Push method, device and electronic device for driving training guidance

Abstract

The present application discloses a method, device and electronic device for pushing driving training guidance, which relates to the field of computer technology, and in particular to artificial intelligence fields such as intelligent driving and large models. The specific scheme is: obtaining questions of the target object collected in the driving training mode; identifying the questions and determining the correlation between the questions and the current practice scene of the vehicle; in response to the correlation being related, obtaining the vehicle's status information and driving environment information; determining the driving training guidance response corresponding to the question based on the question, status information and driving environment information; and pushing the driving training guidance response to the target object. During the driving training process, for questions related to the current practice scene, a driving training guidance response can be provided to the target object based on the question, the vehicle's status information and the driving environment information, thereby ensuring the quality of the driving training guidance response and enabling the target object to learn driving skills independently, thus realizing the intelligence of driving training and reducing labor costs.

Description

Technical Field

[0001] The present application relates to the field of computer technology, in particular to artificial intelligence fields such as intelligent driving and large models, and specifically to a method, device and electronic device for pushing driving training guidance. Background Art

[0002] As vehicles become increasingly popular, driving a vehicle has gradually become a necessary life skill for modern people. In related technologies, users who need driving training mainly conduct driving training and learn driving skills under the guidance of a human coach. Summary of the Invention

[0003] This application provides a method, device, and electronic device for pushing driving training guidance. The specific solution is as follows:

[0004] According to one aspect of the present application, a method for pushing a driving training guide is provided, comprising:

[0005] The problem of obtaining target objects collected in driving training mode;

[0006] Identify the problem and determine its correlation with the vehicle's current practice scenario;

[0007] In response to the association relationship being relevant, acquiring vehicle status information and driving environment information;

[0008] Determine the driving training guidance response corresponding to the question based on the question, status information and driving environment information;

[0009] Push driving training guidance responses to the target audience.

[0010] According to another aspect of the present application, a driving training guide push device is provided, comprising:

[0011] A first acquisition module is used to acquire questions of the target object collected in the driving training mode;

[0012] An identification module, for identifying the problem and determining the correlation between the problem and the current practice scenario of the vehicle;

[0013] a second acquisition module, configured to acquire the vehicle status information and the driving environment information in response to the association being related;

[0014] A first determination module is used to determine a driving training guidance response corresponding to the question based on the question, state information and driving environment information;

[0015] The push module is used to push driving training guidance replies to the target object.

[0016] According to another aspect of the present application, an electronic device is provided, including:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the above embodiment.

[0020] According to another aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method according to the above embodiment.

[0021] According to another aspect of the present application, a computer program product is provided, including a computer program, which implements the steps of the method described in the above embodiment when executed by a processor.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present application.

[0024] Figure 1 A flowchart of a method for delivering driving training guidance provided in one embodiment of the present application;

[0025] Figure 2 A flowchart of a method for pushing driving training guidance provided in another embodiment of the present application;

[0026] Figure 3 A flowchart of a method for pushing driving training guidance provided in another embodiment of the present application;

[0027] Figure 4 A schematic diagram of a training route determination process provided in an embodiment of the present application;

[0028] Figure 5 A flowchart of a method for pushing driving training guidance provided in another embodiment of the present application;

[0029] Figure 6 A schematic diagram of a driving training process provided in an embodiment of the present application;

[0030] Figure 7A schematic diagram of the structure of a driving training guidance push device provided in one embodiment of the present application;

[0031] Figure 8 4 is a block diagram of an electronic device used to implement the method for pushing driving training guidance in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following description of exemplary embodiments of the present application is made in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0033] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0034] In the related art, users who need driving training mainly receive driving training and learn driving skills under the guidance of a human instructor. However, this driving training method cannot meet the user's personalized driving training needs and is also relatively costly.

[0035] The following describes the method, device, electronic device, and storage medium for pushing driving training guidance according to embodiments of the present application with reference to the accompanying drawings.

[0036] Figure 1 A flowchart of a method for pushing driving training guidance provided in one embodiment of the present application.

[0037] The method for pushing driving training guidance in the embodiment of the present application can be executed by the device for pushing driving training guidance in the embodiment of the present application. The device can be configured in an electronic device to provide the target object with driving training guidance responses based on the vehicle's status information and driving environment information for questions related to the current practice scenario raised by the target object during the driving training process, thereby ensuring the quality of the driving training guidance responses, enabling the target object to learn driving skills independently, meeting the personalized driving training needs of different target objects, and saving labor costs.

[0038] The target object may refer to a user who is undergoing driving training.

[0039] Among them, the electronic device can be any device with computing capabilities, such as a personal computer, mobile terminal, server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and other hardware devices with various operating systems, touch screens and / or display screens.

[0040] like Figure 1 As shown, the method for pushing the driving training guidance includes:

[0041] Step 101: Obtain questions of a target object collected in a driving training mode.

[0042] In this application, the target person can wake up the human-computer interaction system on the vehicle by using a wake-up word and then, by saying "start driving training," awaken the intelligent virtual coach and start the driving training mode. After entering the driving training mode, the target person can first determine the training route and drive the vehicle along the training route.

[0043] For example, the target object can input the target location in the navigation application, and one or more routes are planned based on the target location input by the target object and the current location of the vehicle. If there are multiple routes, the target object can select one of the routes as the training route.

[0044] In this application, in the driving training mode, the target subject can ask questions, and the voice collection device on the vehicle can collect the target subject's questions, thereby obtaining the target subject's questions collected by the vehicle in the driving training mode. The target subject's questions may be related to the driving training or may not be related to the driving training.

[0045] Step 102 : Identify the problem and determine the correlation between the problem and the current practice scenario of the vehicle.

[0046] In driving training, the target subjects need to practice multiple practice scenarios, including but not limited to traffic light straight-through scenarios, lane change scenarios, left-turn scenarios, right-turn scenarios, overtaking scenarios, etc.

[0047] In this application, a training route may include one or more practice scenarios, and different training routes may include the same or different practice scenarios.

[0048] In this application, the problem of the target object and the current practice scene information of the vehicle can be input into the recognition model, and the problem can be identified by the recognition model to determine the correlation between the problem of the target object and the current practice scene of the vehicle.

[0049] Optionally, the question of the target object may be matched with the current practice scenario to determine the association relationship between the question and the current practice scenario based on the matching degree between the question and the current practice scenario.

[0050] Step 103 : In response to the association being related, obtaining the vehicle status information and driving environment information.

[0051] In this application, if the problem of the target object is related to the current practice scenario, the current vehicle status information and driving environment information can be obtained through the map server, sensors on the vehicle, etc.

[0052] The vehicle's status information may include, but is not limited to, the vehicle's driving status information and the control status of target devices on the vehicle. For example, the driving status information may include, but is not limited to, the vehicle's location information, driving speed, acceleration, the distance between the vehicle and the vehicles ahead and behind it, and the lane the vehicle is in. For example, target devices may include, but are not limited to, the steering wheel, vehicle gear position, accelerator pedal, brake pedal, and headlights. The control status of target devices may include, for example, the on / off status of the high beam, the on / off status of the right turn signal, the on / off status of the left turn signal, the steering wheel's rotation direction and angle, the accelerator pedal's opening, the brake pedal's opening, and the like.

[0053] Among them, the vehicle's driving environment information may include but is not limited to the number of lanes on the road section where the vehicle is located, the speed limit on the road section where the vehicle is located, the height limit on the road section where the vehicle is located, the traffic light information at the intersection ahead of the vehicle, and the traffic sign information at the intersection ahead of the vehicle (such as a sign restricting right turns when the light is red).

[0054] Step 104 : Determine a driving training guidance response corresponding to the question based on the question, the status information, and the driving environment information.

[0055] This application can identify the type of question, determine the question type, and then determine a response strategy that matches the question type. Using this response strategy, the application can determine a driving training guidance response based on state information and driving environment information. Question types can include judgment-type, solution-type, and mixed-type. Mixed-type refers to a question that contains multiple question types, such as a question that includes both judgment-type and solution-type questions.

[0056] For judgment questions, the vehicle's status information, driving environment information, and other information can be matched with the question to determine the judgment result. For example, if the current training scenario is a right turn scenario and the question is "Can I turn right directly at the intersection ahead?", the traffic light information at the intersection ahead shows that the traffic light is green and there is no sign prohibiting right turns. Based on the traffic light information at the intersection ahead, it can be determined that the vehicle can turn right directly.

[0057] For answer-type questions, the knowledge base can be queried based on the target object's question, the vehicle's status information, and the driving environment information to obtain the driving training guidance answer corresponding to the question.

[0058] For mixed-type questions, a large model can be used to generate a corresponding driving training guidance response based on the vehicle's state information and driving environment information. Alternatively, for judgment-type questions and answer-type questions, a large model can also be used to process and generate driving training guidance responses. As an implementation method, the large model can be a general large model that can obtain prompt information. The prompt information, the target object's question, the vehicle's state information, and the driving environment information are input into the large model for processing to generate a corresponding driving training guidance response. The prompt information can be used to instruct the large model to perform the task of generating a driving training guidance response. Thus, by instructing the general large model to perform the task of generating a driving training guidance response through the prompt information, the general large model can be used to generate a driving training guidance response, thereby improving the accuracy of the training guidance response.

[0059] As another implementation, the large model can be a driving domain large model. Questions, vehicle status information, and driving environment information can be fed into the large model for processing, generating driving training guidance responses corresponding to the questions. The driving domain large model can be fine-tuned by supervising an initial large model using a driving test question bank, driving Q&A from a search engine, and so on.

[0060] Optionally, if the relationship between the target object's question and the current practice scenario is irrelevant, the field to which the question belongs can be identified. If the field to which the question belongs is the driving field, the driving question and answer library can be queried to determine the driving training guidance answer to the question.

[0061] Alternatively, if the target subject's question is unrelated to the current practice scenario and pertains to driving, the large model can be used to process the question and generate a corresponding driving training guidance response. Exemplarily, the large model is a general large model that can receive prompt information, where the prompt information instructs the large model to execute the task of generating a driving training guidance response. The prompt information and question are then input into the large model for processing, generating a corresponding driving training guidance response. Exemplarily, the large model can be a driving domain large model that can input the question into the large model for processing, generating a corresponding driving training guidance response.

[0062] Therefore, if the target object's question is unrelated to the current practice scenario and the field to which the question belongs is the driving field, there is no need to obtain the vehicle's status information and driving environment information. The large model can be used to directly process the question and generate driving training guidance responses, which not only saves resources but also improves the accuracy of the responses.

[0063] Optionally, if the relationship between the target object's question and the current practice scenario is irrelevant, a prompt message for focusing on the current practice scenario may be pushed to the target object.

[0064] Alternatively, if the target user's question is about a non-driving area, a prompt message to focus on driving training can be pushed to the target user. For example, if the target user's question is "What's the weather like today?", a prompt message "Please focus on driving training" can be pushed to the target user.

[0065] Therefore, if the problem of the target subject is not related to driving, the target subject can be reminded to focus on driving training, thereby reducing the probability of dangerous situations occurring during driving training and improving safety during driving training.

[0066] Alternatively, if the target user's question is not about driving, a response can be determined, thereby providing answers to various questions. For example, if the target user asks "What's the weather like today?", the response could be "It's sunny today, with a temperature between 18 and 25 degrees Celsius."

[0067] Step 105: Push the driving training guidance reply to the target object.

[0068] In this application, the driving training guidance reply can be played by voice, or the driving training guidance reply can be displayed in text on the vehicle screen while the driving training guidance reply is played by voice, or the driving training guidance animation can be displayed on the vehicle screen while the driving training guidance reply is played by voice, etc.

[0069] In an embodiment of the present application, questions collected by the target subject during the driving training mode can be obtained and identified to determine the correlation between the question and the current practice scenario. If the question is relevant to the current practice scenario, the vehicle's status information and driving environment information are obtained. Based on the question, the vehicle's status information and driving environment information, a driving training guidance response is determined and pushed to the target subject. Thus, during the driving training process, the target subject's questions can be collected. For questions related to the current practice scenario, a driving training guidance response can be provided to the target subject based on the question, the vehicle's status information and the driving environment information. This ensures the quality of the driving training guidance response, enables the target subject to autonomously learn driving skills, realizes intelligent driving training, and reduces labor costs.

[0070] In some embodiments of the present application, questions of the target object collected in the driving training mode can be obtained, the questions can be identified, and the correlation between the questions and the current practice scene of the vehicle can be determined. In response to the correlation being relevant, the vehicle's status information and driving information can be obtained. Based on the question, status information and driving environment information, the driving training guidance reply corresponding to the question can be determined, and the driving training guidance reply can be pushed to the target object. Or, in response to the correlation being irrelevant, the field to which the question belongs can be determined. If the field to which the question belongs is the driving field, prompt information can be obtained, and the prompt information and the question can be input into the large model for processing. The driving training guidance reply corresponding to the question is generated, and the driving training guidance reply can be pushed to the target object. Or, in response to the correlation being irrelevant, prompt information focusing on the current practice scene can be pushed to the target object.

[0071] Figure 2 A flowchart of a method for pushing driving training guidance provided in another embodiment of the present application.

[0072] like Figure 2 As shown, the method for pushing the driving training guidance includes:

[0073] Step 201: Obtain questions of a target object collected in a driving training mode.

[0074] Step 202 : Identify the problem and determine the correlation between the problem and the current practice scenario of the vehicle; wherein the current practice scenario is a lane change scenario.

[0075] In the present application, steps 201 to 202 may be implemented in any of the embodiments of the present application, and are not limited thereto and will not be described in detail.

[0076] Step 203: In response to the association being related, the vehicle status information and driving environment information are acquired.

[0077] In this application, step 203 can be implemented in any of the embodiments of this application, which is not limited and will not be described in detail.

[0078] Step 204 : determining a driving training guidance response based on the driving state information of the vehicle in the state information and the vehicle information of the lane to be entered in the driving environment information.

[0079] In this application, if the current practice scenario of the vehicle is a lane change scenario, the driving training guidance response can be determined based on the vehicle's driving status information in the vehicle's status information and the vehicle information on the lane the vehicle is to enter in the driving environment information.

[0080] The vehicle's driving status information includes, but is not limited to, the vehicle's driving speed, the vehicle's acceleration, the distance between the vehicle and the vehicles ahead and behind it, the lane the vehicle is in, and other information.

[0081] The vehicle information on the lane to be entered by the vehicle includes but is not limited to the number of vehicles in the lane to be entered by the vehicle, the distance between vehicles, and other information.

[0082] The driving training guidance response may include but is not limited to the vehicle's lane change timing, whether the lane change timing has been reached, the reasons for reaching or not reaching the lane change timing, lane change operation guidance, etc.

[0083] For example, the target object's question is "Can I change lanes to the right now? What is the reason?" It can be seen that the lane the vehicle is about to enter is the right lane of the lane where the vehicle is currently located. Based on the vehicle's driving status information and the vehicle information on the right lane, it can be judged whether the vehicle can currently change lanes to the right. If it cannot change lanes to the right, the reason for not being able to change lanes to the right is determined, such as the vehicles on the right lane are relatively dense or the lane lines on both sides of the lane where the vehicle is located are solid lines and cannot change lanes.

[0084] For example, if the target object's question is "How do I change lanes to the right?", I can first determine whether I can change lanes to the right based on the distance between my vehicle and the vehicle in front, the information of vehicles in the right lane, etc. If I cannot change lanes to the right, I can determine the reason why I cannot change lanes to the right. If I can change lanes to the right, I can provide instructions for changing lanes to the right, such as turning on the right turn signal, observing the rearview mirror to confirm that it does not affect the driving of other vehicles, and then gently turning the steering wheel to the right to drive the vehicle into the right lane.

[0085] Step 205: Push the driving training guidance reply to the target object.

[0086] In the present application, step 205 may be implemented in any of the embodiments of the present application, which is not limited and will not be described in detail.

[0087] In an embodiment of the present application, when the current practice scenario is a lane change scenario and the question is related to the lane change scenario, the driving training guidance response can be determined based on the vehicle's driving status information and the vehicle information on the lane to be entered by the vehicle, thereby providing the target object with a driving training guidance response for the lane change scenario.

[0088] In some embodiments of the present application, if the current practice scenario is a right turn scenario, and the question is related to the right turn scenario, the driving training guidance response can be determined based on the vehicle's driving status information in the vehicle's status information and the traffic light information and traffic sign information at the intersection ahead in the driving environment information.

[0089] The vehicle's driving status information includes, but is not limited to, the vehicle's driving speed, the vehicle's acceleration, the distance between the vehicle and the vehicles ahead and behind it, the distance between the vehicle and the intersection ahead, the lane the vehicle is in, and other information.

[0090] Among them, the traffic light information at the intersection ahead includes whether there is a right turn indicator light at the intersection ahead, whether the right turn indicator light has a countdown, the duration of the right turn indicator light, etc.

[0091] Among them, traffic sign information includes whether there is a no-right-turn sign, whether there is a no-right-turn-on-red sign, etc.

[0092] The driving training guidance response may include but is not limited to the right turn timing of the vehicle, whether the vehicle has reached the right turn timing, the reason for reaching or not reaching the right turn timing, right turn operation guidance, etc.

[0093] For example, if the target question is "How do I turn right?", the driver can first determine whether a right turn is possible at the intersection ahead based on the vehicle's driving status, the red light at the intersection ahead, and the traffic signs at the intersection ahead. If not, the driver can determine the reason why the right turn is not possible. If the right turn is possible, the driver can then provide instructions for the right turn. For example, the instructions for the right turn might include turning on the right turn signal, slowing down in the right turn lane, turning the steering wheel right to enter the target lane when the right turn signal is green, and then turning off the right turn signal.

[0094] In an embodiment of the present application, when the current practice scenario is a right-turn scenario and the question is related to the right-turn scenario, the driving training guidance response related to the right-turn scenario can be determined based on the vehicle's driving status information, the traffic light information at the intersection ahead, the traffic sign information at the intersection ahead, etc., thereby providing the target object with a driving training guidance response for the right-turn scenario.

[0095] In some embodiments of the present application, if the current practice scenario is an overtaking scenario, and the question is related to the overtaking scenario, the driving training guidance response can be determined based on the vehicle's driving status information and the control status information of the target device on the vehicle in the vehicle's status information, as well as the vehicle information of the left lane of the vehicle in the driving environment information.

[0096] The vehicle's driving status information includes, but is not limited to, the vehicle's driving speed, the vehicle's acceleration, the distance between the vehicle and the vehicles ahead and behind it, the distance between the vehicle and the intersection ahead, the lane the vehicle is in, and other information.

[0097] Among them, the control status information of the target device on the vehicle may include but is not limited to the switch status of the left turn signal, the switch status of the right turn signal, the rotation direction and rotation angle of the steering wheel, the opening of the accelerator pedal, the opening of the brake pedal, etc.

[0098] The vehicle information on the left lane of the vehicle includes but is not limited to the number of vehicles on the left lane, the distance between vehicles on the left lane, and other information.

[0099] The driving training guidance response may include but is not limited to the vehicle's overtaking timing, whether the vehicle has reached the overtaking timing, the reasons for reaching or not reaching the overtaking timing, overtaking operation guidance, etc.

[0100] For example, if the target object's question is "How to overtake?", you can first determine whether overtaking is currently possible based on the vehicle's driving status information, the control status information of the target device on the vehicle, the vehicle information in the vehicle's left lane, etc. If overtaking is not possible, determine the reason for not overtaking. If overtaking is currently possible, determine the overtaking operation instructions.

[0101] For example, the overtaking operation instructions include turning on the left turn signal, clearly seeing from the left rearview mirror that the distance between the vehicle behind in the left lane and the vehicle is relatively large, then changing lanes to the left lane, turning off the left turn signal, accelerating to overtake the vehicle in the original lane, turning on the right turn signal, and when the entire vehicle to be overtaken can be seen in the right rearview mirror, turning the steering wheel right and returning to the original lane.

[0102] In an embodiment of the present application, when the current practice scenario is an overtaking scenario and the question is related to the overtaking scenario, the driving training guidance response can be determined based on the vehicle's driving status information, the control status information of the target device on the vehicle, the vehicle information of the vehicle's left lane, etc., thereby providing the target object with a driving training guidance response for the overtaking scenario.

[0103] In some embodiments of the present application, it is possible to determine in real time whether the vehicle meets the driving requirements based on the vehicle's status information and driving environment information. If there is any behavior that does not meet the driving requirements, irregular behavior prompt information can be pushed to the target object, and operation guidance information can also be determined and pushed to the target object.

[0104] For example, if it is detected that the right wheel of the vehicle has crossed the line, a prompt message that the right wheel of the vehicle has crossed the line can be played, and operational guidance information for turning the steering wheel to the left can be played for the target object.

[0105] In one embodiment of the present application, if it is determined that the vehicle may be in danger based on the vehicle status information and driving environment information, safety reminder information can be pushed to the target object, and the vehicle can also be directly intervened.

[0106] For example, if the vehicle ahead brakes suddenly, a prompt message “The vehicle ahead brakes suddenly, please pay attention” can be played, and the vehicle’s braking system can be controlled to provide braking force to slow down.

[0107] In order to meet the personalized driving training needs of different target objects, in some embodiments of the present application, a training route can be intelligently planned for the target object. Figure 3 Provide explanation. Figure 3A flowchart of a method for pushing driving training guidance provided in another embodiment of the present application.

[0108] like Figure 3 As shown, the method for pushing the driving training guidance further includes:

[0109] Step 301: Obtain the associated information of the target object and the attribute information of the vehicle.

[0110] In this application, the associated information of the target object may include one or more of the following: training requirement information of the target object, historical training status of the target object, portrait information of the target object, etc.

[0111] The training requirement information of the target object may include but is not limited to the training location, training time, training duration, etc. selected by the target object.

[0112] The historical training situation of the target object may include but is not limited to the cumulative training time of the target object, the practice scenes in which the scene scores in the last training were lower than the score threshold, etc.

[0113] The target object's portrait information may include but is not limited to the target object's gender, the target object's age group, etc.

[0114] The attribute information of the vehicle may include but is not limited to the model of the vehicle, the type of vehicle (ie, the model), the length of the vehicle, etc.

[0115] For example, the training needs of the target subject can be inquired through human-computer interaction to obtain the target subject's training needs information. For example, the target subject uses a wake-up word to wake up the human-computer interaction system in the vehicle, and then speaks "start driving training" to wake up the intelligent virtual coach and start driving training mode. The virtual coach can ask the target subject about training location, training time, training duration, training scenarios, etc., where the training scenarios can include commuting, picking up students, and travel scenarios.

[0116] Exemplarily, the portrait information of the target object can be obtained through human-computer interaction, such as the vehicle asks the target object whether the portrait information can be obtained. If the target object confirms that it can, the vehicle can obtain the portrait information of the target object by asking the target object. Or it can be obtained by identifying the image of the target object captured by the camera device in the vehicle, such as the vehicle asks the target object whether the image of the target object can be captured. If the target object agrees to capture, the image of the target object is captured and the captured image of the target object is recognized to obtain the portrait information of the target object. Or it can be obtained through other methods, which are not limited to this.

[0117] Exemplarily, the attribute information of the vehicle may be pre-stored, or provided by the target object during the training preparation phase, or obtained through other means, which is not limited.

[0118] Step 302: Determine at least one target location.

[0119] In this application, one or more target locations input by the target object can be obtained. Alternatively, one or more target locations can be obtained by randomly selecting or sampling according to certain rules within a preset range centered on the vehicle's current location. For example, one target location can be selected in each of the four directions east, south, west, and north of the current location.

[0120] Step 303: Determine a plurality of candidate routes based on the current position of the vehicle and at least one target position.

[0121] In the present application, multiple initial routes can be generated based on the current position of the vehicle and at least one target position. The multiple initial routes can be used as candidate routes, or the multiple initial routes can be screened to obtain multiple candidate routes.

[0122] Since each road is composed of road sections, as an implementation method, the attribute information of each road section on each initial route and the congestion information of each road section can be obtained. Based on the attribute information of each road section on each initial route and the congestion information of each road section on each initial route, the driving difficulty of each road section on each initial route is determined. Based on the driving difficulty of each road section on each initial route, multiple candidate routes are screened out from multiple initial routes.

[0123] The attribute information of the road section may include but is not limited to the grade of the road section, the number of lanes, the length of the road section, etc. The congestion information may include the congestion level, which may be determined based on the traffic volume on the road section.

[0124] In the present application, a correspondence between the attribute information of the road section, the congestion information of the road section and the driving difficulty can be established in advance. Based on the correspondence, the driving difficulty of each road section on each initial route is determined, and based on the driving difficulty of each road section on each initial route, the driving difficulty of each initial route is determined. After that, the initial routes with a driving difficulty greater than a preset difficulty threshold can be screened out, and the remaining initial routes are used as candidate routes.

[0125] Therefore, based on the attribute information and congestion information of each section on the initial route, the driving difficulty of each section on the initial route is determined, and then candidate routes are screened according to the driving difficulty of each section on the initial route, so that the candidate routes can be more in line with the driving training needs.

[0126] As another implementation, the length of the initial route may be determined based on the length of each section on the initial route, initial routes with lengths exceeding a preset length threshold may be screened, and the remaining initial routes may be used as candidate routes.

[0127] Step 304 : Determine a training route from the plurality of candidate routes based on the association information and the attribute information.

[0128] As an implementation method, the data for each section of each candidate route can be sequentially input into a time series model for processing, resulting in a first characteristic vector for each candidate route. Based on the second characteristic vector and the first characteristic vector of each candidate route, the correlation between the target object's association information and the vehicle's attribute information and each candidate route is calculated. The candidate route with the highest correlation can be used as the training route. The second characteristic vector is obtained by inputting the target object's association information and the vehicle's attribute information into a text encoding model for processing. Sequential input into the time series model can be understood as inputting the data for each section into the time series model in the order in which the routes on the candidate routes are connected.

[0129] For ease of understanding, the following Figure 4 To explain, such as Figure 4 As shown, within a preset range centered on the vehicle's current location, target locations are randomly selected or sampled according to certain rules. Multiple initial routes are generated based on the current and target locations. The driving difficulty of each segment of the initial route is determined based on the attribute information and congestion information of each segment. Excessively long routes and routes that are generally too difficult are filtered out to obtain candidate routes. Sequential data consisting of a series of segments of the candidate routes is input into a time series model to obtain a first eigenvector. Correlations are calculated based on the first and second eigenvectors, and training routes are determined from the candidate routes based on the correlations. The second eigenvector is obtained by processing preference questions and answers for driving training, target object portrait information, and vehicle attribute information into a text encoding model. The preference questions and answers for driving training here represent a type of training requirement information.

[0130] Among them, an overly long route may refer to a route whose length is greater than a preset length threshold, and an overall overly difficult route may refer to a route whose driving difficulty exceeds a preset difficulty threshold. The driving difficulty of a route may be determined based on the driving difficulty of each section of the route.

[0131] Therefore, by utilizing the feature vectors corresponding to the associated information of the target object and the attribute information of the vehicle and the feature vectors of the candidate routes, the training route is determined, so that the training route is more in line with the personalized training needs of the target object.

[0132] As another implementation, a target practice scenario for this training session can be determined from multiple candidate practice scenarios based on the target object's associated information and the vehicle's attribute information. The target practice scenario is then matched against each of the multiple candidate routes, and the candidate route with the highest degree of match is determined as the training route. Thus, by determining the target practice scenario based on the target object's associated information and the vehicle's attribute information, and then determining the training route based on the degree of match between the candidate routes and the target practice scenario, the training route can be more tailored to the target object's personalized training needs.

[0133] Optionally, the matching degree between the association information and the attribute information and each candidate practice scene may be calculated, and the candidate practice scene with a matching degree higher than a preset matching degree threshold may be used as the target practice scene.

[0134] Optionally, the degree of matching between the candidate route and the target practice scene may be determined based on whether the candidate route includes the target practice scene, the number of target practice scenes included in the candidate route, and the like.

[0135] For example, the target practice scenarios for the target object's current training include lane change scenarios, left turn scenarios, straight-ahead scenarios at traffic lights, and overtaking scenarios. The candidate routes are r1, r2, and r3. The matching degrees of the candidate routes r1, r2, and r3 with these four practice scenarios can be calculated. Among them, the candidate route r2 has the highest matching degree with these four practice scenarios, so the candidate route r2 can be determined as the training route.

[0136] In an embodiment of the present application, relevant information can be calculated based on the first feature vector corresponding to the candidate route and the association information of the target object and the second feature vector corresponding to the attribute information of the vehicle, and a training route can be determined from multiple candidate routes based on the correlation, or the target practice scenario of this training can be determined based on the association information of the target object and the attribute information of the vehicle, and a training route can be determined from multiple candidate routes based on the matching between the target route scenario and the candidate route, thereby meeting the personalized needs of different target objects and achieving smarter and more personalized driving training.

[0137] In some embodiments of the present application, after determining the training route, teaching guidance texts for each practice scene can be generated based on the training route, each practice scene on the training route, etc., and when the vehicle enters a certain practice scene, the teaching guidance texts for the practice scene are broadcast.

[0138] Among them, the teaching guidance copy of the practice scenario may refer to precautions during practice scenario training, driving operation points, etc.

[0139] Therefore, based on the training route and practice scenarios, teaching guidance documents for each practice scenario are generated, which improves the quality of the teaching guidance documents and can provide personalized driving training guidance for the target objects.

[0140] In order to facilitate the target object to understand his own driving training situation, in some embodiments of the present application, the target object's driving training situation can be scored. Figure 5 Provide explanation. Figure 5 A flowchart of a method for pushing driving training guidance provided in another embodiment of the present application.

[0141] like Figure 5 As shown, the method for pushing the driving training guidance may further include:

[0142] Step 501 : For each road section on the training route, determine the expected score of each road section according to the driving difficulty of each road section and the length of each road section.

[0143] In this application, the target subject drives a vehicle on a training route, where the training route can be determined using the method described in the above embodiment. For each road segment on the training route, the driving difficulty of the road segment can be determined based on the attribute information of the road segment, and the expected score of each road segment can be determined based on the driving difficulty and length of each road segment. For example, the higher the driving difficulty of the road segment and the longer the road segment, the higher the expected score of the road segment.

[0144] Step 502 : Determine the target subject's practice score for each road section based on the target subject's achievement of the teaching requirements for each road section and the handling of emergencies.

[0145] In this application, based on the vehicle's driving data on each road section, the target object's driving operation data of the vehicle, the vehicle's driving environment data, etc., it is possible to determine the target object's achievement of the teaching requirements on each road section and the handling of emergencies when emergencies occur. Then, based on the target object's achievement of the teaching requirements on each road section and the handling of emergencies, the target object is scored to obtain the target object's practice score on each road section.

[0146] Among them, the vehicle's driving data on each road section may include the vehicle's driving direction, driving speed, acceleration, etc. on the road section; the driving operation data may include the vehicle's steering wheel rotation direction and rotation angle, vehicle gear position, accelerator pedal opening, brake pedal opening, headlight switch status, etc. on the road section; the driving environment data may include the speed limit of the road section, whether there is a traffic light, the status information of the traffic light, traffic signs on the road section, lane information of the road section, etc.

[0147] For example, the teaching requirements for a certain road section include that the vehicle speed cannot exceed the speed limit of the section and the vehicle changes lanes to the right. The vehicle's speed in the section does not exceed the speed limit, which scores 1 point, and the absolute value of the difference between the maximum speed and the speed limit is less than the preset value, which scores 0.5 points. However, the vehicle fails to change lanes to the right, which scores no points. If the vehicle reduces its speed when another vehicle suddenly merges into its lane in front, and handles the emergency well, 1 point is added. In this case, the target subject's practice score for the section is 2.5 points.

[0148] Step 503 : Determine the section score of the target object on each section according to the practice score and the expected score of each section.

[0149] In this application, the segment score of the target object on each segment is determined based on the ratio of the practice score to the expected score on each segment.

[0150] Step 504 : Determine the total score of the target object on the training route based on the segment score of each segment on the training route.

[0151] As an implementation method, the segment scores of each segment on the training route may be added together to obtain the total score of the target object on the training route.

[0152] As another implementation, weights can be obtained for each segment on the training route. Based on the weights, the scores for each segment can be weighted and summed to obtain the target object's overall score along the training route. The weights for each segment can be determined based on its attribute information, congestion information, and other factors. Thus, determining the overall score based on the weights of each segment can improve scoring accuracy.

[0153] As another implementation, a training route may include one or more practice scenarios. Based on the vehicle's driving data for each practice scenario along the training route, an overall ride smoothness score for the vehicle in each practice scenario may be determined. Based on the segment scores of the road segments included in each practice scenario and the vehicle's overall ride smoothness score, a scenario score for each practice scenario may be determined. Finally, based on the scenario scores for each practice scenario along the training route, an overall score for the target subject on the training route may be determined. The overall ride smoothness score for each practice scenario may be used to characterize the overall ride smoothness of the vehicle on the road segments included in each practice scenario.

[0154] Thus, a scenario score is determined for each practice scenario based on the segment scores and overall ride smoothness scores of the road segments included in each practice scenario. This not only provides a quantitative assessment of the subject's driving training in each practice scenario, helping the subject understand their training progress in each scenario, but also takes into account the segment scores and the vehicle's overall ride smoothness score, making the assessment more comprehensive and improving the accuracy of the scenario score. Furthermore, an overall score is determined based on the scenario scores of each practice scenario along the training route, providing a quantitative assessment of the entire training process and helping the subject understand their training progress.

[0155] Optionally, a vehicle turning smoothness score can be determined based on the vehicle's turning speed and arc in the driving data for each practice scenario. Furthermore, an overall vehicle speed stability score can be determined based on the vehicle's driving speed in the practice scenario in the driving data. For example, the smaller the average difference in driving speed between adjacent moments in the practice scenario, the higher the vehicle's overall speed stability score. Furthermore, a vehicle starting and deceleration stability score can be determined based on the vehicle's acceleration during starting and deceleration in the driving data. Finally, an overall driving stability score can be determined based on the vehicle turning smoothness score, the overall vehicle speed stability score, and the starting and deceleration stability score. Thus, an overall driving stability score for the vehicle in each practice scenario can be determined based on the vehicle's driving data for each practice scenario, thereby improving the accuracy of the vehicle's overall driving stability score.

[0156] For example, the overall driving stability score can be determined by summing the vehicle's turning smoothness score, the vehicle's overall speed stability score, and the vehicle's starting and deceleration stability score. For example, the overall driving stability score can be determined by obtaining weights for the vehicle's turning smoothness score, the vehicle's overall speed stability score, and the vehicle's starting and deceleration stability score, and performing a weighted sum based on the weights to obtain the overall driving stability score.

[0157] Optionally, the sum of the scene scores of the various practice scenes on the training route may be determined as the total score of the target object on the training route.

[0158] Alternatively, the initial weights of each practice scenario along the training route can be obtained and adjusted based on the scenario score of each practice scenario in the target subject's previous training session to obtain adjusted weights for each practice scenario. The scenario scores of each practice scenario are then weighted and summed based on the adjusted weights to obtain the target subject's total score along the training route. Thus, based on the scenario score of each practice scenario in the previous training session, the score weights of the practice scenarios in the current training session are adjusted, and the total score is determined based on the adjusted weights, thereby improving the accuracy of the total score.

[0159] For example, the initial weight of each practice scenario may be determined according to the difficulty of passing each practice scenario.

[0160] For example, the lower the scenario score of the practice scenario in the previous training, the greater the adjustment value of the weight.

[0161] For example, if a practice scenario's rating in the target subject's previous training session is lower than a rating threshold, the initial weight of the practice scenario can be increased to obtain an adjusted weight for the practice scenario. The weight adjustment value can be determined based on the difference between the rating threshold and the scenario's rating; the larger the difference, the larger the adjustment value. Thus, for practice scenarios whose ratings in the previous training session were lower than the rating threshold, the weight of the practice scenario in the current training session can be increased, thereby making the overall score more consistent with the actual training situation.

[0162] For example, if a practice scene did not appear in the target subject's previous training, or the scene score in the previous practice was higher than the score threshold, the adjustment value of the initial weight of the practice scene can be 0, that is, the adjusted weight is equal to the initial weight.

[0163] It should be noted that if the scene score of a practice scene in the previous training is equal to the score threshold, the initial weight of the practice scene can be increased, or the initial weight of the practice scene can be not adjusted. It can be determined according to actual needs, and this application does not limit this.

[0164] In an embodiment of the present application, the expected score for each section on the training route can be determined based on the driving difficulty of each section and the length of each section, and the practice score of the target object in each section can be determined based on the target object's achievement of the teaching requirements in each section and the handling of emergencies. Based on the practice score and the expected score of each section, the section score of each section is determined, and then based on the section scores of each section on the training route, the total score of the target object on the training route is determined, thereby achieving a quantitative evaluation of the target object's training situation on the entire training route and improving the accuracy of the quantitative evaluation.

[0165] In order to facilitate understanding of the solution of this application, Figure 6 To explain, Figure 6 A schematic diagram of a driving training process provided in an embodiment of the present application.

[0166] like Figure 6 As shown, the driving training process includes:

[0167] Step 601: The vehicle enters a driving training state.

[0168] Step 602: Is the user asking a question detected by voice monitoring? If yes, go to step 603; if not, go to step 604.

[0169] Step 603: Request the large model to generate a driving training guidance response.

[0170] If a user's question is detected, the big model is requested to generate a driving training guidance response. For example, the big model takes as input: the user's question and the role of a professional driving instructor, and outputs a professional guidance response corresponding to the question.

[0171] Step 604: Monitor the vehicle's driving status information, driving environment status information, etc. through a mobile phone, vehicle sensors, cameras, etc.

[0172] If no user is heard asking questions, the vehicle's driving status information and driving environment status information, such as the vehicle's speed, acceleration, traffic light information, and road speed limit, can be monitored through mobile phones, vehicle sensors, cameras, etc.

[0173] Step 605: Acquire driving behavior data, request the large model to generate driving training guidance, and issue an alarm prompt in an emergency.

[0174] In the present application, driving behavior data can be obtained based on the vehicle's driving status information, driving environment status information, etc., wherein the driving behavior data may include the vehicle's driving speed, the distance to the front and rear vehicles, whether it crosses the line, whether it runs a red light, etc.

[0175] Step 606: Notify the user of the driving training guidance and warning prompt information through sound, display screen, etc., and intervene in emergency situations.

[0176] Intervene in emergency situations, such as controlling the vehicle's emergency braking.

[0177] Step 607: Score the user's driving training.

[0178] The scoring method can be found in the above embodiment, so it will not be described here in detail.

[0179] Step 608: Determine whether the user has finished training. If yes, execute step 609 to end the training state. If not, execute step 602 to continue training.

[0180] Step 609, end the training state.

[0181] This application's solution not only provides instructional guidance but also answers user questions through a large model. Furthermore, it can monitor the user's driving behavior in real time, capturing key data using phone sensors, vehicle sensors, and cameras. If a user experiences a driving problem, an immediate alert will be issued, and driving training guidance will be provided to prevent accidents.

[0182] In order to implement the above embodiment, the embodiment of the present application also proposes a driving training guidance push device. Figure 7 A schematic diagram of the structure of a driving training guidance push device provided in one embodiment of the present application.

[0183] like Figure 7 As shown, the driving training guide pushing device 700 includes:

[0184] A first acquisition module 710 is used to acquire questions of a target object collected in a driving training mode;

[0185] Identification module 720, for identifying the problem and determining the correlation between the problem and the current practice scenario of the vehicle;

[0186] The second acquisition module 730 is configured to acquire the vehicle status information and the driving environment information in response to the association relationship being related;

[0187] A first determination module 740 is configured to determine a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information;

[0188] The push module 750 is used to push the driving training instruction reply to the target object.

[0189] Optionally, the current practice scenario is a lane change scenario, and the first determining module 740 is configured to:

[0190] A driving training guidance response is determined based on the driving state information of the vehicle in the state information and the vehicle information on the lane to be entered by the vehicle in the driving environment information.

[0191] Optionally, the current practice scenario is a right turn scenario, and the first determining module 740 is configured to:

[0192] The driving training guidance response is determined based on the driving status information of the vehicle in the status information and the traffic light information and traffic sign information at the front intersection in the driving environment information.

[0193] Optionally, the current practice scenario is an overtaking scenario, and the first determining module 740 is configured to:

[0194] The driving training guidance response is determined based on the driving state information of the vehicle and the control state information of the target device on the vehicle in the state information, and the vehicle information of the left lane of the vehicle in the driving environment information.

[0195] Optionally, the first determining module 740 is configured to:

[0196] Identify the type of problem;

[0197] Based on the type of question, determine the response strategy that matches the type of question;

[0198] A response strategy is adopted to determine a driving training guidance response based on the state information and the driving environment information.

[0199] Optionally, the first determining module 740 is configured to:

[0200] Obtain prompt information; wherein the prompt information is used to instruct the large model to perform the task of generating a driving training guidance response;

[0201] Questions, status information, driving environment information and prompt information are input into the large model for processing to generate driving training guidance responses.

[0202] Optionally, the vehicle travels on a training route, and the apparatus further comprises:

[0203] A third acquisition module is used to obtain the associated information of the target object and the attribute information of the vehicle; wherein the associated information includes one or more of the training requirement information of the target object, the historical training status of the target object, and the portrait information of the target object;

[0204] a second determining module, configured to determine at least one target location;

[0205] a third determining module, configured to determine a plurality of candidate routes based on the current location and at least one target location;

[0206] The fourth determining module is used to determine a training route from a plurality of candidate routes based on the association information and the attribute information.

[0207] Optionally, the fourth determining module is configured to:

[0208] Input the data of each section of each candidate route into the time series model in sequence for processing to obtain the first feature vector of each candidate route;

[0209] Calculating a correlation between the second feature vector and the first feature vector of each candidate route; wherein the second feature vector is obtained by inputting the association information and the attribute information into a text encoding model for processing;

[0210] A training route is determined from the plurality of candidate routes according to the correlation corresponding to each candidate route.

[0211] Optionally, the fourth determining module is configured to:

[0212] Determine the target practice scenario for this training based on the association information and attribute information;

[0213] The target practice scenario is matched with each candidate route among the plurality of candidate routes, and the candidate route with the highest matching degree is determined as the training route.

[0214] Optionally, the third determining module is configured to:

[0215] generating a plurality of initial routes based on the current location and at least one target location;

[0216] Determine the driving difficulty of each road section on each initial route based on the attribute information of each road section on each initial route and the congestion information of each road section;

[0217] A plurality of candidate routes are screened out from the plurality of initial routes according to the driving difficulty of each road segment on each initial route.

[0218] Optionally, the vehicle travels on a training route, and the apparatus further comprises:

[0219] a fifth determination module, configured to determine, for each road segment on the training route, an expected score for each road segment based on the driving difficulty of each road segment and the length of each road segment;

[0220] a sixth determination module, for determining the target subject's practice score for each road section based on the target subject's achievement of the teaching requirements for each road section and the handling of emergencies;

[0221] a seventh determination module, configured to determine a segment score of the target object on each segment based on the practice score and the expected score of each segment;

[0222] The eighth determination module is used to determine the total score of the target object on the training route according to the section score of each section on the training route.

[0223] Optionally, the eighth determining module is configured to:

[0224] Determine the overall driving stability score of the vehicle in each practice scenario based on the driving data of the vehicle in each practice scenario;

[0225] Determining a scenario score for each practice scenario based on the segment scores and the overall ride smoothness score of the segments included in each practice scenario;

[0226] The total score is determined based on the scenario scores of each practice scenario on the training route.

[0227] Optionally, the eighth determining module is configured to:

[0228] Get the initial weight of each practice scenario;

[0229] Adjusting the initial weight of each practice scene according to the scene score of each practice scene in the previous training of the target subject to obtain the adjusted weight of each practice scene;

[0230] According to the adjusted weights of each practice scenario, the scenario scores of each practice scenario are weighted and summed to obtain the total score.

[0231] Optionally, the eighth determining module is configured to:

[0232] In response to a scene score of a practice scene on the training route in a previous training being less than a score threshold, an initial weight of the practice scene is increased to obtain an adjusted weight of the practice scene.

[0233] Optionally, the eighth determining module is configured to:

[0234] Determine a vehicle turning smoothness score based on the vehicle's speed and arc when turning in the driving data;

[0235] Determine the overall speed stability score of the vehicle based on the vehicle's driving speed in the driving data;

[0236] Determine the vehicle's starting and deceleration smoothness score based on the vehicle's acceleration during starting and deceleration in the driving data;

[0237] The overall driving smoothness score is determined based on the vehicle's turning smoothness score, the vehicle's overall speed smoothness score, and the vehicle's starting and deceleration smoothness score.

[0238] Optionally, the device may further include:

[0239] a ninth determining module, configured to determine the field to which the problem belongs in response to the association being irrelevant;

[0240] a fourth acquisition module, configured to acquire prompt information in response to the question belonging to the driving field; wherein the prompt information is used to instruct the large model to perform a task of generating a driving training guidance response;

[0241] The generation module is used to input prompt information and questions into the large model for processing and generate driving training guidance responses.

[0242] Optionally, the push module is also used to:

[0243] In response to the question belonging to a non-driving field, a prompt message for focusing on driving training is pushed to the target object.

[0244] It should be noted that the explanation of the aforementioned embodiment of the method for pushing driving training guidance is also applicable to the device for pushing driving training guidance of this embodiment, and therefore will not be repeated here.

[0245] In an embodiment of the present application, questions collected by the target subject during the driving training mode can be obtained and identified to determine the correlation between the question and the current practice scenario. If the question is relevant to the current practice scenario, the vehicle's status information and driving environment information are obtained. Based on the question, the vehicle's status information and driving environment information, a driving training guidance response is determined and pushed to the target subject. Thus, during the driving training process, the target subject's questions can be collected. For questions related to the current practice scenario, a driving training guidance response can be provided to the target subject based on the question, the vehicle's status information and the driving environment information. This ensures the quality of the driving training guidance response, enables the target subject to autonomously learn driving skills, realizes intelligent driving training, and reduces labor costs.

[0246] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0247] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0248] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 802 or a computer program loaded from a storage unit 808 into a RAM (Random Access Memory) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An I / O (Input / Output) interface 805 is also connected to the bus 804.

[0249] Various components in device 800 are connected to I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0250] The computing unit 801 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), various specialized AI (Artificial Intelligence) computing chips, various computing units that run machine learning model algorithms, a DSP (Digital Signal Processor), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the method for delivering driving training instructions. For example, in some embodiments, the method for delivering driving training instructions can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for delivering driving training instructions described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method of pushing the driving training guidance in any other appropriate manner (for example, by means of firmware).

[0251] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System on Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0252] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0253] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0254] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0255] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0256] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship is established by computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and poor scalability of traditional physical hosts and VPS services. The server may also be a server in a distributed system or a server integrated with blockchain.

[0257] According to an embodiment of the present application, the present application further provides a computer program product, which, when an instruction processor in the computer program product is executed, executes the method for pushing driving training guidance proposed in the above embodiment of the present application.

[0258] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0259] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for pushing driving training instructions, comprising: After entering the driving training mode, multiple initial routes are generated based on the current position of the vehicle and at least one target position input by the target object, and multiple candidate routes are determined from the multiple initial routes based on attribute information and congestion information of each road segment on each initial route; wherein the attribute information of the road segment includes the number of lanes, road segment length, road segment speed limit, and / or road segment height limit; Filtering a training route from the plurality of candidate routes based on the associated information of the target object and the attribute information of the vehicle; The problem of obtaining target objects collected in driving training mode; Identifying the problem and determining a correlation between the problem and a current practice scenario of the vehicle; In response to the association being relevant, acquiring the vehicle status information and the driving environment information; Determining a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information; The driving training instruction response is pushed to the target object so that the vehicle can drive safely on the training route.

2. The method according to claim 1, wherein The current practice scenario is a lane change scenario, and determining a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information includes: The driving training guidance response is determined based on the driving state information of the vehicle in the state information and the vehicle information of the lane to be entered by the vehicle in the driving environment information.

3. The method according to claim 1, wherein The current practice scenario is a right turn scenario, and determining a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information includes: The driving training guidance reply is determined according to the driving state information of the vehicle in the state information and the traffic light information and traffic sign information of the front intersection in the driving environment information.

4. The method according to claim 1, wherein The current practice scenario is an overtaking scenario, and determining a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information includes: The driving training guidance response is determined based on the driving state information of the vehicle and the control state information of the target device on the vehicle in the state information, and the vehicle information of the left lane of the vehicle in the driving environment information.

5. The method according to claim 1, wherein The step of determining a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information includes: Identify the type of problem; Determining, based on the type of the question, a response strategy that matches the type of the question; The response strategy is adopted to determine the driving training guidance response based on the state information and the driving environment information.

6. The method of claim 1, wherein: The step of determining a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information includes: Obtaining prompt information; wherein the prompt information is used to instruct the large model to perform the task of generating a driving training guidance response; The question, the state information, the driving environment information and the prompt information are input into the large model for processing to generate the driving training guidance response.

7. The method of claim 1, wherein: The associated information includes one or more of the training requirement information of the target object, the historical training status of the target object, and the portrait information of the target object.

8. The method of claim 7, wherein: The determining the training route from the plurality of candidate routes according to the association information and the attribute information includes: Input the data of each section of each candidate route into the time series model in sequence for processing to obtain the first feature vector of each candidate route; Calculating a correlation between the second feature vector and the first feature vector of each candidate route; wherein the second feature vector is obtained by inputting the association information and the attribute information into a text encoding model for processing; The training route is determined from the multiple candidate routes according to the correlation corresponding to each candidate route.

9. The method of claim 7, wherein: The determining the training route from the plurality of candidate routes according to the association information and the attribute information includes: Determining a target practice scenario for this training based on the association information and the attribute information; The target practice scenario is matched with each candidate route among the plurality of candidate routes, and the candidate route with the highest matching degree is determined as the training route.

10. The method according to any one of claims 7 to 9, wherein The step of determining a plurality of candidate routes from the plurality of initial routes based on the attribute information and congestion information of each road segment on each initial route includes: Determine the driving difficulty of each road section on each initial route based on the attribute information of each road section on each initial route and the congestion information of each road section; The plurality of candidate routes are screened out from the plurality of initial routes according to the driving difficulty of each road section on each initial route.

11. The method of claim 1, wherein: The method further comprises: For each road segment on the training route, determining an expected score for each road segment based on the driving difficulty of each road segment and the length of each road segment; Determining the target subject's practice score for each road section based on the target subject's achievement of the teaching requirements for each road section and the handling of unexpected situations; Determining a section score of the target object on each section according to the practice score and the expected score of each section; The total score of the target object on the training route is determined according to the segment score of each segment on the training route.

12. The method of claim 11, wherein: Determining the total score of the target object on the training route based on the segment score of each segment on the training route includes: Determining an overall driving stability score of the vehicle in each practice scenario based on the driving data of the vehicle in each practice scenario; determining a scene score for each practice scene based on the road segment scores of the road segments included in each practice scene and the overall driving smoothness score; The total score is determined according to the scenario score of each practice scenario.

13. The method of claim 12, wherein: Determining the total score based on the scenario scores of each practice scenario includes: Get the initial weight of each practice scenario; Adjusting the initial weight of each practice scene according to the scene score of each practice scene in the previous training of the target subject to obtain an adjusted weight of each practice scene; The scene scores of each practice scene are weighted and summed according to the adjusted weights of each practice scene to obtain the total score.

14. The method of claim 13, wherein: The step of adjusting the initial weight of each practice scene according to the scene score of each practice scene in the previous training of the target subject to obtain the adjusted weight of each practice scene includes: In response to a scene score of a practice scene on the training route in a previous training being less than a score threshold, an initial weight of the practice scene is increased to obtain an adjusted weight of the practice scene.

15. The method of claim 12, wherein: Determining the overall driving stability score of the vehicle in each practice scenario based on the driving data of the vehicle in each practice scenario includes: determining a turning smoothness score of the vehicle according to a driving speed and an arc of the vehicle when turning in the driving data; Determining an overall speed stability score of the vehicle according to the driving speed of the vehicle in the driving data; determining a vehicle start-up and deceleration smoothness score according to the acceleration of the vehicle during start-up and deceleration in the driving data; The overall driving smoothness score is determined based on the vehicle turning smoothness score, the vehicle overall speed smoothness score, and the vehicle starting and deceleration smoothness score.

16. The method of any one of claims 1 to 9, further comprising: In response to the association being irrelevant, determining the field to which the problem belongs; In response to the question belonging to the driving field, obtaining prompt information; wherein the prompt information is used to instruct the large model to perform the task of generating a driving training guidance answer; The prompt information and the question are input into a large model for processing to generate the driving training guidance response.

17. The method of claim 16, further comprising: In response to the field to which the question belongs being a non-driving field, a prompt message for focused driving training is pushed to the target object.

18. A driving training guide push device, comprising: a third determination module, configured to, after entering the driving training mode, generate a plurality of initial routes based on the current position of the vehicle and at least one target position input by the target object, and determine a plurality of candidate routes from the plurality of initial routes based on attribute information and congestion information of each road segment on each initial route; wherein the attribute information of the road segment includes the number of lanes, road segment length, road segment speed limit, and / or road segment height limit; a fourth determining module, configured to select a training route from the plurality of candidate routes based on the associated information of the target object and the attribute information of the vehicle; A first acquisition module is used to acquire questions of the target object collected in the driving training mode; an identification module, configured to identify the problem and determine a correlation between the problem and a current practice scenario of the vehicle; a second acquiring module, configured to acquire the state information and driving environment information of the vehicle in response to the association being related; A first determining module is configured to determine a driving training guidance response corresponding to the question based on the question, the state information, and the driving environment information; The push module is used to push the driving training guidance reply to the target object so that the vehicle can drive safely on the training route.

19. The apparatus of claim 18, wherein: The current practice scenario is a lane change scenario, and the first determining module is configured to: The driving training guidance response is determined based on the driving state information of the vehicle in the state information and the vehicle information of the lane to be entered by the vehicle in the driving environment information.

20. The apparatus of claim 18, wherein The current practice scenario is a right turn scenario, and the first determining module is configured to: The driving training guidance reply is determined according to the driving state information of the vehicle in the state information and the traffic light information and traffic sign information of the front intersection in the driving environment information.

21. The apparatus of claim 18, wherein The current practice scenario is an overtaking scenario, and the first determining module is configured to: The driving training guidance response is determined based on the driving state information of the vehicle and the control state information of the target device on the vehicle in the state information, and the vehicle information of the left lane of the vehicle in the driving environment information.

22. The apparatus of claim 18, wherein: The first determining module is configured to: Identify the type of problem; Determining, based on the type of the question, a response strategy that matches the type of the question; The response strategy is adopted to determine the driving training guidance response based on the state information and the driving environment information.

23. The apparatus of claim 18, wherein: The first determining module is configured to: Obtaining prompt information; wherein the prompt information is used to instruct the large model to perform the task of generating a driving training guidance response; The question, the state information, the driving environment information and the prompt information are input into the large model for processing to generate the driving training guidance response.

24. The apparatus of claim 18, wherein: The associated information includes one or more of the training requirement information of the target object, the historical training status of the target object, and the portrait information of the target object.

25. The apparatus of claim 24, wherein: The fourth determining module is configured to: Input the data of each section of each candidate route into the time series model in sequence for processing to obtain the first feature vector of each candidate route; Calculating a correlation between the second feature vector and the first feature vector of each candidate route; wherein the second feature vector is obtained by inputting the association information and the attribute information into a text encoding model for processing; The training route is determined from the multiple candidate routes according to the correlation corresponding to each candidate route.

26. The apparatus of claim 24, wherein: The fourth determining module is configured to: Determining a target practice scenario for this training based on the association information and the attribute information; The target practice scenario is matched with each candidate route among the plurality of candidate routes, and the candidate route with the highest matching degree is determined as the training route.

27. The device according to any one of claims 24 to 26, wherein The step of determining a plurality of candidate routes from the plurality of initial routes based on the attribute information and congestion information of each road segment on each initial route includes: Determine the driving difficulty of each road section on each initial route based on the attribute information of each road section on each initial route and the congestion information of each road section; The plurality of candidate routes are screened out from the plurality of initial routes according to the driving difficulty of each road section on each initial route.

28. The apparatus of claim 18, wherein The device further comprises: a fifth determining module, configured to determine, for each road segment on the training route, an expected score for each road segment according to the driving difficulty of each road segment and the length of each road segment; a sixth determining module, configured to determine a practice score of the target subject in each road section according to whether the target subject has achieved the teaching requirements in each road section and handled emergencies; a seventh determining module, configured to determine a segment score of the target object on each segment based on the practice score and the expected score of each segment; The eighth determination module is configured to determine a total score of the target object on the training route according to the segment score of each segment on the training route.

29. The apparatus of claim 28, wherein The eighth determining module is configured to: Determining an overall driving stability score of the vehicle in each practice scenario based on the driving data of the vehicle in each practice scenario; determining a scene score for each practice scene based on the road segment scores of the road segments included in each practice scene and the overall driving smoothness score; The total score is determined according to the scenario score of each practice scenario.

30. The apparatus of claim 29, wherein: The eighth determining module is configured to: Get the initial weight of each practice scenario; Adjusting the initial weight of each practice scene according to the scene score of each practice scene in the previous training of the target subject to obtain an adjusted weight of each practice scene; The scene scores of each practice scene are weighted and summed according to the adjusted weights of each practice scene to obtain the total score.

31. The apparatus of claim 30, wherein: The eighth determining module is configured to: In response to a scene score of a practice scene on the training route in a previous training being less than a score threshold, an initial weight of the practice scene is increased to obtain an adjusted weight of the practice scene.

32. The apparatus of claim 29, wherein: The eighth determining module is configured to: determining a turning smoothness score of the vehicle according to a driving speed and an arc of the vehicle when turning in the driving data; Determining an overall speed stability score of the vehicle according to the driving speed of the vehicle in the driving data; determining a vehicle start-up and deceleration smoothness score according to the acceleration of the vehicle during start-up and deceleration in the driving data; The overall driving smoothness score is determined based on the vehicle turning smoothness score, the vehicle overall speed smoothness score, and the vehicle starting and deceleration smoothness score.

33. The apparatus of any one of claims 18 to 26, further comprising: a ninth determining module, configured to determine, in response to the association being irrelevant, a field to which the problem belongs; a fourth acquisition module, configured to acquire prompt information in response to the question belonging to the driving field; wherein the prompt information is used to instruct the large model to perform a task of generating a driving training guidance response; A generation module is used to input the prompt information and the question into the large model for processing and generate the driving training guidance response.

34. The apparatus of claim 33, wherein: The push module is further used to: In response to the field to which the question belongs being a non-driving field, a prompt message for focused driving training is pushed to the target object.

35. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 17.

36. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-17.

37. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 17.

Images