Vehicle control method, server, and computer-readable storage medium

Abstract

The application discloses a vehicle control method, a server and a computer readable storage medium. The method comprises: receiving a first voice request forwarded by a vehicle and current state information of the vehicle. Based on a first preset model, a target execution action is determined according to the first voice request and the current state information, and the target execution action is issued to the vehicle to control the vehicle to execute the target execution action. In the case that an abnormality occurs in the execution of the target execution action by the vehicle, target reflection information is generated according to the first voice request and the current state information to control the vehicle according to the target reflection information. In this way, by processing the first voice request and the current state information of the vehicle, the accuracy of analyzing the user request and determining the execution action is improved. Moreover, through the real-time state monitoring and abnormality processing mechanism, the server ensures the safety of the vehicle operation, reduces potential errors and risks, optimizes the performance and efficiency of the system, and thus improves the user experience.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a vehicle control method, a server, and a computer-readable storage medium. Background Technology

[0002] In related technologies, in-vehicle intelligent assistants typically interact with users through cockpit screens. However, currently, in-vehicle intelligent assistants have weak reflective capabilities when performing tasks. If errors occur during operation, the voice assistant often cannot effectively adjust its strategy, leading to task failure and impacting the user experience. Summary of the Invention

[0003] This application provides a vehicle control method, a server, and a computer-readable storage medium.

[0004] This application provides a vehicle control method, the method comprising:

[0005] Receive the first voice request forwarded by the vehicle and the current status information of the vehicle;

[0006] Based on the first preset model, the target action is determined according to the first voice request and the current state information, and the target action is sent to the vehicle to control the vehicle to execute the target action;

[0007] If the vehicle malfunctions while performing the target action, target reflection information is generated based on the first voice request and the current state information, and the vehicle is controlled based on the target reflection information.

[0008] Thus, the server receives the first voice request forwarded by the vehicle and the vehicle's current status information. Next, based on a first preset model, the server determines the target action based on the first voice request and the current status information, and sends the target action to the vehicle to control it to execute the target action. Finally, in the event of an anomaly in the vehicle's execution of the target action, the server generates target reflection information based on the first voice request and the current status information, and controls the vehicle according to this reflection information. In this way, by processing the first voice request and the vehicle's current status information, the accuracy of parsing user requests and determining the action to be executed is improved. Furthermore, through real-time status monitoring and anomaly handling mechanisms, the server ensures the safety of vehicle operation, enhances the system's reflective capabilities, reduces potential errors and risks, optimizes system performance and efficiency, and thus improves the user experience.

[0009] In some implementations, generating target reflection information based on the first voice request and the current state information, and controlling the vehicle based on the target reflection information, includes:

[0010] Based on the current state, the first voice request, and the historical operation information associated with the first voice request, first output information is generated, wherein the historical operation information includes historical operation description information and historical execution operation information.

[0011] Based on the second preset model, the target reflection information is generated according to the first output information and the preset experience base. The preset experience base includes multiple preset reflection information, which includes preset historical operation description information, preset status information, preset execution results, and preset execution operation information.

[0012] Thus, the server generates first output information based on the current state, the first voice request, and historical operation information associated with the first voice request. This historical operation information includes historical operation descriptions and historical executed operation information. Next, based on a second preset model, the server generates target reflection information according to the first output information and a preset experience base. This preset experience base includes multiple preset reflection information entries, which include preset historical operation descriptions, preset state information, preset execution results, and preset executed operation information. In this way, by integrating the current state, the first voice request, and the historical operation information associated with the first voice request, and referring to the preset experience base, the server can continuously generate target reflection information, improving the system's reflection capabilities and speed, thereby increasing the success rate of task execution and improving user experience.

[0013] In some implementations, generating the target reflection information based on the second preset model, according to the first output information and the preset experience base, includes:

[0014] Based on the historical operation description information in the first output information and the preset historical operation description information, the operation similarity is determined;

[0015] Determine the state similarity based on the current state in the first output information and the preset state information;

[0016] The target similarity value is determined based on the operation similarity and the state similarity.

[0017] Based on the target similarity value, candidate preset reflection information is determined from the preset experience base;

[0018] The target reflection information is generated based on the target similarity value, the preset threshold, and the candidate preset reflection information.

[0019] Thus, the server determines the operation similarity based on the historical operation descriptions in the first output information and the preset historical operation descriptions. Next, the server determines the state similarity based on the current state and the preset state information in the first output information. Then, the server determines the target similarity value based on the operation similarity and state similarity. Subsequently, the server determines candidate preset reflection information from a preset experience base based on the target similarity value. Finally, the server generates the target reflection information based on the target similarity value, the preset threshold, and the candidate preset reflection information. In this way, through similarity evaluation, the agent can accurately match the current problem with historical cases in the experience base to generate target reflection information, thereby continuously optimizing its reflection ability and reflection speed.

[0020] In some implementations, generating the target reflection information based on the target similarity value, a preset threshold, and the candidate preset reflection information includes:

[0021] If the maximum value of the target similarity value is greater than or equal to the preset threshold, the target reflection information is generated based on the candidate preset reflection information.

[0022] Thus, when the target similarity value is greater than or equal to a preset threshold, the server generates target reflection information based on candidate preset reflection information. By setting a threshold, it ensures that candidate reflection information is only used when the similarity is sufficiently high, thereby improving the accuracy of decision-making.

[0023] In some embodiments, the method further includes:

[0024] If the preset execution result corresponding to the target reflection information is an execution exception, the preset execution operation information in the target reflection information is sent to the vehicle to complete the vehicle control.

[0025] Thus, if the preset execution result corresponding to the target reflection information is an execution exception, the server sends the preset execution operation information from the target reflection information to the vehicle to complete vehicle control. In this way, the system can respond quickly when an execution exception is detected and take corrective measures, improving the system's fault handling capabilities, enhancing the stability and reliability of vehicle control, thereby improving user experience and overall system performance.

[0026] In some embodiments, the method further includes:

[0027] If the preset execution result corresponding to the target reflection information is successful, the target execution action is determined based on the first preset model, the first voice request, and the current state information.

[0028] Thus, if the preset execution result corresponding to the target reflection information is successful, the server determines the target execution action based on the first preset model, the first voice request, and the current state information. In this way, the system can utilize historical success cases to guide current decisions, thereby improving the accuracy and success rate of execution actions, enhancing the system's intelligent decision-making capabilities, and improving task execution efficiency and user experience.

[0029] In some implementations, generating the target reflection information based on the target similarity value, a preset threshold, and the candidate preset reflection information includes:

[0030] If the target similarity value is less than the preset threshold, a template is generated based on preset reflection information, and the target reflection information is generated according to preset reflection knowledge, the first voice request, and the current state information.

[0031] Thus, when the target similarity value is less than a preset threshold, the server generates a template based on preset reflection information, and generates target reflection information according to preset reflection knowledge, the first voice request, and the current state information. In this way, the system can flexibly generate new reflection information when encountering uncommon or novel situations, thereby improving the system's adaptability and intelligence, enhancing its ability to handle unknown situations, and promoting the system's continuous learning and self-optimization.

[0032] In some embodiments, the method further includes:

[0033] If the target detection object is confirmed to be in an abnormal state based on the current state information, it is confirmed that the target's execution action has become abnormal.

[0034] In this way, if the server confirms that the target object is in an abnormal state based on the current status information, it will confirm that the target's action has become abnormal. This allows the system to promptly detect and respond to abnormal vehicle states, thereby preventing potential malfunctions or dangers, improving vehicle safety and reliability, and enhancing the system's intelligence and user experience.

[0035] This application provides a server, which includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, it implements the vehicle control method described above.

[0036] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the vehicle control method described above.

[0037] Additional aspects and advantages of embodiments of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of this application. Attached Figure Description

[0038] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, wherein:

[0039] Figure 1 This is one of the schematic flowcharts of a vehicle control method according to certain embodiments of this application;

[0040] Figure 2 This is a schematic diagram of the target reflection information generation process in some embodiments of this application;

[0041] Figure 3 This is a second schematic flowchart of a vehicle control method according to certain embodiments of this application;

[0042] Figure 4 This is a third schematic flowchart of a vehicle control method according to certain embodiments of this application;

[0043] Figure 5 This is the fourth flowchart of a vehicle control method according to certain embodiments of this application;

[0044] Figure 6 This is the fifth of the flowcharts illustrating a vehicle control method according to certain embodiments of this application;

[0045] Figure 7 This is a schematic flowchart of a vehicle control method according to certain embodiments of this application, number six.

[0046] Figure 8 This is the seventh flowchart of a vehicle control method according to certain embodiments of this application;

[0047] Figure 9 This is the eighth flowchart of a vehicle control method according to certain embodiments of this application. Detailed Implementation

[0048] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of this application, and should not be construed as limiting the embodiments of this application.

[0049] In related technologies, in-vehicle intelligent assistants typically use the cockpit screen as the primary interaction interface, allowing users to interact with the assistant via touchscreen or voice commands. This interaction method is quite mature in providing functions such as navigation, entertainment, and vehicle diagnostics. However, while these in-vehicle intelligent assistants perform well in performing routine tasks, their ability to reflect on complex situations or unexpected events is relatively weak.

[0050] Specifically, when in-vehicle intelligent assistants encounter errors or unexpected situations while performing tasks, they often fail to effectively adjust their execution strategies. For example, if a user requests navigation to a specific location, but the navigation route does not appear on the cockpit screen, an in-vehicle intelligent assistant with weak reflective capabilities may not be able to automatically provide a solution, requiring the user to troubleshoot manually, resulting in a poor user experience.

[0051] Based on the above issues, please refer to Figure 1 This application provides a vehicle control method, the method comprising:

[0052] 01: Receive the first voice request forwarded by the vehicle and the vehicle's current status information;

[0053] 02: Based on the first preset model, determine the target action according to the first voice request and the current status information, and send the target action to the vehicle to control the vehicle to execute the target action;

[0054] 03: In the event of an abnormality in the vehicle's execution of the target action, target reflection information is generated based on the first voice request and the current status information, and the vehicle is controlled based on the target reflection information.

[0055] This application also provides a server, including a memory and a processor. The vehicle control method of this application can be implemented by the server of this application. Specifically, the memory stores a computer program, and the processor is used to receive a first voice request forwarded by the vehicle and the vehicle's current status information. Based on a first preset model, the processor determines a target execution action according to the first voice request and the current status information, and sends the target execution action to the vehicle to control the vehicle to execute the target execution action. Furthermore, in the event of an abnormality in the vehicle's execution of the target execution action, the processor generates target reflection information according to the first voice request and the current status information, and controls the vehicle based on the target reflection information.

[0056] This application also provides a vehicle control device. The vehicle control method of this application can be implemented by the vehicle control device of this application. Specifically, the vehicle control device includes a receiving module, a determining module, and a generating module. The receiving module is used to receive a first voice request forwarded by the vehicle and the vehicle's current status information. The determining module is used to determine a target execution action based on a first preset model, according to the first voice request and the current status information, and send the target execution action to the vehicle to control the vehicle to execute the target execution action. The generating module is used to generate target reflection information based on the first voice request and the current status information when an abnormality occurs in the vehicle's execution of the target execution action, so as to control the vehicle according to the target reflection information.

[0057] Specifically, the first voice request refers to the voice command issued by the user through the in-vehicle voice assistant during a certain round of voice interaction, including controlling a certain function of the vehicle, querying information, or requesting a service. For example, "Turn on the air conditioning," "What's the weather like today?" and "I need the nearest gas station."

[0058] Current status information refers to the current display content of the vehicle's display components and the vehicle's current perception information.

[0059] The currently displayed content information of a vehicle's display components refers to the information currently presented on the in-vehicle display screen or other display devices. For example, this could include navigation-related content such as the current driving route, destination, estimated arrival time, and traffic conditions; entertainment system-related content such as music playlists, track information, and radio frequencies; or communication-related content such as incoming call information, text message content, and contact lists. Display content information is a crucial component of the vehicle's intelligent control system, providing drivers with essential driving information and entertainment services, and serving as a vital interface for system-user interaction. It should be noted that in this application's embodiments, the in-vehicle display screen is used as the vehicle display component to describe the vehicle control method; that is, the currently displayed content information is a screenshot of the in-vehicle display screen.

[0060] Current perception information refers to the environmental state information and on-board equipment function status information collected by the vehicle through its sensors. Environmental state information includes data about the vehicle's surrounding environment, such as traffic conditions, road conditions, weather conditions, and geographical location. Traffic conditions refer to road traffic conditions collected by sensors such as cameras, radar, or LiDAR, including the position and speed of other vehicles. Road conditions refer to information such as road slipperiness, potholes, and obstacles. Weather conditions refer to weather information obtained through weather sensors or data exchange with external services, such as temperature, rainfall, and wind speed. Geographical location refers to the vehicle's current location information obtained through positioning systems such as GPS. On-board equipment function status perception information includes status data of the vehicle's internal systems and devices, such as the status of the in-vehicle entertainment system, navigation system settings, air conditioning configuration, engine status, battery charge, fuel level, and tire pressure.

[0061] The target execution action refers to the specific operation determined and executed by the system based on the initial voice request, currently displayed content information, and current perception information. This includes click operations, swipe operations, and typing operations. Click operations refer to clicking icons or buttons to activate a specific function or service. For example, if a user says "turn on music," the system may need to click the music app icon in the in-vehicle entertainment system. Swipe operations refer to actions taken when the current page information list is collapsed or too long, requiring the user to swipe the screen or turn pages to view more information. For example, when the navigation system displays a long route, the system may need to swipe the screen to display the complete route. Typing operations refer to clicking the search box and typing content to find specific information or services within the system. For example, if a user says "search for nearby restaurants," the system may need to click the search box and type "nearby restaurants." Typing operations can also instruct users to enter and send text messages within the in-vehicle system, such as sending text messages or commenting on social media. For example, if a user says "message Zhang San," the system may need to open the messaging app, select the contact Zhang San, and open the chat window.

[0062] An anomaly in the execution of a target action refers to a problem or error that occurs when the system attempts to perform a specific operation determined based on the initial voice request, the currently displayed content information, and the current perception information, causing the operation to fail to complete as expected. For example, if a user says "open music," the system should execute the action of clicking the music app icon. However, if the icon is unresponsive or the app fails to launch, this constitutes a click operation anomaly. When a navigation system needs to display a complete route, it should execute the action of swiping the screen. If the screen swiping is not smooth or the system cannot respond to the swipe command, this constitutes a swipe operation anomaly. If a user says "search for nearby restaurants," the system should execute the action of clicking the search box and entering "nearby restaurants." If the search box cannot be activated or the entered text is incorrect, this constitutes a typing operation anomaly. When a user says "send a message to Zhang San," the system should be able to open the messaging app and select a contact. If the messaging app cannot be opened, the contact cannot be selected, or the message fails to be sent, this constitutes a text message sending anomaly.

[0063] Target reflection information refers to the information generated by the system based on the current situation, historical data, and preset experience base when the in-vehicle intelligent assistant encounters an anomaly in executing the target action. This information is used to adjust or correct the execution strategy. It reflects the system's analysis of the reasons for the failure of the current execution action and its thinking on how to better execute user instructions.

[0064] Please see Figure 2 The server receives the first voice request forwarded by the vehicle and the vehicle's current status information. This information may include, but is not limited to, the vehicle's interior temperature, humidity, and speed.

[0065] Next, the server analyzes the first voice request and current state information based on the first preset model to determine the target action. For example, if the voice request is "raise the temperature" and the current temperature inside the car is low, the server may determine that the target action is to start the heating system.

[0066] Subsequently, after determining the target action, the server sends this action to the vehicle. Upon receiving the instruction, the vehicle performs the corresponding operation, such as adjusting the temperature.

[0067] If an anomaly occurs during the execution of the target action (e.g., the temperature fails to rise as expected), the server will generate target reflection information based on the first voice request and current status information, including analyzing the cause of the anomaly and generating solutions, such as checking whether the heating system is working properly.

[0068] In summary, in the vehicle control method and server provided in this application, the server receives a first voice request forwarded by the vehicle and the vehicle's current status information. Next, based on a first preset model, the server determines a target action to be performed according to the first voice request and the current status information, and sends the target action to the vehicle to control the vehicle to perform the target action. Finally, in the event of an anomaly in the vehicle's execution of the target action, the server generates target reflection information based on the first voice request and the current status information, and controls the vehicle according to the target reflection information. Thus, by processing the first voice request and the vehicle's current status information, the accuracy of parsing user requests and determining the action to be performed is improved. Furthermore, through real-time status monitoring and anomaly handling mechanisms, the server ensures the safety of vehicle operation, reduces potential errors and risks, optimizes system performance and efficiency, and thereby improves the user experience.

[0069] Please see Figure 3 In some implementations, step 03 (generating target reflection information based on the first voice request and current state information, so as to control the vehicle based on the target reflection information) includes:

[0070] 031: Generate first output information based on the current state, the first voice request, and the historical operation information associated with the first voice request;

[0071] 032: Based on the second preset model, target reflection information is generated according to the first output information and the preset experience base.

[0072] In some implementations, the determining module is further configured to generate first output information based on the current state, the first voice request, and historical operation information associated with the first voice request; and to generate target reflection information based on the first output information and a preset experience base, using a second preset model.

[0073] In some implementations, the processor is further configured to generate first output information based on the current state, the first voice request, and historical operation information associated with the first voice request; and to generate target reflection information based on the first output information and a preset experience base, using a second preset model.

[0074] Specifically, the first output information refers to data information generated based on the current state, the first voice request, and historical operation information associated with the first voice request, used for subsequent steps. In some embodiments, the first output information generation template is as follows:

[0075] Imagine you are an intelligent assistant. I will give you the following information. Based on this information, please output the action steps and status of this agent:

[0076] User task: <User request query>

[0077] Current state: <current state>

[0078] Historical operation information: <historical plan:P>, <historical action:A>

[0079] Based on the information above, please provide a concise description of the operation steps and status of this agent, within 50 characters:

[0080] describe:

[0081] One possible first output information generated based on the template described above is: In the last operation, the agent selected the "Go here" button but failed to complete the task. The current screen in the car is displaying an advertisement page. The vehicle's infotainment system is in park (P) mode, with no music playing, and the interior temperature is 22 degrees Celsius.

[0082] Historical operation information refers to the operation data collected and stored by the in-vehicle intelligent assistant in past interactions, reflecting the user's behavior patterns, preferences, and the system's past performance. Historical operation information includes user voice requests, historical operation descriptions, historical executed operation information, and screenshots of the in-vehicle display screen when the user's voice request was received. That is, for each voice request's operation state, its i-th step can be defined as S_i(q, p_i, ai, pic_i), where q refers to the user's voice request query, p_i refers to the plan for the current step, a_i refers to the action for the current step, and pic_i refers to the screenshot for the current step. Both plan and action represent the operation required by the user's voice request; the difference is that plan refers to a description of the operation in text that ordinary users can understand, while action refers to the specific instructions for the operation that relevant technicians and the machine can understand.

[0083] For an operation session of an in-vehicle intelligent assistant, we need to record its historical plan: P = [p_1, p_2, ..., p_n] and historical action: A = [a_1, a_2, ..., a_n].

[0084] The preset experience base refers to a data set storing the decision-making process, successful execution cases, and lessons learned from failures of the in-vehicle intelligent assistant. This allows the intelligent assistant to learn from past experiences, improving the quality and efficiency of its decision-making. The decision-making process record details the intelligent assistant's decision-making process when handling user requests, including decision inputs (descriptions of the user's historical operations and the vehicle's current perception state information), execution results, and timestamps (the time the decision occurred). Successful execution cases record instances of successful task execution by the intelligent assistant, including decision inputs, executed operations, and the final successful result. Lessons learned record failures encountered by the intelligent assistant during task execution, including the causes of failure, errors, and possible improvement measures. The aforementioned decision-making process, successful execution cases, and lessons learned are collectively referred to as preset reflection information. That is, the preset experience base includes multiple preset reflection information entries e_i, each of which includes preset historical operation description information, preset state information, preset execution results, and preset execution operation information. Where e_i = (p_i, s_i, r_i, a_i).

[0085] Where p_i refers to the preset historical operation description information of the recorded voice request, s_i refers to the preset state information of the recorded voice request, r_i refers to the preset execution result of the recorded voice request, and a_i refers to the preset execution operation information that the recorded voice request can output, i.e., the next action.

[0086] The server generates first output information based on the current state, the first voice request, and historical operation information associated with the first voice request. The historical operation information includes historical operation descriptions and historical executed operation information. Next, based on a second preset model, the server generates target reflection information according to the first output information and a preset experience base. The preset experience base includes multiple preset reflection information entries, which include preset historical operation descriptions, preset state information, preset execution results, and preset executed operation information.

[0087] In this way, by integrating the current state, the first voice request, and the historical operation information associated with the first voice request, and referring to the preset experience base, the server can continuously generate target reflection information, improve the system's reflection ability and reflection speed, thereby improving the success rate of task execution and user experience.

[0088] Please see Figure 4 In some implementations, step 032 (generating target reflection information based on the second preset model, according to the first output information and the preset experience base) includes:

[0089] 0321: Determine the operation similarity based on the historical operation description information in the first output information and the preset historical operation description information;

[0090] 0322: Determine the state similarity based on the current state and preset state information in the first output information;

[0091] 0323: Determine the target similarity value based on operation similarity and state similarity;

[0092] 0324: Based on the target similarity value, determine candidate preset reflection information from the preset experience base;

[0093] 0325: Generate target reflection information based on target similarity value, preset threshold and candidate preset reflection information.

[0094] In some implementations, the determining module is further configured to determine operation similarity based on historical operation description information and preset historical operation description information in the first output information; and to determine state similarity based on the current state and preset state information in the first output information; and to determine a target similarity value based on operation similarity and state similarity. The determining module is further configured to determine candidate preset reflection information from a preset experience base based on the target similarity value; and to generate target reflection information based on the target similarity value, a preset threshold, and candidate preset reflection information.

[0095] In some embodiments, the processor is further configured to determine operation similarity based on historical operation description information and preset historical operation description information in the first output information; and to determine state similarity based on the current state and preset state information in the first output information; and to determine candidate preset reflection information from a preset experience base based on the target similarity value. The processor is also configured to determine candidate preset reflection information from the preset experience base based on the target similarity value; and to generate target reflection information based on the target similarity value, a preset threshold, and candidate preset reflection information.

[0096] Specifically, preset execution operation information refers to a description of a series of standardized operation commands that may be executed in the vehicle. For example, "The user requests navigation home at 8 pm" or "The user issues a command to turn on the windshield wipers in the rain."

[0097] Preset status information describes the vehicle's status and environmental information when performing a specific operation. For example, "Vehicle fuel level is below 20%" or "Outside temperature exceeds 28 degrees Celsius".

[0098] The preset execution results record the execution results of preset execution operation information and preset status information. For example, "Navigation operation successful, user has arrived at destination" or "Windshield wiper operation successful, windshield wipers are activated".

[0099] Preset execution information includes the actions that the intelligent assistant should take under specific operations and states. For example, "remind the user to go to a gas station when the fuel is low" or "automatically turn on the air conditioning when the car interior temperature is too high".

[0100] The server first compares the historical operation description information p in the first output information. now and the preset historical operation description information p in the preset experience library i To determine the operation similarity, i.e., the operation similarity is sim(p now ,p i For example, if a user repeatedly requests "navigate to the nearest gas station," and there are similar operation descriptions in the preset experience library, then the operation similarity is high.

[0101] Next, the server determines the current state s based on the first output information. now And the preset status information s corresponding to the preset historical operation description information items in the preset experience base. i Determine the state similarity, i.e., the state similarity is sim(s now ,s i For example, if a user's voice request is "navigate to the nearest gas station" and the vehicle's fuel level is low, and there is a similar operation description in the preset experience library, and the status description pages are consistent, then the status similarity is high.

[0102] Then, the server calculates the target similarity value based on operation similarity and state similarity. That is, it calculates the similarity value between the first output information and each preset reflection information, using the formula sim. now =sim(p now ,p i )+sim(s now ,s i Then, these similarity values ​​are compared, and the one with the largest similarity value is selected as the target similarity value.

[0103] Subsequently, based on the target similarity value, the server filters out candidate preset reflection information from the preset experience base. This candidate preset reflection information consists of historical cases and their solutions that are most similar to the current situation.

[0104] Finally, the server generates target reflection information based on the target similarity value, a preset threshold (used to determine if the similarity is high enough), and candidate preset reflection information. For example, if the preset threshold is 0.85, and the target similarity value is higher than or equal to the preset threshold of 0.85, the server may select the candidate preset reflection information as the target reflection information. If the target similarity value is lower than the preset threshold of 0.85, it is determined that there is no preset reflection information similar to the first output information in the preset experience base.

[0105] In this way, through similarity assessment, the agent can accurately match the current problem with historical cases in the experience base to generate target reflection information, thereby continuously optimizing its reflection ability and reflection speed.

[0106] Please see Figure 5 In some implementations, step 0325 (generating target reflection information based on target similarity value, preset threshold, and candidate preset reflection information) includes:

[0107] 03251: When the target similarity value is greater than or equal to the preset threshold, target reflection information is generated based on the candidate preset reflection information.

[0108] In some implementations, the determining module is further configured to generate target reflection information based on candidate preset reflection information when the target similarity value is greater than or equal to a preset threshold.

[0109] In some implementations, the processor is further configured to generate target reflection information based on candidate preset reflection information when the target similarity value is greater than or equal to a preset threshold.

[0110] Specifically, the server compares the calculated target similarity value with a preset threshold. If the target similarity value is greater than or equal to the preset threshold, the server considers the candidate preset reflection information to be sufficiently relevant to the first output information, and the server can select the most similar candidate reflection information as the target reflection information.

[0111] Thus, by setting a threshold, the candidate preset reflection information is only used when the similarity is high enough, thereby improving the accuracy of decision-making.

[0112] Please see Figure 6 In some implementations, the method further includes:

[0113] 03252: If the preset execution result corresponding to the target reflection information is an execution anomaly, the preset execution operation information in the target reflection information is sent to the vehicle to complete vehicle control.

[0114] In some implementations, the determining module is further configured to send the preset execution operation information in the target reflection information to the vehicle in order to complete vehicle control when the preset execution result corresponding to the target reflection information is an execution exception.

[0115] In some implementations, the processor is further configured to send preset execution operation information from the target reflection information to the vehicle in the event that the preset execution result corresponding to the target reflection information is an execution exception, so as to complete vehicle control.

[0116] Specifically, preset execution operation information refers to a series of standardized operation instructions pre-set in the in-vehicle intelligent assistant system. These instructions guide the vehicle to perform specific actions under certain circumstances. When the server detects that the preset execution result corresponding to the candidate preset reflection information is an execution anomaly, it sends these preset execution operation information to the vehicle to complete vehicle control. For example, if a program on the in-vehicle display becomes unresponsive, it exits to the main interface and re-enters the program.

[0117] The server first filters from a pre-defined experience base to select the candidate pre-defined reflection information that best matches the current situation; this is the target reflection information. Next, the server checks the corresponding pre-defined execution results in these candidate reflection information. If a pre-defined execution result is marked as "execution exception," it means that in similar situations, the previous execution action failed to complete the task successfully. In this case, the server sends pre-defined execution operation information from the candidate pre-defined reflection information to the vehicle. This operation information represents a pre-defined solution for the execution exception. The vehicle then executes the corresponding control actions based on the sent pre-defined execution operation information to resolve or correct the execution exception.

[0118] In this way, the system can respond quickly when it detects execution anomalies and take corrective measures, improving the system's fault handling capabilities, enhancing the stability and reliability of vehicle control, and thus improving the user experience and the overall performance of the system.

[0119] Please see Figure 7 In some implementations, the method further includes:

[0120] 03253: If the preset execution result corresponding to the target reflection information is successful, the target execution action is determined based on the first preset model, the first voice request, and the current state information.

[0121] In some implementations, the determining module is used to determine the target execution action based on a first preset model, according to the first voice request and the current state information, when the preset execution result corresponding to the target reflection information is successful.

[0122] In some implementations, the processor is further configured to determine the target execution action based on the first preset model, according to the first voice request and the current state information, if the preset execution result corresponding to the target reflection information is successful.

[0123] Specifically, the server first filters candidate pre-defined reflection information from a pre-defined experience base to select the most suitable match for the current situation. The server then checks the corresponding pre-defined execution results in these candidate reflection information. If the pre-defined execution result is marked as "execution successful," it means that in similar situations, the previous execution action successfully completed the task. In this case, the server determines the target execution action based on the first voice request and the current state information. This is based on experience from successful cases, and the server believes that similar execution actions are likely to succeed as well.

[0124] In this way, the system can use historical success stories to guide current decisions, thereby improving the accuracy and success rate of actions, enhancing the system's intelligent decision-making capabilities, and improving task execution efficiency and user experience.

[0125] Please see Figure 8 In some implementations, step 0325 (generating target reflection information based on target similarity value, preset threshold, and candidate preset reflection information) includes:

[0126] 03254: When the target similarity value is less than the preset threshold, generate a template based on the preset reflection information, and generate target reflection information based on the preset reflection knowledge, the first voice request and the current state information.

[0127] In some implementations, the determining module is used to generate a template based on preset reflection information when the target similarity value is less than a preset threshold, and to generate target reflection information based on preset reflection knowledge, the first voice request and the current state information.

[0128] In some implementations, the processor is further configured to generate a template based on preset reflection information when the target similarity value is less than a preset threshold, and to generate target reflection information based on preset reflection knowledge, the first voice request and the current state information.

[0129] Specifically, pre-defined reflective knowledge refers to a series of rules and guidelines pre-set in the in-vehicle intelligent assistant system to help the intelligent assistant make correct decisions and operations in specific situations. For example, the pre-defined reflective knowledge might be: "The agent can be operated when the vehicle is in P gear; when the vehicle is in D gear, operations that may affect driving require secondary confirmation." An application scenario might be: "When a user requests the intelligent assistant to perform an operation while driving, the system needs to check the current vehicle gear position. If the vehicle is in D gear (driving gear), the system will require the user to confirm again to ensure that the operation will not distract the driver or affect driving safety." Another example is: "If the vehicle screen is currently displaying an advertisement page, the back button needs to be selected. If there is no cross or back button on the page, any blank space can be clicked." An application scenario might be: "When a user wants to perform an operation, but the vehicle screen displays an advertisement page, the intelligent assistant needs to recognize this situation and guide the user back to the main interface. If there is no obvious close button on the page, the intelligent assistant will instruct the user to click a blank area on the screen to close the advertisement."

[0130] The server first calculates the target similarity value, then compares the calculated similarity value with a preset threshold. The preset threshold is a standard set in the system to determine whether the similarity is high enough.

[0131] If the target similarity value is less than a preset threshold, the server considers the existing preset reflection information insufficiently matched to the current situation. Therefore, based on the preset reflection information generation template, the server generates target reflection information according to preset reflection knowledge, the first voice request, and the current state information. In some implementations, the preset reflection information generation template is as follows:

[0132] Imagine you are an intelligent assistant. The agent is currently in an abnormal state and needs to reflect on its actions and output a reflection action that allows it to continue completing its original task. I will provide you with the following reference information. Please use this information to output a reflection plan and reflection actions:

[0133] User task: <User voice request query>

[0134] Current status: <Input information template>

[0135] Historical operation information: <historical plan:P>, <historical action:A>

[0136] Reference knowledge: <Pre-set reflection knowledge>

[0137] Based on the information above, please output your reflection plan and reflection actions concisely, within 20 words:

[0138] Output:

[0139] A target reflection information generated based on the aforementioned preset reflection information generation template might be: In the last operation, the agent selected the "Go here" button but failed to complete the task. The current screen status in the car is an advertising page. The vehicle's infotainment system is in park (P) gear, with no music playing, and the interior temperature is 22 degrees Celsius. Now, close the advertising page on the vehicle's display screen. After generating the above target reflection information, the server processes it according to the first preset model to determine whether the task can continue. If not, it regenerates new target reflection information until the preset target reflection information generation limit is reached or the task is successfully executed. During this process, each generated target reflection information, voice request, and current status are recorded for subsequent updates to the preset experience base.

[0140] In this way, the system can flexibly generate new reflective information when encountering uncommon or novel situations, thereby improving the system's adaptability and intelligence, enhancing its ability to handle unknown situations, and promoting the system's continuous learning and self-optimization.

[0141] Please see Figure 9 In some implementations, the method further includes:

[0142] 04: If the target object is confirmed to be in an abnormal state based on the current status information, it is confirmed that the target's execution action has become abnormal.

[0143] In some implementations, the confirmation module is used to confirm that the target's action has become abnormal if the target detection object is found to be in an abnormal state based on the current state information.

[0144] In some implementations, the processor is also configured to confirm that the target's execution action has become abnormal if the target detection object is found to be in an abnormal state based on the current state information.

[0145] Specifically, an abnormal state of the detected object refers to a situation in the in-vehicle intelligent assistant system where the detected object (such as vehicle components, external environmental factors, etc.) does not exhibit a normal or expected state. Examples include: the in-vehicle display screen remaining inactive for more than n seconds; the vehicle's status repeatedly changing within n seconds; the in-vehicle display screen's status repeatedly changing within n seconds; the user not responding within n seconds after a follow-up question; the in-vehicle display screen remaining on an advertising page; and the in-vehicle display screen being on an unclickable image page.

[0146] The server continuously receives and monitors the vehicle's current status information, which may include various vehicle performance indicators, sensor data, user feedback, etc. The server then analyzes this information according to a pre-defined model to identify any abnormal states. If the analysis indicates an abnormal state in the target object (such as a vehicle component or system), the server will confirm that the target's action has malfunctioned. Once the anomaly is confirmed, the server generates target reflection information to ensure the vehicle can safely and effectively respond to the current situation.

[0147] In this way, the system can promptly detect and respond to abnormal vehicle conditions, thereby preventing potential malfunctions or dangers, improving vehicle safety and reliability, and enhancing the system's intelligence and user experience.

[0148] This application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the steps of the vehicle control method described above.

[0149] It is understood that a computer program includes computer program code. Computer program code can be in the form of source code, object code, executable files, or some intermediate form. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, external hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0150] In this specification, the terms "specifically," "furthermore," "particularly," "understandably," etc., refer to specific features, structures, materials, or characteristics described in connection with embodiments or examples that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0151] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of executable request code comprising one or more steps for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0152] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A vehicle control method, characterized in that, The method includes: Receive a first voice request forwarded by the vehicle and the current status information of the vehicle, the current status information including the current display content information of the vehicle display components and the current perception information of the vehicle; Based on the first preset model, the target action is determined according to the first voice request and the current state information, and the target action is sent to the vehicle to control the vehicle to execute the target action; In the event that the vehicle malfunctions while performing the target action, a first output message is generated based on the first voice request, the current status information, and the historical operation information associated with the first voice request. The historical operation information includes historical operation description information and historical execution operation information. Based on the second preset model, target reflection information is generated according to the first output information and the preset experience base, so as to control the vehicle according to the target reflection information. The target reflection information includes a correction execution strategy for correcting the anomaly. The preset experience base includes multiple preset reflection information. The preset reflection information includes preset historical operation description information, preset state information, preset execution results, and preset execution operation information. The preset execution operation information is a description of the operation instructions that the vehicle may execute. The preset state information describes the vehicle state and environmental information when the vehicle executes the target operation. The preset execution results record the execution results of the preset execution operation information and the preset state information. The preset execution operation information includes the execution actions in the target operation and state.

2. The vehicle control method according to claim 1, characterized in that, The generation of the target reflection information based on the second preset model, according to the first output information and the preset experience base, includes: Based on the historical operation description information in the first output information and the preset historical operation description information, the operation similarity is determined; Determine the state similarity based on the current state in the first output information and the preset state information; The target similarity value is determined based on the operation similarity and the state similarity. Based on the target similarity value, candidate preset reflection information is determined from the preset experience base; The target reflection information is generated based on the target similarity value, the preset threshold, and the candidate preset reflection information.

3. The vehicle control method according to claim 2, characterized in that, The step of generating the target reflection information based on the target similarity value, the preset threshold, and the candidate preset reflection information includes: If the target similarity value is greater than or equal to the preset threshold, the target reflection information is generated based on the candidate preset reflection information.

4. The vehicle control method according to claim 3, characterized in that, The method further includes: If the preset execution result corresponding to the target reflection information is an execution exception, the preset execution operation information in the target reflection information is sent to the vehicle to complete the vehicle control.

5. The vehicle control method according to claim 3, characterized in that, The method further includes: If the preset execution result corresponding to the target reflection information is successful, the target execution action is determined based on the first preset model, the first voice request, and the current state information.

6. The vehicle control method according to claim 3, characterized in that, The step of generating the target reflection information based on the target similarity value, the preset threshold, and the candidate preset reflection information includes: If the target similarity value is less than the preset threshold, a template is generated based on preset reflection information, and the target reflection information is generated according to preset reflection knowledge, the first voice request, and the current state information.

7. The vehicle control method according to claim 1, characterized in that, The method further includes: If the target detection object is confirmed to be in an abnormal state based on the current state information, it is confirmed that the target's execution action has become abnormal.

8. A server, characterized in that, The server includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images