Animation generation method, device and equipment for vehicle-mounted virtual image

Abstract

The embodiment of the invention discloses an animation generation method, device and equipment for a vehicle-mounted virtual image, the method is applied to a vehicle-mounted terminal, the method comprises the steps that first skeleton data is acquired, the first skeleton data is used for indicating multiple pieces of pose information of the vehicle-mounted virtual image of the vehicle-mounted terminal, the first skeleton data is determined according to target information of the vehicle-mounted terminal, and the first skeleton data is used for indicating multiple pieces of pose information of the vehicle-mounted virtual image of the vehicle-mounted terminal; the target information comprises at least one of navigation information of the vehicle-mounted terminal, driving information of a vehicle corresponding to the vehicle-mounted terminal and information of an environment where the vehicle-mounted terminal is located; and rendering the vehicle-mounted virtual image based on the first skeleton data, and displaying a target animation corresponding to the at least one piece of pose information. The animation production cost can be reduced, the richness of interaction between the vehicle-mounted virtual image and the user is improved, and the use experience of the user is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of automotive electronics technology, and are related to, but not limited to, a method, device, and apparatus for generating animation of an in-vehicle virtual image. Background Art

[0002] With the popularization and development of intelligent connected vehicle technology, interaction with vehicle users based on in-vehicle virtual images can bring users a more vivid and interesting interactive experience, which not only enhances the user's driving pleasure, but also makes operations such as navigation settings and vehicle status inquiries more convenient.

[0003] In related technologies, in order to improve the interactive effect of the in-vehicle virtual image, it is usually necessary to configure a variety of animation effects for the in-vehicle virtual image in different interactive scenarios. This undoubtedly increases the time cost of animation designers and leads to a huge accumulation of animation resources, occupying a large amount of storage space, which may limit system performance or increase the hardware burden, thereby affecting the user experience. Summary of the Invention

[0004] In view of this, the method, device, and apparatus for generating animations of in-vehicle virtual characters provided in the embodiments of the present application can reduce animation production costs, increase the richness of the interaction between the in-vehicle virtual characters and users, and thus enhance the user experience. The method, device, and apparatus for generating animations of in-vehicle virtual characters provided in the embodiments of the present application are implemented as follows:

[0005] In a first aspect, the present application provides a method for generating an animation of an in-vehicle virtual image, which is applied to an in-vehicle terminal. The method comprises:

[0006] Acquiring first skeleton data, the first skeleton data being used to indicate multiple pose information of an in-vehicle avatar of the in-vehicle terminal, the first skeleton data being determined based on target information of the in-vehicle terminal, the target information including at least one of navigation information of the in-vehicle terminal, driving information of a vehicle corresponding to the in-vehicle terminal, and environmental information of the in-vehicle terminal;

[0007] The vehicle-mounted virtual image is rendered based on the first skeleton data to display a target animation corresponding to the at least one posture information.

[0008] As an optional implementation manner, in the first aspect of the embodiment of the present application, each of the plurality of pose information includes position information and rotation information of a skeleton of the in-vehicle avatar, and rendering the in-vehicle avatar based on the first skeleton data to display a target animation corresponding to the at least one pose information includes:

[0009] Obtaining a skeleton motion of the vehicle-mounted virtual image according to a time sequence of the plurality of posture information;

[0010] The vehicle-mounted virtual image is rendered according to the skeleton action to obtain and display the target animation.

[0011] As an optional implementation, in the first aspect of the embodiment of the present application, before obtaining the first skeleton data, the method further includes:

[0012] Acquiring the target information of the vehicle-mounted terminal;

[0013] The obtaining of the first skeleton data includes:

[0014] generating prompt words according to the target information of the vehicle-mounted terminal, wherein the prompt words are used to describe the skeleton movements of the vehicle-mounted virtual image;

[0015] The first skeleton data is generated according to the prompt word.

[0016] As an optional implementation, in the first aspect of the embodiment of the present application, when the target information includes multiple types of information, generating a prompt word according to the target information of the vehicle terminal includes:

[0017] For each type of target information, determining whether the information satisfies a preset condition corresponding to the information;

[0018] If the number of pieces of information that meet the corresponding preset conditions in the multiple pieces of information is greater than or equal to a preset threshold, generating a first prompt word, wherein the first prompt word is a prompt word indicating a positive emotion;

[0019] When the number of information satisfying the corresponding preset conditions in the multiple information is less than a preset threshold, a second prompt word is generated, where the second prompt word is a prompt word indicating warning information, and the warning information is information that does not satisfy the corresponding preset conditions.

[0020] As an optional implementation, in the first aspect of the embodiment of the present application, when the target information includes multiple types of information, generating a prompt word according to the target information of the vehicle terminal includes:

[0021] generating a first prompt word when each of the plurality of information satisfies a corresponding preset condition, wherein the first prompt word is a prompt word indicating a positive emotion;

[0022] When there is information in the plurality of information that does not meet the corresponding preset condition, a second prompt word is generated, where the second prompt word is a prompt word indicating warning information, and the warning information is information that does not meet the corresponding preset condition.

[0023] As an optional implementation, in the first aspect of the embodiment of the present application, when generating the second prompt word, the method further includes:

[0024] Acquire second skeleton data, where the second skeleton data is skeleton data of a target accessory, and the target accessory is the accessory corresponding to the warning information;

[0025] The vehicle-mounted virtual image and the target accessory are rendered based on the first skeleton data and the second skeleton data, and the target animation including the target accessory is displayed.

[0026] As an optional implementation, in the first aspect of the embodiment of the present application, generating a prompt word according to the target information of the vehicle-mounted terminal includes:

[0027] The target information of the vehicle-mounted terminal is input into a first target model to generate the prompt word, wherein the first target model is obtained by training a first preset model based on sample information and sample prompt words corresponding to the target information.

[0028] As an optional implementation, in the first aspect of the embodiment of the present application, generating the first skeleton data according to the prompt word includes:

[0029] The prompt word is input into the second target model to generate the first skeleton data. The second target model is obtained by training the second preset model based on the sample prompt word and the sample skeleton data.

[0030] As an optional implementation, in the first aspect of the embodiment of the present application, generating a prompt word according to the target information of the vehicle-mounted terminal includes:

[0031] Inputting the target information of the vehicle-mounted terminal into a first target model to generate the prompt word, wherein the first target model is obtained by training a first preset model based on sample information corresponding to the target information and the sample prompt word;

[0032] The step of generating the first skeleton data according to the prompt word includes:

[0033] The prompt word is input into the second target model to generate the first skeleton data. The second target model is obtained by training the second preset model based on the sample prompt word and the sample skeleton data.

[0034] As an optional implementation manner, in the first aspect of the embodiment of the present application, obtaining the first skeleton data includes:

[0035] When a connection is established with a server, the first skeleton data is obtained from the server.

[0036] As an optional implementation manner, in the first aspect of the embodiment of the present application, obtaining the first skeleton data includes:

[0037] Acquire the first skeleton data according to a preset cycle; or,

[0038] When a preset operation on the in-vehicle virtual image is detected, the first skeleton data is obtained.

[0039] A second aspect of the present application provides a method for generating an animation of a vehicle-mounted virtual image, which is applied to a server. The method comprises:

[0040] Acquiring target information of the vehicle-mounted terminal, the target information including at least one of navigation information of the vehicle-mounted terminal, driving information of a vehicle corresponding to the vehicle-mounted terminal, and environmental information of the vehicle-mounted terminal;

[0041] generating first skeleton data according to the target information, wherein the first skeleton data is used to indicate multiple pose information of the vehicle-mounted virtual image of the vehicle-mounted terminal;

[0042] The first skeleton data is sent to the vehicle-mounted terminal, so that the vehicle-mounted terminal renders the vehicle-mounted virtual image based on the first skeleton data and displays a target animation corresponding to the at least one posture information.

[0043] As an optional implementation, in the second aspect of the embodiment of the present application, generating the first skeleton data according to the target information includes:

[0044] generating prompt words according to the target information of the vehicle-mounted terminal, wherein the prompt words are used to describe skeletal movements;

[0045] The first skeleton data is generated according to the prompt word.

[0046] A third aspect of the present application provides a vehicle-mounted virtual image animation generation device, which is applied to a vehicle-mounted terminal and includes:

[0047] a first acquisition module, configured to acquire first skeleton data, the first skeleton data being used to indicate multiple pose information of an in-vehicle avatar of the in-vehicle terminal, the first skeleton data being determined based on target information of the in-vehicle terminal, the target information including at least one of navigation information of the in-vehicle terminal, driving information of a vehicle corresponding to the in-vehicle terminal, and environmental information of the in-vehicle terminal;

[0048] A rendering and display module is used to render the vehicle-mounted virtual image based on the first skeleton data and display a target animation corresponding to the at least one posture information.

[0049] A fourth aspect of the present application provides a vehicle-mounted virtual image animation generation device, which is applied to a vehicle-mounted terminal and includes:

[0050] A second acquisition module is configured to acquire target information of the vehicle-mounted terminal, wherein the target information includes at least one of navigation information of the vehicle-mounted terminal, driving information of a vehicle corresponding to the vehicle-mounted terminal, and environmental information of the vehicle-mounted terminal;

[0051] a generating module, configured to generate first skeleton data according to the target information, wherein the first skeleton data is used to indicate a plurality of position and posture information of the vehicle-mounted virtual image of the vehicle-mounted terminal;

[0052] The sending module is used to send the first skeleton data to the vehicle-mounted terminal, so that the vehicle-mounted terminal renders the vehicle-mounted virtual image based on the first skeleton data and displays a target animation corresponding to the at least one posture information.

[0053] In a fifth aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method described in the first aspect or the second aspect of the embodiment of the present application is implemented.

[0054] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method provided in the first or second aspect of the embodiment of the present application is implemented.

[0055] Compared with the related art, the embodiments of the present application have the following beneficial effects:

[0056] The present application provides a method applied to a vehicle-mounted terminal, which first obtains first skeleton data, and the first skeleton data is used to indicate multiple posture information of a vehicle-mounted virtual image of the vehicle-mounted terminal, thereby enriching the performance effect of the vehicle-mounted virtual image. Subsequently, the vehicle-mounted virtual image is rendered based on the first skeleton data, and a target animation corresponding to at least one posture information can be displayed, thereby realizing intuitive interaction between the vehicle-mounted virtual image and the user, and reducing the time cost of animation production and the storage requirements for storing large amounts of animation data.

[0057] Since the skeleton data is determined based on target information including at least one of the navigation information of the vehicle-mounted terminal, the driving information of the vehicle corresponding to the vehicle-mounted terminal, and the environmental information of the vehicle-mounted terminal, the animation of the vehicle-mounted virtual image can be more in line with the user's actual driving scene, providing more vivid and immediate interactive feedback, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0059] Figure 1A A schematic diagram of an application scenario of the method for generating animation of a vehicle-mounted virtual image provided in an embodiment of the present application;

[0060] Figure 1B A schematic diagram of another application scenario of the method for generating an animation of a vehicle-mounted virtual image provided in an embodiment of the present application;

[0061] Figure 2 A schematic diagram of a flow chart of a method for generating an animation of a vehicle-mounted virtual image provided in an embodiment of the present application;

[0062] Figure 3 Another flowchart of the method for generating an animation of a vehicle-mounted virtual image provided in an embodiment of the present application;

[0063] Figure 4 A schematic diagram of a skeleton action corresponding to first skeleton data in the method for generating an animation of an in-vehicle virtual image provided by an embodiment of the present application;

[0064] Figure 5 A schematic diagram of a target animation in the method for generating an animation of an in-vehicle virtual image provided in an embodiment of the present application;

[0065] Figure 6 A schematic diagram of a process for generating first skeleton data in the method for generating an animation of a vehicle-mounted virtual image provided by an embodiment of the present application;

[0066] Figure 7 Another schematic diagram of the skeleton motion corresponding to the first skeleton data in the method for generating an animation of an in-vehicle virtual image provided by an embodiment of the present application;

[0067] Figure 8 A schematic diagram of a skeleton action corresponding to the second skeleton data in the method for generating an animation of an in-vehicle virtual image provided by an embodiment of the present application;

[0068] Figure 9 Another schematic diagram of a target animation in the method for generating an animation of an in-vehicle virtual image provided by an embodiment of the present application;

[0069] Figure 10 A schematic diagram of a process of applying the method for generating an animation of a vehicle-mounted virtual image provided in an embodiment of the present application to a server;

[0070] Figure 11 A schematic diagram of another flow chart of the method for generating an animation of a vehicle-mounted virtual image provided in an embodiment of the present application;

[0071] Figure 12 A schematic diagram of the structure of the vehicle-mounted virtual image animation generation device provided in the embodiment of the present application applied to a vehicle-mounted terminal;

[0072] Figure 13 A schematic diagram of a structure of a server in which the animation generation device for a vehicle-mounted virtual image provided in an embodiment of the present application is applied;

[0073] Figure 14 This is a schematic diagram of the structure of the computer device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0074] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the specific technical solutions of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0075] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0076] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0077] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0078] With the increasing popularity and vigorous development of intelligent connected vehicle technology, in-vehicle avatars, as an emerging interactive medium, are gradually changing the way people interact with vehicles. Carefully designed avatars provide users with a highly intelligent interaction mechanism. They not only communicate with users through vivid expressions, movements, and personalized language, but also provide concise and clear operational guidance when necessary. This makes operations such as navigation settings, entertainment selections, and vehicle status inquiries more intuitive and convenient, providing users with a vivid and engaging driving and interactive experience, thereby significantly improving the user experience, as well as the frequency and stickiness of users using in-vehicle avatars.

[0079] In related technologies, in order to achieve rich and diverse in-vehicle virtual image animations, animation designers are usually required to use animation production software to design animation content for the in-vehicle virtual image one by one according to different scenes and functions. In this way, the in-vehicle terminal can select the corresponding animation from the prepared animation library based on the recognized instructions. However, this method also has some limitations: on the one hand, the process of manually producing animations is time-consuming and labor-intensive; on the other hand, the completed animation resources will occupy a large amount of storage space on the in-vehicle terminal. In addition, since vehicles generate various types of complex data while driving, the animation performance of the in-vehicle virtual image may appear mechanical and not smooth enough due to the incompleteness of the produced animation library, which in turn has a negative impact on the overall user experience.

[0080] In view of this, the embodiments of the present application provide a method, device and equipment for generating animation of an in-vehicle virtual image. The method can be applied to an in-vehicle terminal to reduce the cost of animation production and improve the richness of the interaction between the in-vehicle virtual image and the user, thereby improving the user experience.

[0081] The following explains the actual scenario in which the method for generating an animation of a vehicle-mounted virtual image provided in an embodiment of the present application is applied and the vehicle-mounted virtual image contained in the scenario.

[0082] See also Figure 1A , Figure 1A A schematic diagram of an application scenario of the method for generating animation of a vehicle-mounted virtual image provided in an embodiment of the present application is shown as follows: Figure 1A The application scenario diagram shown includes a vehicle 10 and a vehicle-mounted terminal 11 .

[0083] It should be noted that the vehicle-mounted terminal 11 in this application is a terminal device that integrates control and data acquisition functions. It can not only assist the vehicle 10 in driving, but also acquire and process various data generated by the vehicle 10 in real time during driving, including but not limited to speed, location, and navigation information. Optionally, the vehicle-mounted terminal 11 is provided with a display screen, or is connected to a display screen, to display the target animation.

[0084] The on-board virtual image is a virtual image presented in the internal display device of the vehicle 10, which can be used to interact with the user corresponding to the on-board terminal 11. It can perform corresponding actions and expressions based on various data generated during the driving of the vehicle 10, bringing passengers a more vivid and personalized interactive experience.

[0085] In the present application, an on-board terminal 11 provided in a vehicle 10 is capable of acquiring first skeleton data and rendering an on-board virtual character based on the first skeleton data to display a corresponding target animation. The first skeleton data is determined based on target information of the on-board terminal, and the target information includes at least one of navigation information of the on-board terminal, driving information of a vehicle corresponding to the on-board terminal, and environmental information of the on-board terminal.

[0086] Optional, in Figure 1A In the illustrated application scenario, the vehicle-mounted terminal 11 can process the target information to obtain the first skeleton data. This allows the vehicle 10 and the vehicle-mounted terminal 11 to obtain the first skeleton data, render, and display the corresponding target animation even when not connected to other devices or a network, ensuring a smooth user experience even in environments with poor signal or no network.

[0087] See also Figure 1B , Figure 1B This is a schematic diagram of another application scenario of the method for generating animation of a vehicle-mounted virtual image provided by an embodiment of the present application, such as Figure 1B The application scenario diagram shown includes a vehicle 10 , a vehicle-mounted terminal 11 and a server 20 .

[0088] It should be noted that the vehicle 10 can establish a communication connection with the server 20 through the on-board terminal 11. Through this communication connection, the on-board terminal 11 can not only upload various data collected from the vehicle 10 to the server 20 for analysis and storage, but also receive real-time updated information, instructions or software upgrades from the server 20.

[0089] Optional, in Figure 1B In the application scenario shown, the first skeleton data can be generated by the server 20 and sent to the vehicle-mounted terminal 11. In this way, after the vehicle-mounted terminal 11 obtains the first skeleton data sent by the server 20, it can render it and display the corresponding target animation. The computing power requirements for the vehicle-mounted terminal 11 are reduced. When a communication connection is established with the server 20, the animation effect can still be displayed even if the computing power of the vehicle-mounted terminal 11 is low. At the same time, excessive occupation of the computing resources of the vehicle-mounted terminal 11 is avoided, so that the method provided in this application can be deployed on vehicle-mounted terminals with different computing power levels, thereby improving the compatibility and flexibility of the method provided in this application.

[0090] The following explains the implementation process of the method for generating the animation of the vehicle-mounted virtual image.

[0091] See also Figure 2 , Figure 2 A flow chart of a method for generating an animation of a vehicle-mounted virtual image provided by an embodiment of the present application. The animation generation of the vehicle-mounted virtual image can be applied to a vehicle-mounted terminal, such as Figure 2 As shown, the method may include the following steps:

[0092] S201, obtain first skeleton data, the first skeleton data is used to indicate multiple posture information of the vehicle-mounted virtual image of the vehicle-mounted terminal, the first skeleton data is determined based on the target information of the vehicle-mounted terminal, and the target information includes at least one of the navigation information of the vehicle-mounted terminal, the driving information of the vehicle corresponding to the vehicle-mounted terminal, and the environmental information of the vehicle-mounted terminal.

[0093] In an embodiment of the present application, the posture information can indicate the position and posture of the in-vehicle virtual image in three-dimensional space. For example, the posture information can include but is not limited to the position or coordinates of each skeleton of the in-vehicle virtual image, the orientation, and possible other posture parameters (such as the rotation angle between the skeletons, the degree of inclination, etc.). Through multiple posture information, the in-vehicle virtual image can be rendered on a two-dimensional plane, such as the display screen or other display interface of the in-vehicle terminal, to present a dynamic animation effect, making the behavior and performance of the in-vehicle virtual image more vivid and improving the user experience.

[0094] The target information of the present application may include at least one of the navigation information of the vehicle-mounted terminal, the driving information of the vehicle corresponding to the vehicle-mounted terminal, and the environmental information of the vehicle-mounted terminal.

[0095] Navigation information can include detailed information about the vehicle's current route, such as destination coordinates, estimated time of arrival, road conditions along the way (including congestion, construction information, road closures, etc.), route recommendations, and locations along the way (such as gas stations, restaurants, parking lots, etc.). In addition, navigation information can also include real-time updated traffic signal information, such as traffic light status, speed limit reminders, and turn instructions.

[0096] The driving information of the vehicle corresponding to the on-board terminal may include the basic status parameters of the vehicle, such as current speed, engine or motor status, fuel remaining or power, odometer reading, tire pressure, etc. It can also record the vehicle's driving trajectory, including latitude and longitude coordinates, timestamp, acceleration and deceleration, etc., which are not limited here.

[0097] The vehicle terminal's environmental information may include weather conditions (such as temperature, humidity, rainfall probability, wind direction and speed), air quality, road slipperiness, and light intensity (differentiating between daytime, nighttime, and tunnels) in the area where the vehicle is located. Environmental information may also include vehicle driving environment information, such as obstacle detection results and surrounding vehicle behavior predictions, which are not limited here.

[0098] Optionally, in addition to the above information types, the target information of the present application may also include vehicle system context information (such as voice conversation context information, vehicle control status context information, etc.) and user status information (such as user's emotion recognition information, personnel status information, etc.), so that the first skeleton data determined according to the target information can be more in line with the actual scene and improve the user experience. Among them, the voice conversation context information may include the instructions issued by the user, the reply of the vehicle terminal and the relevant voice interaction content. Through the voice conversation context information, the vehicle terminal can understand the user's intentions and needs in order to obtain the corresponding first skeleton data. The vehicle control status context information may include but is not limited to the vehicle's hardware control information (such as the current status and historical operation records of hardware devices such as windows, sunroofs, seat heating / ventilation, air conditioning, and lighting systems) and the enabled status and setting parameters of driving assistance related functions. The user's emotion recognition information can reflect the user's emotional state, and the personnel status information can include information such as the number of people in the car and the number of seats, all of which can be captured by the vehicle's in-car camera and recognized by the vehicle terminal, which is not limited here.

[0099] The above-mentioned target information including at least one information provides a rich data source for determining the first skeleton data, so that the first skeleton data is not only highly personalized, but also can fit the actual scene of the vehicle, reflecting excellent adaptability.

[0100] For example, when the target information includes navigation information of the vehicle terminal and the user's emotion recognition information, if the navigation information indicates that the vehicle is approaching the destination and the emotion recognition information indicates that the user is in a happy state, the target animation rendered by the first skeleton data determined by the target information can present a jumping action, which can deepen the user's sense of immersion and improve the user experience.

[0101] Optionally, the types and numbers of information included in the target information may be pre-set by the vehicle terminal when it is manufactured, or may be set by the user according to the user's needs after leaving the factory, and are not limited here.

[0102] Optionally, the target information may also include all types of information currently available to the vehicle terminal to enrich the data source. For example, when the user does not use the navigation function of the vehicle terminal, the target information may include multiple types of information in addition to navigation information.

[0103] In the present application, the method for obtaining the first skeleton data can be generated by the vehicle-mounted terminal according to the target information, or generated by a server that establishes a communication connection with the vehicle-mounted terminal and sends the generated first skeleton data to the vehicle-mounted terminal.

[0104] Optionally, if the vehicle terminal's hardware performance meets preset requirements, the vehicle terminal can process the target information and generate first skeletal data that matches the current scenario. This method reduces data transmission latency and is independent of network connectivity. Therefore, even in the absence of an internet connection or in a poor network environment, the first skeletal data can still be stably generated, providing vehicle terminal users with interactive services with the in-vehicle avatar.

[0105] Optionally, for vehicle-mounted terminals with relatively limited computing power, the vehicle-mounted terminal can send target information to the server for processing. After receiving the target information sent by the vehicle-mounted terminal, the server will use its powerful computing power to generate the first skeleton data, and send it back to the vehicle-mounted terminal through a network or other connection method, thereby reducing the performance requirements for the vehicle-mounted terminal and better adapting to various application scenarios.

[0106] S202: Render the in-vehicle virtual image based on the first skeleton data to display a target animation corresponding to at least one posture information.

[0107] In the present application, after the vehicle-mounted terminal obtains the first skeleton data, it is necessary to render it to display the target animation viewed by the user of the vehicle-mounted terminal.

[0108] It should be noted that users can control the display of the in-vehicle virtual avatar through interactive means such as touch, for example, to pause or end its display. Therefore, the specific content of the target animation can be flexibly adjusted: when the user intervenes, the target animation can be an independent animation segment matching at least one specific pose information; when the user does not perform any operation, the target animation may cover multiple consecutive pose information indicated by the first skeletal data, forming a complete animation sequence.

[0109] Optionally, rendering the vehicle-mounted virtual image based on the first skeleton data may include steps such as data parsing, model binding, and animation generation. First, by parsing the first skeleton data, the position information of each skeleton point and possible additional information, such as rotation angle, scaling ratio, etc., contained in at least one posture information are obtained. Then, the vehicle-mounted terminal will bind the parsed skeleton data with the preset vehicle-mounted virtual image model. This process ensures that each skeleton can accurately correspond to the corresponding part on the vehicle-mounted virtual image model, wherein the vehicle-mounted virtual image model can be a preset cartoon model, a preset vehicle-related brand image model, or a character model uploaded by the user, which is not limited here. Then, based on the bound vehicle-mounted virtual image model, the vehicle-mounted terminal can calculate the vehicle-mounted virtual image model action frame corresponding to the at least one posture information according to the action changes indicated by the at least one posture information of the first skeleton data. Finally, the vehicle-mounted terminal can play the rendered vehicle-mounted virtual image model action frame to display the target animation.

[0110] Optionally, after calculating the vehicle-mounted virtual image model action frame corresponding to at least one posture information, the vehicle-mounted terminal can also use graphics rendering technology to add visual effects such as lighting and shadows to the vehicle-mounted virtual image to improve the user's experience of watching the target animation.

[0111] In the method for generating an animation for an in-vehicle avatar provided in an embodiment of the present application, first skeletal data is obtained, and then the in-vehicle avatar is rendered based on the first skeletal data. A target animation corresponding to at least one pose information can be displayed, thereby enabling intuitive interaction between the in-vehicle avatar and the user, providing the user with more vivid and immediate interactive feedback, and improving the user experience. This also reduces the time cost of animation production and the storage requirements for storing large amounts of animation data.

[0112] The following explains the timing of obtaining the first skeleton data and the implementation process of rendering the first skeleton data in the embodiment of the present application.

[0113] See also Figure 3 , Figure 3 Another flow chart of the method for generating animation of a vehicle-mounted virtual image provided by an embodiment of the present application is provided. The method for generating animation of a vehicle-mounted virtual image can be applied to a vehicle-mounted terminal, such as Figure 3 As shown, the method may include the following steps:

[0114] S301, obtaining first skeleton data according to a preset period; or obtaining first skeleton data when a preset operation on the vehicle-mounted virtual image is detected.

[0115] In some possible embodiments, the vehicle-mounted terminal obtains the first skeleton data, including:

[0116] Acquire first skeleton data according to a preset cycle; or,

[0117] When a preset operation on the in-vehicle virtual image is detected, first skeleton data is obtained.

[0118] It is understandable that in order to optimize the system performance of the vehicle terminal and reduce unnecessary resource usage, the vehicle terminal can set a preset cycle or set an event trigger condition to determine whether to obtain the first skeleton data and render it to display the target animation.

[0119] Optionally, the preset period can be one minute, two minutes, etc. The preset period can be set when the vehicle terminal leaves the factory, or it can be adjusted by providing corresponding period adjustment controls according to the user's usage needs and habits. There is no limitation here.

[0120] Optionally, the preset operation on the in-vehicle virtual image can be a touch operation of the user on the real in-vehicle virtual image, so that after the user touches the in-vehicle virtual image in standby state, the first skeleton data is obtained, and the corresponding target animation is rendered and displayed, aiming to enhance the user experience and ensure that the in-vehicle terminal can be personalized according to the needs and preferences of different users. At the same time, triggering animation rendering through touch operation also increases the interactivity between the user and the in-vehicle virtual image.

[0121] In addition to touch operations, preset operations can also be preset voice commands. When the user speaks a preset voice command containing a preset trigger word or sentence, the vehicle terminal can instantly recognize and respond, and then obtain the first skeleton data. This method allows users to trigger the acquisition of the first skeleton data with simple voice content, enhancing the convenience of operation and user experience.

[0122] S302, obtaining the skeleton movement of the in-vehicle virtual image according to the time sequence of the plurality of posture information; rendering the in-vehicle virtual image according to the skeleton movement, obtaining and displaying the target animation.

[0123] In some possible embodiments, each position information includes the position information and rotation information of the skeleton of the in-vehicle avatar. The position information and rotation information of the skeleton can be used to describe the posture and movement of the in-vehicle avatar in three-dimensional space.

[0124] Optionally, the first skeleton data may be skeleton data in BVH (BioVision Hierarchy) format, and the data in BVH format may include skeleton information and data blocks, wherein the skeleton information includes forming a hierarchical structure with position and rotation components according to a hierarchical relationship of human bones, and the data block records the rotation information of each bone of the human body in each frame.

[0125] Optionally, in addition to the BVH format, the first skeleton data can also be in the FBX, C3D and other formats, which can be freely selected according to the compatibility and hardware performance of the vehicle terminal and are not limited here.

[0126] It should be noted that the number of bones or joints corresponding to each posture information can be set according to actual needs and the model of the on-board virtual image. Usually, in order to show the dynamic effect of the on-board virtual image more delicately and realistically, the number of bones or joints can be increased, but too many bones or joints will also increase the calculation complexity accordingly. Therefore, in actual applications, it can be set according to actual needs and is not limited here.

[0127] Optionally, the vehicle-mounted virtual image is rendered according to the skeleton action to obtain and display the target animation. The first skeleton data can be parsed by the Unity3d engine, and the skeleton action is mapped to the vehicle-mounted virtual image model to generate the target animation.

[0128] For example, taking the first skeleton data in BVH format as an example, if the multiple posture information of the first skeleton data determined by the target information indicates that the vehicle-mounted virtual image performs a jumping action, the skeleton action corresponding to the first skeleton data can be as follows: Figure 4 shown. Figure 4 A schematic diagram of a skeleton action corresponding to the first skeleton data in the method for generating an animation of a vehicle-mounted virtual image provided by an embodiment of the present application, Figure 4 Parts A, B, and C are three positions corresponding to the in-vehicle virtual image (including the rotation information of each skeleton). Through the time sequence of each position information, a jumping action effect can be presented.

[0129] When the multiple posture information of the first skeleton data determined by the target information indicates that the vehicle-mounted virtual image performs a jumping action, the terminal device can render the skeleton action of the vehicle-mounted virtual image according to the time sequence of the multiple posture information and display the target animation corresponding to the skeleton action. Figure 5 shown. Figure 5 This is a schematic diagram of a target animation in the method for generating an animation of a vehicle-mounted virtual image provided by an embodiment of the present application. Figure 5 Parts A, B, and C are the animation contents of the target animation corresponding to the skeletal movements. By displaying the target animation to the user, an immersive interactive experience can be provided to the user.

[0130] It should be noted that if Figure 4 and Figure 5The schematic diagram shown is for example only. To present a smooth animation, the first skeleton data can be made to include more posture information, or interpolation techniques such as frame generation can be used to increase the number of frames per second of the target animation, thereby smoothly transitioning between various action stages and reducing the target's sense of lag, thereby effectively improving the smoothness and viewing experience of the target animation and enhancing the user's experience of interacting with the in-vehicle virtual image.

[0131] By implementing the above technical solution, the vehicle-mounted terminal can avoid continuously acquiring the first skeleton data and generating the target animation, thereby reducing resource usage. It can also enable the vehicle-mounted virtual image in the rendered target animation to present coherent movements, thereby improving the interactive experience.

[0132] The following explains the implementation process of generating the first skeleton data by the vehicle-mounted terminal in the embodiment of the present application.

[0133] See also Figure 6 , Figure 6 A schematic diagram of a process for generating first skeleton data in the method for generating animation of a vehicle-mounted virtual image provided by an embodiment of the present application. The method for generating animation of a vehicle-mounted virtual image can be applied to a vehicle-mounted terminal, such as Figure 6 As shown, the method may include the following steps:

[0134] S601, obtaining target information of the vehicle terminal.

[0135] In some possible embodiments, before the vehicle-mounted terminal obtains the first skeleton data, the method further includes: obtaining target information of the vehicle-mounted terminal.

[0136] The target information in this application may include at least one of the navigation information of the vehicle-mounted terminal, the driving information of the vehicle corresponding to the vehicle-mounted terminal, and the environmental information of the vehicle-mounted terminal. In addition, it may also include vehicle system context information (such as voice conversation context information, vehicle control status context information, etc.) and user status information (such as user emotion recognition information, personnel status information, etc.) and other information.

[0137] Optionally, the vehicle terminal can obtain target information by accessing various data resources stored in the vehicle terminal's built-in memory, or by acquiring real-time data collected by various sensors installed inside the vehicle.

[0138] It should be noted that the sensors installed inside the vehicle may include but are not limited to GPS modules (used to provide geographic location and navigation information), environmental perception devices (such as radar, lidar or ultrasonic sensors, used to detect the surrounding environment), microphones (used to capture sounds inside and outside the vehicle, including voice conversation content), and cameras (used for visual recognition, such as identifying user emotions, the status of people in the vehicle, etc.).

[0139] Through the above method, the vehicle-mounted terminal can obtain target information and provide strong data support for the subsequent generation of target animation.

[0140] S602: Generate prompt words according to the target information of the vehicle-mounted terminal, where the prompt words are used to describe the skeleton movements of the vehicle-mounted virtual image.

[0141] In some possible embodiments, the vehicle-mounted terminal obtains the first skeleton data, including:

[0142] Generate prompt words based on the target information of the vehicle terminal, and the prompt words are used to describe the skeleton movements of the vehicle virtual image;

[0143] Generate first skeleton data according to the prompt word.

[0144] It should be noted that the prompt word can be a character, word, or sentence used to describe the action of the in-vehicle virtual character. For example, the prompt word can be "jump", "sit down", "jump up happily", "sit down calmly", etc., without limitation.

[0145] In some possible embodiments, when the target information includes only one type of information, the prompt word may be determined according to a preset mapping option between the preset information and the preset prompt word and the target information.

[0146] For example, if the target information includes navigation information and the navigation information indicates that the vehicle is approaching the destination, the corresponding prompt word according to the preset mapping relationship may be "jump for joy." If the target information includes emotion recognition information and indicates that the user is calm, the corresponding prompt word according to the preset mapping relationship may be "sit down calmly."

[0147] In some possible embodiments, when the target information includes multiple types of information, prompt words are generated according to the target information of the vehicle terminal, including:

[0148] For each type of target information, determine whether the information meets the preset conditions corresponding to the information;

[0149] When the number of pieces of information that meet the corresponding preset conditions in the multiple pieces of information is greater than or equal to a preset threshold, generating a first prompt word, the first prompt word being a prompt word indicating a positive emotion;

[0150] When the number of information satisfying corresponding preset conditions among the multiple information is less than a preset threshold, a second prompt word is generated, where the second prompt word is a prompt word indicating warning information, and the warning information is information that does not satisfy the corresponding preset conditions.

[0151] It should be noted that the preset conditions corresponding to each type of information can be flexibly set according to actual needs. When a certain information meets its corresponding preset conditions, it indicates that the information has positive attributes for the user. The preset threshold can be an integer greater than or equal to 1 and can be set according to actual needs and is not limited here.

[0152] For example, the preset conditions for navigation information may include the distance to the destination being less than a preset distance threshold and the absence of a red light ahead; the preset conditions for vehicle driving information may include the vehicle speed being less than the current road speed limit and the remaining fuel (or battery level) being greater than a preset fuel (or battery level) threshold; the environmental information for the vehicle terminal may include the weather being clear outside and the absence of vehicles ahead; the preset conditions for user emotion recognition information may include the user being happy; and the preset conditions for personal status information may include the user being wearing a seat belt. In actual applications, corresponding preset conditions may be set for different information as needed, and this is not limited here.

[0153] After determining that the number of information satisfying corresponding preset conditions in the multiple information is greater than or equal to a preset threshold, a first prompt word indicating positive emotion is generated. The first prompt word may be "jump happily", "dance happily", etc.

[0154] Optionally, when the value of the preset threshold is equal to the number of multiple types of information included in the target information, it can be understood that when the target information includes multiple types of information, prompt words are generated according to the target information of the vehicle terminal, including:

[0155] When each of the multiple types of information meets the corresponding preset conditions, generating a first prompt word, the first prompt word being a prompt word indicating a positive emotion;

[0156] When there is information that does not meet the corresponding preset conditions among the multiple types of information, a second prompt word is generated, where the second prompt word is a prompt word indicating warning information, and the warning information is the information that does not meet the corresponding preset conditions.

[0157] For example, in one embodiment, the in-vehicle terminal acquires target information indicating that the user will be using the vehicle on the weekend, with the destination set to a suburban park. The system then obtains favorable weather conditions from the vehicle control module, smooth road conditions from the navigation module, and a happy expression from the in-vehicle camera. If the in-vehicle terminal determines that each of these conditions satisfies the corresponding pre-set conditions, it generates a first prompt, "Jump for joy," and displays the corresponding target animation accordingly.

[0158] It is understood that when some information among multiple types of information does not meet the corresponding preset conditions, it can be understood that some information requires the user's attention. Therefore, a second prompt word corresponding to the warning information that does not meet the preset conditions can be generated to remind the user to pay attention to the relevant information. For example, if the weather is good and the user is in a good mood, but the navigation information indicates that the road ahead is congested and does not meet the preset conditions corresponding to the navigation information, the navigation information can be determined to be a warning information and the second prompt word "anxious pacing" can be generated. At the same time, the corresponding voice message of the navigation information can be output to let the user know the road conditions in advance and prepare mentally.

[0159] For example, if the number of pieces of information that meet the corresponding preset conditions among multiple pieces of information is less than a preset threshold, and if the vehicle's driving information does not meet the corresponding preset conditions due to exceeding the road speed limit, the second prompt word generated may be a prompt word such as "wave your right hand up and down." If the environmental information of the vehicle-mounted terminal does not meet the corresponding preset conditions due to rain outside the vehicle, the second prompt word generated may be a prompt word such as "cover your head with your hand." If two or more pieces of information do not meet the preset conditions, the method provided in this application can also output a prompt word such as "wave" to alert the user to the warning information.

[0160] Optionally, when there are multiple warning messages, a second prompt word corresponding to the target warning message with the highest warning priority among the multiple warning messages can be generated according to a preset warning priority mapping relationship, where the preset warning priority mapping relationship includes a mapping relationship between information and priority.

[0161] Optionally, when the vehicle-mounted terminal displays the target animation corresponding to the second prompt word, the method provided in the present application further includes: displaying warning information, and / or outputting voice content corresponding to the warning information.

[0162] In some possible embodiments, generating prompt words according to target information of the vehicle-mounted terminal includes:

[0163] The target information of the vehicle terminal is input into the first target model to generate prompt words. The first target model is obtained by training the first preset model based on sample information corresponding to the target information and the sample prompt words.

[0164] It should be noted that the first target model can be trained and stored on the vehicle terminal or on the server. When the first target model is trained on the server, the server's powerful computing power can be leveraged to achieve better training results and increase training speed. With the trained first target model, the vehicle terminal can quickly and efficiently generate the required prompt words in actual applications, ensuring the vehicle terminal's responsiveness and accuracy when processing target information.

[0165] Optionally, the in-vehicle terminal can collect user feedback on the displayed target animation and send the feedback to the server. This feedback may include, but is not limited to, user satisfaction ratings for the animation content and ratings of the target animation's effectiveness in conveying the warning message, in order to optimize the first target model. Upon receiving this feedback, the server can further analyze user behavior patterns and preferences to optimize the training strategy and parameters of the first target model, thereby improving the accuracy of generated prompt words.

[0166] Optionally, the first preset model can be a natural language generation (NLG) model based on deep learning technology, such as a recurrent neural network (RNN), a long short-term memory network (LSTM), etc., which can extract key features from the input target information and output prompt words accordingly.

[0167] S603: Generate first skeleton data according to the prompt word.

[0168] In some possible embodiments, the vehicle-mounted terminal generates the first skeleton data according to the prompt word, including:

[0169] The prompt word is input into the second target model to generate the first skeleton data. The second target model is obtained by training the second preset model based on the sample prompt word and the sample skeleton data.

[0170] It should be noted that the second target model can be trained on the vehicle terminal or server and stored in the vehicle terminal. The vehicle terminal can collect the user's feedback on the displayed target animation and send the feedback results to the server to optimize the second target model. After receiving the feedback results, the server can further analyze the user's behavior patterns and preferences to optimize the training strategy and training parameters of the second target model to improve the performance of the first skeleton data output by the second target model, making the vehicle virtual image in the displayed target animation more rich and vivid.

[0171] Optionally, the second preset model can be constructed based on deep learning technology. Since the first skeleton data itself has the structural characteristics of multiple bones (joints), the second preset model can be a network model with a structure such as a graph neural network (GNN) or a graph convolutional network (GCN), which can output the first skeleton data corresponding to the prompt word based on the input prompt word.

[0172] In some possible embodiments, the vehicle-mounted terminal can use a generative MOMASK model to generate the first skeleton data based on the prompt word. The core of the MOMASK model is to use masks to predict and edit missing parts in the sequence, achieving fine control of the 3D motion sequence. In this application, the prompt word can be output to the MOMASK model to obtain the output first skeleton data.

[0173] S604: Render the in-vehicle virtual image based on the first skeleton data to display a target animation corresponding to at least one posture information.

[0174] In some possible embodiments, when generating the second prompt word, the method further includes:

[0175] Acquire second skeleton data, where the second skeleton data is skeleton data of a target accessory, and the target accessory is the accessory corresponding to the warning information;

[0176] The vehicle-mounted virtual image and the target accessory are rendered based on the first skeleton data and the second skeleton data, and a target animation including the target accessory is displayed.

[0177] Optionally, the vehicle terminal may determine the target accessory corresponding to the warning information through a preset accessory mapping relationship, where the preset accessory mapping relationship includes a mapping relationship between preset warning information and preset accessories.

[0178] It should be noted that if the warning information is vehicle driving information, the target accessory can be a traffic sign corresponding to the driving information. If the warning information is environmental information, the target accessory can be an umbrella or sunglasses corresponding to the environmental information. By displaying the target accessory corresponding to the warning information in the target animation, users of the in-vehicle terminal can observe the warning information more quickly and intuitively, adding more fun and practicality to the interactive experience of the in-vehicle avatar.

[0179] Optionally, in the case where there are multiple warning messages, the target accessories may be multiple accessories corresponding to the multiple warning messages, so as to attract the user's attention and ensure that each important warning message can receive the user's timely attention and processing.

[0180] Optionally, the vehicle-mounted terminal obtains the second skeleton data, including:

[0181] The warning information is input into the third target model to generate second skeleton data. The third target model is obtained by training the third preset model based on the sample warning information and the sample skeleton data.

[0182] It should be noted that the third target model and the third preset model may be network models with the same structure as the second target model and the second preset model, which will not be described in detail here.

[0183] Exemplarily, in one embodiment, the target information acquired by the vehicle-mounted terminal includes the navigation information of the vehicle-mounted terminal, the driving information of the vehicle corresponding to the vehicle-mounted terminal, and the environmental information of the vehicle-mounted terminal, wherein the navigation information indicates that the vehicle is 2.1 kilometers away from the set destination, the driving information indicates that the current vehicle speed is 70 kilometers per hour, and the environmental information indicates that the environment outside the vehicle is sunny, and the preset conditions corresponding to each target information are as follows: the preset condition corresponding to the navigation information is that the distance to the set destination is less than 3 kilometers, and the preset condition corresponding to the driving information is that the speed limit of the current road section is 60 kilometers per hour.

[0184] The vehicle-mounted terminal can generate a second prompt word when N types of information among the multiple types of information do not meet corresponding preset conditions. Optionally, when N is 1, because the current vehicle speed indicated by the driving information does not meet the corresponding preset conditions, the warning information is driving information, the second prompt word is the prompt word corresponding to the driving information, and the target accessory is the accessory corresponding to the driving information. Optionally, the second prompt word can be a prompt word such as "right hand swing up and down" or "arms crossed", and the target accessory can be a traffic sign or a warning sign with a word such as "slow down" (not limited here).

[0185] Taking the second prompt word as "swing your right hand up and down" and the target accessory as a warning sign with "slow down" as an example, the skeleton action corresponding to the first skeleton data can be as follows: Figure 7 As shown, Figure 7 Another schematic diagram of the skeleton action corresponding to the first skeleton data in the method for generating the animation of the in-vehicle virtual image provided by the embodiment of the present application, Figure 7 Parts A, B, and C are the three pose information corresponding to the in-vehicle virtual image (including the rotation information of each bone). Through the time sequence of each pose information, the rendered in-vehicle virtual image can present the animation effect of the right hand swinging up and down.

[0186] The second skeleton data of the target accessory can be as follows Figure 8 As shown, Figure 8 A schematic diagram of the skeleton movement corresponding to the second skeleton data in the method for generating an animation of a vehicle-mounted virtual image provided by an embodiment of the present application, Figure 7 Parts A, B, and C represent the three poses of the target component. By sequentially chronologically sequencing these poses, the rendered component can be animated to appear as if it were swaying side to side, attracting the user's attention. It should be noted that a greater or lesser number of skeletal joints can be configured depending on the type and complexity of the target component, and this is not a limitation.

[0187] The vehicle terminal can render the vehicle virtual image and the target accessories based on the first skeleton data and the second skeleton data, and display the target animation including the target accessories. Figure 9 , Figure 9 This is another schematic diagram of the target animation in the method for generating an animation of a vehicle-mounted virtual image provided by an embodiment of the present application. Figure 9 Parts A, B and C are the animation content of the target animation. By displaying the target animation including the target accessories to the user, the target animation content can be improved and warning information can be prompted to the user, thereby improving the user experience.

[0188] Optionally, after the vehicle-mounted terminal obtains the second skeleton data, the method further includes:

[0189] Correcting the position information of each bone in the second skeleton data according to the position information of the target bone in the first skeleton data to obtain corrected second skeleton data;

[0190] The vehicle terminal renders the vehicle virtual image and the target accessory based on the first skeleton data and the second skeleton data, and displays a target animation including the target accessory, including:

[0191] The vehicle-mounted virtual image and the target accessory are rendered based on the first skeleton data and the corrected second skeleton data, and a target animation including the target accessory is displayed.

[0192] It should be noted that the target skeleton can be the skeleton corresponding to the head or hand of the vehicle-mounted virtual image, so that the position information of the corrected second skeleton data is associated with the position information of the target skeleton, so that the target accessories in the displayed target animation can move with the designated part of the vehicle-mounted virtual image, thereby improving the animation quality.

[0193] By implementing the above technical solution, the in-vehicle terminal can generate prompt words based on the acquired target information, and generate first skeleton data based on the prompt words, so that the in-vehicle virtual image can be rendered based on the first skeleton data to display the target animation. Compared with the traditional method in which animation designers need to design animation content for each in-vehicle virtual image one by one and build a huge animation library for the in-vehicle terminal to select and play, this solution not only significantly reduces the labor and time costs of animation production, but also makes the animation performance of the in-vehicle virtual image more flexible and changeable, able to promptly respond to information such as vehicle status and environmental changes, providing users with a richer and more vivid interactive experience.

[0194] The following explains the implementation process of the server generating the first skeleton data and sending the generated first skeleton data to the vehicle-mounted terminal in the embodiment of the present application.

[0195] See also Figure 10 , Figure 10A flow chart of the application of the method for generating animation of a vehicle-mounted virtual image provided in an embodiment of the present application to a server. The method for generating animation of a vehicle-mounted virtual image can be applied to a server, such as Figure 10 As shown, the method may include the following steps:

[0196] S1001, obtaining target information of the vehicle-mounted terminal, where the target information includes at least one of navigation information of the vehicle-mounted terminal, driving information of a vehicle corresponding to the vehicle-mounted terminal, and environmental information of the vehicle-mounted terminal.

[0197] In some possible embodiments, the server may obtain the target information of the vehicle-mounted terminal based on the communication connection established between the vehicle-mounted terminal and the server.

[0198] S1002, generating first skeleton data according to target information, where the first skeleton data is used to indicate multiple pose information of an in-vehicle virtual image of the in-vehicle terminal.

[0199] In some possible embodiments, the server generates first skeleton data according to the target information, including:

[0200] Generate prompt words based on the target information of the vehicle terminal, and the prompt words are used to describe the skeleton movement;

[0201] Generate first skeleton data according to the prompt word.

[0202] Optionally, the server generates prompt words based on the target information of the vehicle terminal, including:

[0203] When each of the multiple types of information meets the corresponding preset conditions, generating a first prompt word, the first prompt word being a prompt word indicating a positive emotion;

[0204] When N types of information among the multiple types of information do not meet the corresponding preset conditions, a second prompt word is generated, where the second prompt word is a prompt word corresponding to the warning information, where the warning information is information that does not meet the corresponding preset conditions, and N is an integer greater than or equal to 1.

[0205] Optionally, the server generates prompt words based on the target information of the vehicle terminal, including:

[0206] The target information of the vehicle terminal is input into the fourth target model to generate prompt words. The fourth target model is obtained by training the fourth preset model based on sample information corresponding to the target information and the sample prompt words.

[0207] It should be noted that the fourth target model and the fourth preset model may be network models with the same structure as the first target model and the first preset model, which will not be described in detail here.

[0208] Optionally, the server generates first skeleton data according to the prompt word, including:

[0209] The prompt word is input into the fifth target model to generate the first skeleton data. The fifth target model is obtained by training the fifth preset model based on the sample prompt word and the sample skeleton data.

[0210] It should be noted that the fifth target model and the fifth preset model may be network models with the same structure as the second target model and the second preset model, which will not be described in detail here.

[0211] Optionally, the server may adopt a generative MOMASK model to generate the first skeleton data according to the prompt word.

[0212] Optionally, when generating the second prompt word, the method applied to the server further includes:

[0213] generating second skeleton data, where the second skeleton data is skeleton data of a target accessory, and the target accessory is the accessory corresponding to the warning information;

[0214] The second skeleton data is sent to the vehicle terminal, so that the vehicle terminal renders the vehicle virtual image and the target accessories based on the first skeleton data and the second skeleton data, and displays the target animation including the target accessories.

[0215] Optionally, the server may determine the target accessory corresponding to the warning information through a preset accessory mapping relationship, where the preset accessory mapping relationship includes a mapping relationship between preset warning information and preset accessories.

[0216] Optionally, the server obtains the second skeleton data, including:

[0217] The warning information is input into the sixth target model to generate second skeleton data. The sixth target model is obtained by training the sixth preset model based on the sample warning information and the sample skeleton data.

[0218] It should be noted that the third target model and the third preset model may be network models with the same structure as the second target model and the second preset model, which will not be described in detail here.

[0219] S1003: Send the first skeleton data to the vehicle-mounted terminal, so that the vehicle-mounted terminal renders the vehicle-mounted virtual image based on the first skeleton data and displays a target animation corresponding to at least one posture information.

[0220] By implementing the above technical solution, the server can obtain the target information of the vehicle-mounted terminal through the communication connection with the vehicle-mounted terminal and generate the first skeleton data and send it to the vehicle-mounted terminal. This can reduce the computing power requirements for the vehicle-mounted terminal, so that the method provided in this application can be deployed on vehicle-mounted terminals with different computing power levels, thereby improving the compatibility and flexibility of the method provided in this application.

[0221] See also Figure 11 , Figure 11 Another flow chart of the method for generating animation of a vehicle-mounted virtual image provided by an embodiment of the present application is provided, wherein the vehicle-mounted terminal can establish a communication connection with the server to obtain the first skeleton data sent by the server, such as Figure 11 As shown, the method may include the following steps:

[0222] S1101, sending target information to the vehicle terminal.

[0223] The vehicle-mounted terminal can send the acquired target information to the server through a communication connection with the server, so that the server can process the target information and obtain the first skeleton data corresponding to the target information.

[0224] S1102, obtaining target information of the vehicle terminal.

[0225] The server can obtain the target information sent by the vehicle-mounted terminal through the communication connection with the vehicle-mounted terminal and process it.

[0226] S1103: Generate prompt words according to the target information of the vehicle-mounted terminal.

[0227] The server can generate prompt words through a pre-trained network model or other preset generation strategies.

[0228] S1104: Generate first skeleton data according to the prompt word.

[0229] The server may further generate first skeleton data using the generated prompt words.

[0230] S1105, sending the first skeleton data.

[0231] After the server generates the first skeleton data, the first skeleton data needs to be sent to the vehicle-mounted terminal so that the vehicle-mounted terminal can render the vehicle-mounted virtual image based on the first skeleton data and display the corresponding target animation.

[0232] S1106, obtaining first skeleton data.

[0233] When the vehicle-mounted terminal establishes a connection with the server, it obtains the first skeleton data from the server.

[0234] S1107: Render the vehicle-mounted virtual image based on the first skeleton data to display a target animation.

[0235] After obtaining the first skeleton data, the vehicle terminal can render the vehicle virtual image based on the first skeleton data and display the target animation, so that the user can intuitively observe the dynamic performance of the vehicle virtual image while using the vehicle terminal.

[0236] By implementing the above technical solution, the cost of animation production can be reduced, and the richness of the interaction between the in-vehicle avatar and the user can be improved. At the same time, the movements of the in-vehicle avatar in the target animation are ensured to be consistent with the actual application scenario of the in-vehicle terminal, thus improving the user experience of the in-vehicle terminal.

[0237] It should be understood that, although the steps in the above-mentioned flowcharts are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above-mentioned flowcharts may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0238] Based on the foregoing embodiments, an embodiment of the present application provides an animation generation device for a vehicle-mounted virtual image, which includes the modules included and the units included in each module, and can be implemented by a processor; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0239] Figure 12 This is a structural diagram of the vehicle-mounted virtual image animation generation device provided in the embodiment of the present application applied to a vehicle-mounted terminal, such as Figure 12 As shown, the device is applied to a vehicle-mounted terminal, and includes a first acquisition module 1201 and a rendering and display module 1202, wherein:

[0240] The first acquisition module 1201 is used to obtain first skeleton data, which is used to indicate multiple posture information of the vehicle-mounted virtual image of the vehicle-mounted terminal. The first skeleton data is determined based on the target information of the vehicle-mounted terminal, and the target information includes at least one of the navigation information of the vehicle-mounted terminal, the driving information of the vehicle corresponding to the vehicle-mounted terminal, and the environmental information of the vehicle-mounted terminal.

[0241] The rendering and display module 1202 is used to render the vehicle-mounted virtual image based on the first skeleton data and display a target animation corresponding to at least one posture information.

[0242] In some possible embodiments, each posture information includes position information and rotation information of the skeleton of the vehicle-mounted virtual image. The rendering and display module 1202 is also used to obtain the skeleton movement of the vehicle-mounted virtual image according to the time sequence of the multiple posture information; render the vehicle-mounted virtual image according to the skeleton movement, and obtain and display the target animation.

[0243] In some possible embodiments, the first acquisition module 1201 is further configured to acquire target information of the vehicle-mounted terminal.

[0244] In some possible embodiments, the first acquisition module 1201 is further configured to acquire the first skeleton data from the server when a connection is established with the server.

[0245] In some possible embodiments, the first acquisition module 1201 is further configured to acquire the first skeleton data according to a preset period; or acquire the first skeleton data when a preset operation on the in-vehicle virtual image is detected.

[0246] In some possible embodiments, the first acquisition module 1201 includes a prompt word generation module and a skeleton data generation module. The prompt word generation module of the first acquisition module 1201 is used to generate prompt words based on the target information of the vehicle-mounted terminal. The prompt words are used to describe the skeleton movements of the vehicle-mounted virtual image.

[0247] In some possible embodiments, the skeleton data generating module of the first acquiring module 1201 is configured to generate first skeleton data according to a prompt word.

[0248] In some possible embodiments, the prompt word generation module of the first acquisition module 1201 is also used to determine, for each type of information in the target information, whether the information meets the preset conditions corresponding to the information; when the number of information that meets the corresponding preset conditions in the multiple information is greater than or equal to a preset threshold, a first prompt word is generated, and the first prompt word is a prompt word indicating positive emotions; when the number of information that meets the corresponding preset conditions in the multiple information is less than the preset threshold, a second prompt word is generated, and the second prompt word is a prompt word indicating warning information, and the warning information is information that does not meet the corresponding preset conditions.

[0249] In some possible embodiments, the first acquisition module 1201 is further configured to acquire second skeleton data, where the second skeleton data is skeleton data of a target accessory, and the target accessory is the accessory corresponding to the warning information.

[0250] In some possible embodiments, the rendering and display module 1202 is further configured to render the vehicle-mounted virtual image and the target accessory based on the first skeleton data and the second skeleton data, and display a target animation including the target accessory.

[0251] In some possible embodiments, the prompt word generation module of the first acquisition module 1201 is also used to input the target information of the vehicle-mounted terminal into the first target model to generate prompt words. The first target model is obtained by training the first preset model based on sample information corresponding to the target information and the sample prompt words.

[0252] In some possible embodiments, the skeleton data generation module of the first acquisition module 1201 is also used to input the prompt word into the second target model to generate the first skeleton data. The second target model is obtained by training the second preset model based on the sample prompt word and the sample skeleton data.

[0253] Figure 13 This is a structural diagram of the vehicle-mounted virtual image animation generation device provided in the embodiment of the present application applied to a server, such as Figure 13 As shown, the device is applied to a server and includes a second acquisition module 1301, a generation module 1302 and a sending module 1303, wherein:

[0254] The second acquisition module 1301 is used to acquire target information of the vehicle terminal, where the target information includes at least one of navigation information of the vehicle terminal, driving information of the vehicle corresponding to the vehicle terminal, and environmental information of the vehicle terminal.

[0255] The generating module 1302 is used to generate first skeleton data according to the target information, where the first skeleton data is used to indicate multiple position information of the vehicle-mounted virtual image of the vehicle-mounted terminal.

[0256] The sending module 1303 is used to send the first skeleton data to the vehicle-mounted terminal, so that the vehicle-mounted terminal renders the vehicle-mounted virtual image based on the first skeleton data and displays a target animation corresponding to at least one posture information.

[0257] In some possible embodiments, the generation module 1302 includes a prompt word generation module and a skeleton data generation module. The prompt word generation module of the generation module 1302 is used to generate prompt words according to target information of the vehicle-mounted terminal, and the prompt words are used to describe skeleton movements.

[0258] In some possible embodiments, the skeleton data generating module of the generating module 1302 is used to generate the first skeleton data according to the prompt word.

[0259] The description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0260] It should be noted that in the embodiments of this application Figure 12 or Figure 13 The division of modules in the device shown is schematic and is only a logical functional division. In actual implementation, other division methods may be used. In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or can exist physically separately, or two or more units can be integrated into a single unit. The above-mentioned integrated units can be implemented in the form of hardware or software functional units. It can also be implemented in the form of a combination of software and hardware.

[0261] It should be noted that, in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling an electronic device to execute all or part of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0262] The embodiment of the present application provides a computer device, the internal structure of which can be as follows: Figure 14 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0263] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method provided in the above embodiment are implemented.

[0264] An embodiment of the present application provides a computer program product containing instructions, which, when executed on a computer, enables the computer to execute the steps of the method provided in the above method embodiment.

[0265] Those skilled in the art will understand that Figure 14 The structure shown in the figure is only a block diagram of a part of the 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 component arrangement.

[0266] In one embodiment, the vehicle-mounted virtual image animation generation device provided by the present application for a vehicle-mounted terminal or server can be implemented in the form of a computer program. The computer program can be used in Figure 14 The computer device is operated on the computer device shown. The memory of the computer device can store various program modules that constitute the above-mentioned device. The computer program composed of each program module enables the processor to execute the steps of the method of each embodiment of the present application described in this specification.

[0267] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0268] It should be understood that "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other. For the sake of brevity, they will not be repeated here.

[0269] The term "and / or" in this article is only a description of the association relationship between associated objects, indicating that there can be three relationships. For example, object A and / or object B can mean: object A exists alone, object A and object B exist at the same time, and object B exists alone.

[0270] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0271] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical or other forms.

[0272] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed across multiple network units; some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

[0273] In addition, all functional modules in the embodiments of the present application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the above-mentioned integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0274] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and other media that can store program codes.

[0275] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0276] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0277] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0278] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0279] The above is merely an embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for generating an animation of a vehicle-mounted virtual image, characterized in that: Applied to a vehicle-mounted terminal, the method includes: Acquiring first skeleton data, the first skeleton data being used to indicate multiple pose information of an in-vehicle avatar of the in-vehicle terminal, the first skeleton data being determined based on target information of the in-vehicle terminal, the target information including at least one of navigation information of the in-vehicle terminal, driving information of a vehicle corresponding to the in-vehicle terminal, and environmental information of the in-vehicle terminal; The vehicle-mounted virtual image is rendered based on the first skeleton data to display a target animation corresponding to the at least one posture information.

2. The method according to claim 1, characterized in that Each of the plurality of pose information includes position information and rotation information of a skeleton of the in-vehicle avatar, and rendering the in-vehicle avatar based on the first skeleton data to display a target animation corresponding to the at least one pose information includes: Obtaining a skeleton motion of the vehicle-mounted virtual image according to a time sequence of the plurality of posture information; The vehicle-mounted virtual image is rendered according to the skeleton action to obtain and display the target animation.

3. The method according to claim 1 or 2, characterized in that Before acquiring the first skeleton data, the method further includes: Acquiring the target information of the vehicle-mounted terminal; The obtaining of the first skeleton data includes: generating prompt words according to the target information of the vehicle-mounted terminal, wherein the prompt words are used to describe the skeleton movements of the vehicle-mounted virtual image; The first skeleton data is generated according to the prompt word.

4. The method according to claim 3, characterized in that When the target information includes multiple types of information, generating prompt words according to the target information of the vehicle-mounted terminal includes: For each type of target information, determining whether the information satisfies a preset condition corresponding to the information; If the number of pieces of information that meet the corresponding preset conditions in the multiple pieces of information is greater than or equal to a preset threshold, generating a first prompt word, wherein the first prompt word is a prompt word indicating a positive emotion; When the number of information satisfying the corresponding preset conditions in the multiple information is less than a preset threshold, a second prompt word is generated, where the second prompt word is a prompt word indicating warning information, and the warning information is information that does not satisfy the corresponding preset conditions.

5. The method according to claim 4, characterized in that In the case of generating the second prompt word, the method further includes: Acquire second skeleton data, where the second skeleton data is skeleton data of a target accessory, and the target accessory is the accessory corresponding to the warning information; The vehicle-mounted virtual image and the target accessory are rendered based on the first skeleton data and the second skeleton data, and the target animation including the target accessory is displayed.

6. The method according to claim 3, characterized in that The generating of prompt words according to the target information of the vehicle-mounted terminal includes: Inputting the target information of the vehicle-mounted terminal into a first target model to generate the prompt word, wherein the first target model is obtained by training a first preset model based on sample information corresponding to the target information and the sample prompt word; The step of generating the first skeleton data according to the prompt word includes: The prompt word is input into the second target model to generate the first skeleton data. The second target model is obtained by training the second preset model based on the sample prompt word and the sample skeleton data.

7. A method for generating an animation of a vehicle-mounted virtual image, characterized in that: Applied to a server, the method includes: Acquiring target information of the vehicle-mounted terminal, the target information including at least one of navigation information of the vehicle-mounted terminal, driving information of a vehicle corresponding to the vehicle-mounted terminal, and environmental information of the vehicle-mounted terminal; generating first skeleton data according to the target information, wherein the first skeleton data is used to indicate multiple pose information of the vehicle-mounted virtual image of the vehicle-mounted terminal; The first skeleton data is sent to the vehicle-mounted terminal, so that the vehicle-mounted terminal renders the vehicle-mounted virtual image based on the first skeleton data and displays a target animation corresponding to the at least one posture information.

8. An animation generating device for a vehicle-mounted virtual image, characterized in that: Applied to vehicle terminals, including: a first acquisition module, configured to acquire first skeleton data, the first skeleton data being used to indicate multiple pose information of an in-vehicle avatar of the in-vehicle terminal, the first skeleton data being determined based on target information of the in-vehicle terminal, the target information including at least one of navigation information of the in-vehicle terminal, driving information of a vehicle corresponding to the in-vehicle terminal, and environmental information of the in-vehicle terminal; A rendering and display module is used to render the vehicle-mounted virtual image based on the first skeleton data and display a target animation corresponding to the at least one posture information.

9. An animation generating device for a vehicle-mounted virtual image, characterized in that: Applied to vehicle terminals, including: A second acquisition module is configured to acquire target information of the vehicle-mounted terminal, wherein the target information includes at least one of navigation information of the vehicle-mounted terminal, driving information of a vehicle corresponding to the vehicle-mounted terminal, and environmental information of the vehicle-mounted terminal; a generating module, configured to generate first skeleton data according to the target information, wherein the first skeleton data is used to indicate a plurality of position and posture information of the vehicle-mounted virtual image of the vehicle-mounted terminal; The sending module is used to send the first skeleton data to the vehicle-mounted terminal, so that the vehicle-mounted terminal renders the vehicle-mounted virtual image based on the first skeleton data and displays a target animation corresponding to the at least one posture information.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 or 7 are implemented.

Images