Method for adjusting cabin atmosphere and vehicle-mounted infotainment system

Abstract

The present application relates to a method for adjusting a cabin atmosphere, comprising: analyzing a received user instruction to determine a multimedia item expected to be played by a user (S1); generating multimedia fusion content about the cabin atmosphere state parameter based on the original content of the multimedia item and / or the acquired vehicle sensing information and / or the user state information (S2); and checking a multimedia playing condition at least based on the user instruction, the state parameter of the cabin atmosphere actuator, the collected vehicle sensing information and the user state information, and when the multimedia playing condition meets the requirement, generating a control parameter of the cabin atmosphere actuator for adjusting the cabin atmosphere based on the state parameter of the cabin atmosphere actuator and the multimedia fusion content (S3). According to the method and the device, the multimedia fusion content conforming to the generation is displayed in multiple aspects by automatically adjusting the cabin atmosphere while the multimedia item is played, so that personalized and customized immersive experience is provided, and a tedious manual setting process of a multimedia function is omitted.

Description

Technical Field

[0001] The present application relates to the field of in-vehicle entertainment, and in particular to a method for adjusting the cabin atmosphere, an in-vehicle infotainment system, a vehicle including the in-vehicle infotainment system according to the present application, and a computer program product for at least assisting in implementing the steps of the method according to the present application. Background Art

[0002] The in-vehicle infotainment system is an important part of the vehicle's smart cockpit, which provides various entertainment services for drivers and passengers. For example, when using the music playback function, the in-vehicle infotainment system can set the smart cockpit atmosphere while playing music tracks, including background images, text, atmosphere lights, etc., to provide passengers with an immersive entertainment experience. However, the current in-vehicle infotainment system can only adjust the smart cockpit atmosphere according to the fixed template provided by the content provider. It is fixed and single and difficult to match the current vehicle operating status and user emotional state, which affects the user's experience and willingness to use the in-vehicle infotainment system.

[0003] Therefore, there is room for improvement in the current in-vehicle infotainment system. Summary of the invention

[0004] The purpose of the present application is to provide a method for adjusting the cabin atmosphere, an in-vehicle infotainment system, a vehicle including the in-vehicle infotainment system according to the present application, and a computer program product, so as to at least partially solve the problems in the prior art.

[0005] According to a first aspect of the present application, a method for adjusting cabin atmosphere is provided, and the method may include:

[0006] - Step S1: The received user instruction may be analyzed to determine the multimedia item that the user desires to play;

[0007] - Step S2: generating multimedia fusion content about cabin atmosphere state parameters based on the original content of the multimedia project and / or the collected vehicle sensing information and / or user state information; and

[0008] -Step S3: checking multimedia playback conditions based at least on user instructions, state parameters of the cabin atmosphere actuator, collected vehicle sensing information and user state information, and if the multimedia playback conditions meet the requirements, generating control parameters of the cabin atmosphere actuator for adjusting the cabin atmosphere based on the state parameters of the cabin atmosphere actuator and the multimedia fusion content.

[0009] The core concept of the present application includes at least: performing semantic analysis on the original content of the multimedia project that the user expects to play, and generating cabin atmosphere state parameters that conform to the scenes, emotions, artistic conception, etc. to be expressed by the multimedia project as multimedia fusion content, and adjusting the multimedia fusion content and checking the multimedia playback conditions in combination with vehicle sensing information and user status information, and using a natural language model to generate control parameters of the cabin atmosphere actuator when the multimedia playback conditions meet the requirements, and automatically triggering the control of the cabin atmosphere actuator to adjust the cabin atmosphere, and displaying the generated multimedia fusion content in multiple aspects while playing the multimedia project, thereby providing users with a personalized and customized immersive experience and eliminating the tedious manual setting process of multimedia functions.

[0010] According to an optional embodiment of the present application, step S2 may include:

[0011] - Step S21: the original content of the multimedia project may be segmented, and the segmented content may be semantically analyzed to generate a first prompt word for characterizing the multimedia playback content, and / or generate a first prompt word for characterizing the multimedia playback scene based on the collected vehicle sensing information and / or user status information;

[0012] - Step S22: generating a first response about a cabin atmosphere state parameter through a first language model based on the first prompt word; and

[0013] - Step S23: The first response may be format converted and time-axis unified to generate multimedia fusion content about the cabin atmosphere state parameters.

[0014] According to another optional embodiment of the present application, step S23 may include:

[0015] - Step S231: converting the generated first response into a predetermined data format, and returning to step S21 in case of failure in the data format conversion to regenerate the first prompt word; and

[0016] - Step S232: unifying the time axis of each cabin atmosphere state parameter in the first response after data format conversion, and marking the timestamp information of each cabin atmosphere state parameter to generate multimedia fusion content;

[0017] -Step S233: Perform content review on the multimedia fusion content, and return to step S21 if the content review fails.

[0018] According to another optional embodiment of the present application, step S3 may include:

[0019] - Step S31: The multimedia playback scenario may be analyzed based on vehicle sensing information, user status information and user instructions;

[0020] - Step S32: whether the multimedia playback conditions meet the requirements based on the multimedia playback scene and the state parameters of the cabin atmosphere actuator;

[0021] - Step S33: if the multimedia playback conditions meet the requirements, a second prompt word about the multimedia playback scene may be generated based on the state parameter of the cabin atmosphere actuator and the multimedia fusion content;

[0022] - Step S34: generating a second response on the control parameter of the cabin atmosphere actuator through a second language model based on the second prompt word;

[0023] - Step S35: the second response may be format converted and time-axis unified to generate control parameters of a cabin atmosphere actuator for adjusting the cabin atmosphere; and

[0024] - Step S36: When the multimedia playback condition does not meet the requirement, the user instruction can be re-obtained through interaction with the user, and the process returns to step S31.

[0025] According to another optional embodiment of the present application, step S35 may include:

[0026] - Step S351: converting the generated second response into a predetermined data format, and returning to step S33 in case of failure in the data format conversion, to regenerate the second prompt word;

[0027] - Step S352: unifying the time axis of the control parameters of each cabin atmosphere actuator in the second response after data format conversion, and marking the timestamp information of each control parameter.

[0028] According to another optional embodiment of the present application, the cabin atmosphere state parameters may include multimedia image parameters, cabin atmosphere light parameters and / or cabin fragrance parameters, etc., wherein the multimedia image parameters, for example, include picture data, video data and / or text data of multimedia playback, etc.

[0029] According to another optional embodiment of the present application, the control parameters of the cabin atmosphere actuator may include control parameters of a multimedia display, control parameters of a cabin atmosphere light, and / or control parameters of a cabin fragrance regulator, etc.

[0030] According to another optional embodiment of the present application, the vehicle sensing information may include time information, vehicle speed information, accelerator pedal information, brake information, outside weather information, window status information and / or cabin temperature information, etc.

[0031] According to another optional embodiment of the present application, the user status information may include the driver's driving status, navigation trip information, the user's emotional state and / or the passenger's riding status, etc.

[0032] According to another optional embodiment of the present application, the multimedia project may include music tracks, language art programs and / or news broadcast programs, etc.

[0033] According to another optional embodiment of the present application, the first prompt word may be sent to a cloud server, and a first response regarding a cabin atmosphere parameter may be received from the cloud server, wherein the first response is generated by a first large language model deployed in the cloud server.

[0034] According to another optional embodiment of the present application, a first response regarding the cabin atmosphere parameters can be generated based on the first prompt word through a first large language model deployed on the vehicle side, and the cloud server can update the first large language model deployed on the vehicle side, for example, through RestAPI.

[0035] According to another optional embodiment of the present application, the second prompt word may be sent to a cloud server, and a second response regarding a control parameter of a cabin atmosphere actuator may be received from the cloud server, wherein the second response is generated by a second largest language model deployed in the cloud server.

[0036] According to another optional embodiment of the present application, a second response regarding the control parameters of the cabin atmosphere actuator can be generated based on the second prompt word through a second largest language model deployed on the vehicle side, and the cloud server can update the second largest language model deployed on the vehicle side, for example, through RestAPI.

[0037] According to another optional embodiment of the present application, the method may further include:

[0038] - Step S4: Each cabin atmosphere actuator may be controlled based on the generated control parameters of the cabin atmosphere actuator, so as to display the multimedia fusion content by adjusting the cabin atmosphere.

[0039] According to a second aspect of the present application, an in-vehicle infotainment system is provided. The in-vehicle infotainment system is used to execute the method according to the present application. The in-vehicle infotainment system may include the following components:

[0040] - A human-computer interaction module, which is configured to receive and analyze user instructions;

[0041] - an information collection module, which is configured to collect vehicle sensing information and user status information;

[0042] - a multimedia content configuration module configured to generate multimedia fusion content about cabin atmosphere state parameters based on the original content of the multimedia project and / or the collected vehicle sensing information and / or user state information; and

[0043] - an actuator control parameter configuration module, which is configured to check multimedia playback conditions based on at least user instructions, state parameters of the cabin atmosphere actuator, collected vehicle sensing information and user state information, and generate control parameters of the cabin atmosphere actuator for adjusting the cabin atmosphere based on the state parameters of the cabin atmosphere actuator and the multimedia fusion content when the multimedia playback conditions meet the requirements.

[0044] According to a third aspect of the present application, a vehicle is provided, which may include the in-vehicle infotainment system according to the present application.

[0045] According to a fourth aspect of the present application, a computer program product, such as a computer-readable program carrier, is provided, which contains or stores computer program instructions, and when the computer program instructions are executed by a processor, they at least assist in implementing the steps of the method described in the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The principles, features and advantages of the present application may be better understood by describing the present application in more detail below with reference to the accompanying drawings. The accompanying drawings show:

[0047] Figure 1 A flowchart showing a method for adjusting cabin atmosphere based on multimedia items according to an exemplary embodiment of the present application;

[0048] Figure 2 A flowchart showing a method for adjusting cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application;

[0049] Figure 3 A flowchart showing a method for adjusting cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application;

[0050] Figure 4 A flowchart showing a method for adjusting cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application;

[0051] Figure 5 A flowchart showing a method for adjusting cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application;

[0052] Figure 6 A flowchart showing a method for adjusting cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application;

[0053] Figure 7 A schematic block diagram showing an in-vehicle infotainment system according to an exemplary embodiment of the present application; and

[0054] Figure 8 A schematic diagram of a vehicle according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0055] In order to make the technical problems, technical solutions and beneficial technical effects to be solved by the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and multiple exemplary embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the scope of protection of the present application.

[0056] Figure 1 A workflow diagram of a method for adjusting cabin atmosphere based on multimedia items according to an exemplary embodiment of the present application is shown. The following exemplary embodiments describe the method according to the present application in more detail.

[0057] like Figure 1 As shown, the method may include steps S1 to S3. In step S1, the received user instructions may be analyzed to determine the multimedia items that the user desires to play. When the user uses the in-vehicle infotainment system 10, the user may directly input user instructions about the multimedia items that the user desires to play, such as "please play a certain music track" through a dialogue with the human-computer interaction module 11. The human-computer interaction module 11 may perform semantic analysis on the user instructions through natural language processing technology to determine the multimedia items that the user desires to play, and the multimedia items may include, for example, music tracks, language art programs (such as talk shows, crosstalk, storytelling, etc.) and / or news broadcast programs.

[0058] In step S2, multimedia fusion content about cabin atmosphere state parameters can be generated based on the original content of the multimedia project and / or the collected vehicle sensing information and / or user status information. After determining the multimedia project that the user wants to play, the multimedia content configuration module 13 can obtain the original content of the multimedia project, such as audio data and lyrics data of the music track, from the server of the multimedia content provider through the vehicle communication network. In the prior art, a fixed-mode cabin atmosphere is usually used when playing the multimedia project, including background images, text, atmosphere lights, etc. In the current embodiment of the present application, artificial intelligence technology, especially a large language model, can be used to perform semantic analysis on the original content of the multimedia project to understand the content described by the multimedia project, and multimedia fusion content can be generated in combination with the semantic analysis results. In the meaning of the present application, multimedia fusion content is a collection of cabin atmosphere state parameters. Controlling the cabin atmosphere actuator based on the cabin atmosphere state parameters can show the user a cabin atmosphere adapted to the original content described by the multimedia project, thereby providing a personalized immersive experience.

[0059] In addition, vehicle sensing information can be collected during the operation of the vehicle, which is used to characterize the current driving environment of the vehicle and / or the cabin environment of the passengers in the vehicle. The vehicle sensing information includes, for example: time information, which can not only indicate the current time information, provide support for the operation time control of each cabin atmosphere state parameter, but also indicate the driving time, such as driving for several hours, or driving in the middle of the night, etc.; vehicle speed information, which is used to indicate, for example, whether the vehicle is currently driving at a low speed, medium speed or high speed, and different degrees of driving concentration are required in different driving speed scenarios; accelerator pedal information and brake information, which are used to indicate whether the vehicle is currently in a traffic congestion section with frequent starting / braking; weather information outside the vehicle, which is used to indicate whether the vehicle is currently driving in a rainy environment, a snowy environment, a foggy environment, a clear environment, a high temperature environment or a low temperature environment, etc.; window status information, which is used to indicate the degree of window opening, wherein the smaller the degree of window opening, the better the sound insulation effect of the cabin; cabin temperature information, which is used to indicate the temperature of the cabin environment where the passengers in the vehicle are located, etc.

[0060] User status information can also be collected during the operation of the vehicle, which is used to characterize the physiological and / or psychological state of the driver and / or passengers in the vehicle, including, for example: the driver's driving status, which is used to indicate the driver's concentration and / or fatigue in driving operations; navigation trip information, which is used to indicate the user's destination - for example, including work, home, restaurant, tourist attraction, long-distance destination, etc. - and the current type of road section, such as urban roads, highways, rural roads, etc.; user emotional state, which is used to indicate whether the driver and / or passenger's current emotional state is happy, sad, angry or anxious, etc.; passenger riding status, which is used to indicate whether the passenger is dozing off, reading, talking on the phone or looking at the scenery outside the window, etc.

[0061] The following combination Figure 2 The workflow diagram of the method for adjusting the cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application illustrates in detail the production process of multimedia fusion content. Figure 2 As shown, the step S2 may include steps S21 to S23. In step S21, the original content of the multimedia project may be segmented, and the segmented content may be semantically analyzed to generate a first prompt word for characterizing the multimedia playback content. Here, for example, the lyrics of a music track may be segmented according to the semantics of the lyrics content, so that each paragraph of lyrics describes the same or similar content, and then the natural language processing technology is used to perform semantic analysis on each paragraph of lyrics to obtain the content to be expressed by each paragraph of lyrics, such as scenes, emotions, artistic conception, etc. Next, the first prompt word generation module may generate a first prompt word for characterizing the multimedia playback content according to the content of each paragraph of lyrics, wherein the prompt word is the input data of the large language model, which can clearly describe the task to be completed by the large language model and provide the background knowledge or context of the task, thereby guiding the large language model to generate the desired output data. The first prompt word generation module is a functional module capable of processing natural language, which may be a software module for generating templated prompt words, or a natural language model, especially a large language model.

[0062] In step S21, a first prompt word for characterizing the multimedia playback scene may also be generated based on the collected vehicle sensing information and / or user status information. The current vehicle driving scene may be determined based on the vehicle sensing information, and the physiological state and / or psychological state of the driver and / or passenger in the vehicle may be determined based on the user status information, thereby making the generated first prompt word more consistent with the user's expectations for the current multimedia playback scene.

[0063] In step S22, a first response to the cabin atmosphere state parameters may be generated based on the first prompt word through the first large language model. Here, the input first prompt word is encoded into a vector representation that can be processed by the computer through the first large language model, and the vector representation is understood and analyzed according to the knowledge and patterns learned in pre-training to generate an output vector. Then, the first large language model decodes the generated output vector to generate content in a specified format as a first response to the cabin atmosphere state parameters, wherein the cabin atmosphere state parameters may include multimedia image parameters, cabin atmosphere light parameters and / or cabin fragrance parameters, etc., and the multimedia image parameters include, for example, picture data, video data and / or text data of multimedia playback. It can be understood that the cabin atmosphere state parameters generated in this way can adapt to the content to be expressed in each verse, including scenes, emotions, artistic conception, etc.

[0064] The first language model can be deployed locally on the vehicle side, and data transmission can be achieved through inter-process communication on the vehicle side, including transmitting the first prompt word from the first prompt word generation module to the first language model, and transmitting the first response from the first language model to the first format conversion module for format conversion of the first response. The first language model can also be deployed in a cloud server. The first prompt word generation module deployed on the vehicle side sends the generated first prompt word to the cloud server, for example, through RestAPI (Representational State Transfer Application Programming Interface). The first language model deployed in the cloud server generates a first response about the cabin atmosphere parameter based on the received first prompt word, and sends the generated first response to the vehicle side, for example, through RestAPI, and further processes the received first response on the vehicle side. Optionally, the cloud server can periodically update the first language model deployed on the vehicle side, for example, through RestAPI.

[0065] In step S23, the first response may be formatted and time-axis unified to generate multimedia fusion content about the cabin atmosphere state parameters. Since the first response includes different types of cabin atmosphere state parameters, the first response needs to be formatted into a standard data structure, and the time axes of the various types of cabin atmosphere state parameters need to be unified so that the various types of cabin atmosphere actuators 2 can operate in cooperation with each other to realize the cabin atmosphere state parameters.

[0066] Next, combine Figure 3 The workflow diagram of the method for adjusting the cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application is shown in detail step S23. Figure 3As shown, the step S23 may include steps S231 to S233. In step S231, the generated first response is converted into a predetermined data format. When there is non-standard format data such as garbled characters in the first response, the data format conversion fails. In the case of data format conversion failure, the process returns to step S21 to regenerate the first prompt word.

[0067] In step S232, the time axis of each cabin atmosphere state parameter in the first response after data format conversion can be unified, and the timestamp information of each cabin atmosphere state parameter can be marked to generate multimedia fusion content. The marked timestamp information is used to indicate the state transition moment of each cabin atmosphere state parameter, so that each cabin atmosphere actuator 2 operates in collaboration with each other according to the state transition moment. The generated multimedia fusion content contains fusion information about the change process of each cabin atmosphere state parameter over time. Through the collaborative operation of these cabin atmosphere state parameters, the scene, emotion, artistic conception, etc. to be expressed by each paragraph of lyrics can be fully displayed, thereby providing users with a customized immersive experience.

[0068] In step S233, the multimedia fusion content may be subject to content review to check, for example, whether there is copyright infringement and / or whether there is any illegal content. If the content review fails, the generated multimedia fusion content is discarded, and the process returns to step S21 to regenerate the first prompt word. If the content review passes, the generated multimedia fusion content may be retained, and the multimedia fusion content may be used to generate control parameters of the cabin atmosphere actuator 2 in step S3.

[0069] In step S3, the multimedia playback conditions may be checked based on at least the user instructions, the state parameters of the cabin atmosphere actuator 2, the collected vehicle sensing information and the user state information, and if the multimedia playback conditions meet the requirements, the control parameters of the cabin atmosphere actuator 2 for adjusting the cabin atmosphere may be generated based on the state parameters of the cabin atmosphere actuator 2 and the multimedia fusion content. Figure 4 The illustrated workflow diagram of a method for adjusting a cabin atmosphere based on a multimedia project according to another exemplary embodiment of the present application elaborates step S3 .

[0070] like Figure 4As shown, step S3 may include steps S31 to S36. In step S31, the multimedia playback scene may be analyzed based on vehicle sensing information, user status information, and user instructions. When analyzing the current multimedia playback scene, the current vehicle driving scene may be determined according to the vehicle sensing information, and the physiological state and / or psychological state of the driver and / or passenger in the vehicle compartment may be determined according to the user status information. At the same time, the user's instructions may also be obtained through a dialogue with the user to obtain the user's desired settings for multimedia playback, such as audio volume, display brightness, color and other picture parameters, pause and start of multimedia playback, activation and deactivation of the cabin fragrance function, and so on.

[0071] The multimedia playback scene can be analyzed based on the vehicle sensing information, user status information and user instructions, and in step S32, it is checked whether the multimedia playback conditions meet the requirements based on the multimedia playback scene and the state parameters of the cabin atmosphere actuator 2. Here, the cabin atmosphere actuator 2 may include a multimedia display, a cabin atmosphere light and / or a cabin fragrance regulator, etc., and its state parameters are used to characterize the executableness of the cabin atmosphere actuator 2 with respect to the corresponding cabin atmosphere adjustment function. The state parameters of the cabin atmosphere actuator 2 can be obtained, for example, through an on-board communication network (such as a CAN bus), thereby evaluating whether the multimedia playback conditions meet the requirements based on the analysis results of the multimedia playback scene and the state parameters of the cabin atmosphere actuator 2.

[0072] For example, the first multimedia playback scenario is driving at a low speed on a congested road section on the way home, the driver is tired, the car windows are completely closed, and the driver inputs a command to enable the cabin fragrance function. Based on the first multimedia playback scenario and the acquired state parameters of the cabin atmosphere actuator 2, it can be determined that the multimedia playback conditions meet the requirements. For another example, the second multimedia playback scenario is driving at a medium speed on a road section heading to a tourist attraction, the driver is not tired, the passengers are looking at the scenery outside the window, and the weather outside the car is clear. The driver inputs a command to enable the multimedia player. Based on the second multimedia playback scenario and the acquired state parameters of the cabin atmosphere actuator 2, it can be determined that the multimedia playback conditions meet the requirements.

[0073] When the multimedia playback conditions meet the requirements, in step S33, a second prompt word about the multimedia playback scene can be generated based on the state parameters of the cabin atmosphere actuator 2 and the multimedia fusion content, for example, through a second prompt word generation module. The first prompt word generation module is also a functional module that can process natural language. It can be a software module for generating templated prompt words, or it can be a natural language model, especially a large language model. In step S34, a second response about the control parameters of the cabin atmosphere actuator 2 can be generated based on the second prompt word through a second large language model. Here, the control parameters of the cabin atmosphere actuator 2 may include control parameters of the multimedia display, control parameters of the cabin atmosphere lights, and / or control parameters of the cabin fragrance regulator, etc.

[0074] The second largest language model can be deployed locally on the vehicle side, and data transmission can be achieved through inter-process communication on the vehicle side, including transmitting the second prompt word from the second prompt word generation module to the second largest language model, and transmitting the second response from the second largest language model to the second format conversion module for format conversion of the second response. The second largest language model can also be deployed in a cloud server. The second prompt word generation module deployed on the vehicle side sends the generated second prompt word to the cloud server, for example, through RestAPI (Representational State Transfer Application Programming Interface). The second largest language model deployed in the cloud server generates a second response about the control parameters of the cabin atmosphere actuator 2 based on the received second prompt word, and sends the generated second response to the vehicle side, for example, through RestAPI, and further processes the received second response on the vehicle side. Optionally, the second largest language model deployed on the vehicle side can be updated by the cloud server, for example, through RestAPI.

[0075] In step S35, the second response may be format converted and time-axis unified to generate control parameters for adjusting the cabin atmosphere of the cabin atmosphere actuator 2. Since the second response includes control parameters of different types of cabin atmosphere actuators 2, it is necessary to format the second response into a standard data structure and unify the time axis of each control parameter so that various types of cabin atmosphere actuators 2 can operate in collaboration with each other to play the multimedia fusion content by adjusting the cabin atmosphere.

[0076] Next, combine Figure 5 The flowchart of the method for adjusting the cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application is shown in detail step S35. Figure 5As shown, the step S35 may include steps S351 and S352. In step S351, the generated second response is converted into a predetermined data format. When there is data in a non-standard format such as garbled characters in the second response, the data format conversion fails, and in the case of data format conversion failure, the process returns to step S33 to regenerate the second prompt word. In step S352, the time axis of the control parameters of each cabin atmosphere actuator 2 in the second response after data format conversion can be unified, and the timestamp information of each control parameter can be marked. The marked timestamp information is used to indicate the change process of the control parameters of each cabin atmosphere actuator 2 over time, so that each cabin atmosphere actuator 2 can be controlled to operate in cooperation with each other according to the change process of the corresponding control parameters over time. While playing the song, the multimedia fusion content generated by controlling the cabin atmosphere playback can fully display the scene, emotion, artistic conception, etc. to be expressed by each paragraph of lyrics, thereby providing users with a personalized immersive experience.

[0077] For another example, in the third multimedia playback scenario, the driver is driving at high speed with high concentration on a highway to a long-distance destination, the passengers are using the multimedia display to read, and the weather conditions are relatively bad. Since the multimedia display cannot be used to play the multimedia fusion content and the current driving scenario requires the driver's high concentration, the multimedia playback conditions do not meet the requirements. In step S36, the user instructions can be retrieved through interaction with the user, and the process returns to step S31.

[0078] Figure 6 FIG. 2 shows a workflow diagram of a method for adjusting cabin atmosphere based on multimedia items according to another exemplary embodiment of the present application. Figure 6 As shown, the method may further include step S4. In step S4, each cabin atmosphere actuator 2, including a multimedia display, a cabin atmosphere light and / or a cabin fragrance regulator, etc., may be controlled based on the generated control parameters of the cabin atmosphere actuator 2 to display the multimedia fusion content by adjusting the cabin atmosphere.

[0079] According to an embodiment of the present application, semantic analysis is performed on the original content of the multimedia project that the user wishes to play, and cabin atmosphere state parameters that meet the scenes, emotions, artistic conception, etc. to be expressed by the multimedia project are generated as multimedia fusion content. The multimedia fusion content is adjusted and the multimedia playback conditions are checked in combination with vehicle sensing information and user status information. When the multimedia playback conditions meet the requirements, the natural language model is used to generate control parameters of the cabin atmosphere actuator, and the cabin atmosphere actuator is automatically triggered to adjust the cabin atmosphere. While playing the multimedia project, the generated multimedia fusion content is displayed in multiple aspects, thereby providing users with a personalized and customized immersive experience and eliminating the tedious manual setting process of multimedia functions.

[0080] In addition, it should be noted that the step numbers described herein do not necessarily represent a chronological order, but are merely a figure mark. The order can be changed according to specific circumstances as long as the technical purpose of the present application can be achieved.

[0081] Figure 7 A schematic block diagram of an in-vehicle infotainment system according to an exemplary embodiment of the present application is shown.

[0082] like Figure 7 As shown, the in-vehicle infotainment system 10 may include the following components:

[0083] - A human-computer interaction module 11, which is configured to receive and analyze user instructions;

[0084] -Information collection module 12, which is configured to collect vehicle sensing information and user status information;

[0085] - a multimedia content configuration module 13, which is configured to generate multimedia fusion content about cabin atmosphere state parameters based on the original content of the multimedia project and / or the collected vehicle sensing information and / or user state information; and

[0086] - an actuator control parameter configuration module 14, which is configured to check multimedia playback conditions based at least on user instructions, state parameters of the cabin atmosphere actuator 2, collected vehicle sensing information and user state information, and to generate control parameters of the cabin atmosphere actuator 2 for adjusting the cabin atmosphere based on the state parameters of the cabin atmosphere actuator 2 and the multimedia fusion content when the multimedia playback conditions meet the requirements.

[0087] Figure 8 1 shows a schematic diagram of a vehicle 1 according to an exemplary embodiment of the present application. Figure 8 As shown, a vehicle 1 may include an in-vehicle infotainment system 10 according to the present application.

[0088] It should be understood that, in this document, the expressions "first", "second", "third", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance, nor should they be understood as implicitly indicating the number of the indicated technical features.

[0089] If an embodiment includes an “and / or” relationship between a first feature and a second feature, it should be interpreted as follows: according to one embodiment, the embodiment has both the first feature and the second feature, and according to another embodiment, the embodiment has either only the first feature or only the second feature.

[0090] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even when only a single embodiment is described with respect to specific features. The feature examples provided in the present disclosure are intended to be illustrative, not restrictive, unless otherwise stated. In specific implementations, multiple features may be combined with each other, where technically feasible, according to actual needs. Various substitutions, changes, and modifications may also be conceived without departing from the spirit and scope of the present application.

Claims

1. A method for adjusting cabin atmosphere, the method comprising: Step S1: analyzing the received user instruction to determine the multimedia item that the user desires to play; Step S2: generating multimedia fusion content about cabin atmosphere state parameters based on the original content of the multimedia project and / or the collected vehicle sensing information and / or user state information; as well as Step S3: checking multimedia playback conditions based at least on user instructions, state parameters of the cabin atmosphere actuator (2), collected vehicle sensing information and user state information, and generating control parameters of the cabin atmosphere actuator (2) for adjusting the cabin atmosphere based on the state parameters of the cabin atmosphere actuator (2) and the multimedia fusion content when the multimedia playback conditions meet the requirements.

2. The method according to claim 1, wherein: The step S2 comprises: Step S21: segmenting the original content of the multimedia project, and performing semantic analysis on the segmented content to generate a first prompt word for characterizing the multimedia playback content, and / or generating a first prompt word for characterizing the multimedia playback scene based on the collected vehicle sensing information and / or user status information; Step S22: generating a first response about a cabin atmosphere state parameter through a first large language model based on the first prompt word; and Step S23: performing format conversion and time axis unification on the first response to generate multimedia fusion content about the cabin atmosphere state parameters.

3. A method according to any one of the preceding claims, wherein: The step S23 comprises: Step S231: converting the generated first response into a predetermined data format, and returning to step S21 in case of failure in the data format conversion to regenerate the first prompt word; and Step S232: unifying the time axis of each cabin atmosphere state parameter in the first response after data format conversion, and marking the timestamp information of each cabin atmosphere state parameter to generate multimedia fusion content; Step S233: Perform content review on the multimedia fusion content, and return to step S21 if the content review fails.

4. A method according to any one of the preceding claims, wherein: The step S3 comprises: Step S31: analyzing the multimedia playback scene based on vehicle sensing information, user status information and user instructions; Step S32: determining whether the multimedia playback conditions meet the requirements based on the multimedia playback scene and the state parameters of the cabin atmosphere actuator (2); Step S33: when the multimedia playback conditions meet the requirements, generating a second prompt word about the multimedia playback scene based on the state parameter of the cabin atmosphere actuator (2) and the multimedia fusion content; Step S34: generating a second response regarding a control parameter of the cabin atmosphere actuator (2) based on the second prompt word through a second language model; Step S35: performing format conversion and time axis unification on the second response to generate control parameters of the cabin atmosphere actuator (2) for adjusting the cabin atmosphere; and Step S36: When the multimedia playback condition does not meet the requirement, reacquire the user instruction through interaction with the user and return to step S31.

5. A method according to any one of the preceding claims, wherein: The step S35 comprises: Step S351: converting the generated second response into a predetermined data format, and returning to step S33 to regenerate the second prompt word if the data format conversion fails; Step S352: unifying the time axis of the control parameters of each cabin atmosphere actuator (2) in the second response after data format conversion, and marking the timestamp information of each control parameter.

6. A method according to any one of the preceding claims, wherein: The cabin atmosphere state parameters include multimedia image parameters, cabin atmosphere light parameters and / or cabin fragrance parameters, wherein the multimedia image parameters include, for example, picture data, video data and / or text data of multimedia playback; and / or The control parameters of the cabin atmosphere actuator (2) include control parameters of a multimedia display, control parameters of a cabin atmosphere light and / or control parameters of a cabin fragrance regulator; and / or The vehicle sensing information includes time information, vehicle speed information, accelerator pedal information, brake information, outside weather information, window status information and / or cabin temperature information; and / or The user status information includes the driver's driving status, navigation trip information, the user's emotional state and / or the passenger's riding status; and / or The multimedia items include music tracks, language arts programs and / or news broadcast programs.

7. A method according to any one of the preceding claims, wherein: Sending the first prompt word to a cloud server, and receiving a first response about a cabin atmosphere parameter from the cloud server, wherein the first response is generated by a first large language model deployed in the cloud server; and / or Based on the first prompt word, a first response about the cabin atmosphere parameter is generated by a first language model deployed on the vehicle side, and the cloud server updates the first language model deployed on the vehicle side, for example, through a RestAPI; and / or sending the second prompt word to a cloud server, and receiving a second response from the cloud server regarding a control parameter of a cabin atmosphere actuator (2), wherein the second response is generated by a second large language model deployed in the cloud server; and / or Based on the second prompt word, a second response regarding the control parameter of the cabin atmosphere actuator (2) is generated by a second language model deployed on the vehicle side, and the cloud server updates the second language model deployed on the vehicle side, for example, through a RestAPI; and / or The method further comprises step S4: controlling each cabin atmosphere actuator (2) based on the generated control parameters of the cabin atmosphere actuator (2), so as to display the multimedia fusion content by adjusting the cabin atmosphere.

8. An in-vehicle infotainment system (10), the in-vehicle infotainment system (10) being configured to execute the method according to any one of the preceding claims, the in-vehicle infotainment system (10) comprising the following components: A human-computer interaction module (11), which is configured to receive and analyze user instructions; An information collection module (12), configured to collect vehicle sensing information and user status information; A multimedia content configuration module (13), configured to generate multimedia fusion content about cabin atmosphere state parameters based on the original content of the multimedia project and / or the collected vehicle sensing information and / or user state information; and An actuator control parameter configuration module (14) is configured to check multimedia playback conditions based at least on user instructions, state parameters of the cabin atmosphere actuator (2), collected vehicle sensing information and user state information, and to generate control parameters of the cabin atmosphere actuator (2) for adjusting the cabin atmosphere based on the state parameters of the cabin atmosphere actuator (2) and the multimedia fusion content when the multimedia playback conditions meet the requirements.

9. A vehicle (1) comprising an in-vehicle infotainment system (10) according to claim 8. 10 . A computer program product, such as a computer-readable program carrier, comprising or storing computer program instructions, which, when executed by a processor, at least assist in implementing the steps of the method according to claim 1 .

Images