Video editing method and device, equipment and storage medium

Abstract

The invention relates to a video editing method and device, equipment and a storage medium. The method comprises the following steps: acquiring voice information input by a user in a video editing interface; obtaining current prompt information input by a user in the video editing interface; processing the current prompt information by using reference data to obtain a video editing instruction; wherein the reference data pair comprises reference prompt information and a reference intention category corresponding to the reference prompt information; and performing video editing based on the video editing instruction. According to the embodiment of the invention, the current prompt information is input in the video editing interface, the current prompt information is processed by using the pre-acquired reference data to obtain the video editing instruction, and video editing is carried out based on the video editing instruction. According to the video editing method and device, video editing is carried out based on the prompt information input by the user, the user does not need to input a video editing instruction, and video editing can be achieved, so that video editing is easy to operate.

Description

Technical Field

[0001] The present disclosure relates to the field of video processing technology, and in particular to a video editing method, device, equipment and storage medium. Background Art

[0002] With the development of Internet technology and terminal technology, more and more people need to make and publish videos.

[0003] In the video editing related technology, the user needs to accurately input the video editing instruction to perform video editing. However, for users who are not familiar with video editing, it is difficult to correctly input the editing instruction. Therefore, how to implement video editing without the user inputting the editing instruction is a problem to be solved urgently. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present disclosure provide a video editing method, device, equipment and storage medium, which realize video editing based on prompt information input by the user. Video editing can be realized without the user inputting video editing instructions, making video editing easy to operate.

[0005] In a first aspect, an embodiment of the present disclosure provides a video editing method, comprising: obtaining current prompt information input by a user in a video editing interface; processing the current prompt information using a reference data pair to obtain a video editing instruction; wherein the reference data pair includes reference prompt information and a reference intent category corresponding to the reference prompt information; and performing video editing based on the video editing instruction.

[0006] In a second aspect, an embodiment of the present disclosure provides a video editing device, comprising: a current prompt information acquisition module, used to obtain current prompt information input by a user in a video editing interface; a video editing instruction determination module, used to process the current prompt information using a reference data pair to obtain a video editing instruction; wherein the reference data pair includes reference prompt information and a reference intent category corresponding to the reference prompt information; and a video editing module, used to perform video editing based on the video editing instruction.

[0007] In a third aspect, an embodiment of the present disclosure provides an electronic device, the electronic device comprising:

[0008] one or more processors;

[0009] A storage device for storing one or more programs;

[0010] When the one or more programs are executed by the one or more processors, the one or more processors implement the video editing method as described in any one of the first aspects above.

[0011] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the video editing method as described in any one of the above-mentioned first aspects.

[0012] The disclosed embodiments provide a video editing method, apparatus, device and storage medium, the method comprising: obtaining current prompt information input by a user in a video editing interface; processing the current prompt information using reference data pairs to obtain video editing instructions; wherein the reference data pairs include reference prompt information and reference intent categories corresponding to the reference prompt information; and performing video editing based on the video editing instructions. The disclosed embodiments input the current prompt information in a video editing interface, process the current prompt information using pre-acquired reference data pairs, obtain video editing instructions, and perform video editing based on the video editing instructions. Video editing based on the prompt information input by the user is implemented, and video editing can be implemented without the user inputting a video editing instruction, making video editing easy to operate. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flowchart of a video editing method in an embodiment of the present disclosure;

[0015] Figure 2 is a structural schematic diagram of a video editing device in an embodiment of the present disclosure;

[0016] Figure 3 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0019] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0020] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. The modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0021] With the development of Internet technology and terminal technology, more and more people need to make and publish videos. As a result, many video editing applications have emerged and are widely used. In related video editing applications, the commonly used editing method is: displaying video editing tracks, video materials and controls for video editing in the video editing interface, and users can click on the video editing tracks, video materials or video editing controls in the video editing interface to achieve the corresponding video editing.

[0022] In an actual application scenario, if the user wants to add a dynamic sticker between the 3rd and 8th seconds of a video, the user needs to select the timeline in the video editing track, and then drag the dynamic sticker to be added to the timeline, or drag it to the video preview canvas. Then, according to the setting controls corresponding to the dynamic sticker, set the effect of the dynamic sticker, for example: set the dynamic sticker's entry time, entry method, exit time, exit method, display position in the video screen, display transparency, and other display effects.

[0023] In another actual application scenario, if the user wants to make a video related to the input text, the user enters the text in the video editing interface, clicks the text-video generation control in the video editing interface, and then generates a video related to the text based on the input text.

[0024] In the above application scenarios, the user needs to accurately input the video editing instruction to perform video editing. However, for users who are not familiar with video editing, it is difficult to correctly input the editing instruction. Therefore, how to implement video editing without the user inputting the editing instruction is a problem to be solved urgently.

[0025] In order to solve the above technical problems, the embodiments of the present disclosure provide a video editing method, device, equipment, storage medium and program product. The video editing method includes: obtaining current prompt information input by a user in a video editing interface; processing the current prompt information using a reference data pair to obtain a video editing instruction; wherein the reference data pair includes reference prompt information and a reference intent category corresponding to the reference prompt information; and performing video editing based on the video editing instruction.

[0026] In the disclosed embodiment, the disclosed embodiment inputs the current prompt information in the video editing interface, processes the current prompt information using the pre-acquired reference data, obtains the video editing instruction, and performs video editing based on the video editing instruction. The video editing is performed based on the prompt information input by the user, and the video editing can be performed without the user inputting the video editing instruction, making the video editing easy to operate.

[0027] Figure 1 This is a flowchart of a video editing method in an embodiment of the present disclosure. This embodiment is applicable to the situation of editing videos. The method can be executed by a video editing device. The video editing device can be implemented in software and / or hardware. The video editing device can be configured in an electronic device.

[0028] like Figure 1 As shown, the video editing method provided by the embodiment of the present disclosure mainly includes steps S101-S103.

[0029] S101: Acquire current prompt information input by a user in a video editing interface.

[0030] In the embodiment of the present disclosure, the current prompt information can be understood as the prompt information input by the user in the video editing interface for video editing, wherein the prompt information can be voice information or text information, which is not specifically limited in the implementation of the present disclosure.

[0031] In one embodiment of the present disclosure, when the prompt information is voice prompt information, the video editing method is performed by an electronic device equipped with a voice acquisition device. The electronic device may be a smart mobile terminal, a smart wearable device, a laptop computer, a desktop computer, a tablet computer, etc. The electronic device is equipped with a voice acquisition device, which may be a voice acquisition device built into the electronic device, such as a built-in microphone of the electronic device; the voice acquisition device may also be a voice acquisition device that establishes a communication connection with the electronic device, such as a microphone that is wired to the electronic device, a microphone that is wirelessly linked to the electronic device, etc.

[0032] In the disclosed embodiment, the electronic device is installed with video editing software, or a video editing client can be opened in the form of a web page, and both the video editing software and the web version of the video editing client can perform video editing according to the video editing instructions input by the user. Further, in response to receiving the video editing software start instruction, the video editing software is opened, and a video editing interface is displayed on the display screen of the electronic device. Further, the video editing interface can be the homepage of the video editing software, or it can be a sub-interface corresponding to a certain editing function in the video editing software.

[0033] In one embodiment of the present disclosure, a prompt information input control is set in the video editing software, wherein the prompt information input control is used to respond to the user's trigger operation and enable the function of editing the video using the prompt information. In other words, in response to the user's trigger operation of the prompt information input control, the video editing software starts to execute the video editing method provided by the embodiment of the present disclosure.

[0034] In one embodiment of the present disclosure, the prompt information input control may be a switch control in the setting item, and after the user triggers the prompt information input control, the function of using the prompt information to edit the video is turned on, that is, in the subsequent process, the prompt information input by the user is collected. After the user triggers the prompt information control again, the function of using the prompt information to edit the video is turned off, that is, in the subsequent process, the prompt information input by the user is stopped from being collected.

[0035] In one embodiment of the present disclosure, an input box is provided in the video editing interface, and the user can input text information in the input box, and the text information serves as the current prompt information.

[0036] In one embodiment of the present disclosure, an input box is set in the video editing interface, and a voice collection control is set in the input box. When the user performs a long press operation on the voice collection control, the current voice information input by the user is collected. After the user stops performing the long press operation on the voice collection control, the user's voice information is stopped from being collected.

[0037] S102. Process the current prompt information using a reference data pair to obtain a video editing instruction; wherein the reference data pair includes reference prompt information and a reference intent category corresponding to the reference prompt information.

[0038] In the disclosed embodiment, the video editing instruction refers to an instruction for performing an editing operation on a video. For example, the video editing instruction may be an instruction for adding video material to a video draft. The video editing instruction may be an instruction for automatically generating a video draft based on existing video material.

[0039] In one embodiment of the present disclosure, the current voice information is processed using reference data pairs to obtain video editing instructions, including: acquiring multiple groups of reference data pairs; obtaining an intent recognition model using the multiple groups of reference data pairs; performing intent recognition on the current prompt information using the intent recognition model to obtain a target intent; and generating a video editing instruction using the target intent.

[0040] In the disclosed embodiment, the reference data pair includes: reference prompt information and reference intent category corresponding to the reference prompt information. For example: when the reference prompt information is "help me make a promotional video based on the input text", its corresponding reference intent category is "picture and text into a film". When the reference prompt information is "search for some templates suitable for children's programs", its corresponding reference intent category is "find templates"; when the reference prompt information is "find a cute sticker", its corresponding reference intent category is "find materials"; when the reference prompt information is "find a sound effect that makes people feel grand", its corresponding reference intent category is "find materials". When the reference prompt information is "how to remove watermarks", its corresponding reference intent category is "find functions". When the reference prompt information is "can chroma cutout be enabled", its corresponding reference intent category is "find functions".

[0041] In one embodiment of the present disclosure, a large language model is used to generate reference data pairs required for training a model through prompt word engineering, and the reference data pairs are marked respectively using a pre-trained language model.

[0042] In one embodiment of the present disclosure, the obtaining of multiple groups of reference data pairs includes: obtaining a preset intent category as a reference intent category; obtaining description information corresponding to the reference intent category; and generating reference prompt information corresponding to the reference intent category based on the description information using a large language model.

[0043] In the disclosed embodiment, the preset intent category can be obtained by classifying common editing operations in the field of video editing. In the disclosed embodiment, the preset intent category is mainly divided into four categories, namely: one-click video, picture and text video, find function, and find material.

[0044] In the disclosed embodiment, the descriptive information corresponding to the reference intent category refers to information used to describe the video operations that can be achieved by the reference intent category. Specifically: when the reference intent category is text-to-picture video, the corresponding descriptive information is: a text and script can be automatically generated and made into a video based on the user's description text. When the reference intent category is one-click video, the corresponding descriptive information is to search and match the desired template from the template library. When the reference intent category is to find a function, the corresponding descriptive information is used to query a specific function location. When the reference intent category is to find materials, the corresponding descriptive information is to describe the information related to the preset materials. The preset materials include 10 categories: "stickers, filters, special effects, music, sound effects, timbre, transitions, animations, text templates, and material packages."

[0045] In the disclosed embodiment, the above-mentioned reference intent category is processed using a large language model to obtain at least one reference prompt information.

[0046] In a specific implementation, when the reference image information is a picture and text video, the corresponding description information is: a marketing copy and script can be automatically generated according to the user's description and made into a video. The corresponding reference prompt information can be "write a copy", "help me make a promotional video according to the script", etc.

[0047] In a specific implementation, when the reference intent information is one-click video, the corresponding description information is: search and match the desired template from the template library, and the template styles are diverse, including fresh, DJ card point, suitable for spring outing vlog, etc. The corresponding reference prompt information can be: "Search for some templates suitable for children's programs", "Recommend me a template suitable for handmade videos", "How to make a card point template".

[0048] In a specific implementation, when the reference intent information is to find a function, the corresponding description information is to query a specific function location in the video editing software, and the corresponding reference prompt information may be "where is the position where the blur becomes clear", "why is there no watermark removal button", "can chroma cutout be enabled".

[0049] In a specific implementation, when the reference intent information is to find materials, there is a material library in the video editing software, which only includes 10 categories: "stickers, filters, special effects, music, sound effects, timbre, transitions, animations, text templates, and material packages". When and only when the user asks about content related to these materials, the corresponding reference prompt information may be "I want some classical-style stickers", "Find a sound effect that feels grand", "Search for fade-in and fade-out animations", or "Add a brush font".

[0050] In one embodiment of the present disclosure, the use of the intention recognition model to perform intent recognition on the current prompt information to obtain the target intent includes: using the intention recognition model to perform intent recognition on the current prompt information to obtain a target intent category; extracting operation information from the current prompt information to obtain target operation information; and using the target intent category and the target operation information to obtain the target intent.

[0051] In the disclosed embodiment, editing instructions corresponding to operation information corresponding to the target intent category are obtained from the editing instruction library of the video editing platform as a preset editing instruction library.

[0052] In the disclosed embodiment, after the editing instructions are filtered out through the operation information, the retrieval amount of the instructions can be further reduced.

[0053] In the disclosed embodiment, the correspondence between intentions and editing instructions is stored in the preset editing instruction library. According to the target intention category, the preset editing instructions are queried to obtain the initial editing instructions corresponding to the target intention category.

[0054] In the disclosed embodiment, the parameters in the corresponding execution code implied in the current prompt information are extracted, that is, the corresponding operation parameters in the current prompt information. For example, the current prompt information is "add a funny sticker", and the initial editing instruction is the existing "add a cute sticker"->addSticker({keyword:'cute'}), and the operation extraction model will extract the "funny" parameter. In the disclosed embodiment, the "funny" parameter is extracted in the operation extraction model, and "funny" is used to replace "cute" in the initial editing instruction, and finally the addSticker({keyword:'funny'}) code is reorganized, which is the video editing instruction.

[0055] In the embodiments of the present disclosure, two target intent category determination schemes are provided.

[0056] In an embodiment of the present disclosure, a plurality of groups of reference data pairs are used to obtain an intent recognition model, including: using the reference data to perform supervised training on a first language model to obtain the intent recognition model, wherein the first language model includes a large language model.

[0057] In the disclosed embodiment, supervised training of intent recognition and operation extraction using a model achieves the best balance between effect and performance.

[0058] In one embodiment of the present disclosure, the use of multiple groups of reference data pairs to obtain an intent recognition model includes: using the multiple groups of reference data pairs as reference data for a second language model; using the intent recognition model to perform intent recognition on the current prompt information to obtain a target intent category, including: using the second language model to perform context learning processing on the current prompt information to obtain a target intent category.

[0059] In the disclosed embodiment, intent category recognition is performed based on the contextual learning capability of a large language model without the need for training, and only a number of (prompt, intent category) data pairs are required.

[0060] It should be noted that the first language model needs to be trained with reference data before it can process the prompt information. The second language model does not need to be trained with reference data. It only needs to extract attribute information from the reference data and process the prompt information based on the language model's context learning ability.

[0061] S103: Perform video editing based on the video editing instruction.

[0062] In the disclosed embodiment, the current prompt information is parsed to obtain the video editing instructions contained in the current prompt information, and the video is edited based on the video editing instructions.

[0063] In one embodiment of the present disclosure, the editing effect corresponding to the video editing operation is displayed in a video preview area in the video editing interface.

[0064] In a possible implementation, if the video editing operation is to generate a video draft, the video draft is imported into the corresponding video editing track, and the video screen corresponding to the video draft is displayed in the video preview area.

[0065] In another possible implementation, if the video editing operation is to edit a generated video draft, the editing information corresponding to the video editing operation is updated in the video editing track, and the corresponding editing effect is displayed in the corresponding video screen.

[0066] Figure 2 FIG. 1 is a schematic diagram of the structure of a video editing device in an embodiment of the present disclosure. Figure 2As shown, the video editing device 20 provided in the embodiment of the present disclosure mainly includes: a current prompt information acquisition module 21, a video editing instruction determination module 22 and a video editing module 43.

[0067] Among them, the current prompt information acquisition module 21 is used to obtain the current prompt information input by the user in the video editing interface; the video editing instruction determination module 22 is used to process the current prompt information using reference data to obtain video editing instructions; wherein the reference data pair includes reference prompt information and a reference intention category corresponding to the reference prompt information; the video editing module 23 is used to perform video editing based on the video editing instructions.

[0068] In one embodiment of the present disclosure, the video editing instruction determination module 22 includes: a reference data pair acquisition unit, where a user acquires multiple groups of reference data pairs; an intention recognition model determination unit, which is used to obtain an intention recognition model using the multiple groups of reference data pairs; a target intention determination unit, which is used to use the intention recognition model to perform intent recognition on the current prompt information to obtain the target intention; and a video editing instruction generation unit, which is used to generate a video editing instruction using the target intention.

[0069] In one embodiment of the present disclosure, a target intention determination unit includes: a target intention category determination unit, which is used to use the intention recognition model to perform intent recognition on the current prompt information to obtain a target intention category; a target operation determination subunit, which is used to extract operation information from the current prompt information to obtain target operation information; and a target intention determination subunit, which is used to use the target intention category and the target operation information to obtain the target intention.

[0070] In one embodiment of the present disclosure, the reference data is used to perform supervised training on the first language model to obtain an intent recognition model.

[0071] In one embodiment of the present disclosure, the multiple groups of reference data pairs are used as reference data for the second language model; the second language model performs context learning processing on the current prompt information to obtain a target intent category.

[0072] In one embodiment of the present disclosure, a reference data pair acquisition unit includes: a reference intent category acquisition subunit, used to acquire a preset intent category as a reference intent category; a reference description information acquisition subunit, used to acquire description information corresponding to the reference intent category; and a reference prompt information generation subunit, used to generate reference prompt information corresponding to the reference intent category based on the description information using a large language model.

[0073] In one embodiment of the present disclosure, the reference data pair acquisition unit further includes a signing sub-unit for signing the reference data pairs respectively using the trained language model after acquiring the multiple groups of reference data pairs.

[0074] In one embodiment of the present disclosure, the prompt information includes text prompt information and / or voice prompt information.

[0075] The video editing device provided in the embodiment of the present disclosure can execute the steps executed in the video editing method provided in the embodiment of the method of the present disclosure, and the execution steps and beneficial effects are no longer repeated here.

[0076] Figure 3 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 3 , which shows a schematic diagram of the structure of an electronic device 300 suitable for implementing the embodiment of the present disclosure. The electronic device 300 in the embodiment of the present disclosure may include, but is not limited to, a supercomputer. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0077] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303 to implement the video editing method of the embodiment described in the present disclosure. In the RAM 303, various programs and data required for the operation of the terminal device 300 are also stored. The processing device 501, the ROM 502, and the RAM 303 are connected to each other via a bus 3. An input / output (I / O) interface 305 is also connected to the bus 304.

[0078] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the terminal device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The terminal device 300 is shown to have various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0079] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the video editing method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0080] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0081] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0082] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0083] In a possible implementation of the present disclosure, the computer-readable medium carries one or more programs. When the one or more programs are executed by the terminal device, the terminal device can implement the video editing method described in any one of the above embodiments.

[0084] In a possible implementation manner of the present disclosure, when the above one or more programs are executed by the terminal device, the terminal device may also execute other steps described in the above embodiments.

[0085] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0086] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0087] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0088] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0089] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0090] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0091] In addition, although each operation is described in a specific order, this should not be required to perform these operations in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0092] Although the subject matter has been described in terms of specific structural features and / or method logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A video editing method, characterized in that: include: Obtain the current prompt information input by the user in the video editing interface; Processing the current prompt information using a reference data pair to obtain a video editing instruction; wherein the reference data pair includes reference prompt information and a reference intent category corresponding to the reference prompt information; Video editing is performed based on the video editing instruction.

2. The video editing method according to claim 1, characterized in that: The step of processing the current voice information using the reference data to obtain a video clipping instruction includes: Obtain multiple sets of reference data pairs; Using the multiple sets of reference data pairs, an intent recognition model is obtained; Using the intention recognition model to perform intention recognition on the current prompt information to obtain the target intention; The target intent is used to generate a video clip instruction.

3. The video editing method according to claim 2, characterized in that: The using the intention recognition model to perform intention recognition on the current prompt information to obtain the target intention includes: Using the intention recognition model to perform intention recognition on the current prompt information to obtain a target intention category; Extracting operation information from the current prompt information to obtain target operation information; The target intention category and the target operation information are used to obtain the target intention.

4. The video editing method according to claim 1, characterized in that: Using multiple sets of reference data pairs, an intent recognition model is obtained, including: The reference data is used to perform supervised training on the first language model to obtain an intent recognition model.

5. The video editing method according to claim 2, characterized in that: The method of obtaining an intention recognition model by using multiple groups of reference data pairs includes: using the multiple groups of reference data pairs as reference data for a second language model; The intent recognition model is used to perform intent recognition on the current prompt information to obtain a target intent category, including: The second language model is used to perform context learning processing on the current prompt information to obtain a target intent category.

6. The video editing method according to claim 2, characterized in that: The obtaining of multiple groups of reference data pairs includes: Obtain a preset intent category as a reference intent category; Obtaining description information corresponding to the reference intent category; A large language model is used to generate reference prompt information corresponding to the reference intent category based on the description information.

7. The video editing method according to claim 2, characterized in that: After obtaining the plurality of reference data pairs, the method further comprises: The reference data pairs are respectively labeled using a pre-trained language model.

8. The video editing method according to any one of claims 1 to 7, characterized in that: The prompt information is text prompt information or voice prompt information.

9. A video editing device, characterized in that: include: The current prompt information acquisition module is used to obtain the current prompt information input by the user in the video editing interface; A video editing instruction determination module, used to process the current prompt information using a reference data pair to obtain a video editing instruction; wherein the reference data pair includes reference prompt information and a reference intent category corresponding to the reference prompt information; The video editing module is used to perform video editing based on the video editing instruction.

10. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the video editing method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the video editing method according to any one of claims 1 to 8 is implemented.

Images