Video processing method and apparatus, and terminal device

Abstract

The present disclosure provides a video processing method and apparatus, and a terminal device. The method comprises: acquiring indication information corresponding to a first video, wherein the indication information is used for indicating an editing effect with regard to the first video; determining a plurality of segmented words associated with the indication information, a part-of-speech of each segmented word and a dependency relationship among the plurality of segmented words; on the basis of the part-of-speech of each segmented word, the dependency relationship among the plurality of segmented words and the plurality of segmented words, determining an operation type and an operation parameter which are associated with an editing operation; and on the basis of the operation type and the operation parameter, performing editing processing on the first video, so as to obtain a second video. The embodiments of the present disclosure can improve the accuracy of video editing.

Description

Video processing method, device and terminal equipment

[0001] This application claims priority to Chinese patent application No. 202311199842.X filed on September 15, 2023, and the contents of the above-mentioned Chinese patent application disclosure are hereby incorporated by reference in their entirety as a part of this application. Technical Field

[0002] The embodiments of the present disclosure relate to a video processing method, apparatus, and terminal device. Background Art

[0003] The user can input natural language text into the terminal device, and the terminal device can determine the specific editing operation described in the natural language text by parsing the natural language text, and perform the editing operation on the video.

[0004] In some cases, a terminal device can identify named entities in natural language text and, based on the correspondence between the named entities and the editing operations, determine the editing operation corresponding to the natural language text. However, related technologies can only recognize single editing operations and simple natural language text, and cannot accurately identify complex editing operations, resulting in low video editing accuracy.

[0005] Summary of the Invention

[0006] The embodiments of the present disclosure provide a video processing method, apparatus, and terminal device, which are used to solve the technical problem of low accuracy in video editing in related technologies.

[0007] In a first aspect, an embodiment of the present disclosure provides a video processing method, the method comprising:

[0008] Obtaining indication information corresponding to the first video, where the indication information is used to indicate an editing effect on the first video;

[0009] Determining a plurality of segmented words associated with the indication information, a part of speech of each segmented word, and dependency relationships between the plurality of segmented words;

[0010] Determining an operation type and an operation parameter associated with the editing operation based on the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words;

[0011] The first video is edited according to the operation type and the operation parameters to obtain a second video.

[0012] In a second aspect, an embodiment of the present disclosure provides a video processing device, comprising an acquisition module, a first determination module, a second determination module, and a processing module, wherein:

[0013] The acquisition module is used to acquire indication information corresponding to the first video, where the indication information is used to indicate the editing effect of the first video;

[0014] The first determining module is used to determine a plurality of segmented words associated with the indication information, the part of speech of each segmented word, and the dependency relationship between the plurality of segmented words;

[0015] The second determining module is configured to determine an operation type and an operation parameter associated with the editing operation based on the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words;

[0016] The processing module is used to edit the first video according to the operation type and the operation parameters to obtain a second video.

[0017] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: a processor and a memory;

[0018] The memory stores computer-executable instructions;

[0019] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the video processing method as described in the first aspect and various possible aspects of the first aspect.

[0020] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the video processing method as described in the first aspect and various possible aspects of the first aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] FIG1 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0023] FIG2 is a flow chart of a video processing method provided by an embodiment of the present disclosure;

[0024] FIG3 is a schematic diagram of a process for determining a first video according to an embodiment of the present disclosure;

[0025] FIG4 is a schematic diagram of determining a dependency relationship provided by an embodiment of the present disclosure;

[0026] FIG5 is a schematic diagram of an intent database provided by an embodiment of the present disclosure;

[0027] FIG6 is a schematic diagram of a process for determining a second video according to an embodiment of the present disclosure;

[0028] FIG7 is a schematic diagram of a method for determining an intent phrase provided by an embodiment of the present disclosure;

[0029] FIG8 is a schematic diagram of another method for determining an intent phrase provided by an embodiment of the present disclosure;

[0030] FIG9 is a schematic structural diagram of a video processing device provided by an embodiment of the present disclosure; and

[0031] FIG10 is a schematic structural diagram of a terminal device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0033] To facilitate understanding, the concepts involved in the embodiments of the present disclosure are explained below.

[0034] Terminal device: is a device with wireless transceiver function. The terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted. The terminal device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a vehicle-mounted terminal device, a wireless terminal in self-driving, a wireless terminal device in remote medical, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, a wireless terminal device in smart home, a wearable terminal device, etc. The terminal device involved in the embodiments of the present disclosure can also be called a terminal, user equipment (UE), an access terminal device, a vehicle-mounted terminal, an industrial control terminal, a UE unit, a UE station, a mobile station, a mobile station, a remote station, a remote terminal device, a mobile device, a UE terminal device, a wireless communication device, a UE agent or a UE device, etc. Terminal devices can also be fixed or mobile.

[0035] The application scenario of the embodiment of the present disclosure is described below with reference to FIG1 .

[0036] Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure. Please refer to Figure 1, which includes: a terminal device. Among them, the display page of the terminal device can be a video editing page, which includes a video to be edited, and the background music of the video is music A. When the user inputs text to the terminal device: change the background music of the video to music B, the terminal device can determine that the editing function corresponding to the text is to replace the background music, the editing object is the video, and the editing parameter is music B, and edit the video based on the above information to obtain a new video, the video content of which is the same as the original video, and the background music of the video is music B. In this way, the terminal device can perform editing operations on the video based on the voice or text input by the user, thereby improving the efficiency of editing and reducing the complexity of editing operations.

[0037] It should be noted that FIG1 is only an illustrative illustration of the application scenario of the embodiment of the present disclosure, and does not limit the application scenario of the embodiment of the present disclosure.

[0038] In the related art, a terminal device can convert the natural language text input by the user into a corresponding editing operation and edit the video based on the editing operation. Currently, the terminal device can identify named entities in the natural language text and determine the editing operation corresponding to the natural language text based on the correspondence between the named entities and the editing operation. For example, if the user inputs: Help me add a cyan-orange filter to the second video, the terminal device can identify that the named entities include: add filter, second video and cyan-orange, and obtain the editing operation based on the category of each named entity, where the editing operation can specifically be function: add filter, object: second video, parameter: cyan-orange, and the terminal device can perform the corresponding editing operation on the video. However, the above method can only identify a single, simple editing operation. If the natural language text input by the user includes multiple editing operations, or if the natural language text is highly complex, the terminal device cannot accurately identify the editing operation corresponding to the natural language text, resulting in low accuracy in video editing.

[0039] In order to solve the technical problems in the related art, the embodiment of the present disclosure provides a video processing method, in which a terminal device can obtain indication information corresponding to a first video, and determine multiple segmentations associated with the indication information, the part of speech of each segmentation, and the dependency relationship between the multiple segmentations. The terminal device can determine the starting segmentation among the multiple segmentations based on the dependency relationship and the part of speech of the multiple segmentations, and determine the intention phrase and parameter phrase among the multiple segmentations according to the part of speech of the starting segmentation, the dependency relationship and the part of speech of the multiple segmentations, and determine the operation type based on the intention phrase, and determine the operation parameters based on the parameter phrase. The terminal device can edit the first video according to the operation type and the operation parameters to obtain a second video. In the above method, since the terminal device can accurately identify the operation type and operation parameters corresponding to the editing operation described by the indication information based on the part of speech of each segmentation and the dependency relationship between the multiple segmentations, the terminal device can accurately determine the editing effect described by the indication information, thereby improving the accuracy of video editing.

[0040] The following detailed description of the technical solution of the present disclosure and how the technical solution of the present disclosure solves the above-mentioned technical problems is provided with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. The embodiments of the present disclosure will be described below in conjunction with the accompanying drawings.

[0041] FIG2 is a flow chart of a video processing method provided by an embodiment of the present disclosure. Referring to FIG2 , the method may include:

[0042] S201. Obtain indication information corresponding to a first video.

[0043] The execution subject of the embodiment of the present disclosure may be a terminal device, or a video processing device provided in the terminal device. The video processing device may be implemented based on software, or based on a combination of software and hardware, which is not limited in the embodiment of the present disclosure.

[0044] The first video may be the video to be edited. For example, if the user's requirement is to add sticker effects to video A, the first video may be video A. If the user's requirement is to replace the background music in video B, the first video may be video B.

[0045] Optionally, the terminal device may determine the first video based on an operation input by the user. For example, the user may open a video editing application in the terminal device and add a corresponding video in the video editing application, which may be the first video.

[0046] Optionally, the terminal device may receive the first video sent by another device. For example, a database may pre-store multiple videos to be edited, and the terminal device may obtain any one of the videos in the database to obtain the first video.

[0047] The following describes the process of determining the first video by the terminal device in conjunction with FIG3 .

[0048] Figure 3 is a schematic diagram of a process for determining a first video according to an embodiment of the present disclosure. Referring to Figure 3 , a terminal device is included. The terminal device's display page includes page 301, page 302, and page 303. Page 301 is the terminal device's application display page, which may include a video editing application. When a user clicks on the video editing application, the terminal device's display page jumps from page 301 to page 302.

[0049] Referring to Figure 3, page 302 may be a page of a video editing application. Page 302 may include a control for starting creation, draft video 1, draft video 2, draft video 3, and draft video 4 (draft videos may be unfinished videos). When a user clicks the control for starting creation, the display page of the terminal device jumps from page 302 to page 303.

[0050] Referring to Figure 3 , page 303 may be a video page, which may include Video A, Video B, Video C, Video D, Video E, and Video F. When a user clicks Video A, the selection control for Video A is highlighted, and the terminal device may determine Video A as the first video. It should be noted that if a user clicks Draft Video 1 on page 302, the terminal device does not need to jump to page 303; the terminal device may determine Draft Video 1 as the first video.

[0051] The instruction information is used to indicate the editing effect of the first video. For example, the instruction information can be voice, text, video, etc., which is not limited in the embodiments of the present disclosure. For example, if the instruction information is editing text, the editing text can describe the specific editing operation on the first video. For example, the editing text can be: adding cartoon stickers to the second segment of the video, adding cheerful background music to the video, adding a fresh and bright filter to the third segment of the video, etc.

[0052] It should be noted that the indication information may be associated with a natural language text describing the editing operation. However, the terminal device can only determine the editing operation corresponding to the indication information after recognizing the natural language text.

[0053] Optionally, the terminal device can determine the edited text input by the user as indication information, or the terminal device can determine the voice input by the user as indication information (after the terminal device receives the user's voice, it can convert the voice into text based on voice recognition technology), or the terminal device can receive indication information sent by other devices (such as servers, etc.), which is not limited in this embodiment of the present disclosure.

[0054] S202: Determine multiple segmented words associated with the indication information, the part of speech of each segmented word, and dependency relationships between the multiple segmented words.

[0055] Optionally, after receiving the indication information, the terminal device may convert the indication information into edit text associated with the natural language, and then determine, based on the edit text, multiple segmented words associated with the indication information, the part of speech of each segmented word, and the dependency relationships between the multiple segmented words. For example, if the indication information is text, the terminal device may directly determine the multiple segmented words, the part of speech of each segmented word, and the dependency relationships between the multiple segmented words in the indication information. If the indication information is speech, the terminal device may first convert the speech into text, and then determine the multiple segmented words, the part of speech of each segmented word, and the dependency relationships between the multiple segmented words from the text.

[0056] Optionally, the segmented words may be words in the edit text associated with the indication information. For example, if the edit text associated with the indication information is: background music is replaced with cheerful music, the segmented words in the edit text may include: background music, replacement, cheerful, music.

[0057] Optionally, the terminal device may determine multiple word segments in the edit text associated with the indication information based on named entity recognition. For example, the terminal device may process the edit text associated with the indication information using any named entity recognition algorithm or model to obtain multiple word segments in the edit text.

[0058] Optionally, the terminal device can pre-acquire a word segmentation vocabulary, which may include multiple word segmentations. The terminal device can match the edit text associated with the indication information with the multiple word segmentations in the vocabulary to improve the accuracy of the word segmentation of the edit text. For example, in actual application, a specific field usually has some proper nouns and proper operations. The named entity recognition algorithm cannot accurately identify the words of proper nouns and proper operations. Therefore, the terminal device can pre-store multiple proper nouns and proper operation words in the word segmentation vocabulary, thereby improving the accuracy of word segmentation. For example, the words of proper operations may include: cutout, beauty, etc., and the proper nouns may include: sticker name, filter name, song name, singer name, etc., which is not limited in the present embodiment. For example, the terminal device can obtain the above-mentioned professional nouns and professional operation nouns in the material library of audio and video editing and the function table of editing operations. The terminal device can also obtain the above-mentioned professional nouns and professional operation nouns based on the knowledge graph, which is not limited in the present embodiment.

[0059] Parts of speech may refer to the basis for classifying a word based on its characteristics. For example, parts of speech may include nouns, verbs, adjectives, conjunctions, adverbs, and interjections, which are not limited in the present disclosure.

[0060] It should be noted that after the terminal device determines the multiple segmented words associated with the indication information, it can determine the part of speech of each segmented word based on any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0061] Alternatively, a dependency relationship may refer to a relationship between words. For example, the dependency relationship between word 1 and word 2 may be: an adjectival modifier (amod) modifying a noun phrase, or the dependency relationship between word 1 and word 2 may be: two words connected by a coordinating conjunction (e.g., and, or).

[0062] It should be noted that the above examples are merely illustrative of the dependency relationships between words, and are not intended to limit the dependency relationships of the embodiments of the present disclosure. There are many dependency relationships between words, and the embodiments of the present disclosure will not be described in detail here.

[0063] Optionally, the terminal device may determine the dependency relationship between multiple word segments associated with the indication information based on any feasible implementation method (eg, based on a model, algorithm implementation, etc.), which is not limited in the embodiments of the present disclosure.

[0064] 4 , the process of determining multiple segmented words associated with the indication information, the part of speech of each segmented word, and the dependency relationship between the multiple segmented words will be described below.

[0065] Figure 4 is a schematic diagram of determining a dependency relationship provided by an embodiment of the present disclosure. Please refer to Figure 4, which includes: text. Among them, the text can be: add music and sound effects. The terminal device (not shown in Figure 4) can segment the text, and the multiple segmentations obtained include: add, music, and, sound effects. Among them, the part of speech of add is a verb, the part of speech of music and sound effects is a noun, and the part of speech of and is a conjunction. The terminal device can determine that the dependency relationship of add is the root node in the text, the dependency relationship between music and sound effects is a parallel relationship, the dependency relationship between add and music is a verb-direct object relationship, and the dependency relationship between add and sound effects is a verb-direct object relationship.

[0066] S203: Determine an operation type and operation parameters associated with the editing operation according to the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words.

[0067] The operation type may indicate an operation intention associated with the editing operation. For example, if the operation type is to change the background music, the user's editing intention for the video is to change the background music in the video.

[0068] The operation parameter may be a parameter corresponding to the operation type. For example, if the operation type is to change the type of background music, the operation parameter may be the name of the music.

[0069] Among them, the terminal device can determine the intention phrases and parameter phrases associated with the editing operation in multiple participles based on the following feasible implementation method: based on the dependency relationship and the parts of speech of multiple participles, determine the starting participle in multiple participles, according to the part of speech of the starting participle, the dependency relationship and the parts of speech of multiple participles, determine the intention phrases and parameter phrases in multiple participles, based on the intention phrases, determine the operation type, and based on the parameter phrases, determine the operation parameters.

[0070] The intent phrase may indicate the type of editing operation. For example, the intent phrase may be "change background music to," and the corresponding operation type is replacing background music; the intent phrase may be "change filter to," and the corresponding operation type is replacing filters; the intent phrase may be "add stickers," and the corresponding operation type is adding stickers.

[0071] The parameter phrase can indicate the operation parameters corresponding to the operation type. For example, if the instruction information is: Replace the background music with Music 1, the intention phrase in the instruction information can be: Background Music Replacement, and the parameter phrase in the instruction information can be: Music 1, that is, the operation type corresponding to the operation parameter of replacing the background music is Music 1. For example, if the operation type is to add a filter, the parameter phrase can be: Bright, Orange, that is, the editing operation can be: Add Bright, Orange Filter, with Bright and Orange being the operation parameters of the editing operation.

[0072] The part of speech of the starting participle is a part of speech from a preset part-of-speech set. For example, the preset part-of-speech set may include verbs, nouns, and proper nouns. For example, the starting participle may be a verb such as add or replace, a noun such as music or sound effect, or a proper noun such as filter or cutout.

[0073] Among them, the terminal device can determine the starting participle from multiple participles based on the following feasible implementation method: taking a pre-set dependency relationship (such as a dependency relationship dep that the system cannot recognize, a verb-direct object dependency relationship dobj, and a semantically determined word dependency relationship ccomp), and a participle whose head word is a root node (i.e., head is a root node participle) as a candidate for the starting participle. For example, if the head of a participle is a root node participle (if the participle is the first participle of the edited text, the dependency relationship of the participle is the root node root), and the dependency relationship between the participle and the root node participle is a verb-direct object dependency relationship, the terminal device can use the participle as a candidate for the starting participle.

[0074] If the part of speech of the root node's segmentation word is in the preset part of speech set, the root node's segmentation word is determined as the starting segmentation word. If the part of speech of the root node's segmentation word is not in the preset part of speech set, the starting segmentation word is determined from the candidates for the starting segmentation word. For example, if the root node's segmentation word is "add," the part of speech of the segmentation word is a verb, and the terminal device can determine the starting segmentation word as "add." If the root node's segmentation word is "help," the part of speech of the segmentation word is not in the preset part of speech set, and therefore, the terminal device can determine the starting segmentation word from the candidates for the starting segmentation word.

[0075] For example, if the indicative information is the text: Hurry up and add background music, then the participle of the root node in the text is: Hurry up, and the candidates for the starting participle are: Add, Background music. Since the part of speech of the participle of the root node is not a noun, a verb, or a proper noun, the terminal device can determine the first participle among the candidates for the starting participle: Add as the starting participle of the indicative information.

[0076] Optionally, if the starting participle is a root node, the terminal device may determine that the dependency relationship between the participle of the root node in the instruction information is a parallel relationship, and the participle whose part of speech is a verb or a preposition is also determined as the starting participle. For example, if the instruction information is to add music and change the timbre, the root in the instruction information is add. Since the dependency relationship between the participle "change" and the participle "add" is a parallel relationship, the terminal device can determine that the starting participle corresponding to the instruction information is: add, change, that is, the instruction information corresponds to two operation types, one operation type is the type of adding function, and the other operation type is the type of replacing function.

[0077] Optionally, after the terminal device determines the starting participle, it can determine the intent phrase and parameter phrase in the multiple participles based on the part of speech of the starting participle, the dependency relationship between the multiple participles, and the part of speech of the multiple participles. For example, if the part of speech of the starting participle is a verb, it means that the terminal device has determined the action of the editing operation corresponding to the indication information. The terminal device also needs to determine the participle used to assist in describing the operation type in the multiple participles based on the dependency relationship and the part of speech of the multiple participles, and then combine it with the starting participle to obtain the intent phrase describing the editing operation. For example, the indication information is: add music, the starting participle in the text is add, and music can be information that assists in describing the operation type. Therefore, the intent phrase of the text can be: add music, that is, the operation type is the type of adding music.

[0078] Optionally, the embodiment of the present disclosure may determine the parameter phrase based on the following feasible implementation method: according to the part of speech and dependency relationship of the starting participle, determine the first-level search term in multiple participles; if there is a second-level search term corresponding to the first-level search term in the multiple participles, then combine the first search term and the second search term to obtain the parameter phrase; if there is no second-level search term corresponding to the first-level search term in the multiple participles, then determine the first-level search term as the parameter phrase.

[0079] The search term is used to describe the operation parameters corresponding to the editing operation. For example, the search term can be bright, orange, cheerful, music name, sound effect name, sticker name, etc., which is not limited in the embodiment of the present disclosure.

[0080] The terminal device determines the first-level search term from multiple segmented words based on the part of speech and dependency relationship of the starting segmented word. There are two situations:

[0081] Case 1: The part of speech of the initial participle is a noun.

[0082] If the part of speech of the starting participle is a noun, then among the multiple participles, the participles whose dependency relationship with the starting participle is a dependency relationship in the third dependency set are determined as the first-level search terms. For example, the third dependency set may include: dependency relationships of adjective modifiers that modify noun phrases (amod), dependency relationships of words that determine semantics (ccomp), etc. For example, if the instruction information is to replace background music with music A, where the starting participle is background music and the starting participle is a noun, then the first-level search term can be music A (with a dependency relationship of ccomp).

[0083] Case 2: The part of speech of the initial participle is a verb.

[0084] If the part of speech of the starting participle is a verb, then among the multiple participles, the participles whose dependency relationship with the starting participle is a dependency relationship in the fourth dependency relationship set are determined as first-level search terms, or nouns among the multiple participles are determined as first-level search terms. For example, the fourth dependency relationship set may include dependency relationships of nominal subjects (nsubj), dependency relationships of verbs and direct objects (dobj), etc. For example, the indicative information is "add cheerful music", where the starting participle is "add", which is a verb. Therefore, the first-level search term can be cheerful, that is, the intended phrase of the indicative information is "add music", and the parameter phrase is "cheerful".

[0085] Optionally, if the part of speech of the initial participle is a verb, the terminal device may determine the nouns in the multiple participles as the first-level search terms. For example, the instruction information may be "adding a special effect of a sun sticker," where the initial participle is "add," which is a verb. Therefore, the first-level search term may be "sun sticker," i.e., the intent phrase of the instruction information is "add special effect," and the parameter phrase is "sun sticker."

[0086] Optionally, after the terminal device determines the first search term among multiple participles, it can also determine whether the second search term exists in the indication information. The terminal device can determine it as the second-level search term based on the fact that head is the first search term and the participle whose dependency relationship is in the fifth dependency set. For example, the fifth dependency set may include: the dependency relationship of adjective modifiers that modify noun phrases (amod), and the dependency relationship of adverbs that are not clauses (adverb modifier, advmod). For example, if the indication information is to add a particularly bright filter, the terminal device can determine that the first-level search term is bright, and then determine that the second-level search term is special.

[0087] Optionally, after the terminal device determines the first-level search term, if a second-level search term exists, the first-level search term and the second-level search term are combined to obtain a parameter phrase. For example, if the first-level search term is bright and the second-level search term is special, the terminal device may determine the parameter phrase to be special bright.

[0088] Optionally, if the second-level search term does not exist in the indication information, the terminal device may determine the first-level search term as the parameter phrase after obtaining the first-level search term. For example, if the indication information is changed from "background music" to "music 1," the terminal device may determine that the starting word segment is "background music" and further determine that the first-level search term is "music 1." Since there is no second-level search term, the terminal device may determine that the parameter phrase is "music 1."

[0089] It should be noted that if there is no corresponding parameter phrase for the intent phrase, the terminal device can determine whether there is a parallel intent phrase for the intent phrase. If so, the parameter phrase corresponding to the parallel intent phrase is determined as the parameter phrase corresponding to the intent phrase. For example, the instruction information is to add cheerful music and sound effects. The terminal device can determine that the starting participle is to add. Since music and sound effects are in a parallel relationship, the terminal device can obtain intent phrase 1 as adding music and intent phrase 2 as adding sound effects. Among them, the parameter phrase corresponding to intent phrase 1 is cheerful, and there is no parameter phrase for intent phrase 2. However, since the music in intent phrase 1 and the sound effects in intent phrase 2 are in a parallel relationship, the terminal device can determine that the parameter phrase corresponding to intent phrase 2 is also cheerful.

[0090] It should be noted that, for an English search term, for an English editing text having the sentence structure of "change the music with sth", the terminal device may determine the participle after the preposition as the search term.

[0091] Optionally, the terminal device determines the operation type based on the intent phrase, which can be specifically: according to the intent phrase, determine the target intent phrase in the intent database, and determine the preset operation type corresponding to the target intent phrase as the operation type corresponding to the intent phrase.

[0092] The intent database may include multiple preset intent phrases and preset operation types corresponding to each preset intent phrase. For example, for the operation type of changing background music, the preset intent phrases corresponding to the operation type may include phrases such as replace background music, change background music, and change background music.

[0093] The intention database is described below with reference to FIG5 .

[0094] Figure 5 is a schematic diagram of an intent database provided by an embodiment of the present disclosure. Please refer to Figure 5, which includes an intent database. The intent database includes operation type 1, operation type 2, and operation type 3. The intent phrases corresponding to operation type 1 include: phrase A, phrase B, and phrase C, that is, the operation types described by phrase A, phrase B, and phrase C are all operation type 1. The intent phrases corresponding to operation type 2 include: phrase D, phrase E, and phrase F, that is, the operation types described by phrase D, phrase E, and phrase F are all operation type 2. The intent phrases corresponding to operation type 3 include: phrase G, phrase H, and phrase I, that is, the operation types described by phrase G, phrase H, and phrase I are all operation type 3.

[0095] It should be noted that Figure 5 is only an illustrative illustration of the intent database in the embodiment of the present disclosure, and is not a limitation of the intent database. In actual application, the intent database may include multiple preset operation types, and each preset operation type may correspond to multiple phrases.

[0096] Optionally, the terminal device may obtain preset operation types in the intent database based on the video editing function. For example, if the video editing function includes adding filters and adding background music, the preset operation types may also include the type of adding filters and the type of adding music.

[0097] Optionally, after determining the preset operation type, the terminal device can generate a preset intent phrase corresponding to the preset operation type based on the large language model. For example, if the terminal device determines that the preset operation type is to add a filter, the terminal device can generate multiple phrases describing the operation of adding a filter based on the large language model (such as "add filter" and "add a filter"). This can improve the accuracy of determining the editing operation and improve the accuracy of video editing.

[0098] Among them, the target intent phrase has the highest similarity with the intent phrase. For example, the terminal device can determine the text similarity between the intent phrase associated with the indication information and each preset intent phrase in the intent database, and then determine the preset intent phrase with the highest text similarity as the target intent phrase. For example, if the intent phrase associated with the indication information is: background music replacement, and the preset intent phrases in the intent database include: background music replacement and adding stickers, then the terminal device can determine that the target intent phrase in the intent database is: background music replacement (with the highest text similarity to background music replacement).

[0099] Optionally, after the terminal device determines the target intent phrase, it can determine the preset operation type corresponding to the target intent phrase in the intent database as the operation type corresponding to the intent phrase associated with the edit text. For example, if the target intent phrase is: replace background music, and the preset operation type corresponding to the target intent phrase is: replace music type, then the operation type corresponding to the intent phrase associated with the indication information (background music changed to) is also: replace music type.

[0100] Optionally, after determining the parameter phrase, the terminal device may determine the operation phrase as an operation parameter associated with the editing operation. For example, if the parameter phrase is "Music 1," the operation parameter is "Music 1." If the parameter phrase is "Music 2," the operation parameter is "Music 2." If the parameter phrase is "Special, Bright, Orange," the operation parameters are "Special, Bright, Orange."

[0101] S204: Edit the first video according to the operation type and the operation parameters to obtain a second video.

[0102] Among them, the terminal device can obtain the second video based on the following feasible implementation method: generate a target script according to the operation type and operation parameters, execute the target script on the first video to edit the first video and obtain the second video.

[0103] The target script includes the code and parameter phrase corresponding to the operation type. For example, if the intent phrase is "change background music" and the parameter phrase is "cheerful music," the terminal device can determine, based on the intent database, that the operation type corresponding to the intent phrase is "replace the music type," and determine, based on the parameter phrase, that the operation parameter corresponding to the replacement music type is "cheerful music." Therefore, the terminal device can generate the target script: ReplaceMusic (code corresponding to the operation type) ({keyword: cheerful music}).

[0104] Optionally, after the terminal device obtains the target script, it can execute the target script to edit the first video to obtain the second video. For example, if the target script is ReplaceMusic({keyword: cheerful music}), the terminal device can replace the background music of the video with cheerful music.

[0105] It should be noted that in the embodiment of the present disclosure, some editing operations cannot be recognized. For example, the number of operation types corresponding to the indication information is less than the number of sentences, and the number of operation types is greater than 1 (add a sticker, to be funny, add a summer filter). In order to avoid editing errors, when the number of operation types and the number of sentences recognized by the terminal device meet the above conditions, the editing operation on the first video is stopped. For example, the number of operation types corresponding to the editing text is 1, and the number of sentences is 2. In this case, the user uses multiple sentences to modify the operation type. In order to avoid errors, the terminal device will also stop editing the first video.

[0106] It should be noted that in the embodiment of the present disclosure, the number of starting participles is related to the number of intent phrases. For example, if the terminal device determines that the number of starting participles in the indication information is 2, the terminal device can generate 2 intent phrases, and the indication information corresponds to 2 operation types.

[0107] It should be noted that, in the process of determining the similarity between the intent phrase and the preset intent phrase in the intent database, the terminal device can call the embedding service, recall the 10 candidates with the highest similarity from the preset intent phrases, and then determine the target intent phrase with the highest similarity among the 10 candidates. If the similarity between each preset intent phrase in the intent database and the intent phrase of the indication information is less than a preset threshold, the terminal device determines that the indication information does not have the operation type of the editing operation, and the terminal device stops performing the editing operation on the first video.

[0108] It should be noted that when the terminal device generates a target script, it can pre-acquire the script template of the operation type corresponding to the intention phrase in the indication information, and then fill the operation parameters into the script template to obtain the target script (the terminal device can pre-configure the corresponding script template for each preset operation type, and the terminal device fills the corresponding operation parameters in the corresponding script template to obtain the target script).

[0109] 6 , the process of the terminal device editing the first video based on the operation type and the operation parameters to obtain the second video will be described.

[0110] FIG6 is a schematic diagram of a process for determining a second video provided by an embodiment of the present disclosure. Please refer to FIG6 , which includes: a first video, an intent database, a parameter phrase, and an intent phrase. The background music of the first video is music A, the parameter phrase is music B, and the intent phrase is background music changed to. The intent database includes an operation type for replacing music and an operation type for adding a filter. The phrases corresponding to the operation type for replacing music are background music replacement and music replacement, and the phrases corresponding to the operation type for adding a filter are adding a new filter and adding a filter.

[0111] Please refer to Figure 6. Since the text similarity between the intent phrase and "background music replacement" is the highest, the terminal device can determine that the target intent phrase in the intent database is background music replacement, and the operation type corresponding to the intent phrase is the type of music replacement. The terminal device (not shown in Figure 6) can generate a target script based on the operation type of replacing music and music B (operation parameters): Replace music ({keyword: music B}). The terminal device can execute the target script to generate a second video, wherein the video content of the second video is the same as the video content of the first video, and the background music of the second video is music B. In this way, based on the operation type, the terminal device can accurately identify the type of editing effects corresponding to the edited text, and then perform editing operations on the first video in combination with the operation parameters to improve the accuracy of video editing.

[0112] It should be noted that in the embodiment of the present disclosure, after the terminal device obtains the instruction information, it can also supplement the instruction information. For example, if there is no noun in the instruction information, but there is a music name or timbre name, the terminal device can fill in the corresponding noun. For example, if the instruction information is "change to ethereal", the terminal device can supplement the instruction information to "change to ethereal timbre".

[0113] For example, if the instruction information includes the meaning of ratio, the terminal device can add the text "ratio" to the instruction information. For example, if the instruction information is: adjust the video size to 9:16, the terminal device can add the text "adjust the video size to 9:16 ratio" to the instruction information.

[0114] For example, when the instruction includes subtitles, the terminal device needs to distinguish whether it contains parameters mapped to different scenarios. For example, if the instruction is to add subtitles in English and Chinese, the terminal device can recognize the language words in the instruction as English and Chinese. Therefore, the terminal device can modify the intent phrase "add subtitles" to "add bilingual subtitles."

[0115] For example, after the terminal device segments the instruction information, if the segmented words include "fast" and "slow", and the part of speech of the segmented words is an interjection, the terminal device can process the operation type corresponding to the intention phrase based on "faster" and "slower". For example, if the number of intention phrases is less than 3, and the intention phrases are fast, slow, or double speed, the terminal device can modify the intention phrase to: faster, slower, or 3x speed.

[0116] It should be noted that after the terminal device determines the target script, if the instruction information contains a scope word, the terminal device may process the scope word as a separate parameter and only take the first qualifying participle. For example, scope words could be "all" or "whole." When determining the scope word, the terminal device may prioritize scope words that modify nouns over those that modify verbs.

[0117] It should be noted that after the terminal device determines the target script, if the instruction information contains an action modifier, the terminal device can process the action modifier as a separate parameter. For example, the action modifier can be picture-in-picture, arbitrary clip, etc.

[0118] The embodiment of the present disclosure provides a video processing method, in which a terminal device can obtain indication information corresponding to a first video, and determine multiple segmentations associated with the indication information, the part of speech of each segmentation, and the dependency relationship between the multiple segmentations. The terminal device can determine a starting segmentation from the multiple segmentations based on the dependency relationship and the part of speech of the multiple segmentations, and determine an intent phrase and a parameter phrase from the multiple segmentations based on the part of speech of the starting segmentation, the dependency relationship, and the part of speech of the multiple segmentations, and determine an operation type based on the intent phrase, and determine the parameter phrase as an operation parameter. The terminal device can edit the first video based on the operation type and the operation parameter to obtain a second video. In this way, since the terminal device can accurately identify the editing effect described by the indication information based on the part of speech of each segmentation and the dependency relationship between the multiple segmentations, the terminal device can accurately determine the editing operation, thereby improving the accuracy of video editing.

[0119] In the embodiment shown in FIG2 , in the above-mentioned video processing method, there are two situations for determining the intended phrase among multiple participles based on the part of speech of the starting participle, the dependency relationship, and the part of speech of multiple participles. The two situations for determining the intended phrase are described below in conjunction with FIG7-FIG8 .

[0120] FIG7 is a schematic diagram of a method for determining an intention phrase provided by an embodiment of the present disclosure. In the embodiment shown in FIG7 , the part of speech of the initial participle is a verb. Referring to FIG7 , the method flow includes:

[0121] S701: Determine, according to the starting participle and the dependency relationship, a first participle of at least one part of speech being a noun from among multiple participles.

[0122] Among them, the dependency relationship between the starting participle and the first participle is the dependency relationship in the first dependency set. For example, the first dependency set may include the dependency relationship between verb and direct object (direct object, dobj), the dependency relationship that the system cannot recognize (dependent, dep), etc. For example, if the starting participle is a verb, the terminal device can obtain nouns and proper nouns with dependency relationships of dobj or dep from multiple participles, and then obtain at least one first participle. For example, if the edited text is: add interesting music, the multiple participles of the edited text include: add, a, interesting, of, music, among which the starting participle is add, and the part of speech of the starting participle is a verb. Since the dependency relationship between music and add is dobj, the terminal device can determine music as the first participle.

[0123] S702: Determine an intention phrase according to the number of first participles, the starting participle, and the first participle.

[0124] The terminal device determines the intended phrase based on the number of first participles, the starting participle, and the first participle. There are two situations:

[0125] Case 1: The number of the first participle is 1.

[0126] If the number of first participles is 1, the starting participle and the first participle are combined to obtain the intended phrase. If the instruction information is: add a cheerful music, then the multiple participles of the instruction information include: add, one, cheerful, of, music, among which the dependency relationship of the participle "add" is root, the dependency relationship of the participle "one" is nummod, the dependency relationship of the participle "cheerful" is "amod", the dependency relationship of the participle "of" is mark, and the dependency relationship of the participle "music" is dobj. Therefore, the terminal device can determine that the starting participle is "add", the part of speech of the starting participle is a verb, the dependency relationship of the participle "music" meets the dependency relationship in the first dependency relationship set, and the participle "music" is a proper noun. The terminal device can determine that the first participle is music. Since the number of first participles is 1, the terminal device can combine the starting participle "add" with the first participle "music" to obtain the intended phrase "add music".

[0127] Case 2: The number of first participles is greater than 1.

[0128] If the number of first participles is greater than one, the terminal device may obtain the type of dependency relationship between the starting participle and each first participle, and determine the intended phrase from the multiple participles based on the type of dependency relationship between the starting participle and each first participle. For example, the dependency relationship type may include dobj, dep, etc., which is not limited in the present embodiment.

[0129] The terminal device determines the intended phrase among multiple participles according to the type of dependency relationship between the starting participle and each first participle. Specifically, it can be: determining the priority of each first participle according to the type of dependency relationship between the starting participle and each first participle, determining the target participle with the highest priority among at least one first participle according to the priority of each first participle, combining the starting participle and the target participle to obtain the intended phrase.

[0130] Optionally, the dependencies included in the first dependency set may be dobj and dep, and therefore, the priority order may be dobj greater than dep. For example, if the dependency type of the first participle 1 is dobj and the dependency type of the first participle 2 is dep, the terminal device may determine that the target participle is the first participle 1.

[0131] Optionally, since the part of speech of the first participle is a noun, but proper nouns are also included in the nouns, the terminal device can further determine the priority between the first participles based on the type of dependency relationship and the part of speech of the first participle. For example, the priority order can be dobj+nz (proper noun) is greater than dep+nz, and dep+nz is greater than dobj+n. For example, the type of dependency relationship of the first participle 1 is dobj, and the type of dependency relationship of the first participle 2 is dep, but the part of speech of the first participle 2 is a proper noun nz, and the part of speech of the first participle 1 is a common noun n. Therefore, the terminal device can determine that the target participle is the second participle.

[0132] Optionally, the terminal device may combine the starting participle and the target participle to obtain the intended phrase. For example, the terminal device determines in the instruction information that the starting participle is "add," the first participle is "music," and the second participle is "city." Since music is a proper noun, the participle "music" has a higher priority than the participle "city." Therefore, the terminal device may determine that the target participle is "music," and combine the starting participle and the target participle to obtain the intended phrase: "add music."

[0133] It should be noted that if a participle in the compiled text has a parallel dependency relationship with the first participle, the terminal device can combine the starting participle with the participle in the parallel relationship to obtain another intended phrase. For example, if the instruction information can be "add music and sound effects", the terminal device can determine that the starting participle is "add", which is a verb, and the terminal device can determine that the first participle is "music", thereby obtaining the intended phrase "add music". Since "music" and "sound effects" are parallel participles, the terminal device can obtain another intended phrase: "add sound effects".

[0134] The embodiment of the present disclosure provides a method for determining an intended phrase, which determines at least one first participle whose part of speech is a noun from among multiple participles based on a starting participle and a dependency relationship. If the number of first participles is 1, the starting participle and the first participle are combined to obtain an intended phrase. If the number of first participles is greater than 1, the terminal device can obtain the type of dependency relationship between the starting participle and each first participle, and determine the intended phrase from among the multiple participles based on the type of dependency relationship between the starting participle and each first participle. In this way, when the starting participle is a verb, the terminal device can accurately identify the functional noun that can be combined with the starting participle in the indication information, and thus can obtain an accurate intended phrase, thereby improving the accuracy of determining the editing operation and thus improving the accuracy of video editing.

[0135] FIG8 is a schematic diagram of another method for determining an intended phrase provided by an embodiment of the present disclosure. In the embodiment shown in FIG8 , the part of speech of the initial participle is a noun. Referring to FIG8 , the method flow includes:

[0136] S801: Determine whether there is a second participle whose part of speech is a verb among the multiple participles based on the initial participle and the dependency relationship.

[0137] If so, execute step S802.

[0138] If not, execute step S803.

[0139] The dependency relationship between the starting participle and the second participle is a dependency relationship in the second dependency relationship set. For example, the second dependency relationship set may include dependency relationships such as dep and ccomp. For example, the instruction information is to change the background music to cheerful music. The starting participle in the instruction information is background music, the part of speech of the starting participle is noun, the dependency relationship between the participle "change to" and the starting participle is ccomp, and the part of speech of the participle "change to" is verb. Therefore, the terminal device can determine that the second participle exists in the instruction information, and the second participle is "change to".

[0140] S802: Combine the second participle and the initial participle to obtain an intended phrase.

[0141] Optionally, if a second participle exists among the multiple participles in the edited text, the terminal device may combine the second participle with the initial participle to obtain the intended phrase. For example, the instruction information is to change the background music to sad music, where the initial participle is background music, and the part of speech of the initial participle is noun. Therefore, the terminal device may determine that the second participle is the verb "change to". The terminal device may combine the initial participle and the second participle to obtain the intended phrase: background music change to.

[0142] Optionally, after the terminal device combines the second participle with the starting participle to obtain the intended phrase, the method further comprises: determining, based on the dependency relationship, whether a candidate participle exists in the plurality of participles that is parallel to the starting participle; if so, combining the second participle with the candidate participle to obtain another intended phrase. For example, since the starting participle has a noun part of speech, if there is a noun that has a parallel dependency relationship with the starting participle, it indicates that the instruction information also includes other operation types. Therefore, the terminal device may combine the second participle with the candidate participle to obtain another intended phrase. For example, if the instruction information is: "Replace music and sound effects with cheerful", the terminal device may determine that the starting participle of the instruction information is "music", the starting participle has a noun part of speech, and the second participle in the instruction information is "replace". Therefore, the terminal device may obtain an intended phrase: "music replacement". Since music and sound effects are in a parallel relationship, the terminal device may obtain another intended phrase: "sound effect replacement", i.e., the operation types included in the instruction information are "replace music" and "replace sound effects".

[0143] S803: Obtain a preset participle whose part of speech is a verb, and combine the preset participle and the initial participle to obtain the intended phrase.

[0144] Optionally, if the second participle does not exist among the multiple participles associated with the indication information, the terminal device may combine the initial participle with a preset participle to obtain the intended phrase. The preset participle may be a participle with a verbal part of speech. For example, the preset participle may be "add," "replace," etc., which is not limited in the present embodiment.

[0145] For example, if the indication information is: sound effect dog barking, the terminal device can determine that the starting participle in the indication information is sound effect, and the starting participle is a noun, so the terminal device needs to determine the second participle in the compiled text. Since dog barking is also a noun, the second participle does not exist in the indication information. The terminal device can obtain the preset participle as add, and then combine the preset participle with the starting participle to obtain the intended phrase: add sound effect.

[0146] The disclosed embodiments provide a method for determining an intended phrase. Based on a starting participle and dependency relationships, the method determines whether a second participle with a verbal part of speech exists among multiple participles. If so, the second participle and the starting participle are combined to obtain the intended phrase. If not, a preset participle with a verbal part of speech is obtained, and the preset participle and the starting participle are combined to obtain the intended phrase. In this way, even when the starting participle has a noun part of speech, the terminal device can obtain a meaningful verb in the instruction information, thereby accurately describing the editing effect based on the form of the intended phrase. Furthermore, by comparing the phrases for similarity, the accuracy of determining the operation type can be improved, thereby improving the accuracy of the editing operation and video editing.

[0147] FIG9 is a schematic diagram of the structure of a video processing device provided by an embodiment of the present disclosure. Referring to FIG9 , the video processing device 900 includes an acquisition module 901, a first determination module 902, a second determination module 903, and a processing module 904, wherein:

[0148] The acquisition module 901 is used to acquire indication information corresponding to the first video, where the indication information is used to indicate the editing effect of the first video;

[0149] The first determining module 902 is configured to determine a plurality of segmented words associated with the indication information, a part of speech of each segmented word, and dependency relationships between the plurality of segmented words;

[0150] The second determining module 903 is configured to determine an operation type and an operation parameter associated with the editing operation based on the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words;

[0151] The processing module 904 is configured to edit the first video according to the operation type and the operation parameters to obtain a second video.

[0152] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0153] Determining a starting participle from the multiple participles based on the dependency relationship and the parts of speech of the multiple participles, where the part of speech of the starting participle is a part of speech in a preset part of speech set;

[0154] Determining the intention phrase and the parameter phrase from the multiple participles according to the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles;

[0155] The operation type is determined based on the intention phrase, and the operation parameters are determined based on the parameter phrase.

[0156] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0157] Determining, based on the starting participle and the dependency relationship, at least one first participle whose part of speech is a noun from the multiple participles, wherein the dependency relationship between the starting participle and the first participle is a dependency relationship in a first dependency relationship set;

[0158] If the number of the first participles is 1, combining the starting participle and the first participle to obtain the intended phrase;

[0159] If the number of the first participles is greater than 1, the type of the dependency relationship between the starting participle and each first participle is obtained, and the intention phrase is determined in the multiple participles according to the type of the dependency relationship between the starting participle and each first participle.

[0160] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0161] Determining the priority of each first participle according to the type of dependency relationship between the starting participle and each first participle;

[0162] Determining a target word with the highest priority among the at least one first word according to the priority of each first word;

[0163] The starting participle and the target participle are combined to obtain the intended phrase.

[0164] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0165] Determining, based on the starting participle and the dependency relationship, whether there is a second participle whose part of speech is a verb among the multiple participles, wherein the dependency relationship between the starting participle and the second participle is a dependency relationship in a second dependency relationship set;

[0166] If yes, then combining the second participle and the initial participle to obtain the intended phrase;

[0167] If not, a preset participle whose part of speech is a verb is obtained, and the preset participle and the starting participle are combined to obtain the intended phrase.

[0168] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0169] According to the dependency relationship, determining whether there is a candidate participle in the plurality of participles that is parallel to the starting participle;

[0170] If so, the second participle and the candidate participle are combined to obtain other intended phrases.

[0171] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0172] Determining a first-level search term from the multiple participles according to the part of speech of the starting participle and the dependency relationship;

[0173] If a second-level search term corresponding to the first-level search term exists in the multiple segmented words, combining the first search term and the second search term to obtain the parameter phrase;

[0174] If the second-layer search term corresponding to the first-layer search term does not exist in the multiple segmented words, the first-layer search term is determined as the parameter phrase.

[0175] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0176] If the part of speech of the starting participle is a noun, determining, among the multiple participles, a participle whose dependency relationship with the starting participle is a dependency relationship in the third dependency relationship set as the first-layer search term;

[0177] If the part of speech of the starting participle is a verb, then the participles among the multiple participles whose dependency relationship with the starting participle is a dependency relationship in the fourth dependency relationship set are determined as the first-level search terms, or nouns among the multiple participles are determined as the first-level search terms.

[0178] According to one or more embodiments of the present disclosure, the second determining module 903 is specifically configured to:

[0179] Determining a target intent phrase in an intent database based on the intent phrase, wherein the intent database includes a plurality of preset intent phrases and a preset operation type corresponding to each preset intent phrase, and the target intent phrase has the highest similarity to the intent phrase;

[0180] The preset operation type corresponding to the target intention phrase is determined as the operation type corresponding to the intention phrase.

[0181] According to one or more embodiments of the present disclosure, the processing module 904 is specifically configured to:

[0182] Generate a target script according to the operation type and the operation parameters, wherein the target script includes a code corresponding to the operation type and the parameter phrase;

[0183] The target script is executed on the first video to edit the first video to obtain a second video.

[0184] The video processing device provided in the embodiment of the present disclosure can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0185] FIG10 is a schematic diagram of the structure of a terminal device provided by an embodiment of the present disclosure. Please refer to FIG10 , which shows a schematic diagram of the structure of a terminal device 1000 suitable for implementing an embodiment of the present disclosure. The terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. The terminal device shown in FIG10 is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0186] As shown in FIG10 , terminal device 1000 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1008 into a random access memory (RAM) 1003. Various programs and data required for the operation of terminal device 1000 are also stored in RAM 1003. Processing device 1001, ROM 1002, and RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to bus 1004.

[0187] Typically, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the terminal device 1000 to communicate with other devices wirelessly or by wire to exchange data. Although FIG10 illustrates a terminal device 1000 having various devices, it should be understood that not all of the devices shown are required to be implemented or present. More or fewer devices may alternatively be implemented or present.

[0188] 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 computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0189] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, 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 that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport 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 thereof.

[0190] The computer-readable medium may be included in the terminal device, or may exist independently without being incorporated into the terminal device.

[0191] The computer-readable medium carries one or more programs. When the one or more programs are executed by the terminal device, the terminal device executes the method shown in the above embodiment.

[0192] An embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, various methods that may be involved in the above embodiments are implemented.

[0193] An embodiment of the present disclosure provides a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements various methods that may be involved in the above embodiments.

[0194] 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 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 stand-alone 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., via the Internet using an Internet Service Provider).

[0195] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two 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 box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0196] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0197] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and 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 chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0198] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can 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 can 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.

[0199] It should be noted that 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".

[0200] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0201] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0202] For example, in response to receiving an active request from the user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thereby, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server or storage medium that performs the operation of the technical solution of the present disclosure based on the prompt message. As an optional but non-limiting implementation method, in response to receiving an active request from the user, the method of sending a prompt message to the user can be, for example, a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0203] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0204] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws and regulations. Data may include information, parameters and messages, such as flow switching indication information.

[0205] In a first aspect, according to one or more embodiments of the present disclosure, the present disclosure provides a video processing method, the video processing method comprising:

[0206] Obtaining indication information corresponding to the first video, where the indication information is used to indicate an editing effect on the first video;

[0207] Determining a plurality of segmented words associated with the indication information, a part of speech of each segmented word, and dependency relationships between the plurality of segmented words;

[0208] Determining an operation type and an operation parameter associated with the editing operation based on the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words;

[0209] The first video is edited according to the operation type and the operation parameters to obtain a second video.

[0210] According to one or more embodiments of the present disclosure, determining the operation type and operation parameters associated with the editing operation based on the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words includes:

[0211] Determining a starting participle from the multiple participles based on the dependency relationship and the parts of speech of the multiple participles, where the part of speech of the starting participle is a part of speech in a preset part of speech set;

[0212] Determining the intention phrase and the parameter phrase from the multiple participles according to the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles;

[0213] The operation type is determined based on the intention phrase, and the operation parameters are determined based on the parameter phrase.

[0214] According to one or more embodiments of the present disclosure, the part of speech of the starting participle is a verb; and determining the intention phrase from the multiple participles according to the part of speech of the starting participle, the dependency relationship, and the parts of speech of the multiple participles includes:

[0215] Determining, based on the starting participle and the dependency relationship, at least one first participle whose part of speech is a noun from the multiple participles, wherein the dependency relationship between the starting participle and the first participle is a dependency relationship in a first dependency relationship set;

[0216] If the number of the first participles is 1, combining the starting participle and the first participle to obtain the intended phrase;

[0217] If the number of the first participles is greater than 1, the type of the dependency relationship between the starting participle and each first participle is obtained, and the intention phrase is determined in the multiple participles according to the type of the dependency relationship between the starting participle and each first participle.

[0218] According to one or more embodiments of the present disclosure, determining the intended phrase from the multiple participles according to the type of dependency relationship between the starting participle and each first participle includes:

[0219] Determining the priority of each first participle according to the type of dependency relationship between the starting participle and each first participle;

[0220] Determining a target word with the highest priority among the at least one first word according to the priority of each first word;

[0221] The starting participle and the target participle are combined to obtain the intended phrase.

[0222] According to one or more embodiments of the present disclosure, the starting participle is a noun; and determining the intended phrase from the multiple participles based on the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles includes:

[0223] Determining, based on the starting participle and the dependency relationship, whether there is a second participle whose part of speech is a verb among the multiple participles, wherein the dependency relationship between the starting participle and the second participle is a dependency relationship in a second dependency relationship set;

[0224] If yes, then combining the second participle and the initial participle to obtain the intended phrase;

[0225] If not, a preset participle whose part of speech is a verb is obtained, and the preset participle and the starting participle are combined to obtain the intended phrase.

[0226] According to one or more embodiments of the present disclosure, after combining the second participle and the initial participle to obtain the intended phrase, the method further includes:

[0227] According to the dependency relationship, determining whether there is a candidate participle in the plurality of participles that is parallel to the starting participle;

[0228] If so, the second participle and the candidate participle are combined to obtain other intended phrases.

[0229] According to one or more embodiments of the present disclosure, determining the parameter phrase from the multiple participles based on the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles includes:

[0230] Determining a first-level search term from the multiple participles according to the part of speech of the starting participle and the dependency relationship;

[0231] If a second-level search term corresponding to the first-level search term exists in the multiple segmented words, combining the first search term and the second search term to obtain the parameter phrase;

[0232] If the second-layer search term corresponding to the first-layer search term does not exist in the multiple segmented words, the first-layer search term is determined as the parameter phrase.

[0233] According to one or more embodiments of the present disclosure, determining a first-level search term from the multiple segmented words based on the part of speech of the starting segmented word and the dependency relationship includes:

[0234] If the part of speech of the starting participle is a noun, determining, among the multiple participles, a participle whose dependency relationship with the starting participle is a dependency relationship in the third dependency relationship set as the first-layer search term;

[0235] If the part of speech of the starting participle is a verb, then the participles among the multiple participles whose dependency relationship with the starting participle is a dependency relationship in the fourth dependency relationship set are determined as the first-level search terms, or nouns among the multiple participles are determined as the first-level search terms.

[0236] According to one or more embodiments of the present disclosure, determining the operation type based on the intention phrase includes:

[0237] Determining a target intent phrase in an intent database based on the intent phrase, wherein the intent database includes a plurality of preset intent phrases and a preset operation type corresponding to each preset intent phrase, and the target intent phrase has the highest similarity to the intent phrase;

[0238] The preset operation type corresponding to the target intention phrase is determined as the operation type corresponding to the intention phrase.

[0239] According to one or more embodiments of the present disclosure, the editing of the first video according to the operation type and the operation parameter to obtain the second video includes:

[0240] Generate a target script according to the operation type and the operation parameters, wherein the target script includes a code corresponding to the operation type and the parameter phrase;

[0241] The target script is executed on the first video to edit the first video to obtain a second video.

[0242] In a second aspect, according to one or more embodiments of the present disclosure, the present disclosure provides a video processing device, the video processing device including an acquisition module, a first determination module, a second determination module, and a processing module, wherein:

[0243] The acquisition module is used to acquire indication information corresponding to the first video, where the indication information is used to indicate the editing effect of the first video;

[0244] The first determining module is used to determine a plurality of segmented words associated with the indication information, the part of speech of each segmented word, and the dependency relationship between the plurality of segmented words;

[0245] The second determining module is configured to determine an operation type and an operation parameter associated with the editing operation based on the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words;

[0246] The processing module is used to edit the first video according to the operation type and the operation parameters to obtain a second video.

[0247] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0248] Determining a starting participle from the multiple participles based on the dependency relationship and the parts of speech of the multiple participles, where the part of speech of the starting participle is a part of speech in a preset part of speech set;

[0249] Determining the intention phrase and the parameter phrase from the multiple participles according to the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles;

[0250] The operation type is determined based on the intention phrase, and the operation parameters are determined based on the parameter phrase.

[0251] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0252] Determining, based on the starting participle and the dependency relationship, at least one first participle whose part of speech is a noun from the multiple participles, wherein the dependency relationship between the starting participle and the first participle is a dependency relationship in a first dependency relationship set;

[0253] If the number of the first participles is 1, combining the starting participle and the first participle to obtain the intended phrase;

[0254] If the number of the first participles is greater than 1, the type of the dependency relationship between the starting participle and each first participle is obtained, and the intention phrase is determined in the multiple participles according to the type of the dependency relationship between the starting participle and each first participle.

[0255] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0256] Determining the priority of each first participle according to the type of dependency relationship between the starting participle and each first participle;

[0257] Determining a target word with the highest priority among the at least one first word according to the priority of each first word;

[0258] The starting participle and the target participle are combined to obtain the intended phrase.

[0259] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0260] Determining, based on the starting participle and the dependency relationship, whether there is a second participle whose part of speech is a verb among the multiple participles, wherein the dependency relationship between the starting participle and the second participle is a dependency relationship in a second dependency relationship set;

[0261] If yes, then combining the second participle and the initial participle to obtain the intended phrase;

[0262] If not, a preset participle whose part of speech is a verb is obtained, and the preset participle and the starting participle are combined to obtain the intended phrase.

[0263] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0264] According to the dependency relationship, determining whether there is a candidate participle in the plurality of participles that is parallel to the starting participle;

[0265] If so, the second participle and the candidate participle are combined to obtain other intended phrases.

[0266] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0267] Determining a first-level search term from the multiple participles according to the part of speech of the starting participle and the dependency relationship;

[0268] If a second-level search term corresponding to the first-level search term exists in the multiple segmented words, combining the first search term and the second search term to obtain the parameter phrase;

[0269] If the second-layer search term corresponding to the first-layer search term does not exist in the multiple segmented words, the first-layer search term is determined as the parameter phrase.

[0270] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0271] If the part of speech of the starting participle is a noun, determining, among the multiple participles, a participle whose dependency relationship with the starting participle is a dependency relationship in the third dependency relationship set as the first-layer search term;

[0272] If the part of speech of the starting participle is a verb, then the participles among the multiple participles whose dependency relationship with the starting participle is a dependency relationship in the fourth dependency relationship set are determined as the first-level search terms, or nouns among the multiple participles are determined as the first-level search terms.

[0273] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0274] Determining a target intent phrase in an intent database based on the intent phrase, wherein the intent database includes a plurality of preset intent phrases and a preset operation type corresponding to each preset intent phrase, and the target intent phrase has the highest similarity to the intent phrase;

[0275] The preset operation type corresponding to the target intention phrase is determined as the operation type corresponding to the intention phrase.

[0276] According to one or more embodiments of the present disclosure, the processing module is specifically configured to:

[0277] Generate a target script according to the operation type and the operation parameters, wherein the target script includes a code corresponding to the operation type and the parameter phrase;

[0278] The target script is executed on the first video to edit the first video to obtain a second video.

[0279] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: a processor and a memory;

[0280] The memory stores computer-executable instructions;

[0281] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the video processing method as described in the first aspect and various possible aspects of the first aspect.

[0282] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the video processing method as described in the first aspect and various possible aspects of the first aspect are implemented.

[0283] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. 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 the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0284] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed 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 have been 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.

[0285] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A video processing method, comprising: Obtaining indication information corresponding to the first video, where the indication information is used to indicate an editing effect on the first video; Determining a plurality of participles associated with the indication information, a part of speech of each participle, and a dependency relationship between the plurality of participles; Determining an operation type and an operation parameter associated with the editing operation according to the part of speech of each participle, the dependency relationship between the multiple participles, and the multiple participles; The first video is edited according to the operation type and the operation parameters to obtain a second video.

2. The method according to claim 1, wherein: The step of determining the operation type and operation parameters associated with the editing operation according to the part of speech of each segmented word, the dependency relationship between the multiple segmented words, and the multiple segmented words includes: Based on the dependency relationship and the parts of speech of the multiple participles, determining a starting participle from the multiple participles, where the part of speech of the starting participle is a part of speech in a preset part of speech set; Determining an intention phrase and a parameter phrase in the multiple participles according to the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles; Based on the intent phrase, the operation type is determined, and based on the parameter phrase, the operation parameters are determined.

3. The method according to claim 2, wherein: The part of speech of the starting participle is a verb; and according to the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles, determining the intended phrase from the multiple participles comprises: According to the starting participle and the dependency relationship, determining at least one first participle whose part of speech is a noun from among the multiple participles, wherein the dependency relationship between the starting participle and the first participle is a dependency relationship in a first dependency relationship set; If the number of the first participle is 1, the starting participle and the first participle are combined to obtain the intended phrase; If the number of the first participles is greater than 1, the type of dependency relationship between the starting participle and each first participle is obtained, and the intended phrase is determined in the multiple participles according to the type of dependency relationship between the starting participle and each first participle.

4. The method according to claim 3, wherein: Determining the intended phrase from the plurality of participles according to the type of dependency relationship between the starting participle and each first participle includes: Determining the priority of each first participle according to the type of dependency relationship between the starting participle and each first participle; According to the priority of each first participle, determining a target participle with the highest priority among the at least one first participle; The starting participle and the target participle are combined to obtain the intended phrase.

5. The method according to claim 2, wherein: The starting participle is a noun; and according to the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles, determining the intended phrase from the multiple participles comprises: According to the starting participle and the dependency relationship, determining whether there is a second participle whose part of speech is a verb among the multiple participles, wherein the dependency relationship between the starting participle and the second participle is a dependency relationship in a second dependency relationship set; If yes, then combine the second participle and the initial participle to obtain the intended phrase; If not, a preset participle whose part of speech is a verb is obtained, and the preset participle and the starting participle are combined to obtain the intended phrase.

6. The method according to claim 5, wherein: After combining the second participle and the initial participle to obtain the intended phrase, the method further includes: According to the dependency relationship, determining whether there is a candidate participle in the plurality of participles that is parallel to the starting participle; If so, the second participle and the candidate participle are combined to obtain other intended phrases.

7. The method according to any one of claims 2 to 5, wherein: Determining the parameter phrase from the multiple participles according to the part of speech of the starting participle, the dependency relationship, and the part of speech of the multiple participles includes: Determining a first-level search term from the plurality of participles according to the part of speech of the starting participle and the dependency relationship; If there is a second-level search word corresponding to the first-level search word in the multiple word segments, combining the first search word and the second search word to obtain the parameter phrase; If there is no second-layer search term corresponding to the first-layer search term in the multiple segmented words, the first-layer search term is determined as the parameter phrase.

8. The method according to claim 7, wherein: Determining a first-level search term from the plurality of segmented words according to the part of speech of the starting segmented word and the dependency relationship includes: If the part of speech of the starting participle is a noun, determining, among the multiple participles, a participle whose dependency relationship with the starting participle is a dependency relationship in the third dependency relationship set as the first-layer search term; If the part of speech of the starting participle is a verb, then the participle among the multiple participles whose dependency relationship with the starting participle is a dependency relationship in the fourth dependency relationship set is determined as the first-level search term, or the noun among the multiple participles is determined as the first-level search term.

9. The method according to any one of claims 2 to 5, wherein: The determining the operation type based on the intention phrase includes: According to the intention phrase, determining a target intention phrase in an intention database, wherein the intention database includes a plurality of preset intention phrases and a preset operation type corresponding to each preset intention phrase, and the target intention phrase has the highest similarity to the intention phrase; The preset operation type corresponding to the target intention phrase is determined as the operation type corresponding to the intention phrase.

10. The method according to any one of claims 1 to 5, wherein: The editing process of the first video according to the operation type and the operation parameter to obtain the second video includes: Generate a target script according to the operation type and the operation parameter, wherein the target script includes a code corresponding to the operation type and the parameter phrase; The target script is executed on the first video to edit the first video to obtain a second video.

11. A video processing device, comprising: An acquisition module, a first determination module, a second determination module and a processing module, wherein: The acquisition module is used to acquire indication information corresponding to the first video, where the indication information is used to indicate the editing effect on the first video; The first determination module is used to determine a plurality of segmented words associated with the indication information, the part of speech of each segmented word, and the dependency relationship between the plurality of segmented words; The second determining module is used to determine the part of speech of each segmentation and the dependencies between the multiple segmentations. The storage relationship and the plurality of participles are used to determine an operation type and an operation parameter associated with the editing operation; The processing module is used to edit the first video according to the operation type and the operation parameters to obtain a second video.

12. A terminal device, comprising: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the video processing method according to any one of claims 1 to 10.

13. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the video processing method according to any one of claims 1 to 10 is implemented.

Images