WO2021244110A1 - 作品生成和编辑方法、装置、终端、服务器和系统 - Google Patents

作品生成和编辑方法、装置、终端、服务器和系统 Download PDF

Info

Publication number
WO2021244110A1
WO2021244110A1 PCT/CN2021/082971 CN2021082971W WO2021244110A1 WO 2021244110 A1 WO2021244110 A1 WO 2021244110A1 CN 2021082971 W CN2021082971 W CN 2021082971W WO 2021244110 A1 WO2021244110 A1 WO 2021244110A1
Authority
WO
WIPO (PCT)
Prior art keywords
work
creation
cloud
module
creative
Prior art date
Application number
PCT/CN2021/082971
Other languages
English (en)
French (fr)
Inventor
丁磊
王超
Original Assignee
华人运通(上海)新能源驱动技术有限公司
华人运通(上海)云计算科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华人运通(上海)新能源驱动技术有限公司, 华人运通(上海)云计算科技有限公司 filed Critical 华人运通(上海)新能源驱动技术有限公司
Publication of WO2021244110A1 publication Critical patent/WO2021244110A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/438—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G06F16/9554—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL] by using bar codes

Definitions

  • This application relates to artificial intelligence technology, in particular to a method, device, terminal, server and system for generating and editing works.
  • the car terminal refers to the abbreviation of in-car infotainment products installed in the car, which can realize the information communication between people and car, car and the outside world (such as car and car) in function.
  • car and machine terminals provide users with multimedia services and navigation services, and the service form is relatively simple.
  • the car terminal can provide diversified services.
  • the embodiments of the application provide a method, device, terminal, server, and system for generating and editing works to solve the problems of related technologies.
  • the technical solutions are as follows:
  • an embodiment of the present application provides a method for generating a work, including:
  • the work creation request includes creation parameters, so that the cloud request creation module creates the corresponding creation work according to the creation parameters;
  • an embodiment of the present application provides a method for generating a work, which is applied to the cloud, including:
  • the work creation request includes the creation parameters
  • the creative work corresponding to the creative task ID is sent to the vehicle terminal.
  • the embodiments of the present application provide a method for generating a work, which is applied to the car and machine side, including:
  • the vehicle terminal is triggered to execute the work generation method of any one of the above aspects, and the target recognition result includes the first recognition result.
  • an embodiment of the present application provides a method for editing a work, which is applied to a mobile terminal, and the method includes:
  • an embodiment of the present application provides a work generation device, including:
  • the work creation request sending module is used to send a work creation request to the cloud, the work creation request includes creation parameters, so that the cloud request work creation module creates the corresponding creation work according to the creation parameters;
  • the creation task ID receiving module is used to receive the creation task ID corresponding to the work creation request returned by the cloud;
  • the first query request sending module is configured to send a first query request to the cloud, where the first query request includes the creative task ID, so that the cloud can query the creative work corresponding to the creative task ID;
  • the work display module is used to receive and display the creative work returned by the cloud and corresponding to the creative task ID on the vehicle and machine side.
  • an embodiment of the present application provides a work generation device, including:
  • the work creation request receiving module is used to receive the work creation request sent by the car and the machine terminal, and the work creation request includes the creation parameters;
  • the creation task ID generation and sending module is used to generate the creation task ID corresponding to the creation request of the work, and send the creation task ID to the vehicle terminal;
  • the request module is used to request the work creation module to create the corresponding creation work according to the creation parameters
  • the first query request receiving module is configured to receive the first query request sent by the vehicle terminal, and the first query request includes the creation task ID;
  • the work query module is used to query the creative work corresponding to the creative task ID;
  • the work sending module is used to send the creative work corresponding to the creative task ID to the vehicle terminal.
  • an embodiment of the present application provides a work generation device, including:
  • the semantic recognition module is used to perform semantic recognition on the voice command to obtain the first recognition result
  • the trigger execution module is used to trigger the vehicle terminal to execute any of the above-mentioned work generation methods according to the target recognition result, and the target recognition result includes the first recognition result.
  • an embodiment of the present application provides a work editing device, including:
  • the logo recognition module is used to identify the editing logo of the works displayed on the car and machine side;
  • the address determination module is used to determine the address of the creative work in the cloud according to the work editing ID, and the creative work is generated according to any of the above work generation methods;
  • the work acquisition and display module is used to acquire the creative work from the cloud according to the address and display it on the mobile terminal.
  • an embodiment of the present application provides a vehicle terminal terminal, including:
  • At least one first processor At least one first processor
  • a first memory communicatively connected with the at least one first processor; wherein,
  • the first memory stores instructions that can be executed by the at least one first processor, and the instructions are executed by the at least one first processor, so that the at least one first processor can execute any of the above car-machine-side works Generation method.
  • an embodiment of the present application provides a server, including:
  • At least one second processor At least one second processor
  • a second memory communicatively connected with the at least one second processor; wherein,
  • the second memory stores instructions that can be executed by the at least one second processor, and the instructions are executed by the at least one second processor, so that the at least one second processor can execute the work generation method of any one of the foregoing aspects .
  • an embodiment of the present application provides a mobile terminal, including:
  • At least one second processor At least one second processor
  • a second memory communicatively connected with the at least one second processor; wherein,
  • the second memory stores instructions that can be executed by the at least one second processor, and the instructions are executed by the at least one second processor, so that the at least one second processor can execute the work editing method of any one of the foregoing aspects .
  • an embodiment of the present application provides a work generation system, which includes the vehicle terminal described in any of the above aspects and the cloud server described in any of the above aspects.
  • an embodiment of the application provides a work generation system, including a car-machine terminal and a cloud.
  • the car-machine terminal includes a work generation module.
  • the cloud includes a creation service module, a work creation module, and an API gateway;
  • the work generation module includes: A creation interface for sending a work creation request to the cloud; a display interface for sending a first query request to the cloud; where the creation request includes creation parameters, and the first query request includes the creation corresponding to the creation request returned by the cloud Task ID;
  • the creation service module includes: a creation interface for requesting the creation module to create a corresponding creation work according to creation parameters; a display interface for querying and returning the creation work corresponding to the creation task ID to the car terminal; among them, the cloud
  • the work creation request is parsed through the API gateway to call the creation interface of the creation service module, and the cloud parses the first query request through the API gateway to call the creation interface of the creation service module.
  • an embodiment of the present application provides a computer-readable storage medium that stores computer instructions in the computer-readable storage medium, and when the computer instructions are executed by a processor, the method for creating a work in any of the above aspects is realized.
  • the advantages or beneficial effects of the above technical solutions include at least: through the communication between the car and the cloud, the creation of works on the car and the machine is provided to the users, and the creation materials such as photos or videos and music taken by the car and the camera can be used for the users. Provide poetry, painting, music, video editing and other creative works.
  • Fig. 1 is a schematic diagram of a method for generating a work according to an implementation of an embodiment of the present application
  • Fig. 2 is a schematic diagram of a method for generating a work according to another implementation of an embodiment of the present application
  • Fig. 3 is a schematic diagram of a method for generating a work according to yet another implementation manner of an embodiment of the present application
  • Fig. 4 is a schematic diagram of a method for generating a work according to still another implementation of an embodiment of the present application.
  • FIG. 5 is a schematic diagram of communication between the vehicle terminal and the cloud according to an implementation manner of an embodiment of the present application
  • Fig. 6 is a schematic diagram of a method for generating a work according to an implementation of an embodiment of the present application
  • FIG. 7 is a schematic diagram of communication between the vehicle terminal and the cloud according to another implementation manner of an embodiment of the present application.
  • FIG. 8 is a schematic diagram of a method for generating a work according to an implementation manner of an embodiment of the present application.
  • FIG. 9 is a schematic diagram of communication between the vehicle terminal and the cloud according to yet another implementation manner of an embodiment of the present application.
  • Figures 11-1 to 11-4 are different examples of the work creation system according to the embodiment of the application.
  • FIG. 12 is a schematic diagram of a method for generating a work according to an implementation of an embodiment of the application.
  • FIG. 13 is a schematic diagram of a method for generating a work according to another implementation of an embodiment of the present application.
  • Fig. 14 is an example of a work creation system according to an embodiment of the application.
  • FIG. 15 is a schematic diagram of a work generating device on the vehicle and machine side according to an embodiment of the present application.
  • Fig. 16 is a schematic diagram of a cloud-based work generating device according to an embodiment of the present application.
  • FIG. 17 is a schematic diagram of a work generating device on the vehicle and machine side according to another embodiment of the present application.
  • Fig. 18 is a block diagram of a terminal or server that can implement the embodiments of the present application.
  • the embodiment of the present application provides a work generation system, which includes a car-machine terminal and a cloud.
  • the artificial intelligence creation of works can be realized through the communication between the car-machine terminal and the cloud.
  • the car-machine terminal may provide a work generation module, such as an artificial intelligence creation (AIC) application (Application, APP), which is used to implement a work generation method on the car-machine terminal.
  • AIC artificial intelligence creation
  • APP Application, APP
  • FIG. 1 shows a flowchart of a method for generating a work according to Embodiment 1 of the present application.
  • the method for generating works can be applied to the car-machine end, that is, it can be realized by the car-machine end.
  • the creation method of the work may include:
  • Step S101 Send a work creation request to the cloud, and the work creation request includes creation parameters, so that the cloud requests the work creation module to create a corresponding work according to the creation parameters.
  • the user can use the input creation instructions provided by the car terminal and select appropriate creation materials, such as pictures, videos, audios, and so on.
  • the car-machine terminal sends a request for creation of a work to the cloud according to the creation instruction.
  • the creative material may be multimedia resources collected by the vehicle multimedia component, such as audio collected by the vehicle microphone multimedia component, image data collected by the vehicle camera multimedia component, etc.
  • the image data includes pictures and videos.
  • the authoring material file is smaller, such as a picture.
  • the creation materials can be sent to the cloud along with the creation request. However, if the creative material is large, if it is sent directly, it will affect the communication efficiency. Therefore, the creative material can be sent (uploaded) to the cloud. After the cloud receives the creative material, it can save it to the cloud and return the address of the creative material to the car machine.
  • the creative materials uploaded by the user can be saved to a network disk, such as an online business system (On-line Business Systems, OBS) in the cloud.
  • the address of the creative material may be a uniform resource locator (Uniform Resource Locator, URL) address.
  • the vehicle terminal can receive the address corresponding to the creative material returned from the cloud, and use the address as a creative parameter, and send it to the cloud along with the request for creation of the work.
  • URL Uniform Resource Locator
  • the authoring parameters may include user expectations, such as theme, style, rhythm, etc., and the user may input user expectations through the AIC APP.
  • Step S102 Receive a creation task ID (Identity Document, identity identification number) corresponding to the work creation request returned from the cloud.
  • a creation task ID Identity Document, identity identification number
  • the cloud After the cloud receives the work creation request sent by the car and machine, it can request the work creation module to create the corresponding work according to the creation parameters.
  • the work creation module may include an intelligent (AI) creation model, and the AI creation model can be obtained by training a deep learning neural network through a large amount of sample data.
  • AI creation models such as AI poetry creation model, AI painting creation model, AI music creation model, AI video editing model, etc.
  • the work creation module can select corresponding models according to different creation materials.
  • the authoring parameter is the address of the authoring material in the cloud, such as a URL address.
  • the work creation module can download the corresponding creation materials from the network disk according to the address.
  • the authoring parameters may include the aforementioned user expectations, which are input as input parameters by the work authoring module into the corresponding AI authoring model, so that the final authored work meets the user's expectations.
  • the cloud can generate a creative task ID corresponding to the work creation request and send the creative task ID to the car machine terminal .
  • Step S103 Send a first query request to the cloud, where the first query request includes the creative task ID, so that the cloud can query the work corresponding to the creative task ID.
  • the car-machine terminal can query from the cloud whether the corresponding work has been completed according to the creative task ID.
  • the cloud queries the corresponding work according to the creative task ID.
  • the cloud database Data Base, DB.
  • the cloud can search for the corresponding work from the work database according to the creation task ID, and send the found work to the car. Machine side.
  • step S103 may include: sending the first query request to the cloud according to a first preset time interval.
  • the car-machine terminal will poll the cloud multiple times to inquire whether the creation has been completed.
  • the cloud inquires whether there is a corresponding creative work from the work database every time according to the first query request. If it exists, it means that the creative work has been completed, and the cloud can send the creative work to the car machine.
  • Step S104 Receive and display the creative work corresponding to the creative task ID returned from the cloud on the vehicle and machine side.
  • the vehicle terminal After receiving the creative work returned from the cloud, the vehicle terminal can display it through the vehicle multimedia component.
  • intelligent creation can be performed based on the creation material provided by the user, and the creation can be displayed to the user on the car and machine side. For example: use photos and videos taken by a car camera as creative materials to create personalized AI poems, AI paintings, AI music, AI videos and other creative works for users.
  • the creative material includes multimedia resources collected by the vehicle-mounted multimedia component.
  • Step S101 may include: detecting the scene condition of the vehicle terminal; controlling the corresponding vehicle-mounted multimedia component to collect the corresponding multimedia resource according to the scene condition, And send a work creation request to the cloud, and the creation request includes the creation parameters corresponding to the multimedia resources.
  • the creation request sent by the car-machine terminal to the cloud can be initiated by the user or automatically initiated according to the scene conditions of the car-machine terminal (vehicle).
  • the car-machine end automatically triggers the corresponding in-vehicle media component to collect the corresponding multimedia resources, and sends a work creation request to the cloud.
  • multimedia resources can be uploaded to the cloud in advance as creative materials, so as to receive the address returned by the cloud (for example, the address of the multimedia resource in the cloud disk).
  • the creation parameters can include this address and be sent to the creation request along with the creation. Cloud.
  • the creation service module of the cloud requests the creation module of the work to create a work, the corresponding multimedia resource can be downloaded from the network disk through this address.
  • the scene condition includes positioning information
  • controlling the corresponding in-vehicle multimedia component to collect corresponding multimedia resources according to the scene condition includes: controlling the in-vehicle multimedia component to collect multimedia resources when the positioning information corresponds to the target journey information .
  • the target journey information is a certain scenic spot. If it is detected that the current location information of the vehicle matches the scenic spot, the vehicle terminal will automatically trigger the on-board multimedia component, such as the camera multimedia component or the microphone multimedia component to collect the corresponding audio, image or Video, so as to record what the user sees and hear during the journey, and generate corresponding AI creation works based on these what they see and hear, and display them on the car and machine side.
  • the on-board multimedia component such as the camera multimedia component or the microphone multimedia component to collect the corresponding audio, image or Video
  • the scene condition includes ambient audio
  • the corresponding in-vehicle multimedia component is controlled to collect corresponding multimedia resources according to the scene condition, including: controlling the microphone multimedia component to collect ambient audio; controlling the camera multimedia component to collect image data; and the multimedia resource includes the environment Audio and image data.
  • the car machine side can automatically trigger the microphone multimedia component to collect environmental audio, and the camera multimedia component to collect image data, so that corresponding AI creation works can be generated based on these environmental audio and image data and displayed on the car machine side.
  • the ambient audio may be the audio inside or around the vehicle.
  • the vehicle terminal detects whether the environmental audio includes a preset trigger word, for example, it can perform semantic recognition on the environmental audio to obtain a corresponding recognition result, and detect whether the recognition result matches the preset secondary trigger word. If it matches, the microphone multimedia component is triggered to continue collecting ambient audio, and the camera multimedia component is triggered to collect image data.
  • a preset trigger word for example, it can perform semantic recognition on the environmental audio to obtain a corresponding recognition result, and detect whether the recognition result matches the preset secondary trigger word. If it matches, the microphone multimedia component is triggered to continue collecting ambient audio, and the camera multimedia component is triggered to collect image data.
  • the scene condition includes the facial image of the target user
  • controlling the corresponding in-vehicle multimedia component to collect the corresponding multimedia resources according to the scene condition includes: determining the emotional state of the target user according to the facial image of the target user; When the emotional state corresponds to the preset emotional state, the vehicle multimedia component is controlled to collect multimedia resources.
  • the user's facial image includes the user's facial features
  • the user's emotional state can be identified according to the facial features.
  • facial features can be input to a trained emotion recognition model to obtain the emotional state of the user. If it is recognized that the user’s emotional state matches the preset emotional state (such as happy), the multimedia resource can be automatically triggered to record the user’s audio, image or video in the emotional state, and based on these multimedia resources, the corresponding AI creation works are generated. And displayed on the car machine end.
  • the user can automatically trigger the in-vehicle multimedia component to collect multimedia resources according to the scene conditions of the vehicle during the use of the vehicle, such as during a journey, record user behaviors, what they see, etc., and generate them based on these materials
  • the corresponding AI creation works are displayed on the car and machine side.
  • the method for generating works on the vehicle and machine side of the embodiment of the present application may further include: step S201, sending a second query request to the cloud, so that the cloud may query multiple works from the work database ,
  • the work includes the above-mentioned creative work;
  • step S202 receiving multiple works returned from the cloud;
  • step S203 displaying multiple works returned from the cloud on the car terminal.
  • users can query the full amount of AI-created works through the AIC APP on the car terminal.
  • the car terminal sends a second query request to the cloud.
  • the cloud queries multiple works from the work database in the cloud and returns to the car terminal.
  • the car machine can display it on the car machine.
  • the works in the work database may be generated by the work creation module, that is, obtained by the work generation method of any of the above embodiments, or may be pre-stored.
  • the method for generating a work on the vehicle and machine side of the embodiment of the present application may further include: step S301, sending a sharing request to the cloud, and the sharing request includes the work ID of the creative work, so that the cloud According to the work ID, query the address of the creative work in the work database; step S302, receive the address of the creative work returned from the cloud; step S303, generate a corresponding work sharing identifier according to the address of the creative work; step S304, display on the car and machine side Work sharing logo.
  • users can share their creations to social media such as WeChat and Weibo.
  • users can trigger sharing instructions for creative works through the sharing portal provided by the AIC APP on the car terminal.
  • the car-machine side After receiving the sharing instruction, the car-machine side sends a sharing request to the cloud.
  • the cloud After the cloud receives the sharing request, it queries the work database in the cloud for the address of the creative work according to the work ID of the creative work, such as the URL address, and sends the address To the car machine end.
  • the car-machine side generates a corresponding work sharing logo, such as a QR code, from the address, and displays it on the car-machine side.
  • Users can use mobile terminals such as mobile phones to scan the QR code and share the work cards to social media.
  • each work stored in the work database corresponds to a work ID, and the work ID can be associated with the creation task ID in the creation stage of the work.
  • step S104 may include: editing the creative work according to the user's editing instructions; displaying the edited creative work on the car terminal.
  • the cloud after the cloud returns to the AI creation work, it can be used to edit the work on the car machine side, such as adding some text or emoticons, to realize the secondary creation of the car machine side, and display the editing on the car machine side (secondary Creation) after the creation.
  • the method for generating a work in this embodiment may further include: sending the edited creative work to the cloud; sending a sharing request to the cloud, and the sharing request includes the work ID of the edited creative work, so that the cloud According to the work ID, query the address of the edited creative work in the cloud; receive the address of the edited creative work returned from the cloud; generate the corresponding work sharing logo according to the address of the edited creative work; display the work sharing on the car and machine side Logo.
  • the edited creative work can be shared on the car-machine side, and the sharing method can refer to step S301 to step S304.
  • the edited creative work can be uploaded to the cloud from the car terminal first, and the cloud can store the edited creative work on the car terminal in the work database, and the edited creative work also corresponds to a work ID.
  • the sharing request sent by the car-machine end to the cloud includes the work ID of the edited creative work, so that the cloud can query from the cloud (such as the work database) based on the work ID Corresponding edited creative work, to obtain the address of the edited creative work, and return the address to the vehicle terminal.
  • the car-machine terminal After receiving the address, the car-machine terminal generates a corresponding sharing identifier.
  • the method of the embodiment of the present application may include: generating a work editing identifier according to the address of the creative work in the cloud; displaying the work editing identifier on the car terminal, so that the mobile terminal can determine that the creative work is based on the work editing identifier.
  • the address of the cloud, and the creation work is obtained from the cloud according to the address and displayed on the mobile terminal.
  • the vehicle terminal can generate a work editing identifier, such as a two-dimensional code, which corresponds to the address of the creative work to be edited in the cloud.
  • the user can scan the two-dimensional code on the vehicle terminal through the mobile terminal, display the creative work on the mobile terminal, and provide the corresponding editing page on the mobile terminal for the user to create the creative work for the second time.
  • the mobile terminal may be a smart device such as a mobile phone and a tablet computer.
  • the mobile terminal can obtain corresponding editing materials according to the editing instructions of the user, and edit creation works according to these editing materials, so as to realize secondary creation on the mobile terminal.
  • the user can share the edited (secondary creation) creation work on the mobile terminal to social media.
  • Fig. 4 shows a flowchart of a method for generating a work according to an embodiment of the present application. This method of generating works can be applied to the cloud. As shown in Figure 4, the method may include:
  • Step S401 Receive a work creation request sent by the car terminal, and the work creation request includes creation parameters
  • Step S402 Generate a creation task ID corresponding to the work creation request
  • Step S403 Send the creative task ID to the car and machine terminal;
  • Step S404 request the work creation module to create the corresponding creative work according to the creation parameters
  • Step S405 Receive a first query request sent by the vehicle terminal, where the first query request includes the creation task ID;
  • Step S406 Query the creative work corresponding to the creative task ID
  • Step S407 Send the creative work corresponding to the creative task ID to the vehicle terminal.
  • the method for generating works in the cloud may include: step S601, receiving a second query request sent by the car terminal; step S602, querying the works database according to the second query request.
  • a work the work includes the above-mentioned creative work; step S603, multiple works are sent to the car machine terminal.
  • the method for generating a work in the cloud may include: step S801, receiving a sharing request sent by the car terminal, and the sharing request includes the work ID of the creative work; step S802, according to the work ID, Query the address of the creative work in the work database; step S803, send the address of the creative work to the car terminal.
  • step S801 receiving a sharing request sent by the car terminal, and the sharing request includes the work ID of the creative work
  • step S802 according to the work ID, Query the address of the creative work in the work database
  • step S803 send the address of the creative work to the car terminal.
  • the embodiment of the application also provides a method for editing a work on a mobile terminal, which includes: identifying the editing identifier of the work displayed on the car terminal; determining the address of the creative work in the cloud according to the work editing identifier, wherein the creative work can be based on any of the above implementations Generated by the method in the creation of the work; obtain the creative work from the cloud according to the address; display the creative work on the mobile terminal.
  • the method for editing a work may further include: obtaining corresponding editing materials according to the editing instructions of the user; editing the creative work according to the editing materials; and sharing the edited creative work.
  • FIG. 10 shows an architecture diagram of a work generation system in an embodiment of the present application.
  • the vehicle terminal includes a work generation module (AIC APP), and the cloud may include a creation service module, a work creation module, and an API (Application Programming Interface) gateway.
  • the work generation module and the creation service module both include a creation (create) interface and a display (pull) interface, respectively.
  • step S101 may include: sending a work creation request to the cloud by calling the creation interface of the car-machine end, so that the cloud can call the creation interface of the creation service module through the API gateway.
  • Step S103 may include: sending a first query request to the cloud by invoking the display interface of the vehicle terminal.
  • step S401 may include: the step of receiving a work creation request sent by the vehicle terminal may include: parsing the work creation request through the API gateway to call the creation interface of the creation service module.
  • Steps S405 and S406 may include: parsing the first query request through the API gateway to call the display interface of the authoring service module.
  • the car-machine terminal calls the display interface of the work generation module at a first preset time interval
  • the cloud calls the display interface of the creation service module at a second preset time interval, so as to realize the creation of the work between the car-machine terminal and the cloud.
  • the creation parameters include the address of the creation material in the cloud
  • the car-machine side also includes an upload interface.
  • the cloud includes a network disk.
  • the car-machine terminal sends the creation material to the network disk by calling the upload interface, and the address is the creation material on the Internet.
  • the cloud includes a work database, and multiple works are stored in the work database.
  • the authoring service module includes a data processing (Data Processing) sub-module.
  • the data processing sub-module can perform data processing on the data received from the vehicle terminal (such as the creative material corresponding to the creation parameters), such as establishing a matching relationship between the vehicle terminal or the user's account information or filtering some sensitive words.
  • the data processing module can also process AI-created works and store them in the works database.
  • the data processing module may be a subsidiary sub-module of the authoring service module.
  • the creation service module can be managed through the operation center.
  • both the work generation module and the creation service module may include a list interface and a share interface, respectively.
  • Step S201 may include: sending a second query request to the cloud by calling a list interface on the vehicle and machine side, so that the cloud can call the list interface of the authoring service module through the API gateway.
  • Step S301 may include: sending a sharing request to the cloud by invoking a share interface on the car-machine end, so that the cloud can call the sharing interface of the authoring service module through the API gateway.
  • step S601 may include: parsing the second query request through the API gateway to call the list interface of the authoring service module to query multiple works from the works database.
  • step S801 may include: parsing the sharing request through the API gateway to call the sharing interface of the authoring service module.
  • AIC APP calls the creation interface to send a creation request to the cloud.
  • the cloud calls the creation interface of the creation service module through the API gateway, which calls the corresponding creation model in the creation module for AI creation. Due to the long creation process, the creation service module generates the creation task ID and returns it to AIC APP.
  • the AIC APP After receiving the creative task ID, the AIC APP calls the display interface according to the creative task ID, thereby sending the first query request to the cloud, and the first query request carries the creative task ID.
  • the cloud invokes the display interface of the creation service module asynchronously through the API gateway.
  • the display interface queries the work database for the work corresponding to the creative task ID, and returns the work to AIC APP when the work is found. .
  • the user can inquire about all the works through the AIC APP, including the works obtained by the work generation method of any of the above embodiments, that is, the AI creation result. Specifically, the user enters a full query instruction through the AIC APP, and the AIC APP calls the list interface to send a second query request to the cloud. The second query request is used to request to query multiple works.
  • the cloud calls the list interface of the creation service module through the API gateway, queries multiple works from the works database, and returns the results to AIC APP. After AIC APP receives multiple works, it can display multiple works in the form of waterfall.
  • the user can scan the QR code with the mobile phone through the sharing portal of the AIC APP, and share the card of the creative work to social media.
  • the creative work may be the work obtained by the work generation method of any of the above implementations, that is, the AI creation result.
  • AIC APP sends a sharing request to the cloud by calling the sharing interface, and the sharing request carries the ID of the creative work.
  • the cloud calls the sharing interface of the creation service module through the API gateway, so as to query the address of the creation work in the work database according to the work ID, and send the address to the car machine terminal.
  • AIC APP After receiving the address, AIC APP generates a corresponding work sharing logo, such as a QR code, and displays it in AIC APP.
  • the creation of corresponding AI creation works such as AI poems, AI paintings, AI music, and AI videos, can be realized based on the creation materials on the car and the machine side, such as a car and machine side album (which can be shot by a camera). Wait, and display and share AI creation works on the car and machine side.
  • the cloud-based work generation method may further include: receiving the result query ID returned by the work creation module according to the creation parameters; according to the second preset time interval, the query from the work creation module corresponds to the result query ID Whether the work of is completed; if it is completed, obtain the work corresponding to the result query ID from the work creation module.
  • the work creation module can first return a result query ID to the creation service module.
  • the result query ID is associated with the creation parameters provided by the car-machine terminal, that is, it is associated with the creative task ID returned from the cloud to the car-machine terminal.
  • the creation service module may use the result query ID to continuously poll the work creation module according to the second preset time interval, until the work corresponding to the result query ID is obtained. That is to say, the polling of the results of the works in the cloud and the results of the works in the cloud are performed asynchronously on the vehicle and the machine side.
  • the method for generating works of the embodiment of the present application can be applied to AI poetry creation.
  • the method of this example may include:
  • the user selects the material from the album through the poetry creation application of the AIC APP on the car terminal. Among them, the picture material is uploaded to the network disk through the upload interface and the URL address of the material is obtained.
  • the user selects creation and calls the creation interface, which is implemented by calling the poetry creation interface of the creation service module through the API gateway, and this implementation calls the AI poetry creation model of the work creation module. Due to the time-consuming creation of AI poetry, the creation service module generates the creation task ID and returns it to the AIC APP on the car and machine side.
  • the poetry creation application of the AIC APP on the car and machine side gets the creation task ID, calls the display interface according to the creation task ID, asynchronously calls the display interface of the creation service module through the API gateway, and polls the AI poetry creation result from the creation module (works ). Repeated polls, AI poetry creation results (works), and returned to the car terminal AIC APP to display the AI poetry creation results (works).
  • the method for generating works of the embodiment of the present application can be applied to AI painting creation. Specifically, it differs from the AI poetry creation method in that AI painting creation uses creative materials for creating paintings, while the AIC APP at the car-machine end calls painting creation applications, and the AI creation model based on it is the painting creation model.
  • the method for generating a work according to an embodiment of the present application can be applied to AI music creation.
  • the creation material used in AI painting creation is music material, such as genre, whether to generate singing, etc. Therefore, the creation material does not need to be uploaded to the Internet disk in advance.
  • the AIC APP on the car-machine side calls the music creation application, and the AI creation model based on it is the music creation model.
  • the creation of corresponding AI poetry works, AI paintings, and AI music can be realized based on the creative materials on the car and machine side, and the AI creation works can be displayed and shared on the car and machine side.
  • the creative material is a video
  • the cloud-based work generation method may also include: in the case that the work creation module completes the work corresponding to the creation parameters, the work creation module calls the creation service module through the API gateway A callback interface to save the works corresponding to the creation parameters to the works database.
  • the method for generating a work according to an embodiment of the present application can be applied to AI video editing.
  • the method of this example may include:
  • the user selects the video material from the album through the video editing application of the AIC APP on the car and machine side, uploads it to the network disk through the upload interface, and gets the video material address, such as the URL address.
  • the user selects creation, and the AIC APP calls the creation interface on the car-machine side to send the creation request carrying the list of video material addresses to the cloud.
  • the cloud uses the API gateway to call the creation interface of the video clip of the creation service module.
  • This interface carries a list of URL addresses of video materials and requests the video clip service of the work creation module.
  • the service downloads all the video materials from the network disk, and according to the AI
  • the video creation model initiates the task of video editing. Because the video editing service is time-consuming, the creation service module will return the creation task ID to the video editing application of the AIC APP on the car and machine side.
  • the work creation module calls the callback interface of the creation service module through the API gateway, and stores the video editing result (work) in the work database.
  • the video editing application of the AIC APP on the vehicle side gets the creative task ID, it calls the display interface according to the creative task ID, and the cloud calls the display interface of the creative service module through the API gateway to poll the video editing results corresponding to the creative task ID (work). Rotate training many times until you get the video editing result (work), and return it to the video editing application of the AIC APP on the car and machine side for display.
  • the video editing application call list interface of the AIC APP on the car and machine side is implemented through the API gateway to call the list interface of the creation service module. This implementation can query multiple video editing results (works) from the work data and return it to the car and machine side
  • the video editing application of AIC APP is used for waterfall flow display.
  • Users can use the mobile device to scan the QR code through the sharing portal of the video editing application of the AIC APP on the car terminal, and share the card of the video editing result (work) to social media.
  • the creation of the corresponding AI video editing work can be realized based on the video creation material (which can be shot by the camera) on the car machine side, and the AI video editing work can be displayed and shared on the car machine side.
  • Embodiment 5 as shown in FIG. 12, an embodiment of the present application provides a method for generating works on the car and machine side, which may include:
  • Step S1201 Perform semantic recognition on the voice command to obtain a first recognition result
  • step S1202 the vehicle terminal is triggered to execute the work generation method according to any of the above embodiments according to the target recognition result, and the target recognition result includes the first recognition result.
  • the car terminal can provide car voice assistants. For example: Used to input voice commands: "Help me write a poem”, “Draw me a painting with the theme of the sunset", etc. After receiving the audio file of the voice command, the on-board voice assistant performs local semantic recognition, and obtains the first recognition result. And according to the first recognition result, call the AIP APP of the car terminal to create, display, and share the corresponding AI creation works.
  • step S1201 may include:
  • Step S1301 Send the voice command to the cloud, so that the cloud generates a second recognition result according to the voice command;
  • Step S1302 Receive the second recognition result returned by the cloud
  • Step S1303 Determine the target recognition result from the first recognition result and the second recognition result according to the preset arbitration rule.
  • the car voice assistant After the car voice assistant receives the audio of the voice command, it will send the audio to the cloud.
  • the cloud transmits audio to the voice service module for ASR (Automatic Speech Recognition) and NLU (Natural Language Processing, natural language processing) recognition.
  • ASR Automatic Speech Recognition
  • NLU Natural Language Processing, natural language processing
  • the voice gateway obtains the recognition result, and the arbitration module in the cloud routes the NLU result to the dialogue management module to generate a second recognition result according to the input.
  • the voice gateway gets the second recognition result and returns it to the in-vehicle voice assistant.
  • the in-vehicle voice assistant obtains the second recognition result from the cloud and the first recognition result returned locally, and decides to use one of them as the target recognition result based on the preset arbitration rules.
  • the arbitration rules can be set according to different scenarios. For example: if the application scene is a local conversation scene, the first recognition result will be used first; if the application scene is a cloud conversation scene, the second recognition result will be used first; if the application scene is a hybrid scene, the recognition result will be determined in the order of arrival Use the first recognition result or the second recognition result.
  • the creation of the corresponding AI creation works can be realized based on the voice dialogue between the user and the car and the car and the car, and the creation of the AI can be displayed and shared on the car and the car.
  • the vehicle terminal also includes a first dialogue management module (vehicle voice assistant), which is used to perform semantic recognition on voice commands to obtain the first recognition result;
  • the cloud includes a second dialogue management module, Used to receive a voice command from the first dialogue management module and generate a second recognition result according to the voice command;
  • the first dialogue management module is also used to determine from the first recognition result and the second recognition result according to a preset arbitration rule Target recognition results, and trigger the work generation module based on the target recognition results.
  • the first dialog management module includes a first protocol encoder, a first protocol decoder, and a first dialog engine; the first protocol encoder is used to encode a voice command and send it to the second dialog management module; The protocol decoder is used to call the first recognition result callback interface (ASR callback and NLU callback), and send the decoded first recognition result to the first dialog engine; the first protocol decoder is also used to call the second recognition result callback interface, Send the decoded second recognition result to the first dialogue engine; the first dialogue engine is used to determine the target recognition result from the first recognition result and the second recognition result according to the preset arbitration rules, and trigger the work generation module .
  • ASR callback and NLU callback ASR callback and NLU callback
  • the second dialogue management module includes a second protocol encoder, a second protocol encoder, a voice gateway, a voice service module, and a second dialogue engine;
  • the voice gateway receives the voice command and passes it through the second protocol decoder The voice command is decoded and sent to the second protocol encoder;
  • the second protocol encoder is used to encode the voice command output by the second protocol decoder;
  • the voice service module performs semantic recognition on the voice command output by the second protocol encoder to obtain the initial recognition result ;
  • the second dialog engine generates a second recognition result according to the initial recognition result;
  • the voice gateway encodes the second recognition result through the second protocol encoder and sends it to the first dialog management module.
  • the method for generating a work of this embodiment may include:
  • the user enters voice commands through the on-board voice assistant, such as: "Help me write a poem", “Draw me a painting with a sunset as the theme", etc.
  • the in-vehicle voice assistant receives the audio of the voice command and performs local recognition, that is, through the voice capability to access the SDK (software development kit) for semantic recognition, the first recognition result is generated, and the in-vehicle voice assistant uploads the audio to the voice gateway in the cloud.
  • the voice gateway decodes the audio through the second protocol decoder, and encodes the audio into the format expected by the voice service module through the second protocol encoder, and transmits the encoded audio to the voice service module for ASR recognition and NLU recognition.
  • the voice gateway obtains the results of ASR recognition and NLU recognition from the voice service module in a streaming manner.
  • the arbitration module of the voice gateway routes the NLU recognition result to the second dialog management module, so that the second dialog management module generates a second recognition result based on the NLU recognition result.
  • the voice gateway obtains the second recognition result, encodes it through the second protocol encoder, and returns it to the in-vehicle voice assistant.
  • the in-vehicle voice assistant receives the second recognition result returned by the voice gateway through the second recognition result callback interface, and selects one of the second recognition result and the first recognition result as the target recognition result according to the preset arbitration strategy.
  • the on-board voice assistant uses the first dialogue engine (legA) to call the on-board AIC APP to implement the corresponding service according to the target recognition result.
  • the target recognition result is voiced on the car and machine side.
  • the on-board AIC APP can open a click-and-speak interface for the on-board voice assistant, and reuse the AI in any of the above embodiments through the atomic operation (target recognition result) output by the first dialogue engine (legA) Poetry creation, AI painting creation, AI music creation and AI video creation methods.
  • FIG. 15 shows a structural block diagram of an apparatus for generating works on the vehicle and machine side according to an embodiment of the present application.
  • the device may include:
  • the work creation request sending module 1501 is used to send a work creation request to the cloud.
  • the work creation request includes creation parameters, so that the cloud requests the work creation module to create the corresponding creation work according to the creation parameters;
  • the creation task ID receiving module 1502 is used to receive the creation task ID corresponding to the work creation request returned by the cloud;
  • the first query request sending module 1503 is configured to send a first query request to the cloud, where the first query request includes a creative task ID, so that the cloud can query the creative work corresponding to the creative task ID;
  • the work display module 1504 is used to receive and display the creative work corresponding to the creative task ID returned from the cloud on the vehicle and machine side.
  • the first query request sending module 1503 is configured to send the first query request to the cloud according to a first preset time interval.
  • the creation parameter is the address of the creation material in the cloud
  • the work generation device further includes:
  • the creative material sending module is used to send the creative material to the cloud
  • the creative material receiving module is used to receive the address corresponding to the creative material returned by the cloud.
  • the work creation request sending module includes:
  • the detection unit is used to detect the scene conditions of the car and the machine end;
  • the control unit is used to control the corresponding on-board multimedia component to collect the corresponding multimedia resources according to the scene conditions, and send a work creation request to the cloud.
  • the creation request includes the creation parameters corresponding to the multimedia resource.
  • the scene condition includes positioning information
  • the control unit is further configured to control the vehicle-mounted multimedia component to collect multimedia resources when the positioning information corresponds to the target journey information.
  • the scene condition includes ambient audio
  • the control unit is further used to: control the microphone multimedia component to collect ambient audio; control the camera multimedia component to collect image data; and the multimedia resources include ambient audio and image data.
  • the scene condition includes the facial image of the target user
  • the control unit is further used to: determine the emotional state of the target user according to the facial image of the target user; when the emotional state of the target user corresponds to the preset emotional state Next, control the vehicle multimedia component to collect multimedia resources.
  • the work generating device further includes:
  • the second query request sending module is configured to send a second query request to the cloud, so that the cloud can query multiple works from the works database;
  • the work receiving module 1504 is also used to receive the multiple works returned by the cloud;
  • the work display module is used to display the multiple works on the machine side of the vehicle.
  • the work generating device further includes:
  • the sharing request sending module is used to send a sharing request to the cloud, and the sharing request includes the work ID of the creative work, so that the cloud can query the address of the creative work in the work database according to the work ID;
  • the address receiving module is used to receive the address of the creative work returned by the cloud
  • the logo generation module is used to generate the corresponding work sharing logo according to the address of the creative work
  • the logo display module is used to display the work sharing logo on the car terminal.
  • the work generating device further includes: a creative work uploading module for sending the edited creative work to the cloud.
  • the sharing request sending module is used to send a sharing request to the cloud, and the sharing request includes the work ID of the edited creative work, so that the cloud can query the edited creative work in the work database according to the work ID
  • the address receiving module is also used to receive the address of the edited creative work returned by the cloud; the identifier generation module is also used to generate a corresponding work sharing identifier based on the edited address of the creative work.
  • the work creation request sending module 1501 sends the creation request of the work to the cloud by calling the creation interface of the vehicle and machine side, so that the cloud can call the creation interface of the creation service module through the API gateway.
  • the first query request sending module 1503 sends the first query request to the cloud by calling the display interface of the vehicle terminal.
  • the second query request sending module sends the second query request to the cloud by calling the list interface of the car-machine end, so that the cloud calls the list interface of the authoring service module through the API gateway.
  • the sharing request sending module sends the sharing request to the cloud by calling the sharing interface of the car-machine end, so that the cloud calls the sharing interface of the creation service module through the API gateway.
  • the work generating device may further include:
  • the editing identification generating module is configured to generate a work editing identification according to the address of the creative work in the cloud;
  • the editing identification display module is used to display the work editing identification on the vehicle terminal, so that the mobile terminal can determine the address of the creative work in the cloud according to the work editing identification, and obtain the address from the cloud according to the address The cloud obtains the creative work and displays it on the mobile terminal.
  • the editing logo display module may include:
  • the editing unit is used to edit the creative work according to the user's editing instructions
  • the display unit it is used to display the edited creation work on the vehicle and machine side.
  • Fig. 16 shows a structural block diagram of a cloud-based work generation device according to an embodiment of the present application. As shown in Figure 16, the device may include:
  • the work creation request receiving module 1601 is used to receive the work creation request sent by the vehicle and the machine terminal, and the work creation request includes the creation parameters;
  • the creation task ID generation and sending module 1602 is used to generate the creation task ID corresponding to the work creation request, and send the creation task ID to the car machine terminal;
  • the request module 1603 is used to request the work creation module to create the corresponding creative work according to the creation parameters;
  • the first query request receiving module 1604 is configured to receive the first query request sent by the vehicle terminal, and the first query request includes the creation task ID;
  • the work query module 1605 is used to query the creative work corresponding to the creative task ID;
  • the work sending module 1606 is used to send the work corresponding to the creative task ID to the car machine terminal.
  • the work generating device further includes:
  • the result query ID receiving module is used to receive the result query ID returned by the work creation module according to the creation parameters
  • the work status query module is used to query whether the creative work corresponding to the result query ID has been completed from the work creation module according to the second preset time interval;
  • the work obtaining module is used to obtain the creative work corresponding to the result query ID from the work creation module when it has been completed.
  • the creative material corresponding to the creative parameter is a video
  • the work generating device further includes:
  • the work saving module is used for when the work creation module completes the work corresponding to the creation parameter, the work creation module calls the callback interface of the creation service module through the API gateway to save the work corresponding to the creation parameter to the work database.
  • the creation parameter is the address of the creation material in the cloud
  • the work generation device further includes:
  • the creative material receiving module is used to receive and save the creative material sent by the car and machine;
  • the creative material sending module is used to send the address corresponding to the creative material to the vehicle terminal.
  • the work generating device further includes:
  • the second query request receiving module is used to receive the second query request sent by the vehicle terminal;
  • the work query module is also used to query multiple works from the work database according to the second query request;
  • the work sending module is also used to send the multiple works to the vehicle terminal.
  • the work generating device further includes:
  • the sharing request receiving module is used to receive the sharing request sent by the vehicle terminal, and the sharing request includes the work ID of the creative work;
  • the address query module is used to query the address of the creative work in the work database according to the work ID;
  • the address sending module is used to send the address of the creative work to the vehicle terminal.
  • the work generating device further includes a creative work receiving module, which is used to receive and save the edited creative work of the car-machine terminal, and the edited creative work corresponds to a work ID.
  • the sharing request receiving module is configured to receive a sharing request sent by the vehicle terminal, and the sharing request includes the work ID, so that the cloud can query the address of the edited creative work in the cloud according to the work ID;
  • the address query module is used to query the address of the creative work in the work database according to the work ID;
  • the address sending module is used to send the edited creative work's address in the cloud to the vehicle terminal.
  • the work creation request receiving module 1601 parses the work creation request through the API gateway to call the creation interface of the creation service module.
  • the first query request receiving module 1604 parses the first query request through the API gateway to asynchronously call the display interface of the authoring service module.
  • the second query request receiving module parses the second query request through the API gateway to call the list interface of the authoring service module to query multiple works from the work database.
  • the sharing request receiving module parses the sharing request through the API gateway to call the sharing interface of the authoring service module.
  • Fig. 17 shows a structural block diagram of an apparatus for generating works on the vehicle and machine side according to an embodiment of the present application.
  • the device may include:
  • the semantic recognition module 1701 is used to perform semantic recognition on the voice command to obtain the first recognition result
  • the trigger execution module 1702 is configured to trigger the vehicle terminal to execute the method according to any one of claims 1 to 9 according to the target recognition result, and the target recognition result includes the first recognition result.
  • the semantic recognition module 1701 may include:
  • the voice command sending module 1703 is configured to send the voice command to the cloud, so that the cloud generates a second recognition result according to the voice command;
  • the recognition result receiving module 1704 is configured to receive the second recognition result returned by the cloud
  • the arbitration module 1705 is used to determine the target recognition result from the first recognition result and the second recognition result according to a preset arbitration rule.
  • An embodiment of the present application provides a work editing device, including:
  • the logo recognition module is used to identify the editing logo of the works displayed on the car and machine side;
  • the address determination module is used to determine the address of the creative work in the cloud according to the work editing ID, and the creative work is generated according to any of the above work generation methods;
  • the work acquisition and display module is used to acquire the creative work from the cloud according to the address and display it on the mobile terminal.
  • the work editing device further includes:
  • the editing material acquisition module is used to acquire the corresponding editing material according to the user's editing instructions
  • Editing module used to edit and create works based on editing materials
  • Sharing module is used to share the edited creation works.
  • Fig. 18 shows a structural block diagram of a terminal or a server according to an embodiment of the present application.
  • the terminal or server includes a memory 1801 and a processor 1802, and the memory 1801 stores instructions that can run on the processor 1802. When the processor 1802 executes the instruction, any one of the work generation methods in the foregoing embodiments is implemented.
  • the number of the memory 1801 and the processor 1802 may be one or more.
  • the terminal or server is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.
  • the terminal or server can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the application described and/or required herein.
  • the terminal or server may also include a communication interface 1803, which is used to communicate with external devices and perform data interactive transmission.
  • Various devices are connected to each other using different buses, and can be installed on a common motherboard or installed in other ways as needed.
  • the processor 1802 may process instructions executed in the terminal or server, including instructions stored in or on the memory to display graphical information of the GUI on an external input/output device (such as a display device coupled to an interface).
  • an external input/output device such as a display device coupled to an interface.
  • multiple processors and/or multiple buses can be used with multiple memories and multiple memories.
  • multiple terminals or servers can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system).
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used to represent in FIG. 18, but it does not mean that there is only one bus or one type of bus.
  • the memory 1801, the processor 1802, and the communication interface 1803 are integrated on one chip, the memory 1801, the processor 1802, and the communication interface 1803 can communicate with each other through internal interfaces.
  • the foregoing processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (Digital Dignal Processing, DSP), and application specific integrated circuits (Application Specific Sntegrated Circuit). ASIC), Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or any conventional processor. It is worth noting that the processor can be a processor that supports an advanced RISC machine (advanced RISC machines, ARM) architecture.
  • the embodiment of the present application provides a computer-readable storage medium (such as the aforementioned memory 1801), which stores computer instructions, and when the program is executed by a processor, the method provided in the embodiment of the present application is implemented.
  • a computer-readable storage medium such as the aforementioned memory 1801
  • the memory 1801 may include a program storage area and a data storage area.
  • the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the terminal or server. Wait.
  • the memory 1801 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices.
  • the storage 1801 may optionally include a storage remotely provided with respect to the processor 1802, and these remote storages may be connected to a terminal or a server through a network.
  • the processor 1802 may be a first processor, a second processor, or a third processor; the memory 1801 may be a first memory, a second memory, or a third memory.
  • any process or method description described in the flowchart or described in other ways herein can be understood to mean that it includes one or more (two or more) executable instructions for implementing the steps of a specific logical function or process. Modules, fragments, or parts of code. And the scope of the preferred embodiments of the present application includes additional implementations, in which functions may be performed in a substantially simultaneous manner or in a reverse order according to the functions involved, not in the order shown or discussed.
  • All or part of the steps of the method in the above-mentioned embodiment can be completed by a program instructing relevant hardware.
  • the program can be stored in a computer-readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or its combination.
  • each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software function modules. If the above-mentioned integrated module is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
  • the storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • Information Transfer Between Computers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请提出一种作品生成和编辑方法、装置、终端、服务器和系统，该作品生成方法包括：向云端发送作品创作请求，该作品创作请求中包括创作参数，以使该云端请求作品创作模块根据该创作参数创作对应的创作作品；接收该云端返回的与该作品创作请求相对应的创作任务ID；向该云端发送第一查询请求，该第一查询请求中包括该创作任务ID，以使该云端查询与该创作任务ID对应的创作作品；接收并在所述车机端展示与该创作任务ID对应的创作作品。本申请实施例通过车机端和云端的通讯，为用户提供车机端的作品创作服务，可以利用车机端摄像头拍摄的照片或视频、音乐等创作素材，为用户提供诗歌、绘画、音乐、视频剪辑等创作作品。

Description

作品生成和编辑方法、装置、终端、服务器和系统
本申请要求于2020年06月04日提交中国专利局、申请号为202010497041.1、发明名称为“作品生成和编辑方法、装置、终端、服务器和系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能技术，尤其涉及一种作品生成和编辑方法、装置、终端、服务器和系统。
背景技术
车机端是指安装在车辆里面的车载信息娱乐产品的简称，在功能上能够实现人与车，车与外界(如车与车)的信息通讯。目前车机端大多为用户提供多媒体服务和导航服务，服务形式比较单一。然而随着车辆的逐渐普及，用户期望车机端可以提供多样化的服务。
发明内容
本申请实施例提供一种作品生成和编辑方法、装置、终端、服务器和系统，以解决相关技术存在的问题，技术方案如下：
第一方面，本申请实施例提供了一种作品生成方法，包括：
向云端发送作品创作请求，该作品创作请求中包括创作参数，以使该云端请求作品创作模块根据该创作参数创作对应的创作作品；
接收该云端返回的与该作品创作请求相对应的创作任务ID；
向该云端发送第一查询请求，该第一查询请求中包括该创作任务ID，以使该云端查询与该创作任务ID对应的创作作品；
接收并在车机端展示该云端返回的与该创作任务ID对应的创作作品。
第二方面，本申请实施例提供了一种作品生成方法，应用于云端，包括：
接收车机端发送的作品创作请求，该作品创作请求中包括创作参数；
生成与该作品创作请求相对应的创作任务ID；
将该创作任务ID发送给该车机端；
请求作品创作模块根据该创作参数创作对应的创作作品；
接收该车机端发送的第一查询请求，该第一查询请求中包括该创作任务ID；
查询与该创作任务ID对应的创作作品；
将与该创作任务ID对应的创作作品发送给该车机端。
第三方面，本申请实施例提供了一种作品生成方法，应用于车机端，包括：
对语音指令进行语义识别，得到第一识别结果；
根据目标识别结果触发该车机端执行上述任一方面的作品生成方法，该目标识别结果包括该第一识别结果。
第四方面，本申请实施例提供一种作品编辑方法，应用于移动终端，该方法包括：
识别车机端展示的作品编辑标识；
根据作品编辑标识确定创作作品在云端的地址，创作作品根据以上任一作品生成方法生成；
根据地址从云端获取创作作品；
在移动终端展示创作作品。
第五方面，本申请实施例提供了一种作品生成装置，包括：
作品创作请求发送模块，用于向云端发送作品创作请求，该作品创作请求中包括创作参数，以使该云端请求作品创作模块根据该创作参数创作对应的创作作品；
创作任务ID接收模块，用于接收该云端返回的与该作品创作请求相对应的创作任务ID；
第一查询请求发送模块，用于向该云端发送第一查询请求，该第一查询请求中包括该创作任务ID，以使该云端查询与该创作任务ID对应的创作作品；
作品展示模块，用于接收并在车机端展示该云端返回的与该创作任务ID对应的创作作品。
第六方面，本申请实施例提供了一种作品生成装置，包括：
作品创作请求接收模块，用于接收车机端发送的作品创作请求，该作品创作请求中包括创作参数；
创作任务ID生成发送模块，用于生成与该作品创作请求相对应的创作任务ID，并将该创作任务ID发送给该车机端；
请求模块，用于请求作品创作模块根据该创作参数创作对应的创作作品；
第一查询请求接收模块，用于接收该车机端发送的第一查询请求，该第一查询请求中包括该创作任务ID；
作品查询模块，用于查询与该创作任务ID对应的创作作品；
作品发送模块，用于将与该创作任务ID对应的创作作品发送给该车机端。
第七方面，本申请实施例提供了一种作品生成装置，包括：
语义识别模块，用于对语音指令进行语义识别，得到第一识别结果；
触发执行模块，用于根据目标识别结果触发该车机端执行上述任一方面的作品生成方法，该目标识别结果包括该第一识别结果。
第八方面，本申请实施例提供一种作品编辑装置，包括：
标识识别模块，用于识别车机端展示的作品编辑标识；
地址确定模块，用于根据作品编辑标识确定创作作品在云端的地址，创作作品根据以上任一作品生成方法生成；
作品获取展示模块，用于根据地址从云端获取创作作品并展示于移动终端。
第九方面，本申请实施例提供了一种车机端终端，包括：
至少一个第一处理器；以及
与该至少一个第一处理器通信连接的第一存储器；其中，
该第一存储器存储有可被该至少一个第一处理器执行的指令，该指令被该至少一个第一处理器执行，以使该至少一个第一处理器能够执行以上任一种车机端的作品生成方法。
第十方面，本申请实施例提供了一种服务器，包括：
至少一个第二处理器；以及
与该至少一个第二处理器通信连接的第二存储器；其中，
该第二存储器存储有可被该至少一个第二处理器执行的指令，该指令被该至少一个第二处理器执行，以使该至少一个第二处理器能够执行上述任一方面的作品生成方法。
第十一方面，本申请实施例提供了一种移动终端，包括：
至少一个第二处理器；以及
与该至少一个第二处理器通信连接的第二存储器；其中，
该第二存储器存储有可被该至少一个第二处理器执行的指令，该指令被该至少一个第二处理器执行，以使该至少一个第二处理器能够执行上述任一方面的作品编辑方法。
第十二方面，本申请实施例提供了一种作品生成系统，包括以上任一方面所述的车机端和以上任一方面所述的云端服务器。
第十三方面，本申请实施例提供一种作品生成系统，包括车机端和云端，车机端包括作品生成模块，云端包括创作服务模块、作品创作模块和API网关；作品生成模块包括：用于向云端发送作品创作请求的创作接口；用于向云端发送第一查询请求的展示接口；其中，作品创作请求中包括创作参数，第一查询请求中包括云端返回的与作品创作请求对应的创作任务ID；创作服务模块包括：用于请求作品创作模块根据创作参数创作对应的创作作品的创作接口；用于查询并向车机端返回与创作任务ID对应的创作作品的展示接口；其中，云端通过API网关解析作品创作请求，以调用创作服务模块的创作接口，云端通过API网关解析第一查询请求，以调用创作服务模块的创作接口。
第十四方面，本申请实施例提供了一种计算机可读存储介质，该计算机可读存储介质内存储有计算机指令，该计算机指令被处理器执行时实现上述任一方面的作品生成方法。
上述技术方案中的优点或有益效果至少包括：通过车机端和云端的通讯，为用户提供车机端的作品创作服务，可以利用车机端摄像头拍摄的照片或视频、音乐等创作素材，为用户提供诗歌、绘画、音乐、视频剪辑等创作作品。
附图说明
图1为根据本申请实施例一种实施方式的作品生成方法的示意图；
图2为根据本申请实施例另一种实施方式的作品生成方法的示意图；
图3为根据本申请实施例又一种实施方式的作品生成方法的示意图；
图4为根据本申请实施例再一种实施方式的作品生成方法的示意图；
图5为根据本申请实施例一种实施方式的车机端和云端的通讯示意图；
图6为根据本申请实施例一种实施方式的作品生成方法的示意图；
图7为根据本申请实施例另一种实施方式的车机端和云端的通讯示意图；
图8为根据本申请实施例一种实施方式的作品生成方法的示意图；
图9为根据本申请实施例又一种实施方式的车机端和云端的通讯示意图；
图10、图11-1至11-4为本申请实施例的作品创作系统的不同示例；
图12为本申请实施例一种实施方式的作品生成方法的示意图；
图13为根据本申请实施例另一种实施方式的作品生成方法的示意图；
图14为本申请实施例的作品创作系统的一个示例；
图15为根据本申请实施例的车机端的作品生成装置的示意图；
图16为根据本申请实施例的云端的作品生成装置的示意图；
图17为根据本申请另一实施例的车机端的作品生成装置的示意图；
图18是可以实现本申请实施例的终端或服务器的框图。
具体实施方式
在下文中，仅简单地描述了某些示例性实施例。正如本领域技术人员可认识到的那样，在不脱离本申请的精神或范围的情况下，可通过各种不同方式修改所描述的实施例。因此，附图和描述被认为本质上是示例性的而非限制性的。
本申请实施例提供一种作品生成系统，包括车机端和云端，通过车机端和云端的通讯可以实现作品的人工智能创作。在一个示例中，车机端可以提供作品生成模块，如人工智能创作(Artificial Intelligence Creation，AIC)应用(Application，APP)，AIC APP用于实现车机端的作品生成方法。
实施例一，图1示出根据本申请实施例一的作品生成方法的流程图。该作品生成方法可以应用于车机端，即可以由车机端实现。
如图1所示，该作品生成方法可以包括：
步骤S101、向云端发送作品创作请求，该作品创作请求中包括创作参数，以使云端请求作品创作模块根据创作参数创作对应的作品。
例如，用户可以利用车机端提供的输入创作指令，并选择合适的创作素材，如图片、视频、音频等。车机端根据创作指令向云端发送作品创作请求。其中，创作素材可以为车载多媒体组件采集的多媒体资源，如车载麦克风多媒体组件采集的音频、车载摄像头多媒体组件采集的图像数据等，图像数据包括图片和视频。
在一个示例中，创作素材文件较小，如图片。可将创作素材随作品创作请求一起发送给云端。但对于创作素材较大的情况，如果直接发送，将影响通讯效率。因此，可以将创作素材发送(上传，upload)至云端，云端在接收到创作素材后，可以将其保存至云端，并将该创作素材的地址返回给车机端。在一个示例中，用户上传的创作素材可以保存至网盘，如云端的联机商用系统(On-line Business Systems，OBS)。进而，该创作素材的地址可以为统一资源定位系统(Uniform Resource Locator，URL)地址。车机端可以接收云端返回的与该创作素材对应的地址，并将该地址作为创作参数，随作品创作请求一起发送给云端。
在一个示例中，创作参数可以包括用户期望，如主题、风格、韵律等，用户可以通过AIC APP输入用户期望。
步骤S102、接收云端返回的与作品创作请求相对应的创作任务ID(Identity Document，身份标识号)。
云端在接收到车机端发送的作品创作请求后，可以请求作品创作模块根据创作参数创作对应的作品。在一个示例中，作品创作模块中可以包括智能(AI)创作模型，该AI创作模型可以通过大量的样本数据训练深度学习神经网络而得到。AI创作模型可以为多个，如AI诗歌创作模型、AI绘画创作模型、AI音乐创作模型、AI视频剪辑模型等，进而作品创作模块可以根据创作素材的不同选择对应的模型。
在一种实施方式中，创作参数为创作素材在云端的地址，如URL地址。作品创作模块可以根据该地址从网盘下载对应的创作素材。
在一个示例中，创作参数可以包括上述的用户期望，用户期望作为输入参数被作品创作模块输入对应的AI创作模型中，从而使最终创作的作品符合用户期望。
进一步地，由于作品创作比较耗时，云端不太可能立即将作品返回给车机端，因此，云端可以生成与作品创作请求相对应的创作任务ID，并将该创作任务ID发送给车机端。
步骤S103、向云端发送第一查询请求，第一查询请求中包括创作任务ID，以使云端查询与创作任务ID对应的作品。
车机端在收到创作任务ID后，可以根据该创作任务ID从云端查询对应的作品是否已完成。云端在接收到第一查询请求后，根据创作任务ID查询对应的作品。在一个示例中，当作品创作完成后会被存入云端的作品数据库(Data Base，DB)中，云端可以根据创作任务ID从作品数据库中查找对应的作品，并将查找到的作品发送给车机端。
在一种实施方式中，在步骤S103中可以包括：按照第一预设时间间隔，向云端发送所述第一查询请求。也就是说，车机端会多次轮询云端，查询创作作品是否已完成。云端每次根据第一查询请求从作品数据库中查询是否存在对应的创作作品，如果存在即说明创作作品已完成，进而云端可以将创作作品发送给车机端。
步骤S104、接收并在车机端展示云端返回的与创作任务ID对应的创作作品。
车机端在接收到云端返回的创作作品后，可通过车载多媒体组件进行展示。
根据本申请实施例的作品生成方法，可以根据用户提供的创作素材进行智能创作，并在车机端为用户展示。例如：以车载摄像头拍摄的照片和视频为创作素材，为用户创作个性化的AI诗歌、AI绘画、AI音乐、AI视频等创作作品。
在一种实施方式中，创作素材包括车载多媒体组件采集的多媒体资源，在步骤S101中可以包括：检测车机端所处的场景条件；根据场景条件控制对应的车载多媒体组件采集对应的多媒体资源，并向云端发送作品创作请求，创作请求中包括与多媒体资源对应的创作参数。
也就是说，车机端向云端发送作品创作请求可以是用户发起的，也可以是根据车机端(车辆)所处的场景条件自动发起的。当检测到车机端所处的场景条件满足预设条件时，车机端自动触发对应的车载对媒体组件采集对应的多媒体资源，并向云端发送作品创作请求。
在一个示例中，多媒体资源作为创作素材可以提前上传至云端，从而收到云端返回的地址(如多媒体资源在云端的网盘的地址)，创作参数可以包括该地址，随作品创作请求一起发送至云端。当云端的创作服务模块请求作品创作模块创作作品时，可以通过该地址从网盘下载对应的多媒体资源。
在一种实施方式中，场景条件包括定位信息，根据场景条件控制对应的车载多媒体组件采集对应的多媒体资源，包括：在定位信息与目标旅途信息相对应的情况下，控制车载多媒体组件采集多媒体资源。
例如：目标旅途信息为某一景点，如果检测到车辆当前的定位信息与该景点相匹配，则车机端会自动触发车载多媒体组件，如摄像头多媒体组件或麦克风多媒体组件采集对应的音频、图像或视频，从而为用户记录旅途中的所见所闻，并基于这些所见所闻生成对应的AI创作作品，并在车机端展示。
在一种实施方式中，场景条件包括环境音频，根据场景条件控制对应的车载多媒体组件采集对应的多媒体资源，包括：控制麦克风多媒体组件采集环境音频；控制摄像头多媒体组件采集图像数据；多媒体资源包括环境音频和图像数据。
例如：车机端可以自动触发麦克风多媒体组件采集环境音频，触发摄像头多媒体组件采集图像数据，从而可以基于这些环境音频和图像数据生成对应的AI创作作品，并在车机端展示。其中，环境音频可以为车辆内部或周围的音频。
在一个示例中，车机端检测环境音频中是否包括预设的触发词，例如可以对环境音频进行语义识别得到对应的识别结果，并检测该识别结果是否与预设从触发词匹配。如果匹配，则触发麦克风多媒体组件继续采集环境音频，并触发摄像头多媒体组件采集图像数据。
在一种实施方式中，场景条件包括目标用户的面部图像，根据场景条件控制对应的车载多媒体组件采集对应的多媒体资源，包括：根据目标用户的面部图像确定目标用户的情绪状态；在目标用户的情绪状态与预设情绪状态相对应的情况下，控制车载多媒体组件采集多媒体资源。
其中，用户的面部图像中包括用户的脸部特征，根据脸部特征可以识别用户的情绪状态。例如，可以将脸部特征输入训练好的情绪识别模型，进而得到用户的情绪状态。如果识别到用户的情绪状态符合预设情绪状态(如高兴)，则可以自动触发多媒体资源，记录用户在该情绪状态下的音频、图像或视频，并基于这些多媒体资源生成对应的AI创作作品，并在车机端展示。
根据本实施例的方法，用户在可以在车辆使用过程中，如旅途过程中，根据车辆的场景条件自动触发车载多媒体组件采集多媒体资源，记录用户行为、所见所闻等，并基于这些素材生成对应的AI创作作品在车机端展示。
在一种实施方式中，如图2所示，本申请实施例的车机端的作品生成方法还可以包括：步骤S201、向云端发送第二查询请求，以使云端从作品数据库中查询多个作品，该作品包括上述的创作作品；步骤S202、接收云端返回的多个作品；步骤S203、在车机端展示云端返回的多个作品。
基于此，用户可通过车机端的AIC APP，查询全量的AI创作的作品。例如：车机端向云端发送第二查询请求，云端在接收到所述第二查询请求后，从云端的作品数据库中查询多个作品，并返回给车机端。车机端在收到多个作品后，可以在车机端展示。
例如：利用车机端的多媒体组件以瀑布流的形式展示多个作品。展示形式本申请实施例不作限定，可根据用户需求进行任意设定。其中，作品数据库中的作品可以是由作品创作模块生成的，即通过以上任一实施方式的作品生成方法而得到，也可以是预存的。
在一种实施方式中，如图3所示，本申请实施例的车机端的作品生成方法还可以包括：步骤S301、向云端发送分享请求，分享请求中包括创作作品的作品ID，以使云端根据作品ID，查询创作作品在作品数据库中的地址；步骤S302、接收云端返回的创作作品的地址；步骤S303、根据创作作品的地址，生成对应的作品分享标识；步骤S304、在车机端展示作品分享标识。
基于此，用户可以将创作作品分享到微信、微博等社交媒体。例如：用户可通过车机端的AIC APP所提供的分享入口，触发创作作品的分享指令。车机端在收到分享指令后向云端发送分享请求，云端接收该分享请求后，根据创作作品的作品ID从云端的作品数据库中查询该创作作品的地址，如URL地址，并将该地址发送给车机端。车机端将该地址生成对应的作品分享标识，如二维码，并在车机端展示。用户可以使用手机等移动终端扫描二维码，分享作品卡片到社交媒体。其中，存入作品数据库中的每一个作品都对应有作品ID，该作品ID在作品创作阶段可以与创作任务ID相关联。
在一种实施方式中，在步骤S104中可以包括：根据用户的编辑指令编辑创作作品；在车机端展示编 辑后的创作作品。
也就是说，云端返回AI创作作品后，用于可以在车机端对该作品进行编辑，例如添加一些文字或表情等，实现车机端的二次创作，并在车机端显示编辑(二次创作)后的创作作品。
在一种实施方式中，本实施例的作品生成方法还可以包括：将编辑后的创作作品发送至云端；向云端发送分享请求，分享请求中包括编辑后的创作作品的作品ID，以使云端根据作品ID，查询编辑后的创作作品在云端的地址；接收云端返回的编辑后的创作作品的地址；根据编辑后的创作作品的地址，生成对应的作品分享标识；在车机端展示作品分享标识。
也就是说，编辑后的创作作品可以在车机端进行分享，分享方法可参照步骤S301～步骤S304。具体地，编辑后的创作作品可以先从车机端上传至云端，云端可以将车机端编辑后的创作作品保存在作品数据库，该编辑后的创作作品也对应有作品ID。在车机端分享编辑后的创作作品时，车机端向云端发送的分享请求中包括的是编辑后的创作作品的作品ID，从而使云端根据该作品ID从云端(如作品数据库中)查询对应的编辑后的创作作品，以获得该编辑后的创作作品的地址，并将该地址返回给车机端。车机端收到该地址后，生成对应的分享标识。
在一种实施方式中，本申请实施例的方法可以包括：根据创作作品在云端的地址，生成作品编辑标识；在车机端展示作品编辑标识，以使移动终端根据作品编辑标识确定创作作品在云端的地址，并根据该地址从云端获取创作作品并展示于移动终端。
车机端可以生成作品编辑标识，如二维码，该作品编辑标识与待编辑的创作作品在云端的地址相对应。用户可通过移动终端扫描车机端的二维码，可以在移动终端展示该创作作品，并在移动终端提供相应的编辑页面供用户对该创作作品进行二次创作。其中，移动终端可以为手机、平板电脑等智能设备。进一步地，移动终端可以根据用户的编辑指令获取对应的编辑素材，并根据这些编辑素材编辑创作作品，实现移动端的二次创作。用户可以在移动终端将编辑(二次创作)后的创作作品分享到社交媒体。
图4示出根据本申请一种实施方式的作品生成方法的流程图。该作品生成方法可以应用于云端。如图4所示，该方法可以包括：
步骤S401、接收车机端发送的作品创作请求，作品创作请求中包括创作参数；
步骤S402、生成与作品创作请求相对应的创作任务ID；
步骤S403、将创作任务ID发送给车机端；
步骤S404、请求作品创作模块根据创作参数创作对应的创作作品；
步骤S405、接收车机端发送的第一查询请求，第一查询请求中包括创作任务ID；
步骤S406、查询与创作任务ID对应的创作作品；
步骤S407、将与创作任务ID对应的创作作品发送给车机端。
本申请实施的云端作品生成方法的一些具体实现方式，可结合图5并参见上述实施例中的对应描述，在此不再赘述。
在一种实施方式中，如图6所示，云端的作品生成方法可以包括：步骤S601、接收车机端发送的第二查询请求；步骤S602、根据第二查询请求，从作品数据库中查询多个作品，该作品包括上述的创作作品；步骤S603、将多个作品发送给车机端。具体地，可结合图7并参见上述实施例中的对应描述，在此不再赘述。
在一种实施方式中，如图8所示，云端的作品生成方法可以包括：步骤S801、接收车机端发送的分享请求，分享请求中包括创作作品的作品ID；步骤S802、根据作品ID，查询该创作作品在作品数据库中的地址；步骤S803、将该创作作品的地址发送给车机端。具体地，可结合图9并参见上述实施例中的对应描述，在此不再赘述。
本申请实施例还提供一种移动终端的作品编辑方法，包括：识别车机端展示的作品编辑标识；根据作品编辑标识确定创作作品在云端的地址，其中，创作作品可以根据以上任一实施方式中的作品生成方法生成；根据地址从云端获取创作作品；在移动终端展示创作作品。
在一种实施方式中，该作品编辑方法还可以包括：根据用户的编辑指令获取对应的编辑素材；根据编辑素材编辑创作作品；分享编辑后的创作作品。
具体实现方式可参见上述车机端的作品编辑方法的对应描述，在此不再赘述。
实施例二，图10示出本申请实施例中的作品生成系统的架构图。需要说明的是，该架构仅为一种实现方式的示例。其中，车机端包括作品生成模块(AIC APP)，云端可以包括创作服务模块、作品创作模块和API(Application Programming Interface，应用程序接口)网关。进一步地，作品生成模块和创作服务模块均分别包括创作(create)接口和展示(pull)接口。
在一种实施方式中，根据实施例二的架构，在步骤S101中可以包括：通过调用车机端的创作接口，向云端发送作品创作请求，以使云端通过API网关调用创作服务模块的创作接口。在步骤S103中可包括：通过调用车机端的展示接口，向云端发送第一查询请求。相应地，在步骤S401中可以包括：接收车机端 发送的作品创作请求的步骤可以包括：通过API网关解析作品创作请求，以调用创作服务模块的创作接口。在步骤S405和S406中可以包括：通过API网关解析第一查询请求，以调用创作服务模块的展示接口。
在一种实施方式中，车机端按照第一预设时间间隔调用作品生成模块的展示接口，云端按照第二预设时间间隔调用创作服务模块的展示接口，从而实现车机端和云端对创作作品的异步查询。
在一种实施方式中，创作参数包括创作素材在云端的地址，车机端还包括上传接口，云端包括网盘，车机端通过调用上传接口向网盘发送创作素材，地址为创作素材在网盘中的地址。进一步地，云端包括作品数据库，作品数据库中存储有多个作品。
在一种实施方式中，创作服务模块包括数据处理(Data Processing)子模块。数据处理子模块可以对从车机端接收到的数据(如创作参数对应的创作素材)进行数据处理，如建立车机端或用户的账号信息的匹配关系或对一些敏感词进行过滤。数据处理模块还可以对AI创作作品处理后存入作品数据库。数据处理模块可以为创作服务模块的附属子模块。创作服务模块可以通过运营中心进行管理。
在一种实施方式中，所述作品生成模块和所述创作服务模块均可以分别包括列表(list)接口和分享(share)接口。
在步骤S201中可以包括：通过调用车机端的列表(list)接口，向云端发送第二查询请求，以使云端通过API网关调用创作服务模块的列表接口。在步骤S301中可以包括：通过调用车机端的分享(share)接口，向云端发送分享请求，以使云端通过API网关调用创作服务模块的分享接口。
相应地，在步骤S601中可以包括：通过API网关解析第二查询请求，以调用创作服务模块的列表接口从作品数据库中查询多个作品。在步骤S801中可以包括：通过API网关解析分享请求，以调用创作服务模块的分享接口。
具体地，用户通过AIC APP选择创作后，AIC APP调用创作接口，从而向云端发送作品创作请求。云端通过API网关调用创作服务模块的创作接口，该接口调用作品创作模块中相对应的创作模型，进行AI创作作品创作。因创作过程较长，创作服务模块生成创作任务ID并返回给AIC APP。
AIC APP接收到创作任务ID后，根据创作任务ID调用展示接口，从而向云端发送第一查询请求，第一查询请求中携带有创作任务ID。相应地，云端通过API网关异步调用创作服务模块的展示接口，该展示接口从作品数据库中查询与创作任务ID相对应的作品，并在查询到存在该作品的情况下将该作品返回给AIC APP。
在一个示例中，用户可通过AIC APP，查询全量的作品，包括以上任一实施方式的作品生成方法所得到的作品，即AI创作结果。具体地，用户通过AIC APP输入全量查询指令，AIC APP调用列表接口，从而向云端发送第二查询请求，该第二查询请求用于请求查询多个作品。相应地，云端通过API网关调用创作服务模块的列表接口，从作品数据库中查询多个作品，并将结果返回给AIC APP。AIC APP在接收到多个作品后，可以将多个作品以瀑布流的形式展示。
在一个示例中，用户可通过AIC APP的分享入口，使用手机扫描二维码，分享创作作品的卡片到社交媒体。其中，该创作作品可以为以上任一实施方式的作品生成方法所得到的作品，即AI创作结果。具体地，AIC APP通过调用分享接口，向云端发送分享请求，该分享请求中携带有创作作品的ID。相应地，云端通过API网关调用创作服务模块的分享接口，从而根据作品ID查询创作作品在作品数据库中的地址，并将该地址发送给车机端。AIC APP在接收到该地址后生成相应的作品分享标识，如二维码，并在AIC APP展示。
通过本实施例的作品生成方法，可以基于车机端的创作素材，如车机端相册(可以由摄像头拍摄)，实现对应的AI创作作品的创作，如AI诗歌、AI绘画、AI音乐、AI视频等，并在车机端对AI创作作品展示和分享。
实施例三，在本实施例中，云端的作品生成方法还可以包括：接收作品创作模块根据创作参数返回的结果查询ID；按照第二预设时间间隔，从作品创作模块查询与结果查询ID对应的作品是否已完成；在已完成的情况下，从作品创作模块获取与结果查询ID对应的作品。
由于作品创作模块进行作品创作比较耗时，因此作品创作模块可以先返回一个结果查询ID给创作服务模块。该结果查询ID与车机端提供的创作参数相关联，即与云端向车机端返回的创作任务ID相关联。创作服务模块可以按照第二预设时间间隔，利用结果查询ID不断轮询作品创作模块，直到获取到与该结果查询ID相对应的作品。也就是说，车机端对云端的作品结果轮询与云端的作品结果轮询是异步进行的。
在一个示例中，如图11-1所示，本申请实施例的作品生成方法可以应用于AI诗歌创作。具体的，该示例的方法可以包括：
(1)根据样本数据训练AI诗歌创作模型。
(2)用户通过车机端AIC APP的诗歌创作应用，从相册中选择素材。其中，图片素材通过上传接口上传到网盘并拿到素材的URL地址。用户选择创作，调用创作接口，该接口通过API网关调用创作服务模块的诗歌创作接口实现，该实现调用作品创作模块的AI诗歌创作模型。因AI诗歌创作耗时，创作服务 模块生成创作任务ID并返回给车机端AIC APP。
(3)车机端AIC APP的诗歌创作应用拿到创作任务ID，根据创作任务ID调用展示接口，通过API网关异步调用创作服务模块的展示接口，从作品创作模块轮询AI诗歌创作结果(作品)。多次轮询，AI诗歌创作结果(作品)，并返回给车机端AIC APP展示AI诗歌创作结果(作品)。
(4)用户可通过车机端AIC APP的诗歌创作应用，查询全量的AI诗歌创作结果(作品)。车机端AIC APP调用列表接口，该接口通过API网关调用创作服务模块的列表接口实现，该实现从作品数据库中查询多个AI诗歌创作结果(作品)，并返回给车机端AIC APP做瀑布流展示。
(5)用户可通过车机端AIC APP的诗歌创作应用提供的分享入口，使用移动设备扫描二维码，分享AI诗歌创作结果(作品)的卡片到社交媒体。
在一个示例中，如图11-2所示，本申请实施例的作品生成方法可以应用于AI绘画创作。具体的，与AI诗歌创作方法的不同在于，AI绘画创作时利用的是创作素材用于创作绘画，车机端AIC APP调用的是绘画创作应用，基于的AI创作模型为绘画创作模型。
在一个示例中，如图11-3所示，本申请实施例的作品生成方法可以应用于AI音乐创作。具体的，与AI诗歌创作方法的不同在于，AI绘画创作时利用的是创作素材是音乐素材，如曲风、是否生成演唱等，因此，创作素材无需提前上传网盘。另外，车机端AIC APP调用的是音乐创作应用，基于的AI创作模型为音乐创作模型。
通过本实施例的作品生成方法，可以基于车机端的创作素材，实现对应的AI诗歌作品、AI绘画、AI音乐的创作，并在车机端对AI创作作品展示和分享。
实施例四，在本实施例中，创作素材为视频，云端的作品生成方法还可以包括：在作品创作模块完成与创作参数对应的作品的情况下，作品创作模块通过API网关调用创作服务模块的回调(callback)接口，以将与创作参数对应的作品保存至作品数据库。
在一个示例中，如图11-4所示，本申请实施例的作品生成方法可以应用于AI视频剪辑。具体的，该示例的方法可以包括：
(1)根据样本数据训练AI视频创作模型。
(2)用户通过车机端AIC APP的视频剪辑应用，从相册中选择视频素材，通过上传接口上传到网盘并拿到视频素材地址，如URL地址。
(3)用户选择创作，车机端AIC APP调用创作接口，从而将携带视频素材地址列表的创作请求发送到云端。云端通过API网关，调用创作服务模块的视频剪辑的创作接口，该接口携带视频素材URL地址的列表，请求作品创作模块的视频剪辑服务，该服务从网盘上下载所有的视频素材，并根据AI视频创作模型启动视频剪辑任务。因视频剪辑服务很耗时，创作服务模块将返回创作任务ID给车机端AIC APP的视频剪辑应用。
(4)视频剪辑任务完成后，即AI视频创作成后，作品创作模块通过API网关调用创作服务模块的回调接口，将视频剪辑结果(作品)存储到作品数据库。
(5)车机端AIC APP的视频剪辑应用拿到创作任务ID后，根据创作任务ID调用展示接口，云端通过API网关调用创作服务模块的展示接口，轮询与创作任务ID对应的视频剪辑结果(作品)。多次轮训，直到拿到视频剪辑结果(作品)，并返回给车机端AIC APP的视频剪辑应用展示。
(6)用户可通过车机端AIC APP的视频剪辑应用，查询全量的视频剪辑结果(作品)。车机端AIC APP的视频剪辑应用调用列表接口，该接口通过API网关调用创作服务模块的列表接口实现，该实现从作品数据可中查询多个视频剪辑结果(作品)，并返回给车机端AIC APP的视频剪辑应用做瀑布流展示。
(7)用户可通过车机端AIC APP的视频剪辑应用的分享入口，使用移动设备扫描二维码，分享视频剪辑结果(作品)的卡片到社交媒体。
通过本实施例的作品生成方法，可以基于车机端的视频创作素材(可以由摄像头拍摄)，实现对应的AI视频剪辑作品的创作，并在车机端对AI视频剪辑作品展示和分享。
实施例五，如图12所示，本申请实施例提供一种车机端的作品生成方法，可以包括：
步骤S1201、对语音指令进行语义识别，得到第一识别结果；
步骤S1202、根据目标识别结果触发车机端执行如上任一实施例的作品生成方法，该目标识别结果包括第一识别结果。
车机端可以提供车载语音助手。例如：用于输入语音指令：“帮我作首诗歌”，“给我画一幅以夕阳为主题的画作”等。车载语音助手拿到语音指令的音频文件后做本地的语义识别，得到第一识别结果。并根据该第一识别结果调用车机端AIP APP进行对应AI创作作品的创作、展示、分享等。
在一种实施方式中，如图13所示，在步骤S1201中可以包括：
步骤S1301、将语音指令发送给云端，以使云端根据语音指令生成第二识别结果；
步骤S1302、接收云端返回的第二识别结果；
步骤S1303、根据预设的仲裁规则，从第一识别结果和第二识别结果中确定出目标识别结果。
车载语音助手拿到语音指令的音频后，会将该音频发送给云端。云端通过语音网关，传递音频给语音服务模块做ASR(Automatic Speech Recognition，自动语音识别技术)和NLU(Natural Language Processing，自然语言处理)识别。语音网关拿到该识别的结果，由云端的仲裁模块路由NLU结果到对话管理模块，以根据输入生成第二识别结果。语音网关拿到第二识别结果并返回给车载语音助手。车载语音助手拿到云端的第二识别结果和本地返回的第一识别结果，基于预设的仲裁规则，决定将其中一个作为目标识别结果。
其中，仲裁规则可以根据场景不同进行设定。例如：如果应用场景为本地会话场景，则优先使用第一识别结果；如果应用场景为云端会话场景，则优先使用第二识别结果；如果应用场景为混合场景，则以识别结果到达的先后顺序决定使用第一识别结果或第二识别结果。
通过本实施例的作品生成方法，可以基于用户与车机端的语音对话，利用车机端的创作素材，实现对应的AI创作作品的创作，并在车机端对AI创作作品展示和分享。
在一个示例中，如图14所示，车机端还包括第一对话管理模块(车载语音助手)，用于对语音指令进行语义识别，得到第一识别结果；云端包括第二对话管理模块，用于从第一对话管理模块接收语音指令，并根据语音指令生成第二识别结果；第一对话管理模块还用于根据预设的仲裁规则，从第一识别结果和第二识别结果中确定出目标识别结果，并根据目标识别结果触发作品生成模块。
在一种实施方式中，第一对话管理模块包括第一协议编码器、第一协议解码器和第一对话引擎；第一协议编码器用于编码语音指令后发送给第二对话管理模块；第一协议解码器用于调用第一识别结果回调接口(ASR回调和NLU回调)，将解码后的第一识别结果发送给第一对话引擎；第一协议解码器还用于调用第二识别结果回调接口，将解码后的第二识别结果发送给第一对话引擎；第一对话引擎用于根据预设的仲裁规则，从第一识别结果和第二识别结果中确定出目标识别结果，并触发作品生成模块。
在一种实施方式中，第二对话管理模块包括第二协议编码器、第二协议编码器、语音网关、语音服务模块和第二对话引擎；语音网关接收语音指令，并通过第二协议解码器解码语音指令后发送给第二协议编码器；第二协议编码器用于编码第二协议解码器输出的语音指令；语音服务模块对第二协议编码器输出的语音指令进行语义识别，得到初始识别结果；第二对话引擎根据初始识别结果生成第二识别结果；语音网关通过第二协议编码器编码第二识别结果后发送给第一对话管理模块。
在一个示例中，如图14所示，本实施例的作品生成方法可以包括：
(1)用户通过车载语音助手，输入语音指令，如：“帮我作首诗歌”，“给我画一幅以夕阳为主题的画作”等。车载语音助手拿到语音指令的音频，做本地识别，即通过语音能力接入SDK(软件开发工具包)进行语义识别，生成第一识别结果，同时车载语音助手上传音频到云端的语音网关。(2)语音网关通过第二协议解码器解码音频，并通过第二协议编码器编码音频为语音服务模块期望的格式，并传递编码音频给语音服务模块做ASR识别和NLU识别。语音网关通过流式的方式从语音服务模块获取ASR识别和NLU识别的结果。(3)语音网关的仲裁模块路由NLU识别的结果到第二对话管理模块，使第二对话管理模块基于NLU识别的结果生成第二识别结果。语音网关拿到第二识别结果，通过第二协议编码器编码后返回给车载语音助手。(4)车载语音助手通过第二识别结果回调接口接收语音网关返回的第二识别结果，按照预设的仲裁策略，从第二识别结果和第一识别结果中选择一个作为目标识别结果。(5)车载语音助手利用第一对话引擎(legA)根据目标识别结果，调用车机端AIC APP实现对应的服务。同时，通过TTS(Text To Speech，从文本到语音)引擎在车机端语音播报目标识别结果。(6)车机端AIC APP可以为车载语音助手开放可点击即可说的接口，通过第一对话引擎(legA)输出的原子操作(目标识别结果)，复用上述任一实施例中的AI诗歌创作、AI绘画创作、AI音乐创作和AI视频创作的方法。
需要说明的是，尽管以上述多个示例介绍了本申请实施例的作品生成系统的作品生成方法，但本领域技术人员能够理解，本申请应不限于此。事实上，用户完全可根据个人喜好和/或实际应用场景灵活设定各模块或各步骤的实现方法。
实施例六，图15示出根据本申请实施例的车机端的作品生成装置的结构框图。如图15所示，该装置可以包括：
作品创作请求发送模块1501，用于向云端发送作品创作请求，作品创作请求中包括创作参数，以使云端请求作品创作模块根据创作参数创作对应的创作作品；
创作任务ID接收模块1502，用于接收云端返回的与作品创作请求相对应的创作任务ID；
第一查询请求发送模块1503，用于向云端发送第一查询请求，第一查询请求中包括创作任务ID，以使云端查询与创作任务ID对应的创作作品；
作品展示模块1504，用于接收并在车机端展示云端返回的与创作任务ID对应的创作作品。
在一种实施方式中，第一查询请求发送模块1503用于按照第一预设时间间隔，向该云端发送该第一查询请求。
在一种实施方式中，该创作参数为创作素材在该云端的地址，该作品生成装置还包括：
创作素材发送模块，用于将该创作素材发送至该云端；
创作素材接收模块，用于接收该云端返回的与该创作素材对应的地址。
在一种实施方式中，作品创作请求发送模块包括：
检测单元，用于检测车机端所处的场景条件；
控制单元，用于根据场景条件控制对应的车载多媒体组件采集对应的多媒体资源，并向云端发送作品创作请求，创作请求中包括与多媒体资源对应的创作参数。
在一种实施方式中，场景条件包括定位信息，控制单元还用于：在定位信息与目标旅途信息相对应的情况下，控制车载多媒体组件采集多媒体资源。
在一种实施方式中，场景条件包括环境音频，控制单元还用于：控制麦克风多媒体组件采集环境音频；控制摄像头多媒体组件采集图像数据；多媒体资源包括环境音频和图像数据。
在一种实施方式中，场景条件包括目标用户的面部图像，控制单元还用于：根据目标用户的面部图像确定目标用户的情绪状态；在目标用户的情绪状态与预设情绪状态相对应的情况下，控制车载多媒体组件采集多媒体资源。
在一种实施方式中，该作品生成装置还包括：
第二查询请求发送模块，用于向该云端发送第二查询请求，以使该云端从作品数据库中查询多个作品；
作品接收模块1504还用于接收该云端返回的该多个作品；
作品展示模块，用于在该车机端展示该多个作品。
在一种实施方式中，该作品生成装置还包括：
分享请求发送模块，用于向该云端发送分享请求，该分享请求中包括创作作品的作品ID，以使该云端根据该作品ID，查询该创作作品在作品数据库中的地址；
地址接收模块，用于接收该云端返回的该创作作品的地址；
标识生成模块，用于根据该创作作品的地址，生成对应的作品分享标识；
标识展示模块，用于在该车机端展示该作品分享标识。
在一种实施方式中，该作品生成装置还包括：创作作品上传模块，用于将编辑后的创作作品发送至云端。进一步地，分享请求发送模块用于向该云端发送分享请求，该分享请求中包括编辑后的创作作品的作品ID，以使该云端根据该作品ID，查询该编辑后的创作作品在作品数据库中的地址；地址接收模块还用于接收该云端返回的该编辑后的创作作品的地址；标识生成模块还用于根据该编辑后的创作作品的地址，生成对应的作品分享标识。
在一种实施方式中，作品创作请求发送模块1501通过调用该车机端的创作接口，向该云端发送该作品创作请求，以使该云端通过API网关调用创作服务模块的创作接口。
在一种实施方式中，第一查询请求发送模块1503通过调用该车机端的展示接口，向该云端发送该第一查询请求。
在一种实施方式中，第二查询请求发送模块通过调用该车机端的列表接口，向该云端发送该第二查询请求，以使该云端通过API网关调用创作服务模块的列表接口。
在一种实施方式中，分享请求发送模块通过调用该车机端的分享接口，向该云端发送该分享请求，以使该云端通过API网关调用创作服务模块的分享接口。
在一种实施方式中，该作品生成装置还可以包括：
编辑标识生成模块，用于根据所述创作作品在所述云端的地址，生成作品编辑标识；
编辑标识展示模块，用于在所述车机端展示所述作品编辑标识，以使移动终端根据所述作品编辑标识确定所述创作作品在所述云端的地址，并根据所述地址从所述云端获取所述创作作品并展示于所述移动终端。
在一种实施方式中，编辑标识展示模块可以包括：
编辑单元，用于根据用户的编辑指令编辑所述创作作品；
在展示单元，用于所述车机端展示编辑后的创作作品。
图16示出根据本申请实施例的云端的作品生成装置的结构框图。如图16所示，该装置可以包括：
作品创作请求接收模块1601，用于接收车机端发送的作品创作请求，作品创作请求中包括创作参数；
创作任务ID生成发送模块1602，用于生成与作品创作请求相对应的创作任务ID，并将创作任务ID发送给车机端；
请求模块1603，用于请求作品创作模块根据创作参数创作对应的创作作品；
第一查询请求接收模块1604，用于接收车机端发送的第一查询请求，第一查询请求中包括创作任务ID；
作品查询模块1605，用于查询与创作任务ID对应的创作作品；
作品发送模块1606，用于将与创作任务ID对应的作品发送给车机端。
在一种实施方式中，该作品生成装置还包括：
结果查询ID接收模块，用于接收该作品创作模块根据该创作参数返回的结果查询ID；
作品状态查询模块，用于按照第二预设时间间隔，从该作品创作模块查询与该结果查询ID对应的创作作品是否已完成；
作品获取模块，用于在已完成的情况下，从该作品创作模块获取与该结果查询ID对应的创作作品。
在一种实施方式中，该创作参数相对应的创作素材为视频，该作品生成装置还包括：
作品保存模块，用于在该作品创作模块完成与该创作参数对应的作品的情况下，该作品创作模块通过API网关调用创作服务模块的回调接口，以将与该创作参数对应的作品保存至作品数据库。
在一种实施方式中，该创作参数为创作素材在该云端的地址，该作品生成装置还包括：
创作素材接收模块，用于接收并保存该车机端发送的创作素材；
创作素材发送模块，用于将与该创作素材对应的地址发送给该车机端。
在一种实施方式中，该作品生成装置还包括：
第二查询请求接收模块，用于接收该车机端发送的第二查询请求；
作品查询模块还用于根据该第二查询请求，从作品数据库中查询多个作品；
作品发送模块还用于将该多个作品发送给该车机端。
在一种实施方式中，该作品生成装置还包括：
分享请求接收模块，用于接收该车机端发送的分享请求，该分享请求中包括创作作品的作品ID；
地址查询模块，用于根据该作品ID，查询该创作作品在作品数据库中的地址；
地址发送模块，用于将该创作作品的地址发送给该车机端。
在一种实施方式中，该作品生成装置还包括创作作品接收模块，用于接收并保存该车机端编辑后的创作作品，该编辑后的创作作品对应有作品ID。进一步地，分享请求接收模块，用于接收该车机端发送的分享请求，该分享请求中包括该作品ID，以使该云端根据该作品ID，查询编辑后的创作作品在该云端的地址；地址查询模块，用于根据该作品ID，查询该创作作品在作品数据库中的地址；地址发送模块，用于将编辑后的创作作品在该云端的地址发送给该车机端。
在一种实施方式中，作品创作请求接收模块1601通过API网关解析该作品创作请求，以调用创作服务模块的创作接口。
在一种实施方式中，第一查询请求接收模块1604通过API网关解析该第一查询请求，以异步调用创作服务模块的展示接口。
在一种实施方式中，第二查询请求接收模块通过API网关解析该第二查询请求，以调用创作服务模块的列表接口从该作品数据库中查询多个作品。
在一种实施方式中，分享请求接收模块通过API网关解析该分享请求，以调用创作服务模块的分享接口。
图17示出根据本申请实施例的车机端的作品生成装置的结构框图。如图17所示，该装置可以包括：
语义识别模块1701，用于对语音指令进行语义识别，得到第一识别结果；
触发执行模块1702，用于根据目标识别结果触发车机端执行权利要求1至9任一项的方法，目标识别结果包括第一识别结果。
在一种实施方式中，如图17所示，语义识别模块1701可以包括：
语音指令发送模块1703，用于将语音指令发送给云端，以使云端根据语音指令生成第二识别结果；
识别结果接收模块1704，用于接收云端返回的第二识别结果；
仲裁模块1705，用于根据预设的仲裁规则，从第一识别结果和第二识别结果中确定出目标识别结果。
本申请实施例各装置中的各模块的功能可以参见上述方法中的对应描述，在此不再赘述。
本申请实施例提供一种作品编辑装置，包括：
标识识别模块，用于识别车机端展示的作品编辑标识；
地址确定模块，用于根据作品编辑标识确定创作作品在云端的地址，创作作品根据以上任一种作品生成方法生成；
作品获取展示模块，用于根据地址从云端获取创作作品并展示于移动终端。
在一种实施方式中，该作品编辑装置还包括：
编辑素材获取模块，用于根据用户的编辑指令获取对应的编辑素材；
编辑模块，用于根据编辑素材编辑创作作品；
分享模块，用于分享编辑后的创作作品。
图18示出根据本申请实施例的终端或服务器的结构框图。如图18所示，该终端或服务器包括：存储器1801和处理器1802，存储器1801内存储有可在处理器1802上运行的指令。处理器1802执行该指令时实现上述实施例中的任一种作品生成方法。存储器1801和处理器1802的数量可以为一个或多个。该终端或服务器旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、 服务器、刀片式服务器、大型计算机、和其它适合的计算机。终端或服务器还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本申请的实现。
该终端或服务器还可以包括通信接口1803，用于与外界设备进行通信，进行数据交互传输。各个设备利用不同的总线互相连接，并且可以被安装在公共主板上或者根据需要以其它方式安装。处理器1802可以对在终端或服务器内执行的指令进行处理，包括存储在存储器中或者存储器上以在外部输入/输出装置(诸如，耦合至接口的显示设备)上显示GUI的图形信息的指令。在其它实施方式中，若需要，可以将多个处理器和/或多条总线与多个存储器和多个存储器一起使用。同样，可以连接多个终端或服务器，各个设备提供部分必要的操作(例如，作为服务器阵列、一组刀片式服务器、或者多处理器系统)。该总线可以分为地址总线、数据总线、控制总线等。为便于表示，图18中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。可选的，在具体实现上，如果存储器1801、处理器1802及通信接口1803集成在一块芯片上，则存储器1801、处理器1802及通信接口1803可以通过内部接口完成相互间的通信。
应理解的是，上述处理器可以是中央处理器(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Dignal Processing，DSP)、专用集成电路(Application Specific Sntegrated Circuit，ASIC)、现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。值得说明的是，处理器可以是支持进阶精简指令集机器(advanced RISC machines，ARM)架构的处理器。
本申请实施例提供了一种计算机可读存储介质(如上述的存储器1801)，其存储有计算机指令，该程序被处理器执行时实现本申请实施例中提供的方法。
可选的，存储器1801可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据终端或服务器的使用所创建的数据等。此外，存储器1801可以包括高速随机存取存储器，还可以包括非瞬时存储器，例如至少一个磁盘存储器件、闪存器件、或其他非瞬时固态存储器件。在一些实施例中，存储器1801可选包括相对于处理器1802远程设置的存储器，这些远程存储器可以通过网络连接至终端或服务器。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。其中，处理器1802可以为第一处理器、第二处理器或第三处理器；存储器1801可以为第一存储器、第二存储器或第三存储器。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包括于本申请的至少一个实施例或示例中。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或隐含地包括至少一个该特征。在本申请的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或多个(两个或两个以上)用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分。并且本申请的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能。在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。应理解的是，本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。上述实施例方法的全部或部分步骤是可以通过程序来指令相关的硬件完成，该程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。此外，在本申请各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。上述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读存储介质中。该存储介质可以是只读存储器，磁盘或光盘等。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到其各种变化或替换，这些都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (53)

  1. 一种作品生成方法，应用于车机端，其特征在于，包括：
    向云端发送作品创作请求，所述作品创作请求中包括创作参数，以使所述云端请求作品创作模块根据所述创作参数创作对应的创作作品；
    接收所述云端返回的与所述作品创作请求相对应的创作任务ID；
    向所述云端发送第一查询请求，所述第一查询请求中包括所述创作任务ID，以使所述云端查询与所述创作任务ID对应的创作作品；
    接收并在所述车机端展示与所述创作任务ID对应的创作作品。
  2. 根据权利要求1所述的方法，其特征在于，向所述云端发送第一查询请求，包括：
    按照第一预设时间间隔，向所述云端发送所述第一查询请求。
  3. 根据权利要求1所述的方法，其特征在于，所述创作参数包括创作素材在所述云端的地址，所述的向云端发送作品创作请求之前还包括：
    将所述创作素材发送至所述云端；
    接收所述云端返回的与所述创作素材对应的地址。
  4. 根据权利要求1所述的方法，其特征在于，向云端发送作品创作请求，包括：
    检测所述车机端所处的场景条件；
    根据所述场景条件控制对应的车载多媒体组件采集对应的多媒体资源，并向所述云端发送所述作品创作请求，所述创作请求中包括与所述多媒体资源对应的创作参数。
  5. 根据权利要求4所述的方法，其特征在于，所述场景条件包括定位信息，根据所述场景条件控制对应的车载多媒体组件采集对应的多媒体资源，包括：
    在所述定位信息与目标旅途信息相对应的情况下，控制所述车载多媒体组件采集多媒体资源。
  6. 根据权利要求4所述的方法，其特征在于，所述场景条件包括环境音频，根据所述场景条件控制对应的车载多媒体组件采集对应的多媒体资源，包括：
    控制麦克风多媒体组件采集所述环境音频；
    控制摄像头多媒体组件采集图像数据；所述多媒体资源包括所述环境音频和所述图像数据。
  7. 根据权利要求4所述的方法，其特征在于，所述场景条件包括目标用户的面部图像，根据所述场景条件控制对应的车载多媒体组件采集对应的多媒体资源，包括：
    根据所述目标用户的面部图像确定所述目标用户的情绪状态；
    在所述目标用户的情绪状态与预设情绪状态相对应的情况下，控制所述车载多媒体组件采集多媒体资源。
  8. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    向所述云端发送分享请求，所述分享请求中包括所述创作作品的作品ID，以使所述云端根据所述作品ID，查询所述创作作品在作品数据库中的地址；
    接收所述云端返回的所述创作作品的地址；
    根据所述创作作品的地址，生成对应的作品分享标识；
    在所述车机端展示所述作品分享标识。
  9. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    根据所述创作作品在所述云端的地址，生成作品编辑标识；
    在所述车机端展示所述作品编辑标识，以使移动终端根据所述作品编辑标识确定所述创作作品在所述云端的地址，并根据所述地址从所述云端获取所述创作作品并展示于所述移动终端。
  10. 根据权利要求1所述的方法，其特征在于，在所述车机端展示与所述创作任务ID对应的创作作品，包括：
    根据用户的编辑指令编辑所述创作作品；
    在所述车机端展示编辑后的创作作品。
  11. 根据权利要求10所述的方法，其特征在于，所述方法还包括：
    将编辑后的创作作品发送至所述云端；
    向所述云端发送分享请求，所述分享请求中包括编辑后的创作作品的作品ID，以使所述云端根据所述作品ID，查询编辑后的创作作品在所述云端的地址；
    接收所述云端返回的编辑后的创作作品的地址；
    根据编辑后的创作作品的地址，生成对应的作品分享标识；
    在所述车机端展示所述作品分享标识。
  12. 根据权利要求8或11所述的方法，其特征在于，向所述云端发送分享请求，包括：
    通过调用所述车机端的分享接口，向所述云端发送所述分享请求，以使所述云端通过API网关调用创作服务模块的分享接口。
  13. 根据权利要求1所述的方法，其特征在于，向云端发送作品创作请求，包括：
    通过调用所述车机端的创作接口，向所述云端发送所述作品创作请求，以使所述云端通过API网关调用创作服务模块的创作接口。
  14. 根据权利要求1所述的方法，其特征在于，向所述云端发送所述第一查询请求，包括：
    通过调用所述车机端的展示接口，向所述云端发送所述第一查询请求。
  15. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    向所述云端发送第二查询请求，以使所述云端从作品数据库中查询多个作品，所述作品包括所述创作作品；
    接收所述云端返回的多个作品；
    在所述车机端展示所述云端返回的所述多个作品。
  16. 根据权利要求15所述的方法，其特征在于，向所述云端发送第二查询请求，包括：
    通过调用所述车机端的列表接口，向所述云端发送所述第二查询请求，以使所述云端通过API网关调用创作服务模块的列表接口。
  17. 一种作品生成方法，应用于云端，其特征在于，包括：
    接收车机端发送的作品创作请求，所述作品创作请求中包括创作参数；
    生成与所述作品创作请求相对应的创作任务ID；
    将所述创作任务ID发送给所述车机端；
    请求作品创作模块根据所述创作参数创作对应的创作作品；
    接收所述车机端发送的第一查询请求，所述第一查询请求中包括所述创作任务ID；
    查询与所述创作任务ID对应的创作作品；
    将与所述创作任务ID对应的创作作品发送给所述车机端。
  18. 根据权利要求17所述的方法，其特征在于，所述方法还包括：
    接收所述作品创作模块根据所述创作参数返回的结果查询ID；
    按照第二预设时间间隔，从所述作品创作模块查询与所述结果查询ID对应的创作作品是否已完成；
    在已完成的情况下，从所述作品创作模块获取与所述结果查询ID对应的创作作品。
  19. 根据权利要求17所述的方法，其特征在于，所述创作参数相对应的创作素材为视频，所述方法还包括：
    在所述作品创作模块完成与所述创作参数对应的创作作品的情况下，所述作品创作模块通过API网关调用创作服务模块的回调接口，以将与所述创作参数对应的创作作品保存至作品数据库。
  20. 根据权利要求17所述的方法，其特征在于，所述创作参数为创作素材在所述云端的地址，所述方法还包括：
    接收并保存所述车机端发送的创作素材；
    将与所述创作素材对应的地址发送给所述车机端。
  21. 根据权利要求17所述的方法，其特征在于，所述方法还包括：
    接收所述车机端发送的第二查询请求；
    根据所述第二查询请求，从作品数据库中查询多个作品，所述作品包括所述创作作品；
    将查询到的多个作品发送给所述车机端。
  22. 根据权利要求17所述的方法，其特征在于，所述方法还包括：
    接收所述车机端发送的分享请求，所述分享请求中包括所述创作作品的作品ID；
    根据所述作品ID，查询所述创作作品在作品数据库中的地址；
    将所述创作作品的地址发送给所述车机端。
  23. 根据权利要求17所述的方法，其特征在于，所述方法还包括：
    接收并保存所述车机端编辑后的创作作品，所述编辑后的创作作品对应有作品ID；
    接收所述车机端发送的分享请求，所述分享请求中包括所述作品ID，以使所述云端根据所述作品ID，查询编辑后的创作作品在所述云端的地址；
    将编辑后的创作作品在所述云端的地址发送给所述车机端。
  24. 根据权利要求17所述的方法，其特征在于，接收车机端发送的作品创作请求，包括：
    通过API网关解析所述作品创作请求，以调用创作服务模块的创作接口。
  25. 根据权利要求17所述的方法，其特征在于，接收所述车机端发送的第一查询请求，包括：
    通过API网关解析所述第一查询请求，以调用创作服务模块的展示接口。
  26. 根据权利要求21所述的方法，其特征在于，接收所述车机端发送的第二查询请求，从作品数据库 中查询多个作品，包括：
    通过API网关解析所述第二查询请求，以调用创作服务模块的列表接口从所述作品数据库中查询多个作品。
  27. 根据权利要求22或23所述的方法，其特征在于，接收所述车机端发送的分享请求，包括：
    通过API网关解析所述分享请求，以调用创作服务模块的分享接口。
  28. 一种作品生成方法，应用于车机端，其特征在于，包括：
    对语音指令进行语义识别，得到第一识别结果；
    根据目标识别结果触发所述车机端执行权利要求1至16任一项所述的方法，所述目标识别结果包括所述第一识别结果。
  29. 根据权利要求28所述的方法，其特征在于，所述方法还包括：
    将所述语音指令发送给云端，以使所述云端根据所述语音指令生成第二识别结果；
    接收所述云端返回的所述第二识别结果；
    根据预设的仲裁规则，从所述第一识别结果和所述第二识别结果中确定出所述目标识别结果。
  30. 一种作品编辑方法，应用于移动终端，其特征在于，包括：
    识别车机端展示的作品编辑标识；
    根据所述作品编辑标识确定创作作品在云端的地址，所述创作作品根据权利要求1至29中任一项所述的方法生成；
    根据所述地址从所述云端获取所述创作作品；
    在所述移动终端展示所述创作作品。
  31. 根据权利要求30所述的方法，其特征在于，所述方法还包括：
    根据用户的编辑指令获取对应的编辑素材；
    根据所述编辑素材编辑所述创作作品；
    分享编辑后的创作作品。
  32. 一种作品生成装置，其特征在于，包括：
    作品创作请求发送模块，用于向云端发送作品创作请求，所述作品创作请求中包括创作参数，以使所述云端请求作品创作模块根据所述创作参数创作对应的创作作品；
    创作任务ID接收模块，用于接收所述云端返回的与所述作品创作请求相对应的创作任务ID；
    第一查询请求发送模块，用于向所述云端发送第一查询请求，所述第一查询请求中包括所述创作任务ID，以使所述云端查询与所述创作任务ID对应的创作作品；
    作品展示模块，用于接收并在车机端展示所述云端返回的与所述创作任务ID对应的创作作品。
  33. 一种作品生成装置，其特征在于，包括：
    作品创作请求接收模块，用于接收车机端发送的作品创作请求，所述作品创作请求中包括创作参数；
    创作任务ID生成发送模块，用于生成与所述作品创作请求相对应的创作任务ID，并将所述创作任务ID发送给所述车机端；
    请求模块，用于请求作品创作模块根据所述创作参数创作对应的创作作品；
    第一查询请求接收模块，用于接收所述车机端发送的第一查询请求，所述第一查询请求中包括所述创作任务ID；
    作品查询模块，用于查询与所述创作任务ID对应的创作作品；
    作品发送模块，用于将与所述创作任务ID对应的创作作品发送给所述车机端。
  34. 一种作品生成装置，其特征在于，包括：
    语义识别模块，用于对语音指令进行语义识别，得到第一识别结果；
    触发执行模块，用于根据目标识别结果触发所述车机端执行权利要求1至15任一项所述的方法，所述目标识别结果包括所述第一识别结果。
  35. 根据权利要求34所述的装置，其特征在于，所述装置还包括：
    语音指令发送模块，用于将所述语音指令发送给云端，以使所述云端根据所述语音指令生成第二识别结果；
    识别结果接收模块，用于接收所述云端返回的所述第二识别结果；
    仲裁模块，用于根据预设的仲裁规则，从所述第一识别结果和所述第二识别结果中确定出所述目标识别结果。
  36. 一种作品编辑装置，其特征在于，包括：
    标识识别模块，用于识别车机端展示的作品编辑标识；
    地址确定模块，用于根据所述作品编辑标识确定创作作品在云端的地址，所述创作作品根据权利要求1至29中任一项所述的方法生成；
    作品获取展示模块，用于根据所述地址从所述云端获取所述创作作品并展示于移动终端。
  37. 一种车机端终端，其特征在于，包括：
    至少一个第一处理器；以及
    与所述至少一个第一处理器通信连接的第一存储器；其中，
    所述第一存储器存储有可被所述至少一个第一处理器执行的指令，所述指令被所述至少一个第一处理器执行，以使所述至少一个第一处理器能够执行权利要求1至16、权利要求28以及权利要求29中任一项所述的方法。
  38. 一种服务器，其特征在于，包括：
    至少一个第二处理器；以及
    与所述至少一个第二处理器通信连接的第二存储器；其中，
    所述第二存储器存储有可被所述至少一个第二处理器执行的指令，所述指令被所述至少一个第二处理器执行，以使所述至少一个第二处理器能够执行权利要求17至27中任一项所述的方法。
  39. 一种移动终端，其特征在于，包括：
    至少一个第三处理器；以及
    与所述至少一个第三处理器通信连接的第三存储器；其中，
    所述第三存储器存储有可被所述至少一个第三处理器执行的指令，所述指令被所述至少一个第三处理器执行，以使所述至少一个第三处理器能够执行权利要求30或31所述的方法。
  40. 一种作品生成系统，其特征在于，包括权利要求37所述的车机端终端以及权利要求38所述的服务器。
  41. 根据权利要求40所述的系统，其特征在于，还包括权利要求39所述的移动终端。
  42. 一种作品生成系统，其特征在于，包括车机端和云端，所述车机端包括作品生成模块，所述云端包括创作服务模块、作品创作模块和API网关；
    所述作品生成模块包括：用于向云端发送作品创作请求的创作接口；用于向所述云端发送第一查询请求的展示接口；其中，所述作品创作请求中包括创作参数，所述第一查询请求中包括所述云端返回的与所述作品创作请求对应的创作任务ID；
    所述创作服务模块包括：用于请求所述作品创作模块根据所述创作参数创作对应的创作作品的创作接口；用于查询并向所述车机端返回与所述创作任务ID对应的创作作品的展示接口；
    其中，所述云端通过所述API网关解析所述作品创作请求，以调用所述创作服务模块的创作接口，所述云端通过所述API网关解析所述第一查询请求，以调用所述创作服务模块的创作接口。
  43. 根据权利要求42所述的系统，其特征在于，所述车机端按照第一预设时间间隔调用所述作品生成模块的展示接口，所述云端按照第二预设时间间隔调用所述创作服务模块的展示接口。
  44. 根据权利要求42所述的系统，其特征在于，所述创作参数包括创作素材在所述云端的地址，所述车机端还包括上传接口，所述云端包括网盘，所述车机端通过调用所述上传接口向所述网盘发送所述创作素材，所述地址为所述创作素材在所述网盘中的地址。
  45. 根据权利要求42所述的系统，其特征在于，所述云端包括作品数据库，所述作品数据库中存储有多个作品，所述作品包括所述创作作品。
  46. 根据权利要求45所述的系统，其特征在于，所述作品生成模块包括用于向所述云端发送第二查询请求的列表接口，所述创作服务模块包括用于从所述作品数据库中查询多个所述作品的列表接口，其中，所述创作服务模块通过所述API网关解析所述第二查询请求，以调用所述创作服务模块的列表接口。
  47. 根据权利要求45所述的系统，其特征在于，所述作品生成模块包括用于向所述云端发送分享请求的分享接口，所述分享请求中包括创作作品的作品ID，所述创作服务模块包括用于根据所述作品ID，查询向所述车机端返回所述创作作品在所述作品数据库中的地址的分享接口，其中，所述创作服务模块通过所述API网关解析所述分享请求，以调用所述创作服务模块的分享接口。
  48. 根据权利要求45所述的系统，其特征在于，所述创作参数相对应的创作素材为视频，所述创作服务模块还包括回调接口，在所述作品创作模块完成与所述创作参数对应的作品的情况下，所述作品创作模块通过所述API网关调用所述创作服务模块的回调接口，以将与所述创作参数对应的作品保存至所述作品数据库。
  49. 根据权利要求42所述的系统，其特征在于，所述创作服务模块还包括数据处理子模块，用于对所述创作参数相对应的创作素材进行数据处理，所述数据处理包括敏感词过滤。
  50. 根据权利要求42至49任一项所述的系统，其特征在于，所述车机端还包括第一对话管理模块，用于对语音指令进行语义识别，得到第一识别结果；所述云端包括第二对话管理模块，用于从所述第一对话管理模块接收所述语音指令，并根据所述语音指令生成第二识别结果；所述第一对话管理模块还用于根据预设的仲裁规则，从所述第一识别结果和所述第二识别结果中确定出目标识别结果，并根据所述目标识别 结果触发所述作品生成模块。
  51. 根据权利要求50所述的系统，其特征在于，所述第一对话管理模块包括第一协议编码器、第一协议解码器和第一对话引擎；
    所述第一协议编码器用于编码所述语音指令后发送给所述第二对话管理模块；
    所述第一协议解码器用于调用第一识别结果回调接口，将解码后的第一识别结果发送给所述第一对话引擎；所述第一协议解码器还用于调用第二识别结果回调接口，将解码后的第二识别结果发送给所述第一对话引擎；
    所述第一对话引擎用于根据预设的仲裁规则，从所述第一识别结果和所述第二识别结果中确定出所述目标识别结果，并触发所述作品生成模块。
  52. 根据权利要求50所述的系统，其特征在于，所述第二对话管理模块包括第二协议编码器、第二协议编码器、语音网关、语音服务模块和第二对话引擎；
    所述语音网关接收所述语音指令，并通过所述第二协议解码器解码所述语音指令后发送给所述第二协议编码器；
    所述第二协议编码器用于编码所述第二协议解码器输出的语音指令；
    所述语音服务模块对所述第二协议编码器输出的语音指令进行语义识别，得到初始识别结果；
    所述第二对话引擎根据所述初始识别结果生成所述第二识别结果；
    所述语音网关通过所述第二协议编码器编码所述第二识别结果后发送给所述第一对话管理模块。
  53. 一种计算机可读存储介质，所述计算机可读存储介质内存储有计算机指令，所述计算机指令被处理器执行时实现如权利要求1至31中任一项所述的方法。
PCT/CN2021/082971 2020-06-04 2021-03-25 作品生成和编辑方法、装置、终端、服务器和系统 WO2021244110A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010497041.1 2020-06-04
CN202010497041.1A CN111400518B (zh) 2020-06-04 2020-06-04 作品生成和编辑方法、装置、终端、服务器和系统

Publications (1)

Publication Number Publication Date
WO2021244110A1 true WO2021244110A1 (zh) 2021-12-09

Family

ID=71433839

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/082971 WO2021244110A1 (zh) 2020-06-04 2021-03-25 作品生成和编辑方法、装置、终端、服务器和系统

Country Status (2)

Country Link
CN (3) CN112699258A (zh)
WO (1) WO2021244110A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115410579A (zh) * 2022-10-28 2022-11-29 广州小鹏汽车科技有限公司 语音交互方法、语音交互装置、车辆和可读存储介质
CN115830171A (zh) * 2023-02-17 2023-03-21 深圳前海深蕾半导体有限公司 基于人工智能绘画的图像生成方法、显示设备及存储介质

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112699258A (zh) * 2020-06-04 2021-04-23 华人运通(上海)新能源驱动技术有限公司 作品生成和编辑方法、装置、终端、服务器和系统
CN114089826A (zh) * 2020-07-30 2022-02-25 华人运通(上海)云计算科技有限公司 车端场景的生成方法、装置、车端和存储介质
CN112061058B (zh) * 2020-09-07 2022-05-27 华人运通(上海)云计算科技有限公司 场景触发的方法、装置、设备和存储介质
CN113067854B (zh) * 2021-03-12 2023-08-25 斑马网络技术有限公司 车载设备内容资源获取方法、装置、设备及存储介质
CN113628618A (zh) * 2021-07-29 2021-11-09 中汽创智科技有限公司 一种基于智能座舱的多媒体文件生成方法、装置及终端
CN114157917B (zh) * 2021-11-29 2024-04-16 北京百度网讯科技有限公司 视频剪辑方法、装置及终端设备
CN114584839A (zh) * 2022-02-25 2022-06-03 智己汽车科技有限公司 拍摄车载视频的剪辑方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104468847A (zh) * 2014-12-31 2015-03-25 北京赛维安讯科技发展有限公司 一种车辆的行程记录信息分享方法、设备、服务器及系统
WO2017128920A1 (zh) * 2016-01-29 2017-08-03 深圳市艾特大师网络科技有限公司 一种消息处理方法、装置及终端
CN110298934A (zh) * 2019-06-18 2019-10-01 重庆长安汽车股份有限公司 行车视频拍摄及分享方法
CN111400518A (zh) * 2020-06-04 2020-07-10 华人运通(上海)新能源驱动技术有限公司 作品生成和编辑方法、装置、终端、服务器和系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101445222B1 (ko) * 2012-07-03 2014-11-04 (주)뉴인 멀티미디어 컨텐츠 저작 시스템 및 저작 도구가 기록된 컴퓨터로 읽을 수 있는 기록매체
GB201314636D0 (en) * 2013-08-15 2013-10-02 Realeyes Data Services Ltd Method of collecting computer user data
JP2018207385A (ja) * 2017-06-08 2018-12-27 株式会社Ｊｖｃケンウッド 表示制御装置、表示制御システム、表示制御方法及び表示制御プログラム
CN110389676A (zh) * 2018-04-20 2019-10-29 比亚迪股份有限公司 车载中控多媒体的操作界面确定方法
CN108965397A (zh) * 2018-06-22 2018-12-07 中央电视台 云端视频编辑方法及装置、编辑设备及存储介质
CN109922290A (zh) * 2018-12-27 2019-06-21 蔚来汽车有限公司 用于车辆的音视频合成方法、装置、系统、设备及车辆
CN110113540B (zh) * 2019-06-13 2021-06-04 广州小鹏汽车科技有限公司 一种车辆拍摄方法、装置、车辆和可读介质
CN111083155A (zh) * 2019-12-25 2020-04-28 斑马网络技术有限公司 车机和云端交互方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104468847A (zh) * 2014-12-31 2015-03-25 北京赛维安讯科技发展有限公司 一种车辆的行程记录信息分享方法、设备、服务器及系统
WO2017128920A1 (zh) * 2016-01-29 2017-08-03 深圳市艾特大师网络科技有限公司 一种消息处理方法、装置及终端
CN110298934A (zh) * 2019-06-18 2019-10-01 重庆长安汽车股份有限公司 行车视频拍摄及分享方法
CN111400518A (zh) * 2020-06-04 2020-07-10 华人运通(上海)新能源驱动技术有限公司 作品生成和编辑方法、装置、终端、服务器和系统

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115410579A (zh) * 2022-10-28 2022-11-29 广州小鹏汽车科技有限公司 语音交互方法、语音交互装置、车辆和可读存储介质
CN115410579B (zh) * 2022-10-28 2023-03-31 广州小鹏汽车科技有限公司 语音交互方法、语音交互装置、车辆和可读存储介质
CN115830171A (zh) * 2023-02-17 2023-03-21 深圳前海深蕾半导体有限公司 基于人工智能绘画的图像生成方法、显示设备及存储介质

Also Published As

Publication number Publication date
CN111400518A (zh) 2020-07-10
CN112699257A (zh) 2021-04-23
CN112699258A (zh) 2021-04-23
CN111400518B (zh) 2020-11-17

Similar Documents

Publication Publication Date Title
WO2021244110A1 (zh) 作品生成和编辑方法、装置、终端、服务器和系统
US20220221959A1 (en) Annotations in software applications for invoking dialog system functions
US9530415B2 (en) System and method of providing speech processing in user interface
US10311877B2 (en) Performing tasks and returning audio and visual answers based on voice command
US10535350B2 (en) Conflict resolution enhancement system
CN107463700B (zh) 用于获取信息的方法、装置及设备
CN109564530A (zh) 提供具有可选择的可遍历的状态机的个人辅助模块
CN107895016B (zh) 一种播放多媒体的方法和装置
CN111651231B (zh) 作品生成方法、装置、车机端和移动终端
WO2019047878A1 (zh) 语音操控终端的方法、终端、服务器和存储介质
JP2019518280A (ja) パーソナルアシスタントモジュールとの会話への選択可能アプリケーションリンクの組込み
CN112165647B (zh) 音频数据的处理方法、装置、设备及存储介质
CN111601161A (zh) 视频作品生成方法、装置、终端、服务器和系统
US10997963B1 (en) Voice based interaction based on context-based directives
US11783836B2 (en) Personal electronic captioning based on a participant user's difficulty in understanding a speaker
US20230418874A1 (en) Styling a query response based on a subject identified in the query
US10902461B2 (en) Environmental modification using tone model analysis
US20220405316A1 (en) Speech to text (stt) and natural language processing (nlp) based video bookmarking and classification system
WO2021259073A1 (en) System for voice-to-text tagging for rich transcription of human speech
JP6944920B2 (ja) スマートインタラクティブの処理方法、装置、設備及びコンピュータ記憶媒体
CN113360704A (zh) 语音播放方法、装置和电子设备
KR102127909B1 (ko) 채팅 서비스 제공 시스템, 이를 위한 장치 및 방법
CN111427529A (zh) 交互方法、装置、设备及存储介质
KR102448356B1 (ko) 영상 커뮤니케이션 서비스와 연동하여 대화를 기록하는 방법, 시스템, 및 컴퓨터 판독가능한 기록 매체
CN112866082A (zh) 基于社交软件联系人的通讯方法、装置、存储介质及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21816720

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21816720

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 21816720

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 22.06.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21816720

Country of ref document: EP

Kind code of ref document: A1