Configuration method and device of in-vehicle infotainment system, computer equipment, medium and product

Abstract

The invention relates to a configuration method and device of an in-vehicle infotainment system, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring audio and video data of a target object; the video and audio data comprises image data and voice data of the target object, performing feature extraction on the video and audio data to obtain candidate facial features and candidate voice features of the target object, and configuring an artificial intelligence model for the vehicle machine system based on the target facial features and the target voice features. By adopting the method, the facial features and the sound features of the target object can be accurately simulated, the vehicle-mounted terminal system can more intelligently understand user requirements through introduction of the artificial intelligence model, more accurate and efficient services are provided, and therefore the personalized requirements of the user are met.

Description

Technical Field

[0001] The present application relates to the field of commercial vehicle technology, and in particular to a configuration method, device, computer equipment, medium and product for a vehicle computer system. Background Art

[0002] With the rapid advancement of technology and the increasing diversification of consumer demand, the automotive industry is undergoing unprecedented changes, and intelligence and networking have become an irreversible development trend. This transformation requires automakers to not only continue to innovate in hardware technology, but also to achieve breakthroughs in software services, especially in-vehicle intelligent systems, to meet users' needs for personalization, emotionality and high interactivity.

[0003] Although the car computer systems currently on the market generally have basic functions such as vehicle control, high-precision navigation, and multimedia entertainment, which significantly improve the convenience and fun of driving, they are still insufficient in terms of emotional interaction. Most car computer systems are limited to executing preset tasks and providing basic information services, lack the ability to recognize and respond to the user's emotional state, and it is difficult to establish a deep human-computer emotional connection and meet the user's emotional needs. Summary of the invention

[0004] Based on this, it is necessary to provide a configuration method, device, computer equipment, medium and product for a vehicle system that can meet the personalized needs of users in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for configuring a vehicle system, comprising:

[0006] Acquire audio and video data of the target object; the audio and video data includes image data and voice data of the target object;

[0007] Extract features from the audio and video data to obtain candidate facial features and candidate voice features of the target object;

[0008] Based on the target facial features and target voice features, an artificial intelligence model is configured for the vehicle system.

[0009] In one embodiment, the image data includes facial photos and video images of the target object in a variety of preset scenarios; the preset scenarios include obtaining image data from a preset angle with the target object in a preset expression and a preset posture.

[0010] In one embodiment, the step of extracting features from the audio and video data to obtain candidate facial features and candidate voice features of the target object includes:

[0011] Perform face detection and face positioning on image data to obtain the facial key points of the target object;

[0012] Perform facial alignment on all facial key points and extract features through a neural network model to obtain candidate facial features of the target object;

[0013] Audio attributes are extracted from speech data to obtain candidate sound features of the target object.

[0014] In one embodiment, the step of configuring an artificial intelligence model for a vehicle system based on target facial features and target voice features includes:

[0015] Obtain an artificial intelligence model of the vehicle system, and obtain the facial structure of the source object in the artificial intelligence model;

[0016] The facial structure is configured according to the target facial features, and the human voice is configured for the source object according to the target voice features.

[0017] In one embodiment, the step of configuring the facial structure according to the target facial features includes:

[0018] The candidate facial features are fused with the facial structure through a deep learning model to obtain synthetic image data;

[0019] Perform image processing on the synthesized image data, generate a target image of the source object based on the processed image data, and configure the target image for the artificial intelligence model.

[0020] In one embodiment, the step of configuring a character voice for a source object according to a target sound feature includes:

[0021] synthesizing speech data of a source object according to target sound characteristics;

[0022] The voice data is optimized and processed, the target voice of the source object is generated based on the processed voice data, and the target voice is configured for the artificial intelligence model.

[0023] In a second aspect, the present application also provides a configuration device for a vehicle system, including:

[0024] A data acquisition module, used to acquire audio and video data of a target object; the audio and video data includes image data and voice data of the target object;

[0025] A feature extraction module is used to extract features from the audio and video data to obtain candidate facial features and candidate voice features of the target object;

[0026] The vehicle configuration module is used to configure the artificial intelligence model for the vehicle system based on the target facial features and target voice features.

[0027] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method steps of any one of the first aspects are implemented.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements any one of the method steps in the first aspect when the computer program is executed by a processor.

[0029] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements any one of the method steps in the first aspect when executed by a processor.

[0030] The configuration method, device, computer equipment, medium and product of the above-mentioned vehicle voice system obtains the audio and video data of the target object, extracts features from the audio and video data, obtains candidate facial features and candidate voice features of the target object, and configures an artificial intelligence model for the vehicle system based on the target facial features and target voice features. The artificial intelligence model can accurately simulate the facial features and voice features of the target object. Through the introduction of the artificial intelligence model, the vehicle system can understand user needs more intelligently and provide more accurate and efficient services, thereby meeting the personalized needs of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0032] FIG1 is an application environment diagram of a configuration method of a vehicle system in one embodiment;

[0033] FIG2 is a schematic diagram of a flow chart of a method for configuring a vehicle system in one embodiment;

[0034] FIG3 is a flow chart of a configuration method of a vehicle system in another embodiment;

[0035] FIG4 is a structural block diagram of a configuration device for a vehicle system in one embodiment;

[0036] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0038] The configuration method of the vehicle system provided in the embodiment of the present application can be applied to the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 is used to obtain the audio and video data of the target object through the server 104, perform feature extraction on the audio and video data, obtain the candidate facial features and candidate voice features of the target object, and configure the artificial intelligence model for the vehicle system based on the target facial features and target voice features. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0039] In an exemplary embodiment, as shown in FIG2 , a configuration method for a vehicle system is provided, which is described by taking the method applied to the terminal 102 in FIG1 as an example, and includes the following steps 202 to 206. Among them:

[0040] S202: Acquire audio and video data of the target object; the audio and video data includes image data and voice data of the target object.

[0041] Optionally, the audio and video data includes image data and voice data of the target object, wherein the image data is an image or video of the target object acquired by an image acquisition device, and the voice data is the voice of the target object acquired by an audio acquisition device.

[0042] S204: Extract features from the video and audio data to obtain candidate facial features and candidate voice features of the target object.

[0043] Optionally, for the image data of the target object, the image data can be processed by computer vision technology and other methods to extract the facial features of the target object, which usually includes edge detection, color analysis, texture analysis and more complex deep learning feature extraction methods, such as convolutional neural network (CNN), etc. These features can describe the facial contour, facial features, expression and other information of the target object. For the voice data of the target object, after converting the voice signal into digital form, the features in the voice are extracted through natural language processing and speech recognition technology, which usually includes audio analysis, voice feature extraction and other steps, such as MFCC (Mel frequency cepstral coefficient) and other feature extraction methods, which can describe the pitch, timbre, speaking speed and other information of the voice.

[0044] S206: Based on the target facial features and the target voice features, configure an artificial intelligence model for the vehicle system.

[0045] Optionally, based on the extracted candidate facial features and candidate voice features, a dedicated artificial intelligence model is configured for the vehicle system. The artificial intelligence model is usually trained using a deep learning algorithm, such as a convolutional neural network (CNN) for facial recognition, a recurrent neural network (RNN) or a long short-term memory network (LSTM) for speech recognition. During the training process, the model will learn how to match the input facial features and voice features with known target objects. After the training is completed, the model can process new audio and video data in real time, identify the target object, and provide corresponding functions and services for the vehicle system accordingly.

[0046] In the configuration method of the above-mentioned vehicle-computer system, by acquiring the audio and video data of the target object, feature extraction is performed on the audio and video data to obtain candidate facial features and candidate voice features of the target object, and based on the target facial features and target voice features, an artificial intelligence model is configured for the vehicle-computer system, which can accurately simulate the facial features and voice features of the target object. Through the introduction of the artificial intelligence model, the vehicle-computer system can understand user needs more intelligently and provide more accurate and efficient services, thereby meeting the personalized needs of users.

[0047] In an exemplary embodiment, the image data includes facial photos and video images of the target object in a variety of preset scenarios; the preset scenarios include obtaining image data from preset angles with the target object in a preset expression and a preset posture.

[0048] Optionally, facial photos and video images of the target object are captured in preset scenes (such as different expressions, postures, and angles) through image acquisition devices such as cameras and webcams. These preset scenes are to ensure the diversity and comprehensiveness of the data so as to facilitate more accurate analysis and processing later. For example, the preset expressions may be happy, sad, surprised, etc., the preset postures may be front, side, looking up, etc., and the preset angles may be looking straight, looking down, looking up, etc.

[0049] In this embodiment, by acquiring image data of the target object in a preset expression, preset posture and through a preset angle, the diversity and comprehensiveness of the data can be ensured, thereby improving the accuracy of subsequent feature recognition.

[0050] In an exemplary embodiment, the steps of extracting features from audio and video data to obtain candidate facial features and candidate sound features of the target object include: performing facial detection and facial positioning on image data to obtain facial key points of the target object; performing facial alignment processing on all facial key points and extracting features through a neural network model to obtain candidate facial features of the target object; and performing audio attribute extraction on speech data to obtain candidate sound features of the target object.

[0051] Optionally, first, the face area is detected in the image data by image processing technology, and then the key points of the face, such as the position of the eyes, nose, mouth, etc., are determined by face key point detection technology. Since the posture, angle and size of the face in the image may vary, it is necessary to align the detected face, that is, convert the facial key points to a standard position and size for subsequent feature extraction. After the face alignment process, a neural network model (such as a convolutional neural network CNN) is used to extract features from the face image. These features are usually a deep description of the face and can effectively represent the identity information, expression information, etc. of the face.

[0052] Optionally, the speech data is first preprocessed, including sampling, quantization, denoising and other steps, and then various audio attributes are extracted through audio analysis technology, such as the frequency, amplitude, duration, etc. of the sound. Furthermore, a specific algorithm or model is used to extract features from the audio data to obtain a feature vector that can characterize the sound characteristics, which usually contains the identity information, emotional information, etc. of the sound.

[0053] In this embodiment, the accuracy of facial recognition can be significantly improved through sophisticated facial detection and positioning, facial alignment processing, and advanced feature extraction technology, and the accuracy of voice recognition can be improved through accurate audio attribute extraction and feature extraction.

[0054] In an exemplary embodiment, the step of configuring an artificial intelligence model for a vehicle system based on target facial features and target voice features includes: obtaining the artificial intelligence model of the vehicle system and obtaining the facial structure of a source object in the artificial intelligence model; configuring the facial structure according to the target facial features, and configuring the character voice for the source object according to the target voice features.

[0055] Optionally, the AI ​​model in the vehicle system is usually built based on advanced technologies such as deep learning, and has the ability to process multiple inputs (such as images, voices, etc.) and output corresponding responses. During the configuration process, you first need to obtain or load the AI ​​model that already exists in the vehicle system. This model may be pre-trained or customized for the vehicle system. After that, the facial structure of the source object in the AI ​​model is obtained, where the facial structure refers to the components used in the AI ​​model to represent facial features, such as the position and shape of the eyes, nose, mouth, etc. By parsing the internal structure of the AI ​​model, the facial structure information of the source object can be obtained, which is the basis for subsequent facial feature configuration. Match and adjust the facial features of the target object (such as the position of facial key points, facial contours, etc.) with the facial structure of the source object in the AI ​​model, and modify the facial structure parameters in the AI ​​model so that it can accurately represent the facial features of the target object.

[0056] Optionally, character voice is the part of the AI ​​model used to generate voice output, which usually includes a speech synthesis model and voiceprint features. According to the target sound characteristics (such as timbre, pitch, speaking speed, etc.), the speech synthesis parameters or voiceprint features in the AI ​​model are adjusted to make the generated voice output match the sound characteristics of the target object.

[0057] In this embodiment, by configuring an artificial intelligence model based on the target facial features and voice features for the vehicle system, the facial features and voice features of the target object can be accurately simulated. The introduction of the artificial intelligence model enables the vehicle system to understand user needs more intelligently and provide more accurate and efficient services, thereby meeting the user's personalized needs.

[0058] In an exemplary embodiment, the step of configuring the facial structure according to the target facial features includes: fusing the candidate facial features with the facial structure through a deep learning model to obtain composite image data; performing image processing on the composite image data, generating a target image of the source object according to the processed image data, and configuring the target image for the artificial intelligence model.

[0059] Optionally, the candidate facial features are fused with the preset facial structure through a deep learning model, wherein the deep learning model has learned the complex representation of facial features through a large amount of training data, and can accurately capture and fuse facial features, such as the shape and position of eyes, nose, and mouth. During the fusion process, the model adjusts the source facial structure according to the candidate facial features to match the target facial features, thereby generating synthetic image data with the facial features of the target object. Afterwards, the synthetic image data is further processed to optimize the image quality so that the generated target image is more natural and realistic. Among them, the image processing may include operations such as image enhancement, denoising, and edge smoothing to eliminate artifacts or unevenness that may be generated during the fusion process, and ensure that the generated target image reaches a high visual quality level. Finally, the processed image data is used as the target image of the source object and configured into the artificial intelligence model, and the target image is displayed as a user representative or interactive object in the interactive interface or application scenario of the artificial intelligence model.

[0060] In this embodiment, by configuring an artificial intelligence model for the vehicle system, the facial features and voice features of the target object can be accurately simulated. The introduction of the artificial intelligence model enables the vehicle system to understand user needs more intelligently and provide more accurate and efficient services, thereby meeting the user's personalized needs.

[0061] In an exemplary embodiment, a character voice is configured for a source object according to target sound features, including: synthesizing voice data of the source object according to the target sound features; optimizing the voice data, generating a target voice for the source object based on the processed voice data, and configuring the target voice for an artificial intelligence model.

[0062] Optionally, first, by analyzing the target sound features (such as timbre, pitch, speaking speed, rhythm, etc.), the unique features of the target sound are extracted using voiceprint recognition technology. Then, the voice data of the source object is synthesized based on these features. The initially synthesized voice data is subjected to sound quality optimization processing, such as removing noise, enhancing clarity, adjusting volume, etc., to enhance the auditory experience of the voice. In addition, the voice data can also be adjusted in terms of emotional expression according to the emotional features that the target sound may contain (such as joy, sadness, anger, etc.), so that the generated voice is more vivid and natural, and voice data with target sound features is obtained, that is, the target voice of the source object. The generated target voice is configured into the artificial intelligence model as the voice output or interaction mode of the model. In this way, when the artificial intelligence model interacts with the user, the voice output can be performed with the voice features expected by the user.

[0063] In this embodiment, by configuring an artificial intelligence model for the vehicle system, the facial features and voice features of the target object can be accurately simulated. The introduction of the artificial intelligence model enables the vehicle system to understand user needs more intelligently and provide more accurate and efficient services, thereby meeting the user's personalized needs.

[0064] In an exemplary embodiment, as shown in FIG3 , a method for configuring a vehicle system is provided, the method comprising the following steps:

[0065] Acquire audio and video data of the target object; the audio and video data includes image data and voice data of the target object.

[0066] The image data includes facial photos and video images of the target object in a variety of preset scenarios; the preset scenarios include obtaining image data from preset angles with the target object in a preset expression and preset posture.

[0067] Perform face detection and face positioning on the image data to obtain the facial key points of the target object; perform face alignment processing on all facial key points, and extract features through a neural network model to obtain candidate facial features of the target object; perform audio attribute extraction on the speech data to obtain candidate sound features of the target object.

[0068] Obtain the artificial intelligence model of the vehicle system and obtain the facial structure of the source object in the artificial intelligence model.

[0069] The candidate facial features are fused with the facial structure through a deep learning model to obtain synthetic image data; image processing is performed on the synthetic image data, a target image of the source object is generated based on the processed image data, and the target image is configured for the artificial intelligence model.

[0070] The speech data of the source object is synthesized according to the target sound characteristics; the speech data is optimized and processed, the target speech of the source object is generated according to the processed speech data, and the target speech is configured for the artificial intelligence model.

[0071] In this embodiment, the audio and video data of the target object is acquired and feature extraction is performed on the audio and video data to obtain candidate facial features and candidate voice features of the target object. Based on the target facial features and target voice features, an artificial intelligence model is configured for the vehicle system, which can accurately simulate the facial features and voice features of the target object. Through the introduction of the artificial intelligence model, the vehicle system can understand user needs more intelligently and provide more accurate and efficient services, thereby meeting the personalized needs of users.

[0072] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0073] Based on the same inventive concept, the embodiment of the present application also provides a vehicle system configuration device for implementing the vehicle system configuration method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more vehicle system configuration devices provided below can refer to the limitations of the vehicle system configuration method above, and will not be repeated here.

[0074] In an exemplary embodiment, as shown in FIG4 , a configuration device for a vehicle system is provided, comprising: a data acquisition module 10, a feature extraction module 20 and a vehicle configuration module 30, wherein:

[0075] The data acquisition module 10 is used to acquire audio and video data of the target object; the audio and video data includes image data and voice data of the target object.

[0076] The feature extraction module 20 is used to extract features from the video and audio data to obtain candidate facial features and candidate voice features of the target object.

[0077] The vehicle computer configuration module 30 is used to configure an artificial intelligence model for the vehicle computer system based on target facial features and target voice features.

[0078] In an exemplary embodiment, the image data involved in the data acquisition module 10 includes facial photos and video images of the target object in a variety of preset scenarios; the preset scenarios include acquiring image data from preset angles with the target object in a preset expression and preset posture.

[0079] In an exemplary embodiment, the feature extraction module 20 is also used to perform face detection and face positioning on the image data to obtain the facial key points of the target object; perform face alignment processing on all facial key points, and perform feature extraction through a neural network model to obtain candidate facial features of the target object; perform audio attribute extraction on the speech data to obtain candidate sound features of the target object.

[0080] In an exemplary embodiment, the vehicle configuration module 30 is also used to obtain the artificial intelligence model of the vehicle system and the facial structure of the source object in the artificial intelligence model; configure the facial structure according to the target facial features, and configure the character voice for the source object according to the target sound features.

[0081] In an exemplary embodiment, the vehicle configuration module 30 is also used to fuse candidate facial features with facial structures through a deep learning model to obtain composite image data; perform image processing on the composite image data, generate a target image of the source object based on the processed image data, and configure the target image for the artificial intelligence model.

[0082] In an exemplary embodiment, the vehicle configuration module 30 is also used to synthesize the voice data of the source object according to the target sound characteristics; optimize the voice data, generate the target voice of the source object according to the processed voice data, and configure the target voice for the artificial intelligence model.

[0083] Each module in the configuration device of the above vehicle system can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0084] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a configuration method of a vehicle system is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0085] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0086] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining audio and video data of a target object; the audio and video data includes image data and voice data of the target object; performing feature extraction on the audio and video data to obtain candidate facial features and candidate voice features of the target object; and configuring an artificial intelligence model for the vehicle system based on the target facial features and target voice features.

[0087] In one embodiment, the image data involved when the processor executes the computer program includes facial photos and video images of the target object in a variety of preset scenarios; the preset scenarios include obtaining image data from preset angles with the target object in a preset expression and preset posture.

[0088] In one embodiment, when a processor executes a computer program, it involves extracting features from audio and video data to obtain candidate facial features and candidate sound features of a target object, including: performing facial detection and facial positioning on image data to obtain facial key points of the target object; performing facial alignment processing on all facial key points, and extracting features through a neural network model to obtain candidate facial features of the target object; and extracting audio attributes from speech data to obtain candidate sound features of the target object.

[0089] In one embodiment, the processor executes a computer program that involves configuring an artificial intelligence model for the vehicle system based on target facial features and target voice features, including: obtaining the artificial intelligence model of the vehicle system and obtaining the facial structure of the source object in the artificial intelligence model; configuring the facial structure according to the target facial features, and configuring the character voice for the source object according to the target voice features.

[0090] In one embodiment, the configuration of the facial structure according to the target facial features involved in the execution of a computer program by the processor includes: fusing the candidate facial features with the facial structure through a deep learning model to obtain composite image data; performing image processing on the composite image data, generating a target image of the source object according to the processed image data, and configuring the target image for the artificial intelligence model.

[0091] In one embodiment, the processor executes a computer program that involves configuring a character voice for a source object based on target sound features, including: synthesizing voice data of the source object based on the target sound features; optimizing the voice data, generating a target voice for the source object based on the processed voice data, and configuring the target voice for an artificial intelligence model.

[0092] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining audio and video data of a target object; the audio and video data includes image data and voice data of the target object; performing feature extraction on the audio and video data to obtain candidate facial features and candidate voice features of the target object; and configuring an artificial intelligence model for the vehicle system based on the target facial features and target voice features.

[0093] In one embodiment, the image data involved when the computer program is executed by the processor includes facial photos and video images of the target object in a variety of preset scenarios; the preset scenarios include obtaining image data from preset angles with the target object in a preset expression and preset posture.

[0094] In one embodiment, when a computer program is executed by a processor, it involves extracting features from audio and video data to obtain candidate facial features and candidate sound features of a target object, including: performing facial detection and facial positioning on image data to obtain facial key points of the target object; performing facial alignment processing on all facial key points, and extracting features through a neural network model to obtain candidate facial features of the target object; and extracting audio attributes from speech data to obtain candidate sound features of the target object.

[0095] In one embodiment, the computer program executed by the processor involves configuring an artificial intelligence model for the vehicle system based on target facial features and target voice features, including: obtaining the artificial intelligence model of the vehicle system and obtaining the facial structure of the source object in the artificial intelligence model; configuring the facial structure according to the target facial features, and configuring the character voice for the source object according to the target voice features.

[0096] In one embodiment, the computer program executed by the processor involves configuring the facial structure according to the target facial features, including: fusing the candidate facial features with the facial structure through a deep learning model to obtain composite image data; performing image processing on the composite image data, generating a target image of the source object according to the processed image data, and configuring the target image for the artificial intelligence model.

[0097] In one embodiment, the computer program, when executed by a processor, involves configuring a character voice for a source object based on target sound features, including: synthesizing voice data of the source object based on the target sound features; optimizing the voice data, generating a target voice for the source object based on the processed voice data, and configuring the target voice for an artificial intelligence model.

[0098] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the following steps: obtaining audio and video data of a target object; the audio and video data includes image data and voice data of the target object; performing feature extraction on the audio and video data to obtain candidate facial features and candidate voice features of the target object; and configuring an artificial intelligence model for a vehicle-mounted system based on the target facial features and target voice features.

[0099] In one embodiment, the image data involved when the computer program is executed by the processor includes facial photos and video images of the target object in a variety of preset scenarios; the preset scenarios include obtaining image data from preset angles with the target object in a preset expression and preset posture.

[0100] In one embodiment, when a computer program is executed by a processor, it involves extracting features from audio and video data to obtain candidate facial features and candidate sound features of a target object, including: performing facial detection and facial positioning on image data to obtain facial key points of the target object; performing facial alignment processing on all facial key points, and extracting features through a neural network model to obtain candidate facial features of the target object; and extracting audio attributes from speech data to obtain candidate sound features of the target object.

[0101] In one embodiment, the computer program executed by the processor involves configuring an artificial intelligence model for the vehicle system based on target facial features and target voice features, including: obtaining the artificial intelligence model of the vehicle system and obtaining the facial structure of the source object in the artificial intelligence model; configuring the facial structure according to the target facial features, and configuring the character voice for the source object according to the target voice features.

[0102] In one embodiment, the computer program executed by the processor involves configuring the facial structure according to the target facial features, including: fusing the candidate facial features with the facial structure through a deep learning model to obtain composite image data; performing image processing on the composite image data, generating a target image of the source object according to the processed image data, and configuring the target image for the artificial intelligence model.

[0103] In one embodiment, the computer program, when executed by a processor, involves configuring a character voice for a source object based on target sound features, including: synthesizing voice data of the source object based on the target sound features; optimizing the voice data, generating a target voice for the source object based on the processed voice data, and configuring the target voice for an artificial intelligence model.

[0104] It should be noted that the audio and video data involved in this application (including but not limited to image data, voice data, etc. of the target object) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0105] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0106] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0107] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for configuring a vehicle system, characterized in that: The method comprises: Acquire audio and video data of a target object; the audio and video data includes image data and voice data of the target object; Performing feature extraction on the audio and video data to obtain candidate facial features and candidate voice features of the target object; Based on the target facial features and the target voice features, an artificial intelligence model is configured for the vehicle system.

2. The method according to claim 1, characterized in that: The image data includes facial photos and video images of the target object in a variety of preset scenes; the preset scenes include the target object in a preset expression, preset posture, and image data obtained through a preset angle.

3. The method according to claim 1, characterized in that The step of extracting features from the video and audio data to obtain candidate facial features and candidate voice features of the target object includes: Performing face detection and face positioning on the image data to obtain facial key points of the target object; Performing facial alignment processing on all facial key points and extracting features through a neural network model to obtain candidate facial features of the target object; Audio attributes are extracted from the speech data to obtain candidate sound features of the target object.

4. The method according to claim 1, characterized in that: The configuring an artificial intelligence model for the vehicle system based on the target facial features and the target voice features includes: Acquire an artificial intelligence model of the vehicle system, and acquire the facial structure of a source object in the artificial intelligence model; The facial structure is configured according to the target facial features, and a human voice is configured for the source object according to the target voice features.

5. The method according to claim 4, characterized in that The configuring the facial structure according to the target facial features comprises: Fusing the candidate facial features with the facial structure through a deep learning model to obtain synthetic image data; The synthesized image data is subjected to image processing, a target image of the source object is generated according to the processed image data, and the target image is configured for the artificial intelligence model.

6. The method according to claim 4, characterized in that The configuring the character voice for the source object according to the target sound feature comprises: synthesizing the speech data of the source object according to the target sound feature; The speech data is optimized, a target speech of the source object is generated according to the processed speech data, and the target speech is configured for the artificial intelligence model.

7. A configuration device for a vehicle system, characterized in that: The device comprises: A data acquisition module, used to acquire audio and video data of a target object; the audio and video data includes image data and voice data of the target object; A feature extraction module, used to extract features from the video and audio data to obtain candidate facial features and candidate voice features of the target object; The vehicle computer configuration module is used to configure an artificial intelligence model for the vehicle computer system based on the target facial features and the target voice features.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images