Method and device for generating image

Abstract

The invention discloses an image generation method and device, and the method comprises the steps: obtaining the part attribute information of an equipment three-dimensional model and an equipment operation document of target equipment, and enabling the equipment three-dimensional model to correspond to the target equipment; determining driving information of the equipment three-dimensional model according to the equipment operation document and the component attribute information; and generating a target image according to the driving information and the equipment three-dimensional model, wherein the target image represents a process of operating the target equipment according to the equipment operation document.

Description

Technical Field

[0001] The present application relates to the field of image technology, and in particular to a method and device for generating an image. Background Art

[0002] Using videos to illustrate the operation process of electronic devices is a common guidance method. Users can intuitively understand the installation, use and maintenance process of electronic devices by watching the installation videos, usage videos and maintenance videos of the corresponding devices, but the video production process is relatively cumbersome. Summary of the invention

[0003] To this end, this application discloses the following technical solutions:

[0004] The first aspect of the present application provides a method for generating an image, comprising:

[0005] Obtaining component attribute information of a three-dimensional model of a device and a device operation document of a target device, the three-dimensional model of the device corresponding to the target device;

[0006] Determining driving information of the three-dimensional model of the device according to the device operation document and the component attribute information;

[0007] A target image is generated according to the driving information and the device three-dimensional model, wherein the target image represents a process of operating the target device according to the device operation document.

[0008] Optionally, determining the driving information of the three-dimensional model of the device according to the device operation document and the component attribute information includes:

[0009] Decomposing the device operation document according to the target model to obtain step information of the target device, wherein the step information includes an operation type and a name of an operated component;

[0010] The driving information of the three-dimensional model of the device is determined according to the step information and the component attribute information. The driving information of the three-dimensional model of the device includes the step information and operation parameters corresponding to the components contained in the three-dimensional model of the device.

[0011] Optionally, the step information contained in the device operation document satisfies at least one of the following:

[0012] The component names of the step information contained in the equipment operation document are consistent with the component names of the components contained in the three-dimensional model of the equipment;

[0013] The semantics of the component names of the step information contained in the equipment operation document match the semantics of the component names of the components contained in the equipment three-dimensional model.

[0014] Optionally, the component attribute information includes dimensional parameters of components contained in the three-dimensional model of the equipment, and the dimensional parameters of the components are used to determine operating parameters of the components.

[0015] Optionally, also include:

[0016] Each frame of the target image is displayed in real time.

[0017] Optionally, also include:

[0018] Obtaining a video clip consisting of multiple frames of the target image, each of the video clips corresponding to an operation step in the device operation document;

[0019] A plurality of the video clips are merged to obtain a device operation video corresponding to the device operation document.

[0020] Optionally, the fusing of the plurality of video clips to obtain a device operation video corresponding to the device operation document includes:

[0021] Determining a playback order of the plurality of video clips;

[0022] Determining a segment viewing angle corresponding to the video segment according to a position of a component corresponding to the video segment at the three-dimensional model of the device;

[0023] generating a transition segment according to the segment perspectives of two adjacent video segments, wherein the transition segment represents a process of switching from the segment perspective of a previous video segment to the segment perspective of a subsequent video segment;

[0024] The video clips and the transition clips are spliced ​​according to the playback order to obtain a device operation video corresponding to the device operation document.

[0025] Optionally, the fusing of the plurality of video clips to obtain a device operation video corresponding to the device operation document includes:

[0026] Obtaining operation scenario information of the target device;

[0027] adding video effects to the plurality of video clips according to the operation scene information;

[0028] The multiple video clips after adding video special effects are merged to obtain the device operation video corresponding to the device operation document.

[0029] Optionally, fusing a plurality of the video clips to obtain a device operation video corresponding to the device operation document includes:

[0030] Obtaining audio information corresponding to components contained in the three-dimensional model of the device;

[0031] The video clip and the audio information are integrated to obtain a device operation video corresponding to the device operation document.

[0032] A second aspect of the present application provides a device for generating an image, comprising:

[0033] an obtaining unit, configured to obtain component attribute information of a three-dimensional model of a device and a device operation document of a target device, wherein the three-dimensional model of the device corresponds to the target device;

[0034] A determination unit, configured to determine drive information of the three-dimensional model of the device according to the device operation document and the component attribute information;

[0035] A generating unit is used to generate a target image according to the driving information and the device three-dimensional model, wherein the target image represents a process of operating the target device according to the device operation document. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0037] Figure 1 is a flow chart of a method for generating an image provided by an embodiment of the present application;

[0038] Figure 2 is a flow chart of another method for generating an image provided by an embodiment of the present application;

[0039] Figure 3 is a flow chart of another method for generating an image provided by an embodiment of the present application;

[0040] Figure 4 is a structural schematic diagram of a device for generating an image provided in an embodiment of the present application;

[0041] Figure 5 It is a structural schematic diagram of another device for generating an image provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] This application embodiment provides a method for generating an image. Figure 1 , is a flow chart of the method, and the method may include the following steps.

[0044] S101, obtaining component attribute information of a three-dimensional model of a device and a device operation document of a target device, wherein the three-dimensional model of the device corresponds to the target device.

[0045] The target device can be any device, such as a laptop computer, a desktop computer host, a mobile phone, a robot, a robotic arm, an automated production equipment, etc.

[0046] The device three-dimensional model can be a three-dimensional virtual model that represents the component structure of the target device and is pre-built using three-dimensional modeling technology. The device three-dimensional model can perform actions according to driving information and render the execution process of the action into at least one frame of image.

[0047] The device 3D model may include one or more components of the target device. For example, the device 3D model of a laptop may include components such as a screen, a back panel, back panel screws, a motherboard, and a cooling fan; the device 3D model of a mobile phone may include components such as a screen, a camera, a speaker, and an antenna.

[0048] The component attribute information may include attribute information of one or more components in the device 3D model, and the attribute information may be configured by the user when constructing the device 3D model. The configured attribute information may be recorded in a configuration file corresponding to the device 3D model, and the configuration file of the device 3D model may be directly read in S101 to obtain the component attribute information from the configuration file.

[0049] For any component, the attribute information of the component may include the name of the component, and may also include any one or more of the feasible operation type, size parameters and default operation parameters of the component.

[0050] As some examples, the attribute information of the backplane screw component may include: component name, backplane screw; feasible operation type, lift; size parameters, 1 cm in length, 2 mm in diameter.

[0051] The attribute information of the screen component of the laptop computer may include: component name, screen; feasible operation type, flip open; default operation parameter, 90°.

[0052] The attribute information of the camera component of the mobile phone may include: component name, camera; feasible operation type, rotation; default operation parameter, 720°.

[0053] The device operation document of the target device may be any document that can describe the operation process of the target device, for example, may include at least one of an installation instruction document, a usage instruction document, and a maintenance instruction document of the target device.

[0054] The device operation document can be obtained by scanning an existing paper operation manual or reading an existing electronic operation manual, and determining the content recorded in the manual as the device operation document; or by collecting the user's voice describing the operation process and extracting the voice content as the device operation document through voice recognition technology.

[0055] S102: Determine driving information of the device three-dimensional model according to the device operation document and component attribute information.

[0056] The device operation document may include step information describing the operation steps included in the operation process. In S102, the step information may be first extracted from the device operation document, and then the driving information of the device three-dimensional model may be determined based on the step information and component attribute information.

[0057] There is no limit to the way to extract step information. As an example, see Figure 2 , the device operation document can be input into the target model, and the device operation document can be decomposed according to the target model to obtain the step information of the target device. The step information includes the operation type and the name of the operated component.

[0058] In addition to using the target model, the device operation document can also be decomposed into step information by parsing the device operation document content, such as parsing content with step features from the device operation document through regular expressions and decomposing the device operation document based on the content.

[0059] The target model may be any artificial intelligence (AI) model with document understanding and splitting capabilities, such as a large language model.

[0060] The driving information of the equipment three-dimensional model may include step information and operation parameters corresponding to the components contained in the equipment three-dimensional model, and the step information corresponding to the components may include the operation type and the name of the operated component.

[0061] Optionally, the step information contained in the equipment operation document satisfies at least one of the following:

[0062] Condition 1: The names of the components in the step information contained in the equipment operation document are consistent with the names of the components contained in the equipment 3D model;

[0063] Condition 2: The semantics of the component names of the step information contained in the equipment operation document and the semantics of the component names of the components contained in the equipment three-dimensional model match.

[0064] As an example, a step information included in the device operation document of a laptop computer may be “open the screen of the laptop computer”, and the component name “screen” of the step information is consistent with the component name “screen” of the corresponding component in the device three-dimensional model.

[0065] As another example, another step information included in the device operation document of a laptop computer may be "unscrew the screws on the back panel of the computer." The component name "screw" in the step information is inconsistent with the component name "back panel screw" of the corresponding component in the device 3D model, but the two have the same semantics, and the component name "screw" in the step information also refers to the back panel screw of the device 3D model.

[0066] According to the above step information, when determining the driving information, the step information corresponding to the components contained in the three-dimensional model of the equipment can be determined as follows:

[0067] The step information in the device operation document and the component attribute information of the device three-dimensional model can be compared. If the component name of a step information in the device operation document and the component name of a component in the device three-dimensional model meet the above conditions one or two, it is determined that this step information is the step information corresponding to this component.

[0068] Based on the above example, when the target device is a laptop computer, the target model can determine that the step information corresponding to the screen in the device's three-dimensional model is "open the laptop computer's screen", and the step information corresponding to the back panel screws is "unscrew the screws on the computer's back panel".

[0069] Optionally, the component attribute information may include default operating parameters of the corresponding component. In this case, the default operating parameters of the component may be directly determined as the operating parameters corresponding to the component in the driving information.

[0070] In combination with the above example, the attribute information of the screen component includes "default operating parameter, 90°", and when determining the driving information, the operating parameter of the screen component can be directly determined to be 90°.

[0071] Optionally, the component attribute information may also include dimensional parameters of the components contained in the three-dimensional model of the equipment, and the dimensional parameters of the components are used to determine the operating parameters of the components.

[0072] In this case, the size parameters of the component that are related to the corresponding operation type can be identified, and the size parameters are determined as the operation parameters corresponding to the component.

[0073] Combined with the above example, the attribute information of the back panel screw component may include "size parameters, length 1 centimeter (cm), diameter 2 millimeters". It can be determined that the length size parameter is related to the operation type of the back panel screw component (unscrewing), thereby determining that the operation parameter of the back panel screw component is 1 centimeter.

[0074] Optionally, in order to facilitate the generation of the target image, the step information and operation parameters corresponding to the components in the driving information of the device 3D model may be structured step information and structured operation parameters represented by a specific data structure. The structured driving information may be realized by calling the structured information generation interface of the large model, and the large model may be the same model as the target model of the decomposed device operation document.

[0075] Combined with the above example, in the device operation document, the step information corresponding to the back panel screw component is "unscrew the screws on the back panel of the computer". When determining the driving information of the three-dimensional model of the laptop computer, the step information can be converted into corresponding structured step information, for example, "{component name: back panel screw}, {operation type: turn, lift}", and the corresponding structured operation parameters can include "{operation parameter: 1cm}".

[0076] S103, generating a target image according to the driving information and the device three-dimensional model, wherein the target image represents a process of operating the target device according to the device operation document.

[0077] In step S103, the corresponding components in the three-dimensional model of the device can be controlled to move according to the step information and operation parameters contained in the driving information, and the movement process can be rendered through three-dimensional model rendering technology to generate a target image representing the process of operating the target device according to the device operation document.

[0078] Exemplarily, when the target device is a laptop computer, the driving information may include structured step information and structured operation parameters corresponding to the back panel screws: "{component name: back panel screws}, {operation type: turn, lift}, {operation parameter: 1cm}", and may also include structured step information and structured operation parameters corresponding to the screen: "{component name: screen}, {operation type: flip open}, {operation parameter: 90°}".

[0079] In step S103, according to the above driving information, the back panel screws can be controlled to rotate and lift 1 cm from the back panel, the closed screen can be controlled to flip 90°, and the process of lifting the back panel screws and flipping the screen can be rendered to obtain the above target image.

[0080] The beneficial effects of this embodiment are:

[0081] The related schemes for generating operation videos need to collect a large number of existing operation videos to train the AI ​​model. When the number of operation videos is small, this scheme is difficult to generate accurate operation videos. The scheme of this embodiment can analyze the device operation documents and the component attribute information of the device three-dimensional model to obtain the driving information of the device three-dimensional model, and then obtain the target image representing the operation process based on the driving information and the device three-dimensional model, without relying on existing operation videos for training. Therefore, compared with the schemes of related technologies, the method of generating images in this embodiment has better practicality.

[0082] Furthermore, the method of this embodiment only requires inputting the device operation document and the component attribute information of the device three-dimensional model to automatically obtain the target image representing the operation process of the device, which significantly improves the convenience of producing related operation videos.

[0083] In some optional embodiments, each frame of the target image may be displayed in real time after the target image is generated. That is, the electronic device executing the above method may display each frame of the target image on the display after generating the frame of the target image, and in this way, the process of operating the target device according to the device operation document may be displayed in real time on the display.

[0084] In some optional embodiments, you can also press Figure 3 The method shown fuses the generated target image into a device operation video of the target device to meet the user's need to watch the device operation video repeatedly.

[0085] S301, obtaining component attribute information of a three-dimensional model of a device and a device operation document of a target device, wherein the three-dimensional model of the device corresponds to the target device.

[0086] S302: Determine driving information of the device three-dimensional model according to the device operation document and component attribute information.

[0087] S303, generating a target image according to the driving information and the device three-dimensional model, wherein the target image represents a process of operating the target device according to the device operation document.

[0088] The implementation of steps S301 to S303 refers to the above-mentioned embodiment and will not be described in detail.

[0089] S304, obtaining a video segment consisting of multiple frames of target images, each video segment corresponding to an operation step in the device operation document.

[0090] In step S304, the target model may be used to process the device operation document to determine which step information is contained in each operation step in the device operation document, and to determine which components in the device three-dimensional model the step information corresponds to.

[0091] As an example, the content corresponding to the "remove the backplane" operation step in the device operation document may include "unscrew the screws on the backplane and remove the backplane." After processing by the target model, it can be determined that the "remove the backplane" operation step includes two step information, "unscrew the screws on the backplane" and "remove the backplane." The component corresponding to the former step information is the backplane screw, and the component corresponding to the latter step information is the backplane.

[0092] After the components included in the operation step are determined, the target images corresponding to these components can be combined according to the generation order of the target images and the order in which the components appear in the operation step to obtain a video clip representing the operation process corresponding to the operation step.

[0093] In combination with the above example, the components corresponding to the "remove the back panel" operation step include the back panel screws and the back panel, wherein the back panel screws appear first and the back panel appears later. In step S304, the multiple frames of target images generated when the back panel screws are driven to move according to the driving information can be combined in sequence according to the generation order to form the part corresponding to the back panel screws in the video clip. Then, after the part corresponding to the back panel screws, the multiple frames of target images generated when the back panel is driven to move are combined in sequence according to the generation order, thereby obtaining the video clip corresponding to the "remove the back panel" operation step. When the video clip is played, the movement of the back panel screws based on the corresponding step information and operation parameters can be displayed first. After the movement of the back panel screws is completed, the movement of the back panel based on the corresponding step information and operation parameters can be displayed.

[0094] S305, merging multiple video clips to obtain a device operation video corresponding to the device operation document.

[0095] In this embodiment, multiple video clips may be merged in a variety of ways.

[0096] For example, multiple video clips can be directly spliced ​​into one video, and the spliced ​​video is used as the device operation video. When splicing, the order of the corresponding video clips can be determined according to the order in which the corresponding multiple operation steps appear in the device operation document.

[0097] Exemplarily, the equipment operation document may include the operation step of "removing the backplane", and the operation step after the "removing the backplane" operation step is "removing the fan". Then, in the fused equipment operation video, the video clip corresponding to "removing the fan" can be spliced ​​after the video clip corresponding to "removing the backplane". When playing the video, the video clip corresponding to "removing the backplane" is played first, and then the video clip corresponding to "removing the fan" is played.

[0098] The beneficial effect of this embodiment is that multiple frames of target images are fused into a device operation video corresponding to the device operation document, so that the user can intuitively understand the process of operating the target device based on the device operation document by watching the video.

[0099] In some embodiments, multiple video clips may be fused to obtain a device operation video in the following fusion manner:

[0100] Determine the playback order of multiple video clips;

[0101] Determine the segment viewing angle corresponding to the video segment according to the position of the component corresponding to the video segment in the three-dimensional model of the device;

[0102] Generate a transition segment according to the segment perspectives of two adjacent video segments, where the transition segment represents a process of switching from the segment perspective of a previous video segment to the segment perspective of a subsequent video segment;

[0103] The video clips and transition clips are spliced ​​according to the playback order to obtain the device operation video corresponding to the device operation document.

[0104] The method of determining the playback order of multiple video clips can refer to the above embodiment and will not be described in detail.

[0105] The components corresponding to the video clip may include the components in the video clip that are driven based on the driving information. For example, the components corresponding to the video clip of “removing the fan” may include the fan.

[0106] The segment perspective corresponding to the video segment may be a perspective used to display the driven component in the video segment when the component of the three-dimensional model of the device is driven.

[0107] For example, if a component corresponding to a video clip is located on the left side of the three-dimensional model of the device, it can be determined that the segment perspective corresponding to the video clip is the perspective facing the left side of the three-dimensional model of the device; if a component corresponding to a video clip is located on the back of the three-dimensional model of the device, it can be determined that the segment perspective corresponding to the video clip is the perspective facing the back of the three-dimensional model of the device.

[0108] The transition segment can be generated in such a way that, for two adjacent video segments, when the perspectives of the two segments are inconsistent, the three-dimensional model of the device can be driven to rotate from the perspective of the previous video segment to the perspective of the next video segment, thereby obtaining multiple frames of continuous images representing the rotation process, and the video segment composed of these images is a transition segment.

[0109] Taking a laptop computer as an example, assuming that the target device is a laptop computer, and that video clip 1 corresponding to “removing the back panel” and video clip 2 corresponding to “opening the screen” are two adjacent video clips, with video clip 1 in front and video clip 2 in the back. The perspective of video clip 1 is the perspective facing the back of the three-dimensional model of the device, and the perspective of video clip 2 is the perspective facing the front of the three-dimensional model of the device.

[0110] When generating a transition segment, the device three-dimensional model can be driven to rotate from the back perspective corresponding to video segment 1 to the front perspective corresponding to video segment 2, thereby obtaining N consecutive frames of images representing the rotation of the device three-dimensional model from the back to the front, wherein the first frame image can display the back of the device three-dimensional model, and the Nth frame image can display the front of the device three-dimensional model. The video segment composed of these N consecutive frames of images can obtain the transition segment between video segment 1 and video segment 2.

[0111] When splicing video clips and transition clips, the video clips can be sorted in the playback order, and then the transition clip can be inserted between the corresponding two adjacent video clips, thereby determining the order of the video clips and the transition clips. Finally, the video clips and the transition clips are spliced ​​together end to end in this order to obtain the device operation video.

[0112] For example, assume that the three operation steps correspond to video segment 1, video segment 2 and video segment 3 respectively, and the playback order is that video segment 1 to video segment 3 are played in sequence, transition segment 1 is generated between video segment 1 and video segment 2, and transition segment 2 is generated between video segment 2 and video segment 3. When splicing to obtain the device operation video, the above segments can be spliced ​​together in the following order to form the device operation video:

[0113] Video clip 1, transition clip 1, video clip 2, transition clip 2, video clip 3.

[0114] Optionally, if two adjacent video clips have the same perspective, a transition clip between the two video clips may not be generated. When the device operation video is spliced ​​together, the two video clips with the same perspective may be directly spliced ​​together end to end.

[0115] The beneficial effects of this embodiment are:

[0116] When the viewing angles of two adjacent video clips are inconsistent, by generating and inserting a transition clip, the process of transitioning from the previous clip to the next clip in the device operation video can be made smoother.

[0117] In some embodiments, multiple video clips may be fused to obtain a device operation video in the following fusion manner:

[0118] Obtaining the operation scenario information of the target device;

[0119] Add video effects to multiple video clips based on operation scenario information;

[0120] Multiple video clips with video special effects added are merged to obtain a device operation video corresponding to the device operation document.

[0121] The operation scenario information of the target device may represent the environment in which the target device is located when the target device is operated based on the device operation document.

[0122] For example, for a target device suitable for a conference room, when the target device is installed based on the installation instruction document, the environment may be a conference room; for a target device that is often used outdoors, when the target device is used based on the usage instruction document, the environment may be an outdoor environment; when the target device is repaired based on the repair instruction document, the environment may be a repair workshop.

[0123] After the operation scene information is obtained, a video effect representing the operation scene information may be added to multiple video clips. The video effect may include a background image representing the corresponding environment.

[0124] For example, when the operation scene information represents a conference room environment, a background image representing the indoor environment of the conference room may be added to the video clip; when the operation scene information represents an outdoor environment, a background image representing an outdoor environment may be added to the video clip.

[0125] After adding the video special effects, the multiple video clips after adding the video special effects can be fused in the fusion method of the above-mentioned embodiment to obtain the device operation video.

[0126] In some optional embodiments, multiple video clips may be fused to obtain a device operation video in the following fusion manner:

[0127] Obtaining audio information corresponding to components contained in the three-dimensional model of the device;

[0128] The video clips and audio information are integrated to obtain the device operation video corresponding to the device operation document.

[0129] The audio information corresponding to the component may include the following two types.

[0130] The first type of audio information corresponding to the component may include action audio information. The action audio information may be the sound generated when the corresponding component moves, for example, the sound generated by friction when a screw rotates, the sound when a fan rotates, the sound when a back panel buckle is disassembled or closed, etc.

[0131] The second audio information corresponding to the component may include the voice of the step information corresponding to the component in the device operation document. For example, the audio information corresponding to the backplane screw may include the voice of "unscrew the screw on the backplane", and the audio information corresponding to the backplane may include the voice of "remove the backplane".

[0132] The first type of audio information can be collected in advance and stored in a database. When the audio information needs to be obtained, the component name is obtained from the component attribute information, and the first type of audio information corresponding to the component is searched in the database based on the component name.

[0133] When obtaining the second type of audio information, the step information corresponding to the component in the device operation document can be first determined, and then the step information corresponding to the component can be processed using speech synthesis technology to obtain the speech corresponding to the step information.

[0134] When fusing video clips and audio information, firstly, for each video clip, the component corresponding to the video clip can be determined in the manner of the above embodiment, and then the video clip and the audio information of the corresponding component can be fused to obtain a video clip with audio.

[0135] Combined with the above example, the components corresponding to the "removing the back panel" step may include the back panel screws and the back panel. During the fusion, the video clip corresponding to the "removing the back panel" step, the audio information corresponding to the back panel screws, and the audio information corresponding to the back panel can be fused to obtain the "removing the back panel" video clip with audio.

[0136] In a video clip with audio, the audio information can be synchronized with the movement process of the component displayed in the video clip. For example, in the above example, the audio information of the back plate screw is synchronized with the movement process of the back plate screw in the video clip, and the audio information of the back plate is synchronized with the movement process of the back plate in the video clip. When the video clip is played by a playback device, the playback device first displays the movement process of the back plate screw and plays the audio information of the back plate screw at the same time, and then displays the movement process of the back plate and plays the audio information of the back plate at the same time.

[0137] After obtaining multiple video clips with audio, the multiple video clips with audio can be fused according to the fusion method of the above-mentioned embodiment to obtain a device operation video.

[0138] The beneficial effect of this embodiment is that the audio information of the components is integrated into the device operation video, and the currently moving components can be further indicated through the audio information when the device operation video is played, thereby better guiding the user to operate the target device.

[0139] The present application also provides a device for generating an image, see Figure 4 , the device may include the following units.

[0140] The obtaining unit 401 is used to obtain component attribute information of the device three-dimensional model and the device operation document of the target device, and the device three-dimensional model corresponds to the target device.

[0141] The determination unit 402 is used to determine the driving information of the device three-dimensional model according to the device operation document and the component attribute information.

[0142] The generating unit 403 is used to generate a target image according to the driving information and the three-dimensional model of the device, where the target image represents the process of operating the target device according to the device operation document.

[0143] Optionally, when the determining unit 402 determines the driving information of the device three-dimensional model according to the device operation document and the component attribute information, it can be used to:

[0144] Decompose the equipment operation document according to the target model to obtain the step information of the target equipment, where the step information includes the operation type and the name of the operated component;

[0145] The driving information of the equipment three-dimensional model is determined according to the step information and the component attribute information. The driving information of the equipment three-dimensional model includes the step information and operation parameters corresponding to the components contained in the equipment three-dimensional model.

[0146] Optionally, the step information contained in the equipment operation document satisfies at least one of the following:

[0147] The names of the components in the step information contained in the equipment operation document are consistent with the names of the components contained in the equipment 3D model;

[0148] The semantics of the component names of the step information contained in the equipment operation document and the semantics of the component names of the components contained in the equipment 3D model match.

[0149] Optionally, the component attribute information includes dimensional parameters of components contained in the three-dimensional model of the equipment, and the dimensional parameters of the components are used to determine operating parameters of the components.

[0150] Optional, see Figure 5 The device may further include a display unit 501, configured to:

[0151] Display each frame of the target image in real time.

[0152] Optionally, the apparatus may further include a video generating unit 502, configured to:

[0153] Obtaining a video clip consisting of multiple frames of target images, each video clip corresponds to an operation step in the device operation document;

[0154] Multiple video clips are merged to obtain a device operation video corresponding to the device operation document.

[0155] Optionally, when the video generation unit 502 fuses multiple video clips to obtain a device operation video corresponding to the device operation document, it can be used to:

[0156] Determine the playback order of multiple video clips;

[0157] Determine the segment viewing angle corresponding to the video segment according to the position of the component corresponding to the video segment in the three-dimensional model of the device;

[0158] Generate a transition segment according to the segment perspectives of two adjacent video segments, where the transition segment represents a process of switching from the segment perspective of a previous video segment to the segment perspective of a subsequent video segment;

[0159] The video clips and transition clips are spliced ​​according to the playback order to obtain the device operation video corresponding to the device operation document.

[0160] Optionally, when the video generation unit 502 fuses multiple video clips to obtain a device operation video corresponding to the device operation document, it can be used to:

[0161] Obtaining the operation scenario information of the target device;

[0162] Add video effects to multiple video clips based on operation scenario information;

[0163] Multiple video clips with video special effects added are merged to obtain a device operation video corresponding to the device operation document.

[0164] Optionally, when the video generation unit 502 fuses multiple video clips to obtain a device operation video corresponding to the device operation document, it can be used to:

[0165] Obtaining audio information corresponding to components contained in the three-dimensional model of the device;

[0166] The video clips and audio information are integrated to obtain the device operation video corresponding to the device operation document.

[0167] The working principle of the image generating device of this embodiment can refer to the relevant steps of the image generating method provided in any embodiment of the present application, and will not be repeated here.

[0168] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0169] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0170] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0171] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0172] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for generating an image, comprising: Obtaining component attribute information of a three-dimensional model of a device and a device operation document of a target device, the three-dimensional model of the device corresponding to the target device; Determining driving information of the three-dimensional model of the device according to the device operation document and the component attribute information; A target image is generated according to the driving information and the device three-dimensional model, wherein the target image represents a process of operating the target device according to the device operation document.

2. The method according to claim 1, wherein determining the driving information of the device three-dimensional model according to the device operation document and the component attribute information comprises: Decomposing the device operation document according to the target model to obtain step information of the target device, wherein the step information includes an operation type and a name of an operated component; The driving information of the three-dimensional model of the device is determined according to the step information and the component attribute information. The driving information of the three-dimensional model of the device includes the step information and operation parameters corresponding to the components contained in the three-dimensional model of the device.

3. The method according to claim 2, wherein the step information contained in the equipment operation document satisfies at least one of the following: The component names of the step information contained in the equipment operation document are consistent with the component names of the components contained in the three-dimensional model of the equipment; The semantics of the component names of the step information contained in the equipment operation document match the semantics of the component names of the components contained in the equipment three-dimensional model.

4. According to the method of claim 2, the component attribute information includes size parameters of the components contained in the three-dimensional model of the equipment, and the size parameters of the components are used to determine the operating parameters of the components.

5. The method according to claim 1, further comprising: Each frame of the target image is displayed in real time.

6. The method according to claim 1, further comprising: Obtaining a video clip consisting of multiple frames of the target image, each of the video clips corresponding to an operation step in the device operation document; A plurality of the video clips are merged to obtain a device operation video corresponding to the device operation document.

7. The method according to claim 6, wherein the fusing of the plurality of video clips to obtain the device operation video corresponding to the device operation document comprises: Determining a playback order of the plurality of video clips; Determining a segment viewing angle corresponding to the video segment according to a position of a component corresponding to the video segment at the three-dimensional model of the device; generating a transition segment according to the segment perspectives of two adjacent video segments, wherein the transition segment represents a process of switching from the segment perspective of a previous video segment to the segment perspective of a subsequent video segment; The video clips and the transition clips are spliced ​​according to the playback order to obtain a device operation video corresponding to the device operation document.

8. The method according to claim 6, wherein the fusing of the plurality of video clips to obtain the device operation video corresponding to the device operation document comprises: Obtaining operation scenario information of the target device; adding video effects to the plurality of video clips according to the operation scene information; The multiple video clips after adding video special effects are merged to obtain the device operation video corresponding to the device operation document.

9. The method according to claim 6, fusing a plurality of the video clips to obtain a device operation video corresponding to the device operation document, comprising: Obtaining audio information corresponding to components contained in the three-dimensional model of the device; The video clip and the audio information are integrated to obtain a device operation video corresponding to the device operation document.

10. A device for generating an image, comprising: an obtaining unit, configured to obtain component attribute information of a three-dimensional model of a device and a device operation document of a target device, wherein the three-dimensional model of the device corresponds to the target device; A determination unit, configured to determine drive information of the three-dimensional model of the device according to the device operation document and the component attribute information; A generating unit is used to generate a target image according to the driving information and the device three-dimensional model, wherein the target image represents a process of operating the target device according to the device operation document.

Images