Vehicle operation method and device, electronic equipment and storage medium

Abstract

The invention discloses a vehicle operation method and device, electronic equipment and a storage medium. The method comprises the steps that current behavior data of a driver of a vehicle and current vehicle operation data of the vehicle are acquired; inputting the current behavior data and the current vehicle operation data into an intention recognition model to obtain a first user intention and a second user intention output by the intention recognition model; wherein the intention recognition model can determine models of a first user intention and a second user intention, the first user intention is used for representing a driving demand of a driver, and the second user intention is used for representing a driving demand of a vehicle; and determining a to-be-executed task of the vehicle according to the first user intention and the second user intention, and controlling the vehicle to run according to the to-be-executed task to realize the first user intention and the second user intention. According to the scheme, the multiple intentions generated by the user can be obtained, the accuracy of user intention recognition is improved, the user requirements are met, and the use experience of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent vehicle technology, and in particular to a vehicle operation method, device, electronic device and storage medium. Background Art

[0002] With the development of artificial intelligence and the rise of vehicle intelligence, people have higher and higher requirements for vehicles. In addition to the requirements for vehicle safety and comfort, higher requirements are also placed on vehicle intelligence.

[0003] At present, in the on-board systems of existing intelligent vehicles, the user's driving intention is usually identified through preset commands, the user's needs are obtained, and the driving route is planned.

[0004] However, identifying the user's driving intention through preset commands can only obtain one user intention, which cannot adapt to situations where the user has multiple intentions or the driving environment is complex, resulting in poor accuracy in user intention recognition. As a result, when the vehicle is operated according to the determined user intention, the user's needs cannot be met, thereby affecting the user's experience. Summary of the invention

[0005] The present application provides a vehicle operation method, device, electronic device and storage medium to solve the problem that in the prior art, only one user intention can be obtained by identifying the user's driving intention through preset commands, and it is unable to adapt to the situation where the user has multiple intentions or the driving environment is complex, resulting in poor accuracy in user intention recognition, so that when the vehicle is operated according to the determined user intention, the user's needs cannot be met, thereby affecting the user's experience.

[0006] In a first aspect, the present application provides a vehicle operation method, the method comprising:

[0007] Acquiring current behavior data of a driver of a vehicle and current vehicle operation data of the vehicle;

[0008] Inputting the current behavior data and the current vehicle operation data into an intention recognition model to obtain a first user intention and a second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention according to the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving demand of the driver, and the second user intention is used to characterize the driving demand of the vehicle;

[0009] Determine the task to be performed of the vehicle according to the first user intention and the second user intention, and control the vehicle to run according to the task to be performed to achieve the first user intention and the second user intention.

[0010] In a second aspect, the present application provides a vehicle operation device, the device comprising:

[0011] An acquisition module, used to acquire current behavior data of a driver of a vehicle and current vehicle operation data of the vehicle;

[0012] an intention determination module, configured to input the current behavior data and the current vehicle operation data into an intention recognition model, and obtain a first user intention and a second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention based on the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving demand of the driver, and the second user intention is used to characterize the driving demand of the vehicle;

[0013] An operation module is used to determine the task to be performed of the vehicle according to the first user intention and the second user intention, and control the vehicle to run according to the task to be performed to achieve the first user intention and the second user intention.

[0014] In a third aspect, the present application provides an electronic device comprising 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 vehicle operation method as described in any embodiment of the present application is implemented.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle operation method as described in any embodiment of the present application.

[0016] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the vehicle operation method as described in any embodiment of the present application.

[0017] The solution of the present application obtains the current behavior data of the driver of the vehicle and the current vehicle operation data of the vehicle; inputs the current behavior data and the current vehicle operation data into the intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention according to the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving needs of the driver, and the second user intention is used to characterize the driving needs of the vehicle; the task to be performed of the vehicle is determined according to the first user intention and the second user intention, and the vehicle is controlled to run according to the task to be performed to realize the first user intention and the second user intention. That is, the solution of the present application, by inputting the current behavior data and the current vehicle operation data into the intention recognition model, obtains the first user intention characterizing the driving needs, and the second user intention characterizing the driving needs, so that multiple intentions generated by the user can be obtained, which is suitable for situations with complex driving environments, improves the accuracy of user intention recognition, and thus enables the vehicle to meet user needs when running according to the determined user intention, thereby improving the user's experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of the vehicle operation method provided by the present application;

[0020] Figure 2 It is a schematic diagram of the training process of the intention recognition model of the vehicle operation method provided in this application;

[0021] Figure 3 It is a structural schematic diagram of a vehicle operating device provided by the present application;

[0022] Figure 4 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] Figure 1 The present invention provides a flow chart of a vehicle operation method, which can be executed by a vehicle operation device, which can be implemented in software and / or hardware. In a specific embodiment, the device can be applied to an electronic device, which can be a vehicle-mounted terminal. The following embodiments will be described by taking the application of the device in an electronic device as an example, referring to Figure 1 , the method may specifically include the following steps:

[0025] Step 101, obtaining current behavior data of the driver of the vehicle and current vehicle operation data of the vehicle.

[0026] Specifically, the driver's current behavior data refers to data that can represent the driver's driving state, such as the driver's voice data, the driver's facial expression data, and the driver's body temperature data. The vehicle's current vehicle operation data refers to data that can represent the vehicle's driving state, such as the vehicle's speed data, the vehicle's state data, and the smoothness of the vehicle's driving section. For example, the vehicle's state data may include data such as whether the vehicle's tires are leaking, whether the vehicle has safety hazards, and whether the vehicle's air conditioning is turned on. The acquisition of the vehicle's driver's current behavior data and the vehicle's current vehicle operation data can be obtained by the vehicle-mounted terminal that executes this embodiment from a vehicle state detection device and a driver state detection device installed inside the vehicle. The vehicle state detection device may include a vehicle state sensor that can detect the vehicle state, and the driver state detection device may include a camera, a microphone, and a driver state detection sensor.

[0027] Optionally, the current behavior data includes voice data and image data of the driver. The current vehicle operation data includes vehicle state data and driving environment data of the vehicle.

[0028] Specifically, the current behavior data includes the driver's voice data and image data. The voice data includes the voices emitted by the driver and the voices emitted by other passengers. This embodiment can also perform semantic recognition on the voices emitted by the driver and the voices emitted by other passengers, so as to determine the driver's status data. The image data includes the driver's facial data. For example, when the driver is tired, the driver's facial data can indicate that the driver has a high blinking frequency, so as to determine the driver's status data based on the image data. The current vehicle operation data includes the vehicle status data and driving environment data of the vehicle. The vehicle status data includes data such as whether the vehicle tires of the vehicle are leaking, whether the vehicle has safety hazards, whether the vehicle needs to replenish energy, and whether the air conditioning of the vehicle is turned on, so as to indicate whether the vehicle is in a normal driving state. The driving environment data includes data such as the external environment temperature and the smoothness of the vehicle's driving section, so as to determine whether the user needs to rest.

[0029] Step 102 , input the current behavior data and the current vehicle operation data into the intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model.

[0030] Among them, the intention recognition model is a pre-trained model used to determine the first user intention and the second user intention based on current behavior data and current vehicle operation data. The first user intention is used to characterize the driver's driving needs, and the second user intention is used to characterize the vehicle's driving needs.

[0031] Specifically, the current behavior data and the current vehicle operation data are input into the pre-trained intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model. The first user intention is used to characterize the driver's driving needs, and the driving needs may include the destination needs generated during driving and the driver's own state adjustment needs. For example, the voice information in the car expresses that the driver is hungry and needs to eat lunch. At this time, the current behavior data is input into the intention recognition model, and the first user intention can be obtained that the user needs to eat lunch. For example, the image information in the car expresses that the driver sweats a lot and needs to turn on the air conditioner to cool down. At this time, the current behavior data is input into the intention recognition model, and the first user intention can be obtained that the user needs to turn on the air conditioner to cool down. The second user intention is used to characterize the driving needs of the vehicle. For example, the vehicle state detection sensor of the vehicle sends the remaining fuel of the vehicle to the vehicle terminal, and the vehicle terminal inputs the remaining fuel of the vehicle into the intention recognition model, and the second user intention can be obtained that the vehicle needs to be replenished with energy, that is, the vehicle needs to be refueled. If the energy type of the vehicle is other energy types, such as charging vehicles, hydrogen energy vehicles, etc., the energy replenishment method is the replenishment method corresponding to the energy.

[0032] The intent recognition model can be located inside the vehicle terminal or in a cloud server that can interact with the vehicle terminal, and this solution does not limit this. For example, the intent recognition model can be deployed in a cloud server, and the vehicle terminal connects to the cloud server through a request port to obtain the model output result. The intent recognition model can be deployed inside the vehicle terminal, that is, the vehicle terminal itself can complete the output of the model result. The intent recognition model can be deployed in the cloud server and the vehicle terminal at the same time, wherein the training data used in the training process of the intent recognition model deployed by the vehicle terminal is less than the training data used in the training process of the intent recognition model deployed by the cloud server, so that after the data is input, the output result of the intent recognition model of the cloud server can be used to correct the output result of the intent recognition model of the vehicle terminal, thereby strengthening the learning of the intent recognition model of the vehicle terminal to improve the accuracy of intent recognition. After obtaining the first user intention and the second user intention, the intent recognition model can be further corrected according to the accuracy of intent recognition feedback from the user to further improve the accuracy of intent recognition.

[0033] Step 103, determining the to-be-performed task of the vehicle according to the first user intention and the second user intention, and controlling the vehicle to run according to the to-be-performed task to achieve the first user intention and the second user intention.

[0034] Specifically, after obtaining the first user intention and the second user intention, the task to be performed of the vehicle is determined according to the first user intention and the second user intention. The task to be performed is a vehicle operation task that can satisfy the first user intention and the second user intention of the user after execution. For example, the first user intention is that the user needs to take a nap, and the second user intention is that the vehicle needs to stop driving to facilitate the user's nap. Therefore, the task to be performed of the vehicle is to determine the parking location of the vehicle and drive to the parking location, and control the vehicle to stop driving to facilitate the user's nap. After determining the task to be performed, the vehicle is controlled to run according to the task to be performed, that is, the vehicle is controlled to complete the task to be performed, thereby realizing the first user intention and the second user intention of the user.

[0035] Among them, the process of determining the vehicle's tasks to be performed according to the first user intention and the second user intention can also be obtained by a trained deep learning model. For example, the user's first historical user intention, the user's second historical user intention and the vehicle's actual execution tasks are input into the model to be trained to obtain a task determination model that can determine the vehicle's tasks to be performed according to the first user intention and the second user intention. The model training here can be part of the intent recognition model in this embodiment, that is, the intent recognition model directly outputs the tasks to be performed, or it can be another separate model for determining the vehicle's tasks to be performed according to the first user intention and the second user intention.

[0036] Exemplarily, the first user intention is that the user's low mood needs to be relieved, and the second user intention is that the vehicle needs to drive slowly. According to the first user intention and the second user intention, it is determined that the vehicle's pending tasks are to play cheerful songs for the user and control the vehicle to drive slowly. The vehicle is controlled to operate according to the pending tasks, that is, the vehicle is controlled to play cheerful songs for the user and drive slowly, thereby realizing the user's first user intention and the second user intention.

[0037] Optionally, the first user intention includes a first target location, the second user intention includes a second target location, and the task to be performed includes a path to be driven. Determining the task to be performed of the vehicle according to the first user intention and the second user intention can be achieved through steps 1031 to 1032.

[0038] Step 1031, obtain the current position of the vehicle, and determine the distance between the current position of the vehicle and the first target position, the distance between the current position of the vehicle and the second target position, and the distance between the first target position and the second target position based on the current position of the vehicle, the first target position and the second target position.

[0039] Specifically, the first user intent includes a first target position to be reached to achieve the first user intent, and the second user intent includes a second target position to be reached to achieve the second user intent. The current position of the vehicle is obtained, and based on the current position of the vehicle, the first target position, and the second target position, the distance between the current position of the vehicle and the first target position, the distance between the current position of the vehicle and the second target position, and the distance between the first target position and the second target position are determined to avoid the situation where the path to be traveled is not the shortest distance.

[0040] Exemplarily, the first target location is a fast food restaurant, the second target location is a gas station, and it is determined that the distance between the current location of the vehicle and the fast food restaurant is 2 km, the distance between the current location of the vehicle and the gas station is 3 km, and the distance between the fast food restaurant and the gas station is 1 km.

[0041] Step 1032, based on the distance between the vehicle's current position and the first target position, the distance between the vehicle's current position and the second target position, and the distance between the first target position and the second target position, determine the vehicle's path to be traveled, so that the path to be traveled includes the vehicle's current position, the first target position, and the second target position, and the travel distance of the path to be traveled is the shortest distance between the vehicle's current position, the first target position, and the second target position.

[0042] Specifically, according to the distance between the current position of the vehicle and the first target position, the distance between the current position of the vehicle and the second target position, and the distance between the first target position and the second target position, the shortest distance between the current position of the vehicle, the first target position and the second target position is determined, so as to complete the determination of the path to be traveled, so that the path to be traveled includes the current position of the vehicle, the first target position and the second target position, and the path to be traveled is the shortest distance between the current position of the vehicle, the first target position and the second target position. After the path to be traveled of the vehicle is determined, the vehicle can travel along the path to be traveled, which can meet the first user intention and the second user intention. After determining the shortest distance, the path to be traveled can also be corrected according to the degree of smoothness of the road section. For example, when a traffic jam occurs, the path to be traveled is changed to avoid the increase of the driver's driving time due to congestion in the road section.

[0043] Exemplarily, the first target location is a fast food restaurant, and the second target location is a gas station. Based on the fact that the distance between the vehicle's current location and the fast food restaurant is 2 km, the distance between the vehicle's current location and the gas station is 3 km, and the distance between the fast food restaurant and the gas station is 1 km, the path to be traveled is determined, and the path to be traveled is from the current location to the fast food restaurant and then to the gas station.

[0044] Exemplarily, the first user intention is that the user wants to have lunch, and the second user intention is that the vehicle needs to refuel. The first target location is the location where the user can have lunch, and the second target location is the location where the vehicle can refuel. Therefore, the path to be driven is determined according to the current location of the vehicle, the first user intention, and the second user intention, so that the path to be driven includes the location where the user can have lunch and the location where the vehicle can refuel. Among them, the path to be driven including the location information of the user eating lunch and the location information of the vehicle refueling can also be obtained by the trained deep learning model. For example, the historical location information of the vehicle, the map information, the historical dining information of the user, and the historical energy replenishment information of the vehicle are input into the model to be trained, and a model that can determine the path to be driven including the location information of the user eating lunch and the location information of the vehicle refueling according to the location information of the vehicle and the map information is obtained. The model training here can be a part of the intention recognition model in this embodiment, that is, the intention recognition model directly outputs the path to be driven, or it can be another separate model for outputting the path to be driven according to the current location of the vehicle and the map information.

[0045] The solution of the present application obtains the current behavior data of the driver of the vehicle and the current vehicle operation data of the vehicle; inputs the current behavior data and the current vehicle operation data into the intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention according to the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving needs of the driver, and the second user intention is used to characterize the driving needs of the vehicle; the task to be performed of the vehicle is determined according to the first user intention and the second user intention, and the vehicle is controlled to run according to the task to be performed to realize the first user intention and the second user intention. That is, the solution of the present application, by inputting the current behavior data and the current vehicle operation data into the intention recognition model, obtains the first user intention characterizing the driving needs, and the second user intention characterizing the driving needs, so that multiple intentions generated by the user can be obtained, which is suitable for situations with complex driving environments, improves the accuracy of user intention recognition, and thus enables the vehicle to meet user needs when running according to the determined user intention, thereby improving the user's experience.

[0046] Figure 2 is a schematic diagram of the training process of the intention recognition model of the vehicle operation method provided by the present application. Figure 1 Based on the illustrated embodiment and various optional implementation schemes, the training process of the intent recognition model is described in detail. Figure 2 As shown, the method may include the following steps:

[0047] Step 201 : Acquire first historical behavior data of a driver and first historical vehicle operation data of a vehicle.

[0048] Specifically, the first historical behavior data is the behavior data corresponding to the driver in the first time period closest to the current moment, such as the driver's driving habits, the driver's driving behavior, the driver's facial expressions, and the corresponding relationship between the driver's behavior and time, etc. The first historical vehicle operation data of the vehicle is the operation data corresponding to the vehicle in the first time period closest to the current moment, such as the energy replenishment location, etc. The first historical behavior data and the first historical vehicle operation data are preprocessed, such as cleaning and normalizing the data, to make the data easy to use.

[0049] Step 202: determine training behavior data according to the correlation between the first historical behavior data and the historical first user intention and the historical second user intention.

[0050] Specifically, among the multiple behavior data corresponding to the first historical behavior data, the correlation between each behavior data and the historical first user intention and the historical second user intention is determined, and the correlation can be characterized by the correlation. If the correlation between the behavior data and the historical first user intention is less than the preset correlation, it is determined that the behavior data is irrelevant to the first user intention. If the correlation between the behavior data and the historical first user intention is greater than or equal to the preset correlation, it is determined that the behavior data is related to the first user intention, and the behavior data is determined as one of the training behavior data. If the correlation between the behavior data and the historical second user intention is less than the preset correlation, it is determined that the behavior data is irrelevant to the second user intention. If the correlation between the behavior data and the historical second user intention is greater than or equal to the preset correlation, it is determined that the behavior data is related to the second user intention, and the behavior data is determined as one of the training behavior data. For example, if the behavior data is the voice data generated when the driver sings, and the correlation between the data and the historical first user intention and the historical second user intention is less than the preset correlation, it is determined that the data is irrelevant to both the first user intention and the historical second user intention.

[0051] Optionally, step 202 can be implemented through step 2021.

[0052] Step 2021: determine the data in the first historical behavior data, whose correlation with the historical first user intention and the correlation with the historical second user intention both meet the first correlation requirement, as training behavior data.

[0053] Exemplarily, the first correlation requirement is that the correlation between the behavior data and the user intent is greater than or equal to a preset correlation. If the correlation between the user facial data in the first historical behavior data and the historical first user intent and the historical second user intent is greater than the preset correlation, the correlation between the user facial data and the historical first user intent and the historical second user intent meets the first correlation requirement, and thus the user facial data is determined as one of the training behavior data.

[0054] Step 203: Determine training vehicle operation data according to the correlation between the first historical vehicle operation data and the historical second user intention.

[0055] Specifically, among the multiple types of vehicle operation data corresponding to the first historical vehicle operation data, the correlation between each type of vehicle operation data and the historical second user intention is determined, and the correlation can be characterized by a correlation degree. If the correlation between the vehicle operation data and the historical second user intention is less than a preset correlation degree, it is determined that the vehicle operation data is irrelevant to the second user intention. If the correlation between the vehicle operation data and the historical second user intention is greater than or equal to the preset correlation degree, it is determined that the vehicle operation data is related to the second user intention, and at this time, the vehicle operation data is determined as one of the training vehicle operation data. For example, the vehicle operation data is the window opening size, and the correlation between the data and the historical second user intention is less than the preset correlation degree, it is determined that the data is irrelevant to the second user intention.

[0056] Optionally, step 203 may be implemented through step 2031 .

[0057] Step 2031 , determining data whose correlation between the first historical vehicle operation data and the historical second user intention meets the second correlation requirement as training vehicle operation data.

[0058] Exemplarily, the second correlation requirement is that the correlation between the vehicle operation data and the historical second user intent is greater than or equal to a preset correlation. If the correlation between the vehicle fuel quantity data in the first historical vehicle operation data and the historical second user intent is greater than a preset correlation, the vehicle fuel quantity data meets the second correlation requirement, and thus the vehicle fuel quantity data is determined as one of the training vehicle operation data.

[0059] Step 204 , training the model to be trained according to the training behavior data and the training vehicle operation data to obtain an intention recognition model.

[0060] Specifically, the model to be trained is trained according to the training behavior data and the training vehicle operation data to obtain an intention recognition model that can determine the first user intention and the second user intention according to the current behavior data and the current vehicle operation data. The model to be trained can be a deep learning model that combines a long short-term memory network with a convolutional neural network.

[0061] Optionally, step 204 may be implemented through steps 2041 to 2042 .

[0062] Step 2041, input the training behavior data and the training vehicle operation data into the model to be trained, and obtain the first training user intention and the second training user intention output by the model to be trained.

[0063] Specifically, the training behavior data and the training vehicle operation data are input into the model to be trained to obtain the training results output by the model to be trained, namely, the first training user intention and the second training user intention.

[0064] Step 2042, training the model to be trained according to the first training user intention, the second training user intention, the historical first user intention and the historical second user intention until the model to be trained meets the preset training termination condition, thereby obtaining an intent recognition model.

[0065] Specifically, after obtaining the first training user intention and the second training user intention, the model output result is corrected according to the historical first user intention and the historical second user intention until the model to be trained meets the preset training termination conditions, so that the model can learn the user's behavior and preferences until the intent recognition model is obtained. The preset training termination conditions include the number of iterations reaching the preset number of times and the degree of model convergence being greater than the preset degree of convergence. After obtaining the model, the cross-validation method can also be used to evaluate the performance of the model, and the model output results are verified according to the historical first user intention and the historical second user intention, and the model parameters are adjusted according to the verification results, such as the learning rate, the number of layers, the number of neurons, etc. During the training process, regularization techniques can also be used to prevent the model from overfitting.

[0066] Optionally, after step 2042, steps 41 to 44 may also be performed.

[0067] Step 41, calculating the model evaluation parameters of the intent recognition model.

[0068] Specifically, the model evaluation parameters include precision, recall rate, and F1 score, etc. The test set includes test behavior data, test vehicle operation data, test first user intent, and test second user intent. Calculating the model evaluation parameters of the intent recognition model is to calculate the precision, recall rate, and F1 score of the model based on the test set.

[0069] Step 42, determining the accuracy of the intent recognition model based on the model evaluation parameters.

[0070] Specifically, the accuracy of the intent recognition model can be determined based on the model evaluation parameters, and the generalization ability of the intent recognition model can also be determined.

[0071] Step 43 : if the accuracy of the intention recognition model does not meet the preset accuracy requirement, the second historical behavior data of the driver and the second historical vehicle operation data of the vehicle are obtained.

[0072] The second historical behavior data is different from the first historical behavior data, and the second historical vehicle operation data is different from the first historical vehicle operation data.

[0073] Specifically, the preset accuracy requirement is to determine that the accuracy of the intention recognition model is high and can realize user intention recognition. If the accuracy of the intention recognition model does not meet the preset accuracy requirement, it means that the intention recognition model needs further training. At this time, the driver's second historical behavior data and the vehicle's second historical vehicle operation data are obtained. The second historical behavior data is the behavior data corresponding to the driver in the first time period closest to the end time of the first time period. The second historical vehicle operation data is the operation data corresponding to the vehicle in the first time period closest to the end time of the first time period.

[0074] Step 44, use the second historical behavior data as the new first historical behavior data, the second historical vehicle operation data as the new first historical vehicle operation data, and the intention recognition model as the new model to be trained, and return to execute step 202 until the accuracy of the intention recognition model meets the preset accuracy requirement.

[0075] Specifically, the second historical behavior data is used as the new first historical behavior data, the second historical vehicle operation data is used as the new first historical vehicle operation data, and the intention recognition model is used as a new model to be trained. The intention recognition model is further trained until the accuracy of the intention recognition model meets the preset accuracy requirements, thereby improving the accuracy of the model's user intention recognition.

[0076] The solution of this application uses historical behavior data and historical vehicle driving data that are highly correlated with user intent to train the training model, thereby making user intent recognition more accurate. The performance of the trained model is evaluated, and the model is further trained when the evaluation does not meet the accuracy requirements, further improving the accuracy of the model's user intent recognition, thereby further improving the user experience.

[0077] Figure 3 is a structural schematic diagram of a vehicle operation device provided by the present application, and the device is suitable for executing the vehicle operation method provided by the present application. Figure 3 As shown, the device may specifically include:

[0078] The acquisition module 301 is used to acquire the current behavior data of the driver of the vehicle and the current vehicle operation data of the vehicle.

[0079] The intention determination module 302 is used to input the current behavior data and the current vehicle operation data into the intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention based on the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving needs of the driver, and the second user intention is used to characterize the driving needs of the vehicle.

[0080] The operation module 303 is used to determine the task to be performed of the vehicle according to the first user intention and the second user intention, and control the vehicle to run according to the task to be performed to achieve the first user intention and the second user intention.

[0081] In one embodiment, the intention recognition model of the intention determination module 302 is obtained by training with a model training module, and the model training module is specifically used to: obtain the first historical behavior data of the driver and the first historical vehicle operation data of the vehicle; determine the training behavior data based on the correlation between the first historical behavior data and the historical first user intention and the historical second user intention; determine the training vehicle operation data based on the correlation between the first historical vehicle operation data and the historical second user intention; train the model to be trained based on the training behavior data and the training vehicle operation data to obtain the intention recognition model.

[0082] In one embodiment, the model training module, in determining the training behavior data based on the correlation between the first historical behavior data and the historical first user intention and the historical second user intention, is specifically used to: determine the data in the first historical behavior data whose correlation with the historical first user intention and the correlation with the historical second user intention both meet the first correlation requirement as the training behavior data; determining the training vehicle operation data based on the correlation between the first historical vehicle operation data and the historical second user intention includes: determining the data whose correlation with the historical second user intention meets the second correlation requirement as the training vehicle operation data.

[0083] In one embodiment, the model training module is specifically used for training the model to be trained according to the training behavior data and the training vehicle operation data to obtain the intention recognition model. The model training module is specifically used for: inputting the training behavior data and the training vehicle operation data into the model to be trained to obtain the first training user intention and the second training user intention output by the model to be trained; training the model to be trained according to the first training user intention, the second training user intention, the historical first user intention and the historical second user intention until the model to be trained meets the preset training termination condition to obtain the intention recognition model.

[0084] In one embodiment, the model training module is also used to: after obtaining the intention recognition model, calculate the model evaluation parameters of the intention recognition model; determine the accuracy of the intention recognition model based on the model evaluation parameters; if the accuracy of the intention recognition model does not meet the preset accuracy requirements, obtain the second historical behavior data of the driver and the second historical vehicle operation data of the vehicle; wherein the second historical behavior data is different from the first historical behavior data, and the second historical vehicle operation data is different from the first historical vehicle operation data; use the second historical behavior data as the new first historical behavior data, the second historical vehicle operation data as the new first historical vehicle operation data, and the intention recognition model as the new model to be trained, and return to execute the step of "determining the training behavior data based on the correlation between the first historical behavior data and the historical first user intention and the historical second user intention" until the accuracy of the intention recognition model meets the preset accuracy requirements.

[0085] In one embodiment, the current behavior data acquired by the acquisition module 301 includes the voice data and image data of the driver; the current vehicle operation data includes the vehicle status data and driving environment data of the vehicle.

[0086] In one embodiment, the first user intention of the operation module 303 includes a first target position, the second user intention includes a second target position, and the task to be performed includes a path to be traveled. The operation module 303, in terms of determining the task to be performed of the vehicle according to the first user intention and the second user intention, is specifically used to: obtain the current position of the vehicle, and determine the distance between the current position of the vehicle and the first target position, the distance between the current position of the vehicle and the second target position, and the distance between the first target position and the second target position according to the current position of the vehicle, the first target position, and the second target position; determine the path to be traveled of the vehicle according to the distance between the current position of the vehicle and the first target position, the distance between the current position of the vehicle and the second target position, and the distance between the first target position and the second target position, so that the path to be traveled includes the current position of the vehicle, the first target position, and the second target position, and the travel distance of the path to be traveled is the shortest distance between the current position of the vehicle, the first target position, and the second target position.

[0087] The device of the present application obtains the current behavior data of the driver of the vehicle and the current vehicle operation data of the vehicle; inputs the current behavior data and the current vehicle operation data into the intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention according to the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving needs of the driver, and the second user intention is used to characterize the driving needs of the vehicle; the task to be performed of the vehicle is determined according to the first user intention and the second user intention, and the vehicle is controlled to run according to the task to be performed to realize the first user intention and the second user intention. That is, the scheme of the present application, by inputting the current behavior data and the current vehicle operation data into the intention recognition model, obtains the first user intention characterizing the driving needs, and the second user intention characterizing the driving needs, so that multiple intentions generated by the user can be obtained, which is suitable for situations with complex driving environments, improves the accuracy of user intention recognition, and thus enables the vehicle to meet user needs when running according to the determined user intention, thereby improving the user's experience.

[0088] 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 vehicle operation method provided in any of the above embodiments is implemented.

[0089] The present application also provides a computer-readable medium having a computer program stored thereon, and when the program is executed by a processor, the vehicle operation method provided in any of the above embodiments is implemented.

[0090] Reference below Figure 4 , which shows a structural schematic diagram of an electronic device 400 suitable for implementing the present application. Figure 4 The electronic device shown is only an example and should not bring any limitation to the function and scope of use of the present application.

[0091] like Figure 4 As shown, the electronic device 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The CPU 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0092] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0093] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the system of the present application are executed.

[0094] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0095] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0096] The modules and / or units described in this application may be implemented in software or hardware. The modules and / or units described may also be provided in a processor, for example, may be described as: a processor including an acquisition module, an intent determination module, and an operation module. The names of these modules do not, in some cases, constitute limitations on the modules themselves.

[0097] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device performs the following operations:

[0098] Acquire the current behavior data of the driver of the vehicle and the current vehicle operation data of the vehicle; input the current behavior data and the current vehicle operation data into the intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention according to the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving needs of the driver, and the second user intention is used to characterize the driving needs of the vehicle; determine the tasks to be performed of the vehicle according to the first user intention and the second user intention, and control the vehicle to run according to the tasks to be performed to realize the first user intention and the second user intention.

[0099] According to the technical solution of the present application, the current behavior data of the driver of the vehicle and the current vehicle operation data of the vehicle are obtained; the current behavior data and the current vehicle operation data are input into the intention recognition model to obtain the first user intention and the second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention according to the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving needs of the driver, and the second user intention is used to characterize the driving needs of the vehicle; the task to be performed of the vehicle is determined according to the first user intention and the second user intention, and the vehicle is controlled to run according to the task to be performed to realize the first user intention and the second user intention. That is, the solution of the present application, by inputting the current behavior data and the current vehicle operation data into the intention recognition model, obtains the first user intention characterizing the driving needs, and the second user intention characterizing the driving needs, so that multiple intentions generated by the user can be obtained, which is suitable for situations with complex driving environments, improves the accuracy of user intention recognition, and thus enables the vehicle to meet user needs when running according to the determined user intention, thereby improving the user's experience.

[0100] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements a vehicle operation method as provided in any embodiment of the present application.

[0101] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present application, and the programming language includes an object-oriented programming language, such as Java, Smalltalk, C++, and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0102] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0103] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A vehicle operation method, characterized in that: The method comprises: Acquiring current behavior data of a driver of a vehicle and current vehicle operation data of the vehicle; Inputting the current behavior data and the current vehicle operation data into an intention recognition model to obtain a first user intention and a second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention according to the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving demand of the driver, and the second user intention is used to characterize the driving demand of the vehicle; Determine the task to be performed of the vehicle according to the first user intention and the second user intention, and control the vehicle to run according to the task to be performed to achieve the first user intention and the second user intention.

2. The method according to claim 1, characterized in that: The intent recognition model is trained by the following method: Acquiring first historical behavior data of the driver and first historical vehicle operation data of the vehicle; Determining training behavior data according to the correlation between the first historical behavior data and the historical first user intention and the historical second user intention; Determining training vehicle operation data according to the correlation between the first historical vehicle operation data and the historical second user intention; The model to be trained is trained according to the training behavior data and the training vehicle operation data to obtain the intention recognition model.

3. The method according to claim 2, characterized in that The determining of the training behavior data according to the correlation between the first historical behavior data and the historical first user intention and the historical second user intention includes: Determine, in the first historical behavior data, data whose correlation with the historical first user intention and whose correlation with the historical second user intention both meet the first correlation requirement as the training behavior data; The determining of the training vehicle operation data according to the correlation between the first historical vehicle operation data and the historical second user intention includes: The data whose correlation with the first historical vehicle operation data and the historical second user intention meets the second correlation requirement is determined as the training vehicle operation data.

4. The method according to claim 2, characterized in that: The step of training the model to be trained according to the training behavior data and the training vehicle operation data to obtain the intention recognition model includes: Inputting the training behavior data and the training vehicle operation data into the model to be trained, and obtaining a first training user intention and a second training user intention output by the model to be trained; The model to be trained is trained according to the first training user intention, the second training user intention, the historical first user intention and the historical second user intention until the model to be trained meets a preset training termination condition, thereby obtaining the intention recognition model.

5. The method according to claim 4, characterized in that After obtaining the intention recognition model, the method further includes: Calculating model evaluation parameters of the intent recognition model; Determining the accuracy of the intent recognition model based on the model evaluation parameters; If the accuracy of the intention recognition model does not meet the preset accuracy requirement, obtaining second historical behavior data of the driver and second historical vehicle operation data of the vehicle; wherein the second historical behavior data is different from the first historical behavior data, and the second historical vehicle operation data is different from the first historical vehicle operation data; Use the second historical behavior data as the new first historical behavior data, the second historical vehicle operation data as the new first historical vehicle operation data, and the intention recognition model as the new model to be trained, and return to execute the step of "determining the training behavior data based on the correlation between the first historical behavior data and the historical first user intention and the historical second user intention" until the accuracy of the intention recognition model meets the preset accuracy requirement.

6. The method according to claim 1, characterized in that The current behavior data includes voice data and image data of the driver; The current vehicle operation data includes vehicle status data and driving environment data of the vehicle.

7. The method according to claim 1, characterized in that The first user intention includes a first target location, the second user intention includes a second target location, the task to be performed includes a path to be driven, and determining the task to be performed of the vehicle according to the first user intention and the second user intention includes: Acquire the current position of the vehicle, and determine the distance between the current position of the vehicle and the first target position, the distance between the current position of the vehicle and the second target position, and the distance between the first target position and the second target position according to the current position of the vehicle, the first target position, and the second target position; Based on the distance between the vehicle's current position and the first target position, the distance between the vehicle's current position and the second target position, and the distance between the first target position and the second target position, the path to be traveled of the vehicle is determined, so that the path to be traveled includes the vehicle's current position, the first target position, and the second target position, and the travel distance of the path to be traveled is the shortest distance between the vehicle's current position, the first target position, and the second target position.

8. A vehicle running device, characterized in that: The device comprises: An acquisition module, used to acquire current behavior data of a driver of a vehicle and current vehicle operation data of the vehicle; an intention determination module, configured to input the current behavior data and the current vehicle operation data into an intention recognition model, and obtain a first user intention and a second user intention output by the intention recognition model; wherein the intention recognition model is a pre-trained model for determining the first user intention and the second user intention based on the current behavior data and the current vehicle operation data, the first user intention is used to characterize the driving demand of the driver, and the second user intention is used to characterize the driving demand of the vehicle; An operation module is used to determine the task to be performed of the vehicle according to the first user intention and the second user intention, and control the vehicle to run according to the task to be performed to achieve the first user intention and the second user intention.

9. An electronic device comprising 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 vehicle operation method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the vehicle operation method as claimed in any one of claims 1 to 7 is implemented.

Images