Generation of virtual avatar

Abstract

The present disclosure relates to the technical field of image processing, and provides a virtual avatar generation method and apparatus, a device, and a storage medium. The virtual avatar generation method provided by the present disclosure comprises: on the basis of a generation mode of a virtual avatar which is set by a user, acquiring a material corresponding to the generation mode; on the basis of preference information of the user and in view of key information extracted from the material, generating description information of the virtual avatar; and inputting the description information of the virtual avatar into a target model corresponding to a target style indicated by the description information, and generating the virtual avatar.

Description

Generation of virtual images

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on October 31, 2023, with application number 202311445901.7, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] One or more embodiments of the present disclosure relate to, but are not limited to, the field of image processing technology, and in particular relate to, but are not limited to, a method, apparatus, device, and storage medium for generating a virtual image. Background Art

[0004] The avatar acts as a medium of communication between the driver and the vehicle. It appears on the central control screen in various scenarios. For example, it may appear during the startup animation to offer a greeting; it may answer questions posed by the user; it may also sense the driver's driving status during driving and use a small speaker to remind the driver to drive safely. Therefore, the design of the avatar significantly impacts the user experience.

[0005] Summary of the Invention

[0006] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0007] According to a first aspect of one or more embodiments of the present disclosure, a method for generating a virtual image is provided, which is applied to a central control system of a vehicle. The method includes:

[0008] According to the generation mode of the virtual image set by the user, the material corresponding to the generation mode is obtained; according to the user's preference information and combined with the key information extracted from the material, the description information of the virtual image is generated; the description information of the virtual image is input into the target model corresponding to the target style indicated by the description information to generate the virtual image.

[0009] In some embodiments, when the generation mode is adjusting the default avatar based on environmental information, obtaining the material corresponding to the generation mode includes:

[0010] Acquire a reference image of the default virtual image and environmental information of the current location of the vehicle; determine the reference image and the environmental information as materials required for generating the virtual image;

[0011] The generating of description information of the virtual image based on the user's preference information and key information extracted from the material includes:

[0012] Acquiring at least one first keyword associated with the environmental information; determining a preset template that matches the user's preference information; and obtaining a description statement of the virtual image based on the preset template and the at least one first keyword;

[0013] The reference image and the description sentence are determined as the description information of the virtual image.

[0014] In some embodiments, when the generation mode is adjusting the default avatar based on environmental information and geographical information, obtaining the material corresponding to the generation mode includes:

[0015] Acquiring a reference image of the default virtual image and environmental information and customs of the current location of the vehicle; determining the reference image, the environmental information, and the customs as materials required for generating the virtual image;

[0016] The generating of description information of the virtual image based on the user's preference information and key information extracted from the material includes:

[0017] Obtain at least one first keyword associated with the environmental information and at least one second keyword associated with the customs and habits; determine a preset template that conforms to the user's preference information; obtain a description statement of the virtual image based on the preset template, the at least one first keyword and the at least one second keyword; determine the reference image and the description statement as the description information of the virtual image.

[0018] In some embodiments, when the generation mode is to generate a virtual image based on a collected facial image, obtaining materials corresponding to the generation mode includes:

[0019] Acquiring a facial image captured by an image acquisition device in the vehicle; determining the facial image as a material required for generating the virtual image;

[0020] Generating description information of the virtual image based on the user's preference information and the key information extracted from the material includes:

[0021] Identify the facial image and obtain facial features of the facial image; obtain at least one third keyword associated with the facial features; determine a preset template that meets the preference information of the user; obtain a description statement of the virtual image based on the preset template and the at least one third keyword; determine the facial image and the description statement as description information of the virtual image.

[0022] In some embodiments, when the generation mode is selecting a preset avatar based on the collected in-vehicle information, the method further includes:

[0023] Acquire a first image captured by an image acquisition device in the vehicle; acquire a facial sub-image in the first image; match the facial sub-image with a pre-stored base map to generate a virtual image corresponding to the matched base map.

[0024] In some embodiments, when the generation mode is a customized avatar, obtaining the material corresponding to the generation mode includes:

[0025] Obtaining a description sentence of the virtual image input by the user;

[0026] Determining the description sentence as the material required for generating the virtual image;

[0027] Generating the description information of the virtual image based on the user's preference information and key information extracted from the material includes:

[0028] The description statement is checked, and if the description statement conforms to a set rule, the description statement is determined as the description information of the virtual image.

[0029] In some embodiments, when the generation mode is a customized virtual image, obtaining the material corresponding to the generation mode includes: obtaining the description statement and the second image of the virtual image input by the user; determining the description statement and the second image as the materials required for generating the virtual image; generating the description information of the virtual image based on the user's preference information and the key information extracted from the material, includes: checking the description statement, and if the description statement meets the set rules, determining the description statement and the second image as the description information of the virtual image.

[0030] In some embodiments, inputting the description information of the virtual image into a target model corresponding to a target style indicated by the description information to generate the virtual image includes:

[0031] If it is detected that the user allows network-based generation of the virtual image and the central control system is connected to the network, downloading a target model corresponding to the target style indicated by the description information from a server, and inputting the description information into the target model to obtain the virtual image;

[0032] If it is detected that the user does not allow the generation of a virtual image based on the network, or allows the generation of the virtual image based on the network but the central control system is not connected to the network, a target model corresponding to the target style indicated by the description information is obtained from a pre-stored target model, and the description information is input into the target model to obtain the virtual image.

[0033] According to a second aspect of one or more embodiments of the present disclosure, a virtual image generation device is provided, which is applied to a central control system of a vehicle. The device includes:

[0034] an acquiring unit configured to acquire a material corresponding to a generation mode of the avatar set by the user according to the generation mode of the avatar set by the user;

[0035] The generation unit is configured to generate description information of the virtual image based on the user's preference information and the key information extracted from the material, and input the description information of the virtual image into the target model corresponding to the target style indicated by the description information to generate the virtual image.

[0036] According to a third aspect of one or more embodiments of the present disclosure, an electronic device is provided, including:

[0037] A processor; a memory for storing processor-executable instructions; wherein the processor implements any of the above-mentioned methods by running the executable instructions.

[0038] According to a fourth aspect of one or more embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, any of the above-mentioned methods is implemented.

[0039] The disclosed avatar generation method obtains materials corresponding to a user-set avatar generation mode based on the generated mode. Descriptive information is generated based on the user's preferences and key information extracted from the materials. The avatar description is then input into a target model corresponding to a target style indicated by the description to generate the avatar. This method allows for automatic generation of avatars that meet user preferences based on the generated mode set by the user, thereby improving the user experience.

[0040] Still other aspects will become apparent upon reading and understanding the accompanying drawings and detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] FIG1 is a flow chart of a method for generating a virtual image provided by an exemplary embodiment.

[0042] FIG2 is a schematic diagram of a virtual image generating device provided by an exemplary embodiment.

[0043] FIG3 is a schematic structural diagram of a device provided by an exemplary embodiment. DETAILED DESCRIPTION

[0044] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible implementations consistent with one or more embodiments of the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of one or more embodiments of the present disclosure, as detailed in the appended claims.

[0045] It should be noted that in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this disclosure. In some other embodiments, the method may include more or fewer steps than those described in this disclosure. In addition, a single step described in this disclosure may be broken down into multiple steps for description in other embodiments; and multiple steps described in this disclosure may be combined into a single step for description in other embodiments.

[0046] As a medium of communication between people and cars, the display style of virtual images can reflect the user's individuality. However, the current types of virtual images are single and cannot meet the personalized needs of users.

[0047] In light of this, the present disclosure provides a method for generating an avatar for a vehicle's central control system. The method involves obtaining materials corresponding to a user-defined avatar generation mode based on the generated mode. Furthermore, based on the user's preferences and key information extracted from the materials, the avatar's description is generated. Finally, the avatar's description is input into a target model corresponding to a target style indicated by the description to generate the avatar. This method automatically generates an avatar that meets the user's preferences based on the user's defined avatar generation mode, thereby improving the user experience.

[0048] The following embodiments will introduce the solutions provided by the present disclosure in conjunction with the accompanying drawings.

[0049] FIG1 is a flow chart of a method for generating a virtual image provided by an exemplary embodiment. As shown in FIG1 , the method provided by the embodiment of the present disclosure includes steps 101 to 103 .

[0050] In step 101, according to the generation mode of the avatar set by the user, materials corresponding to the generation mode are obtained.

[0051] In this embodiment, the virtual image generation modes available for users to choose include: adjusting the default virtual image mode based on environmental information, adjusting the default virtual image mode based on environmental information and geographical information, and generating a virtual image mode based on a collected facial image, etc.

[0052] The materials required to generate a virtual image using different generation modes are different. Therefore, after obtaining the generation mode set by the user, the materials corresponding to the generation mode can be obtained. For example, the materials may include environmental information of the vehicle's location, geographical information and / or facial images captured by the image acquisition device in the vehicle.

[0053] In step 102, description information of the virtual image is generated based on the user's preference information and the key information extracted from the material.

[0054] The user preference information refers to the style of the virtual image that the user expects to generate, such as sketch style, watercolor style, anime style, trendy style, mechanical style, two-dimensional style, etc.

[0055] In this embodiment, the user's preference information can be pre-set by the user, or the user's preference information can be determined based on the user's various behavioral data and preferences. For example, a variety of virtual images of different styles are displayed for the user to choose from, and the user's preference information is determined based on the user's selection operation.

[0056] A preset template can be determined based on the user's preference information, wherein the preset template includes a content description part, a style description part and a parameter description part, etc., wherein the content description part is used to indicate the subject of the virtual image, the status of the virtual image, the clothes worn, etc.; the style description part is used to indicate the display style of the virtual image, such as sketch style, watercolor style, anime style, trendy style, mechanical style, and two-dimensional style; the parameter description part is used to indicate the size of the virtual image, etc.

[0057] After determining the user's preferences, the style description portion of the preset template can be determined and combined with the key information extracted from the source material to generate the avatar's description information. In this embodiment, the description information is used to describe the subject, accessories, and display style of the avatar that the user desires to generate.

[0058] In some embodiments, the preset template can be updated, for example, when connected to the Internet, the latest version of the preset template sent by the server is received. It should be understood by those skilled in the art that the user's preference information can also be updated regularly or irregularly, and popular styles can be recommended to the user, which is not limited in this disclosure.

[0059] In step 103, the description information of the virtual image is input into a target model corresponding to the target style indicated by the description information to generate the virtual image.

[0060] Since different styles correspond to different models, the description information of the virtual image is input into the target model corresponding to the target style indicated by the description information to obtain the virtual image described by the description information that meets the user's expectations.

[0061] In this embodiment, the target model corresponding to the target style can be determined based on user settings. That is, if the user does not allow network-based avatar generation, or if network-based avatar generation is allowed but the central control system is not connected to the Internet, the target model corresponding to the target style indicated by the description information is obtained from pre-stored target models. The pre-stored models may have a limited number of styles. In some cases, if no pre-stored models match the target style, a model with a similar style to the target style can be determined as the target model.

[0062] If network-based avatar generation is permitted and the central control system is connected to the network, a target model corresponding to the target style indicated by the description information can be downloaded from the server. The target model downloaded from the server is the latest version of the model, which the server continuously trains based on sample data. Furthermore, the style corresponding to the model stored on the server is relatively refined, so a target model closer to the target style can be obtained. Using the target model downloaded from the server can produce a more effective avatar.

[0063] During implementation, if it is detected that network-based generation of virtual images is allowed and the central control system is connected to the network, a target model corresponding to the target style indicated by the description information is downloaded from the server, and the description information is input into the target model to obtain a virtual image; if it is detected that network-based generation of virtual images is not allowed, or network-based generation of virtual images is allowed but the central control system is not connected to the network, a target model corresponding to the target style indicated by the description information is obtained from a pre-stored target model, and the description information is input into the target model to obtain a virtual image.

[0064] In some embodiments, if the avatar generated after inputting the description information into the target model does not meet the user's expectations, the user can instruct the avatar to be regenerated. Specifically, in response to detecting a regeneration instruction issued by the user, the modification direction indicated by the user is obtained, and the avatar is regenerated according to the modification direction indicated by the user.

[0065] For example, if the generated avatar does not meet the user's expectations, the user can click the regenerate control on the display screen. After detecting the regenerate instruction issued by the user, the modification direction indicated by the user is obtained, and the description information is regenerated according to the modification direction indicated by the user, thereby obtaining a regenerated avatar. The modification direction can be displayed on the display screen to obtain the modification direction input by the user, or the modification direction can be received by voice from the user, which is not limited in this disclosure.

[0066] The following embodiments will illustrate the process of generating a virtual image in different generation modes set by the user.

[0067] In a case where the virtual image generation mode set by the user is a mode of adjusting the default virtual image based on environmental information, obtaining the material corresponding to the generation mode may include: obtaining a reference image of the default virtual image and environmental information of the current location of the vehicle; and determining the reference image and the environmental information as the materials required for generating the virtual image.

[0068] In this embodiment, the reference image for the default avatar can be an image provided by the system, such as a cartoon image. The reference image for the avatar can also be an image uploaded by the user, such as an image of a favorite character of the user. The environmental information includes weather information, such as weather, temperature, humidity, wind direction, wind speed, and air quality.

[0069] In the case where the materials required for generating a virtual image include reference images and environmental information, generating description information of the virtual image based on the user's preference information in combination with key information extracted from the materials may include: obtaining at least one first keyword associated with the environmental information; determining a preset template that conforms to the user's preference information; obtaining a description statement of the virtual image based on the preset template and the at least one first keyword; and determining the reference image and the description statement as the description information of the virtual image.

[0070] A first mapping relationship table between different environmental information and first keywords is pre-constructed, and at least one first keyword associated with the environmental information is determined in the first mapping relationship table.

[0071] In one example, a placeholder in a preset template can be replaced with at least one first keyword to generate a description of the avatar. In another example, a target style that matches the user's preference information and at least one first keyword can be concatenated according to a pre-set concatenation rule to generate a description of the avatar.

[0072] In a mode where the user sets the default virtual image to be adjusted based on environmental information, the default virtual image can be adjusted according to the environmental information. This mode can present the effect of the default virtual image changing with seasons and climate.

[0073] In the case where the generation mode is a mode of adjusting the default virtual image based on environmental information and geographic information, obtaining the material corresponding to the generation mode may include: obtaining a reference image of the default virtual image, and the environmental information and customs of the current location of the vehicle; and determining the reference image, the environmental information and customs as the materials required for generating the virtual image.

[0074] When the materials required for generating a virtual image include the reference image, the environmental information and customs and habits, generating the description information of the virtual image based on the user's preference information in combination with the key information extracted from the materials may include: obtaining at least one first keyword associated with the environmental information and at least one second keyword associated with the customs and habits; determining a preset template that conforms to the user's preference information; obtaining a description statement of the virtual image based on the preset template, at least one first keyword and at least one second keyword; and determining the reference image and the description statement as the description information of the virtual image.

[0075] In this embodiment, customs and habits can include the clothing styles of ethnic minorities in the vehicle's location. For example, in Guizhou, the Miao ethnic group's clothing style can be reflected in the avatar to increase the avatar's interest. Adjusting the default avatar based on environmental and geographic information is suitable for self-driving tours. As you pass through different locations, you can display an avatar that reflects the local customs and habits, thereby improving the user experience.

[0076] In the case where the generation mode is a mode of generating a virtual image based on a captured facial image, obtaining the material corresponding to the generation mode may include: obtaining a facial image captured by an image capture device in the vehicle; and determining the facial image as the material required for generating the virtual image.

[0077] This embodiment uses an image acquisition device on the vehicle to capture a facial image of the driver or a user in a designated seat, and generates a virtual image based on the facial image.

[0078] In the case where the material includes a facial image, generating description information for the virtual image based on the user's preference information and key information extracted from the material may include: identifying the facial image and obtaining facial features of the facial image; obtaining at least one third keyword associated with the facial features; determining a preset template that meets the user's preference information; obtaining a description statement for the virtual image based on the preset template and the at least one third keyword; and determining the facial image and the description statement as the description information for the virtual image. For example, if the facial image is identified and facial features of a smile are obtained, the third keyword is "smile" and the preset template determined based on the user's preference information is a watercolor painting style. The description statement for the virtual image thus obtained is: "having a laughing expression in a watercolor painting style." In this case, the description information of the virtual image determined based on the facial image and the description statement may include: a facial image with a laughing expression in a watercolor painting style.

[0079] Through this embodiment, the collected facial image can be converted into a virtual image that meets the user's preferences, thereby increasing the intimacy between the user and the virtual image and improving the user's experience of interacting with the virtual image.

[0080] In the case where the generation mode is to select a preset virtual image based on the collected in-vehicle information, the method further includes: obtaining a first image captured by an image capture device in the vehicle; obtaining a facial sub-image in the first image; matching the facial sub-image with a pre-stored base map, and generating a virtual image corresponding to the matched base map.

[0081] Users can pre-set different virtual images for different scenarios. For example, in a family outing scenario, a virtual image corresponding to the family scenario is generated, for example, a virtual image corresponding to each person in a family of three.

[0082] Taking a family of three as an example, a facial base map of each family member is pre-stored, and a first image captured by an image acquisition device in the vehicle is obtained. The first image includes images of users in different seats in the vehicle. The facial sub-images in the first image are obtained, and the facial sub-images are matched with the pre-stored facial base map. If the facial sub-images in the first image match the pre-stored facial base map, it means that the current members in the car are family members. In this case, a virtual image corresponding to the matched base map can be generated. For example, a virtual image corresponding to the pre-stored facial base map of each family member is generated. The virtual image generated by this embodiment can increase the atmosphere and fun in the car when family members travel together.

[0083] In the case where the generation mode is a customized avatar, the acquisition of materials corresponding to the generation mode may include: acquiring a description sentence input by the user, and determining the description sentence as the material required for generating the avatar; or acquiring a description sentence and a second image input by the user, and determining the description sentence and the second image as the material required for generating the avatar. In addition, based on the driving of 2D or 3D avatars, virtual engine construction, voice driving, motion capture, facial capture, object tracking and other technologies, a user-customized avatar may be generated; a user avatar and a graphical user interface (GUI) with current point of interest (POI) features may be generated; and scene entertainment and interaction may be performed based on the generated avatar combined with capabilities such as a scene engine.

[0084] In the case where the materials required for generating a virtual image include the descriptive statement or the descriptive statement and the second image, the generation of the descriptive information of the virtual image based on the user's preference information in combination with the key information extracted from the materials may also include: checking the descriptive statement, and if the descriptive statement meets the set rules, determining the descriptive statement or the descriptive statement and the second image as the descriptive information. For example, the descriptive statement input by the user through voice is "Please generate a virtual image of anime character A", which meets the set rules (the set rules are, for example, that the descriptive statement includes semantic information), and the second image is a picture of anime character A uploaded by the user, then the materials include the virtual image of anime character A and the picture of anime character A, the user's preference information is a two-dimensional style, and the preset template is a two-dimensional style template, then the descriptive information can be displayed for anime character A in a two-dimensional style.

[0085] The present disclosure provides users with a variety of methods for generating virtual images, which are convenient for users to choose according to their needs, thereby generating a virtual image that conforms to the user's personalization.

[0086] Based on the same inventive concept, embodiments of the present disclosure also provide a virtual image generation device for use in a vehicle's central control system. Figure 2 is a schematic diagram of a virtual image generation device provided by an exemplary embodiment. As shown in Figure 2, the device includes: an acquisition unit 201 configured to acquire, based on a user-set virtual image generation mode, materials corresponding to the generation mode; a generation unit 202 configured to generate description information for the virtual image based on user preference information and key information extracted from the materials, and input the description information of the virtual image into a target model corresponding to the target style indicated by the description information to generate the virtual image.

[0087] The specific implementation process of each unit can be found in the above embodiments and will not be repeated here.

[0088] FIG3 is a schematic diagram of the structure of a device provided by an exemplary embodiment. Referring to FIG3 , at the hardware level, the device includes a processor 302, an internal bus 304, a network interface 306, a memory 308, and a non-volatile memory 310, and may also include hardware required for other application scenarios. One or more embodiments of the present disclosure may be implemented based on software, such as the processor 302 reading the corresponding computer program from the non-volatile memory 310 into the memory 308 and then running it. Of course, in addition to software implementation, one or more embodiments of the present disclosure do not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but may also be hardware or logic devices.

[0089] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0090] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0092] Computer-readable media include permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0093] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0094] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0095] The foregoing description describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The terms used in one or more embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present disclosure. The singular forms "a," "the," and "the" used in one or more embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0097] It should be understood that although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of the present disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0098] The above description is one or more embodiments of the present disclosure and is not intended to limit the one or more embodiments of the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present disclosure shall be included in the scope of protection of one or more embodiments of the present disclosure.

Claims

1. A method for generating a virtual image, applied to a central control system of a vehicle, the method comprising: According to the generation mode of the virtual image set by the user, obtaining materials corresponding to the generation mode; Generate description information of the virtual image according to the user's preference information and in combination with key information extracted from the material; The description information of the virtual image is input into a target model corresponding to a target style indicated by the description information to generate the virtual image.

2. The method according to claim 1, wherein: In the case where the generation mode is to adjust the default avatar based on environmental information, The acquiring of the material corresponding to the generation mode includes: Acquire a reference image of the default avatar and environmental information of the current location of the vehicle; Determine the reference image and the environmental information as materials required for generating the virtual image; Generating description information of the virtual image according to the preference information of the user and the key information extracted from the material, including: Acquire at least one first keyword associated with the environmental information; Determine a preset template that matches the user's preference information; Obtaining a description sentence of the virtual image according to the preset template and the at least one first keyword; The reference image and the description sentence are determined as the description information of the virtual image.

3. The method according to claim 1, wherein: In the case where the generation mode is to adjust the default avatar based on environmental information and geographic information, The acquiring of the material corresponding to the generation mode includes: Acquire a reference image of the default avatar and environmental information and customs of the current location of the vehicle; Determining the reference image, the environmental information and the customs as materials required for generating the virtual image; Generating description information of the virtual image according to the preference information of the user and the key information extracted from the material, including: Acquire at least one first keyword associated with the environmental information and at least one second keyword associated with the customs and habits; Determine a preset template that matches the user's preference information; According to the preset template, the at least one first keyword and the at least one second keyword, A description sentence of the virtual image; The reference image and the description sentence are determined as the description information of the virtual image.

4. The method according to claim 1, wherein: In the case where the generation mode is to generate a virtual image based on a collected face image, The acquiring of the material corresponding to the generation mode includes: Acquire a facial image captured by an image acquisition device in the vehicle; Determining the human face image as the material required for generating the virtual image; The step of generating description information of the virtual image based on the preference information of the user and the key information extracted from the material includes: Identify the face image and obtain facial features of the face image; Acquire at least one third keyword associated with the facial feature; Determine a preset template that matches the preference information of the user; Obtaining a description sentence of the virtual image according to the preset template and the at least one third keyword; The facial image and the description sentence are determined as description information of the virtual image.

5. The method according to claim 1, wherein: In the case where the generation mode is to select a preset virtual image based on the collected in-vehicle information, the method further includes: Acquire a first image captured by an image acquisition device in the vehicle; Acquire a face sub-image in the first image; The face sub-image is matched with a pre-stored base image to generate a virtual image corresponding to the matched base image.

6. The method according to claim 1, wherein: When the generation mode is a custom avatar, The acquiring of the material corresponding to the generation mode includes: Obtaining a description sentence of the virtual image input by the user; Determining the description sentence as the material required for generating the virtual image; The step of generating the description information of the virtual image according to the preference information of the user and the key information extracted from the material includes: Check the description statement, If the description sentence meets the set rule, the description sentence is determined as the description information of the virtual image.

7. The method according to claim 1, wherein: When the generation mode is a custom avatar, The acquiring the material corresponding to the generation mode includes: Acquire a description sentence of the virtual image and a second image input by the user; determining the description sentence and the second image as the materials required for generating the virtual image; The step of generating the description information of the virtual image according to the preference information of the user and the key information extracted from the material includes: Check the description statement, If the description sentence meets the set rule, the description sentence and the second image are determined as the description information of the virtual image.

8. The method according to claim 1, wherein: The step of inputting the description information of the virtual image into a target model corresponding to a target style indicated by the description information to generate the virtual image comprises: If it is detected that the user allows the generation of the virtual image based on the network and the central control system is connected to the network, a target model corresponding to the target style indicated by the description information is downloaded from the server, and the description information is input into the target model to obtain the virtual image; If it is detected that the user does not allow the generation of a virtual image based on the network, or allows the generation of the virtual image based on the network but the central control system is not connected to the network, a target model corresponding to the target style indicated by the description information is obtained from a pre-stored target model, and the description information is input into the target model to obtain the virtual image.

9. A virtual image generation device, applied to a central control system of a vehicle, the device comprising: an acquisition unit, configured to acquire materials corresponding to a generation mode of the avatar set by a user; The generation unit is configured to generate description information of the virtual image based on the user's preference information and the key information extracted from the material, and input the description information of the virtual image into a target model corresponding to the target style indicated by the description information to generate the virtual image.

10. An electronic device, comprising: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 1 to 8 by running the executable instructions.

11. A computer-readable storage medium having computer instructions stored thereon, wherein the instructions are executed by a processor to implement the method according to any one of claims 1 to 8.

Images