit data of the user class is obtained by clustering the driving habit data of all historical users; Based on the driving habit data of the current user and the driving habit data of each historical user under the target user class, a target similar user to the current user is determined from each historical user under the target user class.

4. The method according to claim 1, characterized in that: Based on the driving habit data of the current user and the driving habit data of each historical user, determining a target similar user of the current user from each historical user includes: Based on the driving habit data of the current user and the driving habit data of each historical user under the current vehicle model, a target similar user of the current user is determined from each historical user under the current vehicle model.

5. The method according to claim 1, characterized in that Determining a predicted driving event of the current user based on the current driving information and historical driving information of each historical driving event recorded for the target similar user includes: For each historical driving event recorded by the target similar user, determining the similarity between the historical driving information of the historical driving event and the current driving information; A predicted driving event of the current user is determined based on the similarity.

6. The method according to claim 5, characterized in that Determining the similarity between the historical driving information of the historical driving event and the current driving information includes: Based on the historical environmental data, historical road data, historical climate data and historical driving data in the historical driving information, and the current environmental data, current road data, current climate data and current driving data in the current driving information, the similarity between the historical driving information and the current driving information is determined.

7. The method according to claim 1, characterized in that The method further comprises: Re-acquiring the driving habit data of the current user; Based on the new driving habit data and the driving habit data of each historical user, the target similar user of the current user is re-determined to determine the predicted driving event of the current user based on the historical driving information of each historical driving event recorded for the newly determined target similar user.

8. The method according to claim 1, characterized in that The method further comprises: In response to detecting a current driving event of the current user, the current driving event and driving information when the current driving event occurs and within a period of time before the current driving event are recorded.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A vehicle, characterized in that: The vehicle comprises the electronic device as claimed in claim 9.

Images