In-vehicle environment adjusting method, electronic equipment, storage medium and program product

Abstract

The invention provides an in-vehicle environment adjusting method, electronic equipment, a storage medium and a program product. Relates to the technical field of intelligent control. The method comprises the following steps: acquiring sound information, environment information and driving information in a vehicle; processing the sound information through a pre-trained sound detection model to obtain a sound event corresponding to the sound information; determining a demand scene corresponding to the sound event based on the sound event, the environment information and the driving information; generating a control strategy corresponding to the demand scene based on the demand scene, the environment information and the driving information; and executing the control strategy. According to the invention, the effect of actively and accurately adjusting the environment in the vehicle is achieved.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to a method for regulating the in-vehicle environment, electronic devices, storage media, and program products. Background Technology

[0002] In the era of intelligent vehicles, driving comfort and personalization are receiving increasing attention. Drivers can adjust the vehicle's interior temperature, fan speed, windows, and other environmental conditions according to their own and / or passengers' individual needs through knobs, screens, or voice control, thus meeting the personalized needs of both drivers and passengers.

[0003] In related technologies, the personalized adjustment of the in-vehicle environment through human-computer interaction by the driver has the problem of not being able to intelligently and timely adjust the in-vehicle environment according to individual needs.

[0004] Therefore, there is an urgent need for a proactive and accurate in-vehicle environment adjustment solution. Summary of the Invention

[0005] This application provides a method for regulating the in-vehicle environment, electronic devices, storage media, and program products to achieve an active and accurate in-vehicle environment regulation effect.

[0006] Firstly, this application provides a method for adjusting the in-vehicle environment, including:

[0007] Acquire sound information, environmental information, and driving information from inside the vehicle;

[0008] The sound information is processed by a pre-trained sound detection model to obtain the sound events corresponding to the sound information;

[0009] Based on sound events, environmental information, and driving information, determine the corresponding demand scenarios for the sound events;

[0010] Based on the demand scenario, environmental information, and driving information, generate control strategies corresponding to the demand scenario;

[0011] Implement control strategies.

[0012] In one possible implementation, the method further includes the following steps before executing the control policy:

[0013] The control strategy is presented to the user through voice broadcast and / or text display;

[0014] Obtain user feedback on the control policy; the feedback is used to indicate whether the control policy should be implemented.

[0015] Enforcement control policies, including:

[0016] When feedback indicates that a control strategy should be implemented, the control strategy should be implemented.

[0017] One possible implementation involves acquiring in-vehicle sound information, environmental information, and driving information, including:

[0018] The sound information inside the vehicle is collected in real time through a distributed microphone array;

[0019] By exchanging information with the vehicle bus, environmental and driving information of the vehicle can be obtained.

[0020] In one possible implementation, sound events include: biological acoustic events, human voice command events, human voice non-semantic events, and / or environmental events.

[0021] One possible implementation scenario includes: health care, safety alarms, comfort and convenience, and / or cabin cleaning.

[0022] In one possible implementation, the training process of the sound detection model includes:

[0023] Obtain the sound training database, which includes sound signals and the corresponding sound event types;

[0024] Based on the sound training database, the correlation information between sound signals and sound event types is learned, and a sound detection model is trained.

[0025] In one possible implementation, the voice training database includes:

[0026] Biological acoustic signals and the corresponding biological acoustic events;

[0027] Human voice command signals and the corresponding human voice command events;

[0028] Non-semantic signals of human voice and the corresponding non-semantic events of human voice; and

[0029] Environmental signals and the corresponding environmental events.

[0030] Secondly, this application provides an in-vehicle environment regulating device, comprising:

[0031] The acquisition module is used to acquire sound information, environmental information, and driving information from inside the vehicle.

[0032] The processing module is used to obtain the sound events corresponding to the sound information through a pre-trained sound detection model; determine the demand scenario corresponding to the sound event based on the sound event, environmental information, and driving information; generate the control strategy corresponding to the demand scenario based on the demand scenario, environmental information, and driving information; and execute the control strategy.

[0033] In one possible implementation, before executing the control strategy, the processing module is further configured to:

[0034] The control strategy is presented to the user through voice broadcast and / or text display;

[0035] Obtain user feedback on the control policy; the feedback is used to indicate whether the control policy should be implemented.

[0036] Enforcement control policies, including:

[0037] When feedback indicates that a control strategy should be implemented, the control strategy should be implemented.

[0038] In one possible implementation, the acquisition module is specifically used for:

[0039] The sound information inside the vehicle is collected in real time through a distributed microphone array;

[0040] By exchanging information with the vehicle bus, environmental and driving information of the vehicle can be obtained.

[0041] In one possible implementation, sound events include: biological acoustic events, human voice command events, human voice non-semantic events, and / or environmental events.

[0042] One possible implementation scenario includes: health care, safety alarms, comfort and convenience, and / or cabin cleaning.

[0043] In one possible implementation, during the training process of the sound detection model, the processing module is further used for:

[0044] Obtain the sound training database, which includes sound signals and the corresponding sound event types;

[0045] Based on the sound training database, the correlation information between sound signals and sound event types is learned, and a sound detection model is trained.

[0046] In one possible implementation, the voice training database includes:

[0047] Biological acoustic signals and their corresponding biological acoustic events; human voice command signals and their corresponding human voice command events; non-semantic human voice signals and their corresponding non-semantic human voice events; and environmental signals and their corresponding environmental events.

[0048] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0049] The memory stores the instructions that the computer executes;

[0050] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0051] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0052] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0053] Sixthly, this application provides a vehicle in which an in-vehicle environment regulation device as described in the second aspect and / or various possible embodiments of the second aspect is provided.

[0054] The in-vehicle environment adjustment method, electronic device, storage medium, and program product provided in this application, by accurately acquiring in-vehicle sound information, environmental information, and driving information, can comprehensively and in real-time grasp various in-vehicle indicators, providing detailed and accurate data support for subsequent in-vehicle environment adjustment decisions. Simultaneously, by combining sound information, environmental information, and driving information, the in-vehicle environment can be adjusted more rationally. A pre-trained sound detection model processes the sound information to obtain the corresponding sound events. This pre-trained sound detection model can quickly and accurately acquire the sound events corresponding to the sound information, improving the processing speed of in-vehicle environment adjustment. Based on sound events, environmental information, and driving information, the corresponding demand scenarios for the sound events are determined, enabling a comprehensive understanding of the vehicle's situation and avoiding the limitations of judging demand scenarios with single information, thus more accurately identifying the demand scenarios. Based on the demand scenarios, environmental information, and driving information, control strategies corresponding to the demand scenarios are generated; this ensures that the control strategies are targeted and can better adapt to the actual conditions inside the vehicle. Executing the control strategies achieves proactive, accurate, and intelligent environmental adjustment, improving driving comfort and safety. Attached Figure Description

[0055] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0056] Figure 1 A schematic diagram illustrating a scenario for the in-vehicle environment adjustment method provided in an embodiment of this application;

[0057] Figure 2 Flowchart of the in-vehicle environment adjustment method provided in the embodiments of this application Figure 1 ;

[0058] Figure 3 Flowchart of the in-vehicle environment adjustment method provided in the embodiments of this application Figure 2 ;

[0059] Figure 4 This is a schematic diagram of the in-vehicle environment regulation device provided in the embodiments of this application;

[0060] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0061] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0062] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0063] In related technologies, the personalized adjustment of the in-vehicle environment through human-computer interaction by the driver has the problem of not being able to intelligently and promptly adjust the in-vehicle environment according to individual needs.

[0064] The in-vehicle environment adjustment method provided in this application combines sound information, environmental information, and driving information to more rationally adjust the in-vehicle environment. A pre-trained sound detection model processes the sound information to obtain corresponding sound events. This pre-trained model enables rapid and accurate acquisition of sound events, improving the processing speed of in-vehicle environment adjustment. Based on sound events, environmental information, and driving information, the corresponding demand scenarios are determined, providing a comprehensive understanding of the vehicle's situation and avoiding the limitations of judging demand scenarios based on single information, thus more accurately identifying the demand scenarios. Based on the demand scenarios, environmental information, and driving information, a control strategy corresponding to the demand scenarios is generated; this ensures the control strategy is targeted and better adapts to the actual conditions inside the vehicle. Executing the control strategy achieves proactive, accurate, and intelligent environmental adjustment, improving driving comfort and safety.

[0065] Figure 1 This is a schematic diagram illustrating a scenario for the in-vehicle environment adjustment method provided in an embodiment of this application. Figure 1 As shown, the specific application scenarios of this application include vehicle 11 and user 12, wherein:

[0066] The vehicle 11 is equipped with a microphone array 111, sensors 112, and a control center 113. The microphone array 111, sensors 112, and control center 113 enable close and efficient interaction with the user 12 to better meet the user's needs. The vehicle 11 collects sound information through the microphone array 111 and environmental and driving information through the sensors 112.

[0067] After receiving the sound information collected by the microphone array 111, the control center 113 analyzes the sound information using a pre-trained sound detection model to determine the corresponding sound event. Then, the control center 113 analyzes the environmental and driving information collected by the sensor 112 along with the sound event to determine the user 12's required scenario. Based on this scenario, the control center 113 generates and executes a control strategy to adjust the vehicle 11's environment.

[0068] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0069] Figure 2 Flowchart of the in-vehicle environment adjustment method provided in the embodiments of this application Figure 1 .like Figure 2As shown, the method includes:

[0070] S201. Obtain sound information, environmental information, and driving information inside the vehicle.

[0071] Sound information refers to the sounds generated inside the vehicle due to vehicle activity, occupant activity, and other actions. Optionally, sound information includes bioacoustic signals, human voice command signals, occupant activity signals, and vehicle movement signals. Bioacoustic signals include signals such as coughing and sneezing, as well as sounds from other animals. Human voice command signals include commands given to the vehicle by the user. For example, a human voice command signal might be "open the sunroof." Occupant activity signals include sound signals generated when the user is active within the vehicle. For example, an occupant activity signal might be the sound of a user opening a package. Vehicle movement signals include sounds emitted by different components within the vehicle during operation, as well as sounds generated while traveling on different roads. For example, vehicle movement signals might include the sound of the engine running, the sound of wind passing through the vehicle's interior, and the sound of tires on different roads—sounds that may exist during vehicle movement.

[0072] Optionally, a microphone can be installed inside the vehicle to capture sound information from inside the vehicle.

[0073] Environmental information includes the vehicle's internal environmental conditions, such as temperature, humidity, and air quality. Furthermore, to provide detailed information on potential changes in the vehicle's internal environment over time, the environmental information also includes the operational status of the vehicle's interior environmental control components. Optionally, these components include devices that regulate the vehicle's interior environment, such as air conditioners, air purifiers, and humidifiers. For example, when the environmental control components include an air conditioner, the operational status of these components includes information such as whether the air conditioner is on, its set temperature, fan speed, and current operating power.

[0074] Furthermore, the environmental information also includes information about the vehicle's external environment. Optionally, based on the vehicle's location information, the environmental information of the location information can be obtained to obtain the vehicle's external environmental information. Optionally, based on sensors deployed outside the vehicle, information such as temperature and air quality outside the vehicle can be obtained to obtain the vehicle's external environmental information.

[0075] Optionally, sensors such as temperature sensors, humidity sensors, and air quality sensors can be installed both inside and outside the vehicle. Environmental information is obtained through these sensors and then transmitted to the vehicle's control center via an in-vehicle network.

[0076] Driving information includes vehicle speed, acceleration, engine speed, and other data. Optionally, the vehicle's control center can interact with other components within the vehicle via a bus to obtain driving information.

[0077] Optionally, an intelligent in-vehicle terminal with multiple sensors can be integrated into the vehicle. This intelligent in-vehicle terminal simultaneously collects sound, environmental, and driving information. Furthermore, the intelligent in-vehicle terminal can interact with other vehicle systems via wireless communication technology to comprehensively acquire information.

[0078] S202. Process the sound information using a pre-trained sound detection model to obtain the sound events corresponding to the sound information.

[0079] Sound information is used as input to a pre-trained sound detection model. The model learns and classifies the sound information using feature extraction and classification algorithms to determine the corresponding sound event type. This pre-trained model can accurately identify various sound events associated with the sound information.

[0080] A pre-trained sound detection model is a model pre-trained based on a deep learning algorithm. This model is used to identify and classify sound information. A sound event is an event corresponding to the sound information obtained by classifying it. For example, sound events include coughing, sneezing, and a baby crying.

[0081] Optionally, a pre-trained sound detection model can be deployed in the vehicle's central processing unit. The central processing unit can then call the sound detection model to process the collected sound information and output the sound events corresponding to the sound information.

[0082] Optionally, cloud computing technology is used to upload the sound information to a cloud server, where a pre-trained sound detection model is deployed. The cloud server calls the pre-trained sound detection model to process the sound information and obtain the corresponding sound events. Then, the cloud server returns the corresponding sound events to the vehicle's central processing unit.

[0083] S203. Based on sound events, environmental information, and driving information, determine the corresponding demand scenarios for the sound events.

[0084] The demand scenario is a comprehensive judgment based on sound events, environmental information, and driving information to determine the specific current demand situation inside the vehicle.

[0085] Optionally, sound events, environmental information, and driving information can be fused and analyzed to determine the current demand scenario through a rule engine or machine learning model.

[0086] For example, if the sound event includes a cough, and the environmental information includes the air conditioner being in strong cooling mode and the outside temperature being low, then the corresponding demand scenario is that the occupant may cough due to the cold.

[0087] For example, if the sound event includes a baby crying, the environmental information includes driving at night, and the driving information includes the vehicle being at high speed, then the corresponding demand scenario is that the baby may be crying due to discomfort and needs to be soothed.

[0088] Optionally, if the vehicle can also detect the user's physiological information, the corresponding demand scenario for the sound event can be determined based on the sound event, environmental information, and driving information. This includes determining the demand scenario corresponding to the sound event based on the sound event, environmental information, physiological information, and driving information. For example, if the sound event includes rapid breathing, the biological information includes a spike in the driver's heart rate, and the driving information includes the vehicle being stationary, then the corresponding demand scenario is a potential medical emergency.

[0089] Optionally, a rules engine can be deployed in the vehicle's central processing unit. This rules engine contains pre-defined rules for determining various demand scenarios based on sound events, environmental information, and driving information. Based on these factors, the rules engine matches and judges the information to determine the corresponding demand scenario for each sound event.

[0090] Optionally, a machine learning model can be deployed in the vehicle's central processing unit. This model is trained on a large amount of historical data and is capable of accurately identifying demand scenarios under various complex conditions. Upon acquiring new sound events, environmental information, and driving information, the machine learning model is invoked to predict and judge potential demand scenarios, thus determining the demand scenario corresponding to the sound event.

[0091] S204. Based on the demand scenario, environmental information, and driving information, generate the control strategy corresponding to the demand scenario.

[0092] Based on the demand scenario, environmental information, and driving information, a control strategy corresponding to the demand scenario is generated. The control strategy is a control command that conforms to the demand scenario, environmental information, and driving information. By executing the control strategy, intelligent and user-friendly control of the vehicle system can be achieved.

[0093] Optional control strategies include: adjusting the air conditioning temperature, switching the air circulation mode, playing entertainment content, and other control commands to the vehicle system.

[0094] Optionally, a control strategy generation algorithm can be deployed in the vehicle's central processing unit. This algorithm generates a control strategy corresponding to a given scenario based on preset rules and logic, combined with the scenario's requirements, environmental information, and driving information. For example, when the scenario is "occupants may cough due to cold," the algorithm generates the control strategy "increase the air conditioning temperature" based on preset rules and logic.

[0095] Optionally, a reinforcement learning model can be deployed in the vehicle's central processing unit. This model continuously learns and optimizes control strategies through interaction with the environment to adapt to demanding scenarios under complex conditions. By combining demand scenarios, environmental information, and driving information, the reinforcement learning model generates control strategies corresponding to the specific demand scenarios.

[0096] S205, Implement control policies.

[0097] The generated control strategy is sent to the corresponding actuators in the vehicle to achieve actual control of the vehicle system. Optional actuators include systems such as the air conditioning system, entertainment system, and window control system.

[0098] Optionally, the control strategy can be sent to the actuators via the vehicle network or CAN bus, and the actuators will perform corresponding operations according to the control strategy. By executing the control strategy, the vehicle system can achieve intelligent and human-centered responses, improving passenger comfort and safety.

[0099] Optionally, for actuators that support wireless communication, the vehicle's central processing unit can send control strategies to the corresponding actuators via wireless communication technology. Upon receiving the control strategy, the actuators perform the corresponding operations to achieve intelligent control of the vehicle system.

[0100] The in-vehicle environment adjustment method provided in this application accurately acquires in-vehicle sound information, environmental information, and driving information, enabling comprehensive and real-time monitoring of various in-vehicle indicators and providing detailed and accurate data support for subsequent in-vehicle environment adjustment decisions. Simultaneously, by combining sound, environmental, and driving information, the in-vehicle environment can be adjusted more rationally. A pre-trained sound detection model processes the sound information to obtain corresponding sound events. This pre-trained model allows for rapid and accurate acquisition of sound events, improving the processing speed of in-vehicle environment adjustment. Based on sound events, environmental information, and driving information, the corresponding demand scenarios are determined, providing a comprehensive understanding of the vehicle's situation and avoiding the limitations of judging demand scenarios based on single information, thus more accurately identifying the demand scenarios. Based on the demand scenarios, environmental information, and driving information, a control strategy corresponding to the demand scenarios is generated, ensuring the control strategy is targeted and better adapts to the actual conditions inside the vehicle. Executing the control strategy achieves proactive, accurate, and intelligent environmental adjustment, improving driving comfort and safety.

[0101] In one possible implementation, prior to step S205, the method further includes:

[0102] Step A: Present the control strategy to the user through voice broadcast and / or text display.

[0103] After generating the control strategy, it is converted into speech or text format, resulting in a speech version of the control strategy and / or a text version. Then, the speech version of the control strategy is read aloud via the in-vehicle voice system, and / or the text version of the control strategy is displayed on a screen. Optionally, after generating the control strategy text, speech synthesis technology is used to convert the text into speech, enabling the speech reading of the control strategy.

[0104] By utilizing the in-vehicle voice system, control policies are presented to users in the form of voice announcements, allowing them to understand the policies without looking at the screen. Alternatively, control policies can be presented as text via the in-vehicle display screen or an application on the user's mobile device, enabling users to read and understand them. This process ensures that users can understand the control policies promptly and conveniently, enhancing their perception and control of the vehicle system and improving the user experience.

[0105] Furthermore, after the control policy text is sent to the in-vehicle touchscreen or the vehicle control application on the user's mobile phone, the application displays the control policy text on the screen in a clear and easy-to-read format. For example, the in-vehicle touchscreen displays: "Control Policy: Increase the air conditioning temperature to 26 degrees Celsius. Please confirm whether to execute." Confirm and reject buttons are also provided for the user to select.

[0106] For example, when the control policy is "raise the air conditioning temperature to 26 degrees Celsius", the generated control policy text is: "The current environment is relatively cold. It is recommended to set the air conditioning temperature to 26 degrees Celsius. Do you want to execute this recommendation?". Then, speech synthesis technology is used to convert the control policy text into speech, which is then read aloud through the in-vehicle voice system, thus realizing the voice announcement of the control policy.

[0107] Step B: Obtain user feedback on the control policy. The feedback is used to indicate whether the control policy should be implemented.

[0108] Feedback is the user's response to whether or not the control policy should be implemented, and it clearly indicates whether the user agrees to implement the control policy.

[0109] After presenting the control strategy, the system awaits user feedback. Users can provide feedback via voice commands, touchscreen buttons, and / or mobile application buttons. By obtaining user feedback, the system respects user wishes, avoids automatically executing control strategies that may not meet user needs or preferences, and thus improves user satisfaction and trust.

[0110] Accordingly, the execution control strategy in step S205 includes: executing the control strategy when the feedback indicates that the control strategy should be executed.

[0111] After receiving user feedback, the system analyzes it. If the feedback indicates the need to execute a control strategy, the system sends the control strategy to the appropriate actuator, which then executes the strategy to ensure it aligns with the user's wishes. This enhances the intelligence and user-friendliness of the vehicle system, further increasing user satisfaction and trust.

[0112] Figure 3 Flowchart of the in-vehicle environment adjustment method provided in the embodiments of this application Figure 2 .like Figure 3 As shown, in this embodiment... Figure 2 Based on the embodiments, step S201 in the in-vehicle environment adjustment method will be described in detail. Step S201 may further include:

[0113] S2011: Real-time acquisition of sound information inside the vehicle via a distributed microphone array.

[0114] Multiple microphones arranged in a specific spatial layout are installed at suitable locations inside the vehicle, forming a distributed microphone array. This distributed arrangement allows for more comprehensive and accurate acquisition of sound information from different areas within the vehicle, reducing blind spots in sound acquisition. The sound is captured in real-time through the continuous operation of each microphone in the array. The sound captured by each microphone is converted into an electrical signal, yielding sound data for each microphone. By integrating the sound data from all microphones, the overall sound information within the vehicle is obtained. Optionally, the sound data is transmitted to the vehicle's sound processing unit via a signal transmission line. The sound processing unit performs preprocessing and integration of the received sound data to obtain the sound information within the vehicle, removing noise interference and improving the quality of the sound signal.

[0115] By employing a distributed microphone array, sound signals can be collected from different angles and positions within the vehicle, capturing sound from every corner of the interior. Optionally, by integrating the sound data from different microphones within the distributed array, the source of the sound can be located, resulting in a more accurate and richer sound signal.

[0116] For example, a main microphone is installed in the center of the car's roof, while an auxiliary microphone is installed above the inner side of each of the four doors, forming a distributed microphone array. After the vehicle is started, the microphone array begins to work in real time, transmitting the collected sound signals to the vehicle's center console through a dedicated audio line inside the car.

[0117] Optionally, if the vehicle has a large interior space, a set of microphone units can be installed in different parts of the vehicle, with each microphone unit including multiple microphones. A microphone array is formed by multiple microphone units.

[0118] For example, a set of microphone units is installed at the front, middle, and rear of a large bus. The microphones within each microphone unit are evenly distributed on the top of their respective areas. The microphone units can communicate with each other via a bus, forming a microphone array of three units. The microphone array then transmits the collected sound signals to the central control unit in the bus driver's cab via a wireless transmission module.

[0119] S2012. By exchanging information with the vehicle bus, the vehicle's environmental and driving information is obtained.

[0120] A vehicle bus is a channel for information transmission and sharing among various electronic control units within a vehicle. It enables high-speed, reliable data communication between different components, connecting various vehicle systems into an organic whole. Through information interaction with the vehicle bus, information between different vehicle systems is obtained, leading to environmental and driving information. By interacting with the bus, environmental and driving information from various vehicle systems can be centrally acquired, enabling comprehensive monitoring of the vehicle's status and providing rich data support for intelligent vehicle control and decision-making.

[0121] Optionally, the vehicle is equipped with multiple sensors that can collect environmental and driving information. Sensor information is obtained by collecting information from multiple sensors. This sensor information is then transmitted to the vehicle's central processing unit via a bus.

[0122] In one possible implementation, sound events include: biological acoustic events, human voice command events, human voice non-semantic events, and / or environmental events.

[0123] Biological acoustic events refer to sounds related to the physiological activities of organisms. Biological acoustic events can reflect the health status or physiological needs of humans or animals. Optionally, biological acoustic events include physiological activity signals such as coughing, sneezing, and snoring.

[0124] Voice command events refer to voice commands issued by occupants inside the vehicle that have clear and meaningful meaning and can be used to directly control various functions or devices of the vehicle. Optionally, voice command events include commands such as "turn on the air conditioning" or "turn up the volume".

[0125] Non-semantic events of human voice refer to sounds made by occupants in a vehicle that do not contain explicit semantic commands but convey certain emotional or state information. Non-semantic events of human voice can reflect the emotional state of the occupants. Optionally, non-semantic events of human voice include sighs, laughter, and crying, among other non-semantic events.

[0126] Environmental events refer to sounds generated by the vehicle's environment, including external traffic noise, natural sounds, and sounds generated by the operation of internal vehicle equipment. For example, traffic noise includes car horns and braking sounds; natural sounds include wind, rain, and thunder; and sounds generated by internal vehicle equipment include air conditioning operation and seat adjustment. By acquiring the types of sound events, a more comprehensive understanding of the occupants' status and the environmental conditions can be achieved, contributing to more intelligent vehicle control and services.

[0127] For example, when passengers inside the vehicle laugh, it is identified as a non-semantic event. Based on the laughter, the system determines that the atmosphere inside the vehicle is relaxed and pleasant. At this time, the interior lighting is adjusted to a warm tone to create a more welcoming atmosphere. When an external car horn is heard while the vehicle is in motion, it is identified as an environmental event. The system analyzes the potential traffic safety hazard and provides a voice prompt to the driver to pay attention to the surrounding road conditions.

[0128] One possible implementation scenario includes: health care, safety alarms, comfort and convenience, and / or cabin cleaning.

[0129] In scenarios requiring health and wellness care, services tailored to the health status and needs of vehicle occupants are needed. In scenarios requiring safety alerts, warning messages need to be issued to vehicle occupants when the vehicle faces potential safety risks or has already experienced a safety issue. Optionally, the warning messages may include one or more of the following: collision warning, driver fatigue alert, and vehicle malfunction warning.

[0130] In scenarios requiring comfort and convenience, the in-vehicle environment can be adjusted to enhance passenger comfort and ease of operation. Optional control strategies for these scenarios include one or more methods such as automatic seat adjustment, temperature and humidity control. In scenarios requiring cabin cleanliness, the vehicle cabin interior needs to be cleaned and purified to maintain fresh air and a tidy environment.

[0131] By setting different demand scenarios, the system can provide targeted services and functions for occupants, fully meeting their diverse and personalized needs. Simultaneously, by accurately identifying demand scenarios and automatically triggering corresponding control strategies, the system can promptly and effectively meet user needs in various situations, allowing users to experience the vehicle's thoughtfulness and practicality, thereby enhancing user trust and satisfaction.

[0132] In one possible implementation, the training process of the sound detection model includes:

[0133] Step A: Obtain the sound training database, which includes sound signals and the corresponding sound event types.

[0134] The sound training database contains a large number of sound signal samples and a corresponding sound event type label for each sample. The data in the sound training database is the foundation for the sound detection model to learn the relationship between sound features and event types. Sound signals include features such as frequency, amplitude, and timbre, reflecting various physical characteristics of sound. Sound event types are the types of sound events included in the sound signals after classification.

[0135] By using a sound training database, sufficient data support is provided for the training of the sound detection model, which helps the model learn a more comprehensive and accurate relationship between sound features and sound event types.

[0136] Step B: Based on the sound training database, learn the correlation information between sound signals and sound event types to train a sound detection model.

[0137] First, a suitable machine learning or deep learning algorithm is selected as the initial model for the sound detection model. Sound signals from the sound training database are used as input to the initial model, and the corresponding sound event types are used as output labels for training. During training, the initial model continuously adjusts its parameters, learning the mapping relationship between sound signal features and event types, gradually reducing the error between its predictions of known sound samples and the true labels. After multiple iterations of training, when the performance of the initial model reaches the preset performance metrics, training is complete, and the final sound detection model is obtained.

[0138] In one possible implementation, the sound training database includes: biological acoustic signals and corresponding biological acoustic events; human voice command signals and corresponding human voice command events; non-semantic human voice signals and corresponding non-semantic human voice events; and environmental signals and corresponding environmental events.

[0139] Biological acoustic signals are electrical signals representing sounds produced by the physiological activities of occupants inside a vehicle. Biological acoustic events are the types of physiological activities represented by biological acoustic signals.

[0140] A voice command signal is an electrical signal representing a voice issued by a person inside the vehicle that has a clear instruction meaning. A voice command event is the content of the instruction represented by the voice command signal.

[0141] Non-semantic human voice signals are electrical signals representing sounds emitted by occupants in a vehicle that do not contain explicit semantic commands but do convey certain emotions or state information. Non-semantic human voice events refer to the emotional state of the occupants reflected in these signals.

[0142] Environmental signals are electrical signals representing the sound generated by the vehicle's environment. Environmental events are the environmental conditions represented by environmental signals.

[0143] Figure 4 This is a schematic diagram of the in-vehicle environment adjustment device provided in an embodiment of this application. Figure 4 As shown, the in-vehicle environment adjustment device 40 provided in this embodiment includes:

[0144] The acquisition module 401 is used to acquire sound information, environmental information, and driving information inside the vehicle;

[0145] The processing module 402 is used to obtain the sound event corresponding to the sound information through a pre-trained sound detection model; determine the demand scenario corresponding to the sound event based on the sound event, environmental information and driving information; generate the control strategy corresponding to the demand scenario based on the demand scenario, environmental information and driving information; and execute the control strategy.

[0146] In one possible implementation, before executing the control strategy, the processing module 402 is further configured to:

[0147] The control strategy is presented to the user through voice broadcast and / or text display;

[0148] Obtain user feedback on the control policy; the feedback is used to indicate whether the control policy should be implemented.

[0149] Enforcement control policies, including:

[0150] When feedback indicates that a control strategy should be implemented, the control strategy should be implemented.

[0151] In one possible implementation, the acquisition module 401 is specifically used for:

[0152] The sound information inside the vehicle is collected in real time through a distributed microphone array;

[0153] By exchanging information with the vehicle bus, environmental and driving information of the vehicle can be obtained.

[0154] In one possible implementation, sound events include: biological acoustic events, human voice command events, human voice non-semantic events, and / or environmental events.

[0155] One possible implementation scenario includes: health care, safety alarms, comfort and convenience, and / or cabin cleaning.

[0156] In one possible implementation, during the training process of the sound detection model, the processing module 402 is further configured to:

[0157] Obtain the sound training database, which includes sound signals and the corresponding sound event types;

[0158] Based on the sound training database, the correlation information between sound signals and sound event types is learned, and a sound detection model is trained.

[0159] In one possible implementation, the voice training database includes:

[0160] Biological acoustic signals and their corresponding biological acoustic events; human voice command signals and their corresponding human voice command events; non-semantic human voice signals and their corresponding non-semantic human voice events; and environmental signals and their corresponding environmental events.

[0161] The in-vehicle environment adjustment device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0162] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0163] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0164] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0165] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0166] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0167] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings of this application's embodiments are not limited to only one bus or one type of bus.

[0168] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0169] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, implement any of the methods described above.

[0170] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0171] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0172] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0173] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0174] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0175] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0176] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0177] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for regulating the in-vehicle environment, characterized in that, include: Acquire sound information, environmental information, and driving information from inside the vehicle; The sound information is processed by a pre-trained sound detection model to obtain the sound event corresponding to the sound information; Based on the sound event, the environmental information, and the driving information, determine the demand scenario corresponding to the sound event; Based on the demand scenario, the environmental information, and the driving information, a control strategy corresponding to the demand scenario is generated. Execute the control strategy.

2. The method according to claim 1, characterized in that, Before executing the control strategy, the method further includes: The control strategy is presented to the user through voice broadcast and / or text display; Obtain feedback from the user regarding the control strategy, the feedback being used to indicate whether the control strategy should be executed; The execution of the control strategy includes: When the feedback indicates that the control strategy should be executed, the control strategy shall be executed.

3. The method according to claim 1, characterized in that, The acquisition of in-vehicle sound information, environmental information, and driving information includes: The sound information inside the vehicle is collected in real time through a distributed microphone array; The environmental information and driving information of the vehicle are obtained through information exchange with the vehicle bus.

4. The method according to claim 1, characterized in that, The sound events include: biological acoustic events, human voice command events, human voice non-semantic events, and / or environmental events.

5. The method according to claim 1, characterized in that, The demand scenarios include: health care, safety alarms, comfort and convenience, and / or cabin cleaning.

6. The method according to claim 1, characterized in that, The training process of the sound detection model includes: Obtain a sound training database, which includes sound signals and the sound event types corresponding to the sound signals; Based on the sound training database, the association information between the sound signal and the sound event type is learned, and the sound detection model is trained.

7. The method according to claim 6, characterized in that, The sound training database includes: Biological acoustic signals and the corresponding biological acoustic events; Human voice command signals and the corresponding human voice command events; Non-semantic signals of human voice and the corresponding non-semantic events of human voice; and Environmental signals and the corresponding environmental events.

8. A vehicle interior environment control device, characterized in that, include: The acquisition module is used to acquire sound information, environmental information, and driving information from inside the vehicle. The processing module is used to obtain the sound events corresponding to the sound information based on the sound information and through a pre-trained sound detection model; Based on sound events, environmental information, and driving information, determine the corresponding demand scenarios for the sound events; Based on the demand scenario, environmental information, and driving information, generate control strategies corresponding to the demand scenario; Used to execute the control strategy.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program, which, when executed, implements the method described in any one of claims 1-7.

12. A vehicle, characterized in that, The vehicle is equipped with the in-vehicle environment regulation device as described in claim 8.

Images