Door handle control method and device, vehicle door and vehicle

Abstract

The invention discloses a door handle control method and device, a vehicle door and a vehicle. A data set of the current vehicle is collected; wherein the data set of the current vehicle comprises vehicle data of the current vehicle and driving behavior data of the current vehicle; predicting state information of the current vehicle according to the data set of the current vehicle; if it is predicted that the state information of the current vehicle is an abnormal state, popping up a door handle of the current vehicle; the state information of the current vehicle is predicted by collecting the vehicle data and the driving behavior data of the current vehicle, when the state information of the current vehicle is predicted to be in an abnormal state or about to be in an abnormal state, the door handle is controlled to pop up, and the situation that the door handle cannot pop up due to an abnormal fault is avoided by popping up the door handle in advance. And the abnormal state is predicted in advance and responded in advance, so that the rescue time of people outside the vehicle is brought forward as much as possible, and the safety of people in the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the technical field of pop-up door wrenches, and in particular to a control method and device for a door handle, a vehicle door and a vehicle. Background Art

[0002] With the continuous development of intelligent technology in the automotive field, new vehicle door handles bounce back when not in use and can be flush with other door parts to achieve a hidden effect. This will not destroy the overall styling features of the vehicle. The appearance is simple and beautiful, and it can also reduce air resistance during driving. It has gradually become one of the common configurations of new energy vehicles.

[0003] The door handle pops out when the passenger needs to open the door, and the existing door wrenches are mostly driven by the drive motor to pop out and rebound. However, when the vehicle fails or is abnormal, the electrical control system may not work properly, and the drive motor of the door handle does not receive the pop-up command, resulting in the door handle not being able to pop out normally. Especially in the event of an emergency, it is difficult for rescuers to operate the door handle from outside the vehicle, and thus they cannot open the door for rescue. Therefore, there is an urgent need for a way to pop out the door handle when the vehicle is abnormal. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a door handle control method, device, vehicle door and vehicle.

[0005] According to one aspect of the present application, a door handle control method is provided, comprising: collecting a data set of a current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; predicting status information of the current vehicle based on the data set of the current vehicle; wherein the status information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident has occurred, and there are passengers in the current vehicle; if the status information of the current vehicle is predicted to be an abnormal state, popping out the door handle of the current vehicle.

[0006] In one embodiment, predicting the state information of the current vehicle based on the data set of the current vehicle includes: inputting the data set of the current vehicle into a vehicle state prediction model to obtain the state information of the current vehicle.

[0007] In one embodiment, the training method of the vehicle state prediction model includes: obtaining training samples; wherein the training samples include vehicle data, driving behavior data and real state information, and the real state information represents the real state of the vehicle corresponding to the vehicle data and the driving behavior data; according to the vehicle data, the driving behavior data and the initial model, obtaining predicted state information corresponding to the vehicle data and the driving behavior data; wherein the initial model represents the vehicle state prediction model before training; adjusting the model parameters of the initial model to reduce the loss between the real state information and the predicted state information, and obtaining the vehicle state prediction model.

[0008] In one embodiment, the door handle control method also includes: if it is predicted that the status information of the current vehicle is normal, and personal features are detected within a preset range of the door handle of the current vehicle, then the identity information corresponding to the personal features is identified; if the identified identity information matches the pre-stored passenger, then the door handle is controlled to perform a corresponding operation.

[0009] In one embodiment, if the identified identity information matches the pre-stored passenger, controlling the door handle to perform a corresponding operation includes: if the identified identity information matches the pre-stored passenger, obtaining the level information of the matched passenger; wherein passengers corresponding to different levels have different ways of opening the door handle; and popping out the door handle according to the matched level information of the passenger and the corresponding way of opening the door handle.

[0010] In one embodiment, after the door handle is popped out, the method for controlling the door handle further includes: if the vehicle door corresponding to the door handle is not opened within a first preset time, or if the vehicle door corresponding to the door handle is opened and then closed again and then not opened within a second preset time, then the door handle is bounced back.

[0011] In one embodiment, the rebounding of the door handle includes: during the process of rebounding the door handle, detecting a foreign object state between the door handle and the vehicle body; if the presence of a foreign object between the door handle and the vehicle body is detected, stopping the rebounding of the door handle.

[0012] According to another aspect of the present application, a door handle control device is provided, comprising: a data set acquisition module, used to acquire a data set of a current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; a state information prediction module, used to predict state information of the current vehicle based on the data set of the current vehicle; wherein the state information of the current vehicle includes a normal state and an abnormal state, wherein the abnormal state indicates that the current vehicle has a fault or an accident has occurred and there are passengers in the current vehicle; a door handle execution module, used to pop out the door handle of the current vehicle if the state information of the current vehicle is predicted to be an abnormal state.

[0013] According to another aspect of the present application, a vehicle door is provided, comprising: a door handle; and a control device for the door handle as described above.

[0014] According to another aspect of the present application, a vehicle is provided, comprising: the vehicle door as described above.

[0015] Compared with the prior art, the door handle control method, device, door and vehicle provided by the present application have at least the following beneficial effects: (1) By collecting a data set of the current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; predicting the status information of the current vehicle based on the data set of the current vehicle; wherein the status information of the current vehicle includes a normal state and an abnormal state, wherein the abnormal state indicates that the current vehicle has a fault or an accident has occurred, and there are passengers in the current vehicle; if the status information of the current vehicle is predicted to be an abnormal state, then popping out the door handle of the current vehicle; that is, by collecting the vehicle data and driving behavior data of the current vehicle to predict the status information of the current vehicle, when it is predicted that the status information of the current vehicle has or will be an abnormal state, controlling the door handle to pop out, and by popping out the door handle in advance, the situation where the door handle cannot be popped out due to an abnormal fault can be avoided, and by predicting the abnormal state in advance and responding in advance, the time for the people outside the vehicle to implement rescue can be shortened as much as possible, thereby improving the safety of the people in the vehicle.

[0016] (2) By classifying passengers, the system adjusts the door handle opening method according to the passenger's level information after identifying the passenger's identity information, thereby improving the safety and flexibility of door opening and improving the user experience.

[0017] (3) When the door handle is rebounded, an anti-pinch mechanism is used to prevent foreign objects from being caught in the door handle when it rebounds, causing damage to the door handle and personal injury. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 It is a flowchart of a door handle control method provided by an exemplary embodiment of the present application.

[0020] Figure 2 It is a flowchart of a door handle control method provided by another exemplary embodiment of the present application.

[0021] Figure 3 It is a schematic diagram of the structure of a door handle control device provided by an exemplary embodiment of the present application.

[0022] Figure 4 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] Figure 1 FIG. 1 is a flow chart of a door handle control method provided by an exemplary embodiment of the present application. Figure 1 As shown, the control method of the door handle includes the following steps: Step 110: Collect the data set of the current vehicle.

[0025] Among them, the data set of the current vehicle includes the vehicle data of the current vehicle and the driving behavior data of the current vehicle. Optionally, the vehicle data in this application is the basic information of the vehicle, such as model, year, mileage, maintenance record, sensor data (including but not limited to engine temperature, oil pressure, brake condition, etc.), and the driving behavior data may include the driver's operating habits (including sudden acceleration frequency, sudden braking frequency, etc.), driving speed, driving route, etc. Optionally, the data set in this application may also include environmental factors, historical fault and accident records, wherein environmental factors may include weather conditions, road conditions, traffic density, etc., and historical fault and accident records may include past fault types, occurrence time, solutions and accident records, etc.

[0026] Step 120: Predict the status information of the current vehicle according to the data set of the current vehicle.

[0027] The status information of the current vehicle includes a normal state and an abnormal state. The abnormal state indicates that the current vehicle is faulty or has an accident, and there are passengers in the current vehicle. The present application predicts the status information of the current vehicle based on the data set of the current vehicle. Specifically, based on the data set of the current vehicle at the current moment, the status information of the current vehicle is predicted after a preset time (e.g., 5 seconds) to predict the future state of the current vehicle, so that the current vehicle can be responded to in advance based on the predicted status information of the current vehicle, thereby improving the response speed and efficiency.

[0028] Step 130: If the status information of the current vehicle is predicted to be an abnormal state, the door handle of the current vehicle is popped out.

[0029] When the status information of the current vehicle is predicted to be abnormal, it means that the current vehicle is about to enter an abnormal or faulty state, that is, the current vehicle is about to break down or have an accident, and there are passengers (especially children) in the car. At this time, the door handle of the current vehicle can be popped out to facilitate people outside the car to quickly open the door and implement rescue in advance, thereby minimizing the damage to people in the car.

[0030] In one embodiment, if the current vehicle status information is predicted to be abnormal, the driver or owner is prompted of the impending abnormality or failure while the door handle of the current vehicle is popped up, wherein the prompting method may be to display on the central control screen in the vehicle or light up the corresponding position, or to prompt through a sound alarm, or to send a prompt signal to the owner's remote receiving terminal (such as a car key or mobile phone, etc.). When the current vehicle is predicted to be abnormal or fail, the driver or owner is prompted to remind passengers to intervene in advance for inspection or leave the current vehicle as soon as possible.

[0031] In one embodiment, if the current vehicle status information is predicted to be an abnormal status and the door handle of the current vehicle is popped up N times, and the owner or driver actively clicks to pop it back N times, the door handle of the current vehicle will not be popped up when the abnormal status is predicted later. Wherein, N is an integer greater than 1, for example, N=3.

[0032] The present application provides a door handle control method, which collects a data set of the current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; predicts the status information of the current vehicle based on the data set of the current vehicle; wherein the status information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident has occurred, and there are passengers in the current vehicle; if the status information of the current vehicle is predicted to be an abnormal state, the door handle of the current vehicle is popped out; that is, the vehicle data and driving behavior data of the current vehicle are collected to predict the status information of the current vehicle, and when it is predicted that the status information of the current vehicle has or is about to be an abnormal state, the door handle is controlled to pop out, and the door handle is popped out in advance to avoid the situation where the door handle cannot be popped out due to an abnormal fault, and the abnormal state is predicted in advance and responded in advance, so as to advance the time for people outside the vehicle to implement rescue as early as possible, thereby improving the safety of people in the vehicle.

[0033] In one embodiment, the specific implementation of the above step 120 may be: inputting the data set of the current vehicle into the vehicle state prediction model to obtain the state information of the current vehicle.

[0034] For example, the present application obtains a vehicle state prediction model through training. After collecting the data set of the current vehicle, the data set is input into the vehicle state prediction model to predict the state information of the current vehicle, thereby providing a basis for the subsequent operation of the door handle. Among them, the vehicle state prediction model can be a fault tree. The various types of data in the data set of the current vehicle correspond to the bottom-level events of the fault tree, and the state information of the current vehicle corresponds to the top-level events of the fault tree. The present application can decompose the vehicle failure or accident as an event into a series of bottom-level events (i.e., the generation of various types of abnormal data in the data set). By analyzing the logical relationship between the bottom-level events and the top-level events, the probability of a specific failure or accident occurring can be evaluated according to the abnormal data, that is, the probability of the vehicle abnormality can be determined according to the data set. Optionally, the present application can set a preset probability threshold. When the vehicle state prediction model determines that the probability of the vehicle state information being in an abnormal state is greater than the preset probability threshold, the vehicle state information is determined to be in an abnormal state, and the operation of popping out the door handle is performed at this time. It should be understood that the vehicle state prediction model trained by the present application can select other models, such as a neural network model, according to the needs of the actual application scenario, as long as the selected model can predict the vehicle state according to the vehicle data set. The present application does not limit the specific form and structure of the vehicle state prediction model.

[0035] In one embodiment, the training method of the above-mentioned vehicle state prediction model may be: obtaining training samples; wherein the training samples include vehicle data, driving behavior data and real state information, and the real state information represents the real state of the vehicle corresponding to the vehicle data and driving behavior data; according to the vehicle data, driving behavior data and the initial model, obtaining predicted state information corresponding to the vehicle data and driving behavior data, wherein the initial model represents the vehicle state prediction model before training; adjusting the model parameters of the initial model to reduce the loss between the real state information and the predicted state information, and obtaining the vehicle state prediction model.

[0036] The training samples in this application can come from existing data, such as vehicle data sets registered or managed by traffic management bureaus or insurance companies, or can be collected using test vehicles. The larger the sample size in the data set, the higher the accuracy of the trained vehicle state prediction model.

[0037] After obtaining the training samples, the present application inputs the vehicle data and driving behavior data in the training samples into the initial model to obtain the predicted state information corresponding to the vehicle data and driving behavior data, and calculates the loss between the actual state information and the predicted state information. If the loss is greater than a preset loss threshold, the model parameters of the initial model are adjusted (i.e., the model parameters are iteratively updated) to reduce the loss between the actual state information and the predicted state information, until the loss is less than the preset loss threshold or the preset number of iterations is reached, then the process stops, thereby obtaining a vehicle state prediction model.

[0038] Preferably, after obtaining the training samples, the present application preprocesses the data in the training samples to obtain the preprocessed training samples, and trains the initial model based on the preprocessed training samples to obtain the vehicle state prediction model. The preprocessing process in the present application is described below using the outlier detection algorithm as an example, wherein the outlier detection algorithm may include a statistically based method (e.g., Z-score, box plot), a distance-based method (e.g., KNN, DBSCAN), and a density-based method (e.g., LOF, Isolation Forest). Since there may be some interfering data (such as duplicate data, outliers, etc.) in the initial data, the present application first cleans the initial data during the preprocessing process to remove duplicate data, process missing values, process outliers, etc.; then select features and select the most representative features. The feature selection methods may include filtering, packaging, and embedding. The data is standardized, dimensionally reduced, and normalized. Among them, the standardization method may include z-score standardization, min-max standardization, and decimal calibration standardization. Dimensionality reduction is to reduce the number of features and computational complexity. The dimension reduction method may include principal component analysis (PCA), independent component analysis (ICA), and linear discriminant analysis (LDA). The normalization method may include z-score standardization, min-max standardization, and decimal calibration standardization. Finally, feature extraction is performed to extract the information that best represents the data characteristics. The feature extraction method may include principal component analysis, independent component analysis, and wavelet transform.

[0039] Before training the vehicle status prediction model, this application performs data cleaning, checks whether each variable has missing values, outliers or abnormal values, and evaluates the distribution form of each variable. According to the type of missing values ​​and the way of handling missing values, the missing value handling may cause statistical analysis to be biased, thus resulting in the accuracy of the prediction results. In addition to missing values, the encoding and type of covariates should also be considered. Covariates can be categorical variables, such as the gender of passengers, where each level of the categorical variable must have enough observations. If there are fewer observations at a certain level, the category levels with fewer observations can be merged; covariates can also be continuous variables, such as age and driving years; covariates can also be counted discrete variables, such as the number of accidents or the number of vehicle anomalies / accidents caused by adverse environments, such as heavy rain, heavy snow, strong winds, hail, mountains, steep roads, deep water, etc. This application can use relevant diagnostic codes to identify vehicle data, use the codes of relevant variables to extract covariate information from the data set, and after data cleaning, reclassify the driving behavior type, environment type, and accident condition variables to ensure that there are only a small number of missing values ​​in the data set (for example, the missing value of each variable is <5%), so as to perform complete data analysis.

[0040] In one embodiment, the present application can input the corresponding data set when the vehicle has an abnormal situation or failure into the vehicle state prediction model to obtain vehicle state information. If the predicted vehicle state information is an abnormal state, it means that the vehicle state prediction model has been verified. Otherwise, it means that the vehicle state prediction model has failed. At this time, the vehicle state prediction model is trained again to improve its prediction accuracy.

[0041] Figure 2 FIG. 1 is a flow chart of a door handle control method provided by another exemplary embodiment of the present application. Figure 2 As shown, the above-mentioned door handle control method may further include: Step 140: If the state information of the current vehicle is predicted to be a normal state, and a person feature is detected within a preset range of the door handle of the current vehicle, the identity information corresponding to the person feature is identified.

[0042] When the current vehicle is in a normal state, it is detected that there are human features within the preset range of the door handle of the current vehicle, that is, when someone approaches the door, the identity information corresponding to the human features is identified, where the identity information may include facial images, etc. For example, the current vehicle may be installed with intelligent sensing devices such as infrared sensors to detect the distance and actions of people outside the vehicle in real time. When the infrared sensor detects that the distance between the person and the vehicle is less than a preset threshold, and the person has the action of opening the door, such as the user reaching out to touch the door, the pop-up mechanism of the door handle is triggered. At this time, biometric identification devices such as cameras installed on the current vehicle may be used to identify the identity information of the person, such as using cameras to identify the facial image of the person.

[0043] Step 150: If the identified identity information matches the pre-stored passenger information, the door handle is controlled to perform a corresponding operation.

[0044] If the identity information of the person approaching the door matches the pre-stored passenger (such as the car owner), the door handle is controlled to perform a corresponding operation (such as directly popping out the door handle or popping out the door handle after further collecting other information) to facilitate the passenger to open the door.

[0045] It should be understood that the present application may adopt a key entry mode, that is, when the vehicle senses that the key is within a specific range of the vehicle and detects that there are human features within a preset range of the door (at this time, the identity information of the person can be further identified and matched), the door handle pops out. The present application may also adopt a keyless entry mode, that is, when the vehicle does not sense that the key is within a specific range of the vehicle and detects that there are human features within a preset range of the door, at this time, it is necessary to further identify and match the identity information of the person, and if there is a match, the door handle pops out.

[0046] It should also be understood that the present application can also use other methods to pop out the door handle, such as by identifying the pre-stored passenger's fingerprint, palm print, iris detection, voice command and other information to pop out the door handle. Taking fingerprint recognition as an example, the passenger can press a specific area on the door with the finger that recorded the fingerprint to identify the passenger's fingerprint information, so that the door handle pops out. The present application can also use methods such as pressing a button (setting a button for popping out the door handle in a specific area on the door) and sliding (performing a sliding operation on the central control screen in the car to pop out the door handle) to trigger the pop-up mechanism of the door handle.

[0047] In one embodiment, the specific implementation method of the above step 150 may be: if the identified identity information matches the pre-stored passenger, the level information of the matched passenger is obtained; wherein, passengers of different levels have different ways of opening the door handle; and according to the level information of the matched passenger and the corresponding way of opening the door handle, the door handle is popped out.

[0048] This application classifies passengers. The following uses intimacy value as an example to illustrate the classification method of passengers. For example, the intimacy value of the owner's family (such as direct relatives, spouse) is 90-100 points, the intimacy value of good friends is 80-90 points, the intimacy value of relatives (non-direct relatives) is 70-80 points, the intimacy value of friends is 50-70 points, the intimacy value of colleagues is 20-50 points, and the intimacy value of strangers is 0-20 points. If the owner has not set the intimacy value of the passenger, the passenger can be ranked and scored according to the number of times the passenger has taken the current vehicle to obtain the initial intimacy value of the passenger, wherein there is a corresponding relationship between the number of rides and the intimacy value, for example, if the number of rides exceeds the first preset value (such as 50 times), the corresponding intimacy value is 90-100, and the number of rides exceeds the second preset value (such as 20 times), the corresponding intimacy value is 80-90. Optionally, the owner can also actively set or adjust the intimacy value of the passenger.

[0049] If the identified person's identity information matches the pre-stored passenger information, the level information of the passenger (the level interval of the intimacy value) is further obtained, and the corresponding way to open the door handle is determined according to the level information of the passenger. For example, if the level of the passenger is a family member, the door handle can be popped out directly. For another example, if the level of the passenger is a friend, it is necessary to further detect whether there is a high-level passenger (such as the owner) near the vehicle or whether there is a key signal. If there is a key signal near the vehicle or the owner is also near the vehicle, the door handle can be popped out.

[0050] In one embodiment, the owner of the vehicle in this application can also authorize the owner account to other passengers for use. For example, the owner can inform other passengers of his owner account and corresponding password. Other passengers can enter the owner account and corresponding password in the vehicle opening application installed on the mobile terminal (mobile phone, etc.) to realize a series of operations such as popping out the door handle, opening the door, and driving the vehicle. Preferably, the owner can set the authorization date, time and other information when authorizing the owner account, for example, authorizing a certain passenger to use his vehicle from 8 am to 5 pm today.

[0051] In one embodiment, after step 150, the control method of the door handle may further include: if the vehicle door corresponding to the door handle is not opened within a first preset time, or the vehicle door corresponding to the door handle is opened and then closed again and then not opened within a second preset time, then the door handle is bounced back.

[0052] When the current vehicle is in a normal state, if the door corresponding to the popped-out door handle is not opened within a first preset time (for example, 60 seconds) after the door handle is popped out, it means that the passenger has no need to open the door, and the door handle is bounced back at this time; if the door corresponding to the door handle is opened and not opened within a second preset time (for example, 10 seconds) after being closed again, it means that the passenger has entered the vehicle or left the vehicle after the door corresponding to the door handle was opened, and the door handle can be bounced back at this time.

[0053] In one embodiment, the specific implementation method of the above step 150 can be: in the process of rebounding the door handle, detecting the state of the foreign object between the door handle and the vehicle body; if the presence of the foreign object between the door handle and the vehicle body is detected, stopping rebounding the door handle.

[0054] During the process of the door handle rebounding, it is detected in real time whether there is a foreign object between the door handle and the vehicle body. If there is a foreign object between the door handle and the vehicle body, the door handle is stopped from rebounding or popped out to avoid the foreign object being caught by the door handle when it rebounds. For example, if a passenger is holding the door handle, the passenger may be easily injured if the door handle is rebounded. Specifically, the present application can integrate highly sensitive contact and non-contact sensors, such as infrared sensors, pressure sensors, or Hall effect sensors, around the pop-up path and receiving groove of the door handle to detect in real time whether there is a foreign object around the door handle. If there is a foreign object, the anti-pinch mechanism is triggered (i.e., the door handle is stopped from rebounding or popping out).

[0055] Preferably, if abnormal resistance is detected during the process of rebounding the door handle (e.g., manual intervention by a passenger), the motor power of the door handle is released to allow the door handle to move freely, thereby further improving safety. The motor power of the door handle is restored after a preset time after the abnormal resistance disappears.

[0056] Optionally, the present application may also dynamically adjust the sensitivity of each device (such as the various sensors mentioned above) and the trigger threshold of the anti-pinch mechanism according to the passengers' usage habits and usage environment to meet the needs of different passengers.

[0057] Optionally, the present application can also identify specific users (such as through an RFID tag attached to a keychain) and automatically activate the enhanced child safety lock function to minimize possible misoperation by children.

[0058] Optionally, the present application may also integrate an LED indicator light or display screen near the door handle, or display the working status of the door handle (such as locked, unlocked, anti-pinch protection activated, etc.) in real time on the display screen inside the vehicle, and issue a warning sound when the anti-pinch mechanism is activated to remind passengers to pay attention to safety.

[0059] Optionally, the application can also be connected to a smartphone application through the vehicle network, allowing the owner to remotely control the locking and unlocking status of the door handles. At the same time, the sensor data and anti-pinch event records can be uploaded to the cloud, making it easier for the owner and repair shop to check the vehicle safety status and perform fault diagnosis.

[0060] Figure 3 Schematic diagram of the structure of a door handle control device provided by an exemplary embodiment of the present application. Figure 3 As shown, the door handle control device 30 includes: a data set acquisition module 31, used to acquire a data set of the current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; a state information prediction module 32, used to predict the state information of the current vehicle based on the data set of the current vehicle; wherein the state information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident, and there are passengers in the current vehicle; a door handle execution module 33, used to pop out the door handle of the current vehicle if the state information of the current vehicle is predicted to be an abnormal state.

[0061] The present application provides a door handle control device, which collects a data set of the current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; predicts the status information of the current vehicle based on the data set of the current vehicle; wherein the status information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident has occurred, and there are passengers in the current vehicle; if the status information of the current vehicle is predicted to be an abnormal state, the door handle of the current vehicle is popped out; that is, the vehicle data and driving behavior data of the current vehicle are collected to predict the status information of the current vehicle, and when it is predicted that the status information of the current vehicle has or is about to be an abnormal state, the door handle is controlled to pop out, and the door handle is popped out in advance to avoid the situation where the door handle cannot be popped out due to an abnormal fault, and the abnormal state is predicted in advance and responded in advance, so as to advance the time for people outside the vehicle to implement rescue as early as possible, thereby improving the safety of people in the vehicle.

[0062] In one embodiment, the state information prediction module 32 may be further configured to: input the data set of the current vehicle into the vehicle state prediction model to obtain the state information of the current vehicle.

[0063] In one embodiment, the training method of the above-mentioned vehicle state prediction model may be: obtaining training samples; wherein the training samples include vehicle data, driving behavior data and real state information, and the real state information represents the real state of the vehicle corresponding to the vehicle data and driving behavior data; according to the vehicle data, driving behavior data and the initial model, obtaining predicted state information corresponding to the vehicle data and driving behavior data, wherein the initial model represents the vehicle state prediction model before training; adjusting the model parameters of the initial model to reduce the loss between the real state information and the predicted state information, and obtaining the vehicle state prediction model.

[0064] In one embodiment, the control device 30 of the door handle can be further configured as follows: if it is predicted that the status information of the current vehicle is normal and personal features are detected within a preset range of the door handle of the current vehicle, then the identity information corresponding to the personal features is identified; if the identified identity information matches the pre-stored passenger, then the door handle is controlled to perform the corresponding operation.

[0065] In one embodiment, the control device 30 of the door handle can be further configured as follows: if the identified identity information matches the pre-stored passenger, the level information of the matched passenger is obtained; wherein, passengers of different levels have different ways of opening the door handle; and the door handle is popped out according to the level information of the matched passenger and the corresponding way of opening the door handle.

[0066] In one embodiment, the control device 30 of the door handle can be further configured to bounce back the door handle if the door corresponding to the door handle is not opened within a first preset time, or if the door corresponding to the door handle is opened and then closed again and then not opened within a second preset time.

[0067] In one embodiment, the control device 30 of the door handle can be further configured to: detect the state of foreign matter between the door handle and the vehicle body during the process of rebounding the door handle; if foreign matter is detected between the door handle and the vehicle body, stop rebounding the door handle.

[0068] The present application also provides a vehicle door, comprising: a door handle; and a control device for the door handle as described above.

[0069] The present application provides a vehicle door, which collects a data set of the current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; predicts the status information of the current vehicle based on the data set of the current vehicle; wherein the status information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident has occurred, and there are passengers in the current vehicle; if the status information of the current vehicle is predicted to be an abnormal state, the door handle of the current vehicle is popped out; that is, the vehicle data and driving behavior data of the current vehicle are collected to predict the status information of the current vehicle, and when it is predicted that the status information of the current vehicle has or is about to be an abnormal state, the door handle is controlled to pop out, and the door handle is popped out in advance to avoid the situation where the door handle cannot be popped out due to an abnormal fault, and the abnormal state is predicted in advance and responded in advance, so as to advance the time for people outside the vehicle to implement rescue as early as possible, thereby improving the safety of people in the vehicle.

[0070] The present application also provides a vehicle, comprising: a vehicle door as described above.

[0071] A vehicle provided by the present application collects a data set of the current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; predicts status information of the current vehicle based on the data set of the current vehicle; wherein the status information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident has occurred, and there are passengers in the current vehicle; if the status information of the current vehicle is predicted to be an abnormal state, the door handle of the current vehicle is popped out; that is, the vehicle data and driving behavior data of the current vehicle are collected to predict the status information of the current vehicle, and when it is predicted that the status information of the current vehicle has or is about to be an abnormal state, the door handle is controlled to pop out, and the door handle is popped out in advance to avoid the situation where the door handle cannot be popped out due to an abnormal fault, and the abnormal state is predicted in advance and responded in advance, so as to advance the time for people outside the vehicle to implement rescue as early as possible, thereby improving the safety of people in the vehicle.

[0072] Below, reference Figure 4 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0073] Figure 4 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0074] like Figure 4 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0075] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0076] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0077] In one example, the electronic device 10 may further include: an input device 13 and an output device 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0078] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0079] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0080] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0081] Of course, to simplify, Figure 4 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0082] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0083] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0084] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0085] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0086] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0087] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0088] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0089] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0090] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A door handle control method, characterized in that: include: Collecting a data set of the current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; Predicting the state information of the current vehicle according to the data set of the current vehicle; wherein the state information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident, and there are passengers in the current vehicle; If the state information of the current vehicle is predicted to be an abnormal state, the door handle of the current vehicle is popped out.

2. The door handle control method according to claim 1, characterized in that: The predicting the state information of the current vehicle according to the data set of the current vehicle includes: The data set of the current vehicle is input into a vehicle state prediction model to obtain state information of the current vehicle.

3. The door handle control method according to claim 2, characterized in that: The training method of the vehicle state prediction model includes: Acquire a training sample; wherein the training sample includes vehicle data, driving behavior data and real state information, and the real state information represents the real state of the vehicle corresponding to the vehicle data and the driving behavior data; According to the vehicle data, the driving behavior data and the initial model, obtaining predicted state information corresponding to the vehicle data and the driving behavior data; wherein the initial model represents a vehicle state prediction model before training; The model parameters of the initial model are adjusted to reduce the loss between the real state information and the predicted state information, thereby obtaining the vehicle state prediction model.

4. The door handle control method according to claim 1, characterized in that: The door handle control method further includes: If the state information of the current vehicle is predicted to be a normal state and a person feature is detected within a preset range of the door handle of the current vehicle, identifying the identity information corresponding to the person feature; If the identified identity information matches the pre-stored passenger information, the door handle is controlled to perform a corresponding operation.

5. The door handle control method according to claim 4, characterized in that: If the identified identity information matches the pre-stored passenger, controlling the door handle to perform a corresponding operation includes: If the identified identity information matches the pre-stored passenger, the level information of the matched passenger is obtained; wherein the way of opening the door handle is different for passengers of different levels; The door handle is popped out according to the matched level information of the passenger and the corresponding way of opening the door handle.

6. The door handle control method according to claim 4, characterized in that: After the door handle is popped out, the door handle control method further includes: If the vehicle door corresponding to the door handle is not opened within a first preset time, or if the vehicle door corresponding to the door handle is opened and then closed again and then not opened within a second preset time, the door handle is retracted.

7. The door handle control method according to claim 6, characterized in that: The rebounding of the door handle comprises: In the process of rebounding the door handle, detecting the state of a foreign object between the door handle and the vehicle body; If a foreign object is detected between the door handle and the vehicle body, the door handle is stopped from rebounding.

8. A door handle control device, characterized in that: include: A data set acquisition module, used to acquire a data set of a current vehicle; wherein the data set of the current vehicle includes vehicle data of the current vehicle and driving behavior data of the current vehicle; A state information prediction module, used to predict the state information of the current vehicle according to the data set of the current vehicle; wherein the state information of the current vehicle includes a normal state and an abnormal state, and the abnormal state indicates that the current vehicle has a fault or an accident, and there are passengers in the current vehicle; The door handle execution module is used to pop out the door handle of the current vehicle if the state information of the current vehicle is predicted to be an abnormal state.

9. A vehicle door, characterized in that: include: Door handles; The door handle control device as claimed in claim 8.

10. A vehicle, characterized in that: include: The vehicle door as claimed in claim 9.

Images