Video processing method, device and terminal equipment

Abstract

The present disclosure provides a video processing method, device and terminal equipment, the method comprising: obtaining indication information corresponding to a first video, the indication information being used to indicate an editing effect of the first video; determining a plurality of words, a part of speech of each word, and a dependency relationship between the plurality of words associated with the indication information; determining an operation type and an operation parameter associated with the editing operation according to the part of speech of each word, the dependency relationship between the plurality of words, and the plurality of words; and editing the first video according to the operation type and the operation parameter to obtain a second video. The accuracy of video editing is improved.

Description

Technical Field

[0001] This disclosure relates to the field of video processing technology, and in particular to a video processing method, apparatus, and terminal device. Background Technology

[0002] Users can input natural language text into the terminal device. The terminal device can parse the natural language text to determine the specific editing operation described by the natural language text and perform the editing operation on the video.

[0003] Currently, terminal devices can identify named entities in natural language text and determine the corresponding editing operation based on the correspondence between named entities and editing operations. However, the above methods can only identify single editing operations and simple natural language text, and cannot accurately identify complex editing operations, resulting in low accuracy in video editing. Summary of the Invention

[0004] This disclosure provides a video processing method, apparatus, and terminal device to solve the technical problem of low accuracy in video editing in the prior art.

[0005] In a first aspect, embodiments of this disclosure provide a video processing method, the method comprising:

[0006] Obtain the instruction information corresponding to the first video, the instruction information being used to indicate the editing effect on the first video;

[0007] Determine the multiple word segments associated with the indicated information, the part-of-speech tag of each word, and the dependency relationships between the multiple word segments;

[0008] Based on the part-of-speech of each word, the dependency relationships between the multiple words, and the multiple words, determine the operation type and operation parameters associated with the editing operation;

[0009] Based on the operation type and the operation parameters, the first video is edited to obtain the second video.

[0010] Secondly, this disclosure provides a video processing apparatus, which includes an acquisition module, a first determination module, a second determination module, and a processing module, wherein:

[0011] The acquisition module is used to acquire indication information corresponding to the first video, and the indication information is used to indicate the editing effect on the first video;

[0012] The first determining module is used to determine multiple word segments associated with the indication information, the part-of-speech tag of each word segment, and the dependency relationships between the multiple word segments;

[0013] The second determining module is used to determine the operation type and operation parameters associated with the editing operation based on the part-of-speech of each word, the dependency relationship between the multiple words, and the multiple words.

[0014] The processing module is used to edit the first video according to the operation type and the operation parameters to obtain the second video.

[0015] Thirdly, embodiments of this disclosure provide an electronic device including: a processor and a memory;

[0016] The memory stores computer-executed instructions;

[0017] The processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the video processing methods described in the first aspect above and various possible aspects of the first aspect.

[0018] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the video processing methods described in the first aspect and various possible aspects thereof.

[0019] This disclosure provides a video processing method, apparatus, and terminal device. The terminal device can acquire instruction information corresponding to a first video, wherein the instruction information is used to indicate the editing effect of the first video. The method determines multiple word segments associated with the instruction information, the part-of-speech tag of each word, and the dependency relationships between the multiple word segments. Based on the part-of-speech tag of each word, the dependency relationships between the multiple word segments, and the multiple word segments, the method determines the operation type and operation parameters associated with the editing operation. Based on the operation type and operation parameters, the first video is edited to obtain a second video. In the above method, because the terminal device can analyze the part-of-speech tag of each word in the edited text and the dependency relationships between the word segments, it can accurately determine the operation type and operation parameters associated with the instruction information, thereby improving the accuracy of the determined editing operation and the accuracy of video editing. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0022] Figure 2 A flowchart illustrating a video processing method provided in an embodiment of this disclosure;

[0023] Figure 3 This is a schematic diagram illustrating a process for determining a first video according to an embodiment of the present disclosure;

[0024] Figure 4 A schematic diagram illustrating the determination of dependency relationships provided in an embodiment of this disclosure;

[0025] Figure 5 A schematic diagram of an intent database provided for an embodiment of this disclosure;

[0026] Figure 6 This is a schematic diagram illustrating a process for determining a second video according to an embodiment of the present disclosure;

[0027] Figure 7 This is a schematic diagram illustrating a method for determining an intent phrase provided in an embodiment of the present disclosure;

[0028] Figure 8 A schematic diagram illustrating another method for determining an intent phrase provided in an embodiment of this disclosure;

[0029] Figure 9 This is a schematic diagram of the structure of a video processing apparatus provided in an embodiment of the present disclosure;

[0030] Figure 10 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this disclosure. Detailed Implementation

[0031] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0032] For ease of understanding, the concepts involved in the embodiments of this disclosure will be explained below.

[0033] Terminal equipment: A device with wireless transceiver capabilities. Terminal equipment can be deployed on land, including indoors or outdoors, handheld, wearable, or vehicle-mounted. The terminal equipment can be a mobile phone, tablet, computer with wireless transceiver capabilities, virtual reality (VR) terminal equipment, augmented reality (AR) terminal equipment, wireless terminals in industrial control, vehicle-mounted terminal equipment, wireless terminals in self-driving vehicles, wireless terminal equipment in remote medical care, wireless terminal equipment in smart grids, wireless terminal equipment in transportation safety, wireless terminal equipment in smart cities, wireless terminal equipment in smart homes, wearable terminal equipment, etc. The terminal equipment involved in the embodiments of this disclosure can also be referred to as a terminal, user equipment (UE), access terminal equipment, vehicle-mounted terminal, industrial control terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal equipment, mobile device, UE terminal equipment, wireless communication equipment, UE agent, or UE device, etc. Terminal devices can be fixed or mobile.

[0034] Below, in conjunction with Figure 1 The application scenarios of the embodiments of this disclosure will be described.

[0035] Figure 1 This is a schematic diagram illustrating an application scenario provided by an embodiment of this disclosure. Please refer to [link / reference]. Figure 1 This includes a terminal device. The terminal device's display page can be a video editing page, containing the video to be edited, with background music "Music A". When a user inputs the text "Change the background music of the video to Music B" into the terminal device, the terminal device can determine that the corresponding editing function is "Replace Background Music", the editing object is the video, the editing parameter is Music B, and based on this information, it edits the video to obtain a new video. The video content of this new video is the same as the original video, and the background music is Music B. In this way, the terminal device can perform video editing operations based on user-inputted voice or text, improving editing efficiency and reducing the complexity of editing operations.

[0036] It should be noted that, Figure 1 This is merely an illustrative representation of the application scenarios of the embodiments of this disclosure and is not intended to limit the application scenarios of the embodiments of this disclosure.

[0037] In related technologies, terminal devices can convert user-input natural language text into corresponding editing operations and then edit videos based on these operations. Currently, terminal devices can identify named entities in natural language text and determine the corresponding editing operations based on the correspondence between named entities and editing operations. For example, if a user inputs: "Add a cyan-orange filter to the second video," the terminal device can identify named entities including: "add filter," "second video," and "cyan-orange," and obtain the editing operation based on the category of each named entity. Specifically, this editing operation could be: function: add filter, object: second video, parameter: cyan-orange. The terminal device can then perform the corresponding editing operation on the video. However, the above method can only recognize single, simple editing operations. If the user-input natural language text includes multiple editing operations, or if the natural language text is highly complex, the terminal device cannot accurately identify the corresponding editing operations, leading to lower accuracy in video editing.

[0038] To address the technical problems in related technologies, this disclosure provides a video processing method. A terminal device can acquire instruction information corresponding to a first video and determine multiple word segments associated with the instruction information, the part-of-speech tag of each segment, and the dependency relationships between the multiple segment segments. Based on the dependency relationships and the part-of-speech tags of the multiple segment segments, the terminal device can determine a starting segment among the multiple segment segments. Based on the part-of-speech tag of the starting segment segment, the dependency relationships, and the part-of-speech tags of the multiple segment segments, the terminal device can determine an intent phrase and a parameter phrase among the multiple segment segments. Based on the intent phrase, the terminal device can determine the operation type, and based on the parameter phrase, the terminal device can determine the operation parameters. The terminal device can then edit the first video according to the operation type and operation parameters to obtain a second video. In this method, because the terminal device can accurately identify the operation type and operation parameters corresponding to the editing operation described by the instruction information based on the part-of-speech tag of each segment segment and the dependency relationships between the multiple segment segments, the terminal device can accurately determine the editing effect described by the instruction information, thereby improving the accuracy of video editing.

[0039] The technical solutions of this disclosure and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this disclosure will now be described with reference to the accompanying drawings.

[0040] Figure 2 This is a schematic flowchart illustrating a video processing method provided in an embodiment of this disclosure. Please refer to [link / reference]. Figure 2 The method may include:

[0041] S201. Obtain the instruction information corresponding to the first video.

[0042] The execution entity of this disclosure can be a terminal device or a video processing device installed in the terminal device. The video processing device can be implemented in software, or it can be implemented using a combination of software and hardware; this disclosure does not limit this approach.

[0043] The first video can be the video to be edited. For example, if the user's requirement is to add sticker effects to video A, then the first video can be video A; if the user's requirement is to replace the background music in video B, then the first video can be video B.

[0044] Optionally, the terminal device can determine the first video based on user input. For example, a user can open a video editing application on the terminal device and add a corresponding video in the application; this video can be the first video.

[0045] Optionally, the terminal device can receive a first video sent by another device. For example, the database can pre-store multiple videos to be edited, and the terminal device can retrieve any one of the videos from the database to obtain the first video.

[0046] Below, in conjunction with Figure 3 The process of determining the first video by the terminal device is explained.

[0047] Figure 3 This is a schematic diagram illustrating a process for determining a first video according to an embodiment of this disclosure. Please refer to [link / reference]. Figure 3 This includes terminal devices. The display pages on the terminal devices include pages 301, 302, and 303. Page 301 is the application display page for the terminal devices, and may include a video editing application. When the user clicks on the video editing application, the display page on the terminal devices jumps from page 301 to page 302.

[0048] Please see Figure 3 Page 302 can be the page for a video editing application. Page 302 may include controls for starting creation, draft video 1, draft video 2, draft video 3, and draft video 4 (draft videos can be unfinished videos). When the user clicks the control to start creation, the terminal device's display page jumps from page 302 to page 303.

[0049] Please see Figure 3Page 303 can be a video page, which may include videos A, B, C, D, E, and F. When the user clicks on video A, the selection control for video A is highlighted, and the terminal device can select video A as the first video. It should be noted that if the user clicks on draft video 1 on page 302, the terminal device does not need to navigate to page 303; the terminal device can select draft video 1 as the first video.

[0050] The instruction information is used to indicate the editing effect on the first video. For example, the instruction information can be voice, text, or video, etc., and this embodiment of the disclosure is not limited to this. 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: add cartoon stickers to the second segment of the video, add cheerful background music to the video, add a fresh and bright filter to the third segment of the video, etc.

[0051] It should be noted that the instruction information can be associated with natural language text describing the editing operation. However, the terminal device can only determine the editing operation corresponding to the instruction information after recognizing the natural language text.

[0052] Optionally, the terminal device can determine the edited text input by the user as instruction information, or the terminal device can determine the voice input by the user as instruction information (after receiving the user's voice, the terminal device can convert the voice into text based on speech recognition technology), or the terminal device can receive instruction information sent by other devices (such as servers, etc.). This disclosure embodiment does not limit this.

[0053] S202, determine the multiple segments associated with the instruction information, the part of speech of each segment, and the dependency relationships between the multiple segments.

[0054] Optionally, after receiving the instruction information, the terminal device can convert the instruction information into editable text associated with natural language. Based on this editable text, it can then determine multiple word segments associated with the instruction information, the part-of-speech tag of each segment, and the dependency relationships between the multiple word segments. For example, if the instruction information is text, the terminal device can directly determine multiple word segments, the part-of-speech tag of each segment, and the dependency relationships between the multiple word segments from the instruction information. If the instruction information is speech, the terminal device can first convert the speech into text, and then determine multiple word segments, the part-of-speech tag of each segment, and the dependency relationships between the multiple word segments from the text.

[0055] Optionally, the word segmentation can be words in the edit text associated with the instruction information. For example, if the edit text associated with the instruction information is: "Background music replaced with cheerful music", then the word segmentation in the edit text can include: background music, replace, cheerful, music.

[0056] Optionally, the terminal device can determine multiple word segments in the edited text associated with the instruction information based on named entity recognition. For example, the terminal device can process the edited text associated with the instruction information using any named entity recognition algorithm or model, thereby obtaining multiple word segments in the edited text.

[0057] Optionally, the terminal device can pre-acquire a word segmentation lexicon, which may include multiple word segments. The terminal device can perform matching operations between the edited text associated with the instruction information and the multiple word segments in the lexicon, thereby improving the accuracy of word segmentation of the edited text. For example, in practical applications, specific fields often have some proper nouns and proper operations. Named entity recognition algorithms cannot accurately identify proper nouns and proper operations. Therefore, the terminal device can pre-store multiple proper nouns and proper operation terms in the word segmentation lexicon, thereby improving the accuracy of word segmentation. For example, proper operation terms may include: cutout, beautification, etc., and proper nouns may include: sticker name, filter name, song name, singer name, etc. This embodiment of the disclosure does not limit this. For example, the terminal device can obtain the above-mentioned professional terms and professional operation terms from the audio and video editing material library and the function table of editing operations. The terminal device can also obtain the above-mentioned professional terms and professional operation terms based on knowledge graphs. This embodiment of the disclosure does not limit this.

[0058] Part of speech can refer to the characteristics of a word as the basis for classifying words. For example, parts of speech can include nouns, verbs, adjectives, conjunctions, adverbs, and interjections, etc., but this embodiment does not limit this.

[0059] It should be noted that after the terminal device determines the multiple word segments associated with the indication information, it can determine the part-of-speech of each word based on any feasible implementation method. This embodiment of the disclosure does not limit this.

[0060] Optionally, dependency can refer to the relationship between words. For example, the dependency between word 1 and word 2 can be an adjectival modifier (amod) that modifies a noun phrase, or it can be two words connected by a coordinating conjunction (such as "and" or "or").

[0061] It should be noted that the above examples are only exemplary to illustrate the dependency relationships between words, and do not limit the dependency relationships of the embodiments of the present disclosure. Among them, there are many dependency relationships between words, and the embodiments of the present disclosure will not elaborate here.

[0062] Optionally, the terminal device may determine the dependency relationships between multiple word segments associated with the indication information based on any feasible implementation manner (such as, based on models, algorithms, etc.), and the embodiments of the present disclosure do not limit this.

[0063] Next, in combination with Figure 4 , the process of determining multiple word segments associated with the indication information, the word nature of each word segment, and the dependency relationships between multiple word segments will be described.

[0064] Figure 4 It is a schematic diagram of determining dependency relationships provided by the embodiments of the present disclosure. Please refer to Figure 4 , including: text. Among them, the text may be: adding music and sound effects. The terminal device ( Figure 4 not shown) may segment the text, and the multiple word segments obtained include: adding, music, and, sound effects. Among them, the word nature of adding is a verb, the word natures of music and sound effects are nouns, and the word nature of and is a conjunction. The terminal device may determine that the dependency relationship of adding is the root node in the text, the dependency relationship between music and sound effects is a parallel relationship, the dependency relationship between adding and music is a verb-direct object relationship, and the dependency relationship between adding and sound effects is a verb-direct object relationship.

[0065] S203. Determine the operation type and operation parameters associated with the editing operation according to the word nature of each word segment, the dependency relationships between multiple word segments, and the multiple word segments.

[0066] Among them, the operation type may indicate the operation intention associated with the editing operation. For example, if the operation type is the type of replacing the background music, the user's editing intention for the video is to replace the background music in the video.

[0067] Among them, the operation parameter may be a parameter corresponding to the operation type. For example, if the operation type is the type of replacing the background music, the operation parameter may be the name of the music.

[0068] Among them, the terminal device may determine the intention phrase and parameter phrase associated with the editing operation in multiple word segments based on the following feasible implementation manner: based on the dependency relationship and the word nature of multiple word segments, determine the starting word segment in multiple word segments, and according to the word nature of the starting word segment, the dependency relationship, and the word nature of multiple word segments, determine the intention phrase and parameter phrase in multiple word segments, determine the operation type based on the intention phrase, and determine the operation parameter based on the parameter phrase.

[0069] The intent phrase can indicate the type of editing operation. For example, the intent phrase can be: "Change background music", which corresponds to the operation type of replacing background music; the intent phrase can be: "Change filter", which corresponds to the operation type of replacing filter; the intent phrase can be: "Add sticker", which corresponds to the operation type of adding sticker.

[0070] The parameter phrases can indicate the operation parameters corresponding to the operation type. For example, if the instruction is: "Replace background music with music 1", then the intent phrase in this instruction can be: "Background music replacement", and the parameter phrase can be: "music 1". That is, the operation parameter corresponding to the operation type of replacing background music is "music 1". For example, if the operation type is adding a filter, then the parameter phrase can be: "bright, orange". That is, the editing operation can be: "Add a bright, orange filter", where "bright" and "orange" are the operation parameters for this editing operation.

[0071] The part of speech of the starting segment is determined by a preset set of parts of speech. For example, the preset set of parts of speech may include verbs, nouns, and proper nouns. For example, the starting segment may be a verb such as "add" or "replace," a noun such as "music" or "sound effects," or a proper noun such as "filter" or "cutout."

[0072] The terminal device can determine the starting segment from multiple segmented words based on the following feasible implementation: Segments with pre-defined dependency relationships (e.g., dependency relationships that the system cannot recognize, such as `dep`, verb-direct object dependency relationships, and semantically significant word dependency relationships, such as `ccomp`), and whose head word is the root node (i.e., the segment whose `head` is the root node), are considered as candidates for the starting segment. For example, if the `head` of a segment is the root node (if the segment is the first segment of the edited text, then its dependency relationship is the root node), and the dependency relationship between this segment and the root node segment is a verb-direct object dependency relationship, then the terminal device can consider this segment as a candidate for the starting segment.

[0073] If the part-of-speech tag of the root node's segment matches a predefined part-of-speech tag set, then the root node's segment is determined as the starting segment. If the part-of-speech tag of the root node's segment does not match a predefined part-of-speech tag set, then the starting segment is determined from the candidate starting segments. For example, if the root node's segment is "add," then the part-of-speech tag of this segment is a verb, and the terminal device can determine the starting segment as "add." If the root node's segment is "help," then the part-of-speech tag of this segment is not a predefined part-of-speech tag set; therefore, the terminal device can determine the starting segment from the candidate starting segments.

[0074] For example, if the instruction message is the text: "Quickly add background music", then the root node of this text is "Quickly", and the candidate starting segment is "add" and "background music". Since the part of speech of the root node is not a noun, verb, or proper noun, the terminal device can determine the first segment in the candidate starting segment as "add" as the starting segment of the instruction message.

[0075] Optionally, if the starting segment is the root node, the terminal device can determine that the segment in the instruction information has a parallel dependency relationship with the root node, and that the segment with the part of speech is a verb or preposition is also determined as the starting segment. For example, if the instruction information is "add music and change timbre", then the root in the instruction information is "add". Since the dependency relationship between the segment "change" and the segment "add" is parallel, the terminal device can determine that the starting segment corresponding to the instruction information is: "add" and "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.

[0076] Optionally, after determining the starting segment, the terminal device can determine the intent phrase and parameter phrase from the multiple segmentations based on the part-of-speech of the starting segment, the dependency relationships between multiple segmentations, and the part-of-speech of the multiple segmentations. For example, if the part-of-speech of the starting segment is a verb, it means that the terminal device has determined the action of the editing operation corresponding to the instruction information. The terminal device also needs to determine the segment used to assist in describing the operation type from the multiple segmentations based on the dependency relationships and the part-of-speech of the multiple segmentations. Then, it can be combined with the starting segment to obtain the intent phrase describing the editing operation. For example, if the instruction information is "add music", the starting segment in this text is "add", and "music" can be information that assists in describing the operation type. Therefore, the intent phrase of this text can be "add music", that is, the operation type is "add music".

[0077] Optionally, embodiments of this disclosure may determine the parameter phrase based on the following feasible implementation: determining a first-level search term among multiple word segments according to the part-of-speech and dependency relationship of the initial word segment; if a second-level search term corresponding to the first-level search term exists among multiple word segments, then combining the first search term and the second search term to obtain the parameter phrase; if a second-level search term corresponding to the first-level search term does not exist among multiple word segments, then determining the first-level search term as the parameter phrase.

[0078] The search terms are used to describe the operation parameters corresponding to the editing operation. For example, search terms can be bright, orange, cheerful, music names, sound effect names, and sticker names, etc., and this embodiment does not limit them.

[0079] In this process, the terminal device determines the first-level search term from multiple word segments based on the part-of-speech and dependency relationships of the initial word segment. There are two possible scenarios:

[0080] Case 1: The part of speech of the initial segment is a noun.

[0081] If the starting segment is a noun, then the segment whose dependency relationship with the starting segment is a dependency relationship from the third dependency relationship set is identified as the first-level search term. For example, the third dependency relationship set may include dependency relationships such as adjective modifiers (amod) that modify noun phrases, and semantically significant word dependency relationships (ccomp). For instance, if the instruction is to change the background music to music A, and the starting segment is "background music" (a noun), then the first-level search term could be "music A" (dependency relationship ccomp).

[0082] Case 2: The part of speech of the initial segment is a verb.

[0083] If the starting segment is a verb, then the segment whose dependency relationship with the starting segment is a dependency relationship in the fourth dependency relationship set is identified as the first-level search term. Alternatively, nouns among the multiple segmentations can be identified as first-level search terms. For example, the fourth dependency relationship set may include dependency relationships with nominal subjects (nsubj) and direct objects (dobj). For instance, if the instruction is "add cheerful music," and the starting segment is "add," which is a verb, then the first-level search term could be "cheerful," meaning the intention phrase of the instruction is "add music," and the parameter phrase is "cheerful."

[0084] Optionally, if the part of speech of the starting word is a verb, the terminal device can determine the nouns from the multiple word segments as the first-level search terms. For example, the instruction information can be the effect of adding a sun sticker, where the starting word is "add" and is a verb. Therefore, the first-level search term can be "sun sticker". That is, the intent phrase of the instruction information is "add effect" and the parameter phrase is "sun sticker".

[0085] Optionally, after determining the first search term from multiple word segments, the terminal device can also determine whether a second search term exists in the instruction information. The terminal device can determine the second-level search term based on word segments where the dependency relation is in the fifth dependency relation set, with "head" as the first search term. For example, the fifth dependency relation set may include: dependency relations of adjective modifiers modifying noun phrases (amod) and dependency relations of adverbs that are not clauses (adverb modifier, advmod). For example, if the instruction information is "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 "particularly bright."

[0086] Optionally, after determining the first-level search term, if a second-level search term exists, the terminal device combines the first-level and second-level search terms to obtain a parameter phrase. For example, if the first-level search term is "bright" and the second-level search term is "especially", the terminal device can determine the parameter phrase as "especially bright".

[0087] Optionally, if the instruction information does not contain a second-level search term, the terminal device can determine the first-level search term as the parameter phrase after obtaining it. For example, if the instruction information is to change "background music" to "music 1", the terminal device can determine that the starting word segmentation is "background music", and thus determine that the first-level search term is "music 1". Since there is no second-level search term, the terminal device can determine that the parameter phrase is "music 1".

[0088] It should be noted that if an intent phrase does not have a corresponding parameter phrase, the terminal device can determine whether there is a parallel intent phrase. If so, the parameter phrase corresponding to the parallel intent phrase is determined as the parameter phrase corresponding to this intent phrase. For example, if the instruction is to add cheerful music and sound effects, the terminal device can determine that the starting word segment is "add". Since music and sound effects are parallel, the terminal device can obtain intent phrase 1 as "add music" and intent phrase 2 as "add sound effects". Among them, the parameter phrase corresponding to intent phrase 1 is "cheerful". Intent phrase 2 does not have a parameter phrase. However, since music in intent phrase 1 and sound effects in intent phrase 2 are parallel, the terminal device can determine that the parameter phrase corresponding to intent phrase 2 is also "cheerful".

[0089] It should be noted that for English search terms, in the form of the English text "change the music with sth", the terminal device can identify the word after the preposition as the search term.

[0090] Optionally, the terminal device determines the operation type based on the intent phrase. Specifically, it can be done by: determining the target intent phrase in the intent database according to the intent phrase, and determining the preset operation type corresponding to the target intent phrase as the operation type corresponding to the intent phrase.

[0091] The intent database can include multiple preset intent phrases and a preset operation type corresponding to each preset intent phrase. For example, for the operation type of changing background music, the preset intent phrases corresponding to this operation type can be phrases such as: replace background music, change background music, and change background music.

[0092] Below, in conjunction with Figure 5 This section provides an explanation of the intent database.

[0093] Figure 5 This is a schematic diagram of an intent database provided in an embodiment of this disclosure. Please refer to [link / reference]. Figure 5 This 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 are: phrase A, phrase B, and phrase C; that is, phrases A, B, and C all describe operation type 1. The intent phrases corresponding to operation type 2 are: phrase D, phrase E, and phrase F; that is, phrases D, E, and F all describe operation type 2. The intent phrases corresponding to operation type 3 are: phrase G, phrase H, and phrase I; that is, phrases G, H, and I all describe operation type 3.

[0094] It should be noted that, Figure 5 This is merely an illustrative representation of the intent database in this embodiment and is not intended to limit the intent database. In actual applications, the intent database may include multiple preset operation types, and each preset operation type may correspond to multiple phrases.

[0095] Optionally, the terminal device can obtain preset operation types from 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 can also include adding filters and adding music.

[0096] Optionally, after determining the preset operation type, the terminal device can generate preset intent phrases corresponding to the preset operation type based on a large language model. For example, if the terminal device determines that the preset operation type is adding a filter, it can generate multiple phrases describing the operation of adding a filter (add filter, add a filter, etc.) based on the large language model. This can improve the accuracy of determining the editing operation and thus improve the accuracy of video editing.

[0097] Among them, the target intent phrase has the highest similarity to the intent phrase. For example, the terminal device can determine the text similarity between the intent phrase associated with the instruction information and each preset intent phrase in the intent database, and then identify the preset intent phrase with the highest text similarity as the target intent phrase. For example, if the intent phrase associated with the instruction information is "background music change", and the preset intent phrases in the intent database include "background music replacement" and "add sticker", then the terminal device can determine that the target intent phrase in the intent database is "background music replacement" (which has the highest text similarity to "background music replacement").

[0098] Optionally, after determining the target intent phrase, the terminal device can set 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 this target intent phrase is "replace music type", then the operation type corresponding to the intent phrase (change background music to) associated with the instruction information is also "replace music type".

[0099] Optionally, after determining the parameter phrase, the terminal device can define the operation phrase as the operation parameter associated with the editing operation. For example, if the parameter phrase is "Music 1", then the operation parameter is "Music 1"; if the parameter phrase is "Music 2", then the operation parameter is "Music 2"; if the parameter phrase is "Special, Bright, Orange", then the operation parameter is "Special, Bright, Orange".

[0100] S204. Based on the operation type and operation parameters, edit the first video to obtain the second video.

[0101] 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 and process the first video, and obtain the second video.

[0102] The target script includes the code corresponding to the operation type and the parameter phrase. For example, if the intent phrase is "change background music" and the parameter phrase is "upbeat music", the terminal device can determine the operation type corresponding to the intent phrase as "replace music type" based on the intent database, and determine the operation parameter corresponding to the replacement music type as "upbeat music" based on the parameter phrase. Therefore, the terminal device can generate the target script: ReplaceMusic(code corresponding to operation type)({keyword: upbeat music}).

[0103] Optionally, after obtaining the target script, the terminal device can execute the target script to edit the first video and obtain the second video. For example, if the target script is ReplaceMusic({keyword: upbeat music}), the terminal device can replace the background music of the video with upbeat music.

[0104] It should be noted that in this embodiment, some editing operations cannot be recognized. For example, the number of operation types corresponding to the instruction information is less than the number of sentences, and the number of operation types is greater than 1 (e.g., add a sticker, make it funny, add a summer filter). 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, if the number of operation types corresponding to the edited text is 1, and the number of sentences is 2, in this case, the user uses multiple sentences to modify the operation type. To avoid errors, the terminal device will also stop editing the first video.

[0105] It should be noted that in this embodiment of the disclosure, the number of initial word segments is related to the number of intent phrases. For example, if the terminal device determines that the number of initial word segments in the instruction information is 2, the terminal device can generate 2 intent phrases, and the instruction information corresponds to 2 operation types.

[0106] It should be noted that, in the process of determining the similarity between the intent phrase and the preset intent phrases in the intent database, the terminal device can call the embedding service to recall the 10 candidates with the highest similarity among 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 instruction information is less than a preset threshold, the terminal device determines that the instruction information does not have an operation type of editing operation, and the terminal device stops editing the first video.

[0107] It should be noted that when the terminal device generates the target script, it can obtain the script template of the operation type corresponding to the intent phrase in the instruction information in advance, 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 can fill the corresponding operation parameters into the corresponding script template to obtain the target script).

[0108] Below, in conjunction with Figure 6 This paper describes the process by which a terminal device edits and processes the first video based on the operation type and operation parameters to obtain the second video.

[0109] Figure 6 This is a schematic diagram illustrating a process for determining a second video according to an embodiment of this disclosure. Please refer to [link / reference]. Figure 6It includes: a first video, an intent database, parameter phrases, and intent phrases. The background music of the first video is "Music A," the parameter phrase is "Music B," and the intent phrase is "Change background music." The intent database includes operation types for replacing music and adding filters. The phrases corresponding to the music replacement operation type are "Background music replacement" and "Music change," while the phrases corresponding to the filter addition operation type are "Add new filter" and "Add a filter."

[0110] Please see Figure 6 Because the intent phrase has the highest text similarity to "background music replacement," 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. (Terminal device) Figure 6 (Not shown) A target script can be generated based on the operation type of replacing music and music B (operation parameter): Replace Music ({keyword: music B}). The terminal device can execute this target script to generate a second video, wherein the video content of the second video is the same as that 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 effect corresponding to the edited text, and then combine it with the operation parameters to perform editing operations on the first video, thereby improving the accuracy of video editing.

[0111] It should be noted that, in this embodiment of the disclosure, after the terminal device obtains the instruction information, it can further supplement the instruction information. For example, if the instruction information does not contain a noun but has a music title 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."

[0112] For example, if the instruction includes the meaning of ratio, the terminal device can add the text "ratio" to the instruction. For example, if the instruction is: Adjust the video size to 9:16, the terminal device can supplement the instruction to: Adjust the video size to a 9:16 ratio.

[0113] For example, when the instruction message includes subtitles, the terminal device needs to distinguish whether it contains parameters mapped to different scenarios. For instance, if the instruction message is: "Add English and Chinese subtitles," the terminal device can recognize that the language words in the instruction message are English and Chinese. Therefore, the terminal device can modify the intention phrase "add subtitles" to "add bilingual subtitles."

[0114] For example, after the terminal device segments the instruction information, if the segmented words include words such as "fast" and "slow," and the part of speech of the segmented words is an interjection, then when determining the operation type corresponding to the intent phrase, the terminal device can process it based on whether it is faster or slower. For example, if the number of intent phrases is less than 3, and the intent phrases are fast, slow, or multiplied speed, the terminal device can modify the intent phrases to: faster, slower, or 3x speed.

[0115] It should be noted that after the terminal device determines the target script, if the instruction information contains a scope word, the terminal device can treat the scope word as a separate parameter and only take the first segment that meets the condition. For example, the scope word can be "all" or "whole". When determining the scope word, the terminal device can prioritize obtaining the scope word that modifies nouns, and then obtain the scope word that modifies verbs.

[0116] It should be noted that after the terminal device determines the target script, if the instruction information contains action modifiers, the terminal device can treat the action modifiers as separate parameters. For example, action modifiers can be picture-in-picture, arbitrary fragment, etc.

[0117] This disclosure provides a video processing method. A terminal device can acquire instruction information corresponding to a first video and determine multiple word segments associated with the instruction information, the part-of-speech tag of each word, and the dependency relationships between the multiple word segments. Based on the dependency relationships and the part-of-speech tags of the multiple word segments, the terminal device can determine a starting word among the multiple word segments. Based on the part-of-speech tag of the starting word, the dependency relationships, and the part-of-speech tags of the multiple word segments, the terminal device can determine an intent phrase and a parameter phrase among the multiple word segments. Based on the intent phrase, the terminal device can determine the operation type and the parameter phrase as the operation parameter. The terminal device can then edit the first video according to the operation type and the operation parameter to obtain a second video. Thus, because the terminal device can accurately identify the editing effect described by the instruction information based on the part-of-speech tag of each word and the dependency relationships between the multiple word segments, the terminal device can accurately determine the editing operation, thereby improving the accuracy of video editing.

[0118] exist Figure 2 In the illustrated embodiment, the video processing method described above determines the intent phrase from multiple segmented words based on the part-of-speech, dependency relationships, and the part-of-speech of the initial segmented word. There are two scenarios, which will be discussed below in conjunction with... Figures 7-8 This section explains two cases of determining the intent phrase.

[0119] Figure 7 This is a schematic diagram illustrating a method for determining an intent phrase provided in an embodiment of this disclosure. Figure 7 In the example shown, the part of speech of the initial word segment is a verb. Please refer to [link to example]. Figure 7 The method process includes:

[0120] S701. Based on the initial segmentation and dependency relationship, determine at least one first segmentation with a noun part of speech among multiple segmentations.

[0121] The dependency relationship between the starting segment and the first segment is defined as a dependency relationship within the first dependency relationship set. For example, the first dependency relationship set may include verb-direct object dependencies (dobj) and dependency relationships that the system cannot recognize (dependent, dep). For instance, if the starting segment is a verb, the terminal device can obtain nouns and proper nouns with dependency relationships of dobj or dep from multiple segments, thus obtaining at least one first segment. For example, if the edited text is: "Add a piece of interesting music," then the multiple segments of this edited text include: add, each, interesting, of, music. The starting segment is add, and its part of speech is a verb. Since the dependency relationship between music and add is dobj, the terminal device can identify music as the first segment.

[0122] S702. Determine the intention phrase based on the number of first segment words, the starting segment word, and the first segment word.

[0123] The terminal device determines the intent phrase based on the number of words in the first segment, the starting segment, and the first segment, which can be done in two ways:

[0124] Case 1: The number of the first segment is 1.

[0125] If the first segment has only one segment, then the starting segment and the first segment are combined to obtain the intent phrase. If the instruction is: "Add a cheerful piece of music," then the multiple segments of this instruction include: add, one, cheerful, of, music. The dependency relation of the segment "add" is root, the dependency relation of the segment "one" is nummod, the dependency relation of the segment "cheerful" is amod, the dependency relation of the segment "of" is mark, and the dependency relation of the segment "music" is dobj. Therefore, the terminal device can determine that the starting segment is "add," which is a verb. The dependency relation of the segment "music" conforms to the dependency relations in the first dependency relation set, and the segment "music" is a proper noun. The terminal device can determine that the first segment is music. Since the first segment has only one segment, the terminal device can combine the starting segment "add" with the first segment "music" to obtain the intent phrase "add music."

[0126] Case 2: The number of the first segment is greater than 1.

[0127] If the number of first word segments is greater than 1, the terminal device can obtain the type of dependency relationship between the starting word and each first word segment, and determine the intent phrase among multiple word segments based on the type of dependency relationship between the starting word and each first word segment. For example, the type of dependency relationship may include dobj, dep, etc., which are not limited in this embodiment.

[0128] The terminal device determines the intent phrase from multiple segments based on the type of dependency relationship between the starting segment and each first segment. Specifically, it can be done by: determining the priority of each first segment based on the type of dependency relationship between the starting segment and each first segment; determining the target segment with the highest priority from at least one first segment based on the priority of each first segment; and combining the starting segment and the target segment to obtain the intent phrase.

[0129] Optionally, the dependency relations included in the first dependency relation set can be dobj and dep, so the priority order can be dobj greater than dep. For example, if the type of the dependency relation of the first word segment 1 is dobj and the type of the dependency relation of the first word segment 2 is dep, then the terminal device can determine that the target word segment is the first word segment 1.

[0130] Optionally, since the part of speech of the first segment is a noun, but nouns also include proper nouns, the terminal device can further determine the priority between the first segment based on the type of dependency relation and the part of speech of the first segment. For example, the priority order can be dobj+nz (proper noun) greater than dep+nz, and dep+nz greater than dobj+n. For example, the type of dependency relation of first segment 1 is dobj, and the type of dependency relation of first segment 2 is dep. However, the part of speech of first segment 2 is the proper noun nz, while the part of speech of first segment 1 is the common noun n. Therefore, the terminal device can determine the target segment as the second segment.

[0131] Optionally, the terminal device can combine the starting segment and the target segment to obtain an intent phrase. For example, if the terminal device determines the starting segment as "add", the first segment as "music", and the second segment as "city" in the instruction information, since "music" is a proper noun, the segment "music" has a higher priority than the segment "city". Therefore, the terminal device can determine the target segment as "music" and combine the starting segment and the target segment to obtain the intent phrase: Add music.

[0132] It should be noted that if the compiled text contains a segmentation that has a parallel dependency relationship with the first segmentation, the terminal device can combine the starting segmentation with that parallel segmentation to obtain other intent phrases. For example, the instruction information could be "add music" and "sound effect." The terminal device can determine that the starting segmentation is "add," which is a verb. The terminal device can determine that the first segmentation is "music," thus obtaining the intent phrase: "add music." Since "music" and "sound effect" are parallel segments, the terminal device can obtain another intent phrase: "add sound effect."

[0133] This disclosure provides a method for determining intent phrases. Based on the starting word and dependency relationships, at least one first word with a noun part of speech is determined from multiple word segments. If the number of first word segments is one, the starting word and the first word segments are combined to obtain the intent phrase. If the number of first word segments is greater than one, the terminal device can obtain the type of dependency relationship between the starting word and each first word segment, and determine the intent phrase from multiple word segments based on the type of dependency relationship between the starting word and each first word segment. Thus, when the starting word is a verb, the terminal device can accurately identify functional nouns in the instruction information that can be combined with the starting word, thereby obtaining accurate intent phrases, improving the accuracy of determining editing operations, and consequently improving the accuracy of video editing.

[0134] Figure 8 This is a schematic diagram illustrating another method for determining an intent phrase provided in an embodiment of this disclosure. Figure 8 In the example shown, the part of speech of the initial word segment is a noun. Please refer to [link to example]. Figure 8 The method process includes:

[0135] S801. Based on the initial segmentation and dependency relationship, determine whether there is a second segmentation with the part of speech of a verb among multiple segmentations.

[0136] If so, proceed to step S802.

[0137] If not, proceed to step S803.

[0138] In this context, the dependency relationship between the starting segment and the second segment is a dependency relationship within the second dependency relationship set. For example, the second dependency relationship set may include dependency relationships such as `dep` and `ccomp`. For instance, if the instruction is to change the background music to upbeat music, the starting segment in this instruction is "background music," and its part of speech is a noun. The dependency relationship between the segment "change to" and the starting segment is `ccomp`, and the part of speech of the segment "change to" is a verb. Therefore, the terminal device can determine that the instruction contains a second segment, which is "change to".

[0139] S802. Combine the second segmentation and the first segmentation to obtain the intention phrase.

[0140] Optionally, if a second segment exists among multiple segmentations in the edited text, the terminal device can combine the second segment with the starting segment to obtain an intent phrase. For example, if the instruction is to change the background music to sad music, the starting segment is "background music," and its part of speech is a noun. Therefore, the terminal device can determine that the second segment is the verb "change to." The terminal device can then combine the starting segment and the second segment to obtain the intent phrase: "Background music changed to."

[0141] Optionally, after the terminal device combines the second segment and the starting segment to obtain the intent phrase, the method further includes: determining, based on dependency relationships, whether there exists a candidate segment parallel to the starting segment among the multiple segmentations; if so, combining the second segment and the candidate segment to obtain other intent phrases. For example, since the starting segment is a noun, if there exists a noun with a parallel dependency relationship to the starting segment, it indicates that the instruction information includes other operation types. Therefore, the terminal device can combine the second segment with the candidate segment to obtain other intent phrases. For example, if the instruction information is: "Music and sound effects replaced with cheerful," the terminal device can determine that the starting segment of the instruction information is "music," and the starting segment is a noun. The terminal device can determine that the second segment in the instruction information is "replacement." Therefore, the terminal device can obtain an intent phrase: "music replacement." Since "music" and "sound effects" are parallel, the terminal device can obtain another intent phrase: "sound effect replacement." That is, the operation types included in the instruction information are "replace music" and "replace sound effects."

[0142] S803. Obtain the preset word segmentation with the part of speech of verb, and combine the preset word segmentation and the starting word segmentation to obtain the intention phrase.

[0143] Optionally, if a second segmentation is not present among the multiple segmentations associated with the indication information, the terminal device can combine the starting segmentation with a preset segmentation to obtain an intent phrase. The preset segmentation can be a segmentation with a verb part of speech. For example, the preset segmentation could be "add" or "replace," but this embodiment does not limit this.

[0144] For example, if the instruction is: "sound effect: dog barking", the terminal device can determine that the starting segment in the instruction is "sound effect" and that the starting segment is a noun. Therefore, the terminal device needs to determine the second segment in the compiled text. Since "dog barking" is also a noun, there is no second segment in the instruction. The terminal device can obtain the preset segment as "add" and then combine the preset segment with the starting segment to obtain the intent phrase: "add sound effect".

[0145] This disclosure provides a method for determining an intent phrase. Based on the initial segmentation and dependency relationships, it determines whether a second segmentation with a verb exists among multiple segmentations. If so, the second segmentation and the initial segmentation are combined to obtain the intent phrase. If not, a preset segmentation with a verb is obtained, and this preset segmentation is combined with the initial segmentation to obtain the intent phrase. Thus, even when the initial segmentation is a noun, the terminal device can still obtain a meaningful verb from the instruction information. This allows for accurate description of the editing effect based on the intent phrase. Furthermore, by comparing phrase similarity, the accuracy of determining the operation type can be improved, thereby improving the accuracy of editing operations and video editing.

[0146] Figure 9 This is a schematic diagram of the structure of a video processing apparatus provided in an embodiment of this disclosure. Please refer to [link / reference]. Figure 9 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:

[0147] The acquisition module 901 is used to acquire indication information corresponding to the first video, the indication information being used to indicate the editing effect on the first video;

[0148] The first determining module 902 is used to determine multiple word segments associated with the indication information, the part-of-speech tag of each word segment, and the dependency relationships between the multiple word segments;

[0149] The second determining module 903 is used to determine the operation type and operation parameters associated with the editing operation based on the part-of-speech of each word, the dependency relationship between the multiple words, and the multiple words.

[0150] The processing module 904 is used to edit the first video according to the operation type and the operation parameters to obtain the second video.

[0151] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0152] Based on the dependency relationship and the part-of-speech tags of the multiple word segments, a starting word segment is determined among the multiple word segments, and the part-of-speech tag of the starting word segment is the part-of-speech tag in a preset part-of-speech tag set;

[0153] Based on the part-of-speech of the initial word segment, the dependency relationship, and the part-of-speech of the multiple word segments, the intention phrase and the parameter phrase are determined from the multiple word segments;

[0154] Based on the intent phrase, the operation type is determined, and based on the parameter phrase, the operation parameters are determined.

[0155] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0156] Based on the starting word segment and the dependency relationship, at least one first word with a noun part of speech is determined from the plurality of word segments, and the dependency relationship between the starting word and the first word segment is a dependency relationship in the first dependency relationship set;

[0157] If the number of the first word segment is 1, then the starting word segment and the first word segment are combined to obtain the intent phrase;

[0158] If the number of the first word segment is greater than 1, then the type of dependency relationship between the starting word and each first word is obtained, and the intention phrase is determined among the multiple words according to the type of dependency relationship between the starting word and each first word.

[0159] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0160] The priority of each first word is determined based on the type of dependency relationship between the starting word and each first word.

[0161] Based on the priority of each first word segment, determine the target word with the highest priority among the at least one first word segment;

[0162] The initial word segment and the target word segment are combined to obtain the intent phrase.

[0163] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0164] Based on the initial word segment and the dependency relationship, determine whether there is a second word with a verb part of speech among the multiple word segments, and the dependency relationship between the initial word segment and the second word segment is a dependency relationship in the second dependency relationship set;

[0165] If so, the second segment and the starting segment are combined to obtain the intended phrase;

[0166] If not, then obtain the preset word segmentation with the part of speech of a verb, and combine the preset word segmentation and the starting word segmentation to obtain the intention phrase.

[0167] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0168] Based on the dependency relationship, determine whether there are candidate segmentations that are parallel to the starting segmentation among the multiple segmentations;

[0169] If so, the second word segment and the candidate word segment are combined to obtain other intention phrases.

[0170] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0171] Based on the part-of-speech of the initial word segment and the dependency relationship, determine the first-level search term among the multiple word segments;

[0172] If a second-level search term corresponding to the first-level search term exists among the multiple word segments, then the first search term and the second search term are combined to obtain the parameter phrase;

[0173] If there is no second-level search term corresponding to the first-level search term among the multiple word segments, then the first-level search term is determined as the parameter phrase.

[0174] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0175] If the part of speech of the starting word is a noun, then the word whose dependency relationship with the starting word is a dependency relationship in the third dependency relationship set is determined as the first-level search word.

[0176] If the part of speech of the starting word is a verb, then the word whose dependency relationship with the starting word is a dependency relationship in the fourth dependency relationship set is determined as the first-level search term, or the noun among the multiple words is determined as the first-level search term.

[0177] According to one or more embodiments of this disclosure, the second determining module 903 is specifically used for:

[0178] Based on the intent phrase, a target intent phrase is determined in the intent database, which includes multiple preset intent phrases and a preset operation type corresponding to each preset intent phrase. The target intent phrase has the highest similarity to the intent phrase.

[0179] The preset operation type corresponding to the target intent phrase is determined as the operation type corresponding to the intent phrase.

[0180] According to one or more embodiments of this disclosure, the processing module 904 is specifically used for:

[0181] Based on the operation type and the operation parameters, a target script is generated, the target script including the code corresponding to the operation type and the parameter phrase;

[0182] The target script is executed on the first video to edit and process it, resulting in a second video.

[0183] The video processing apparatus provided in this embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0184] Figure 10 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this disclosure. Please refer to [link / reference]. Figure 10 The diagram illustrates a structural schematic suitable for implementing the terminal device 1000 of the embodiments of the present disclosure. The terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), portable Android devices (PADs), portable media players (PMPs), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 10 The terminal device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0185] like Figure 10 As shown, the terminal device 1000 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 into a random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the operation of the terminal device 1000. The processing unit 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0186] Typically, the following devices can be connected to the I / O interface 1005: input devices 1006 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1007 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1008 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows terminal device 1000 to exchange data via wireless or wired communication with other devices. Although Figure 10 A terminal device 1000 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0187] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1009, or installed from storage device 1008, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of embodiments of this disclosure.

[0188] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0189] The aforementioned computer-readable medium may be included in the aforementioned terminal device; or it may exist independently and not assembled into the terminal device.

[0190] The aforementioned computer-readable medium carries one or more programs, which, when executed by the terminal device, cause the terminal device to perform the method shown in the above embodiments.

[0191] This disclosure provides a computer-readable storage medium storing computer-executable instructions. When a processor executes the computer-executable instructions, it implements the methods described in various possible ways as described in the above embodiments.

[0192] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the methods described in various possible ways as described in the above embodiments.

[0193] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone 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 remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0194] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0195] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0196] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0197] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0198] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0199] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0200] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0201] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message. As an optional but non-limiting implementation, the prompt message can be sent to the user in the form of a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0202] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0203] It is understood that the data involved in this technical solution (including but not limited to the data itself, its acquisition, or its use) shall comply with the requirements of relevant laws, regulations, and provisions. Data may include information, parameters, and messages, such as flow control instructions.

[0204] In a first aspect, according to one or more embodiments of this disclosure, this disclosure provides a video processing method, the video processing method comprising:

[0205] Obtain the instruction information corresponding to the first video, the instruction information being used to indicate the editing effect on the first video;

[0206] Determine the multiple word segments associated with the indicated information, the part-of-speech tag of each word, and the dependency relationships between the multiple word segments;

[0207] Based on the part-of-speech of each word, the dependency relationships between the multiple words, and the multiple words, determine the operation type and operation parameters associated with the editing operation;

[0208] Based on the operation type and the operation parameters, the first video is edited to obtain the second video.

[0209] According to one or more embodiments of this disclosure, determining the operation type and operation parameters associated with the editing operation based on the part-of-speech tag of each word, the dependency relationships between the multiple word segments, and the multiple word segments includes:

[0210] Based on the dependency relationship and the part-of-speech tags of the multiple word segments, a starting word segment is determined among the multiple word segments, and the part-of-speech tag of the starting word segment is the part-of-speech tag in a preset part-of-speech tag set;

[0211] Based on the part-of-speech of the initial word segment, the dependency relationship, and the part-of-speech of the multiple word segments, the intention phrase and the parameter phrase are determined from the multiple word segments;

[0212] Based on the intent phrase, the operation type is determined, and based on the parameter phrase, the operation parameters are determined.

[0213] According to one or more embodiments of this disclosure, the part of speech of the initial word segment is a verb; the intention phrase is determined from the plurality of word segments based on the part of speech of the initial word segment, the dependency relation, and the part of speech of the plurality of word segments, including:

[0214] Based on the starting word segment and the dependency relationship, at least one first word with a noun part of speech is determined from the plurality of word segments, and the dependency relationship between the starting word and the first word segment is a dependency relationship in the first dependency relationship set;

[0215] If the number of the first word segment is 1, then the starting word segment and the first word segment are combined to obtain the intent phrase;

[0216] If the number of the first word segment is greater than 1, then the type of dependency relationship between the starting word and each first word is obtained, and the intention phrase is determined among the multiple words according to the type of dependency relationship between the starting word and each first word.

[0217] According to one or more embodiments of this disclosure, determining the intent phrase among the plurality of segments based on the type of dependency relationship between the starting segment and each first segment includes:

[0218] The priority of each first word is determined based on the type of dependency relationship between the starting word and each first word.

[0219] Based on the priority of each first word segment, determine the target word with the highest priority among the at least one first word segment;

[0220] The initial word segment and the target word segment are combined to obtain the intent phrase.

[0221] According to one or more embodiments of this disclosure, the initial word segment is a noun; the intention phrase is determined from the plurality of word segments based on the part of speech of the initial word segment, the dependency relation, and the part of speech of the plurality of word segments, including:

[0222] Based on the initial word segment and the dependency relationship, determine whether there is a second word with a verb part of speech among the multiple word segments, and the dependency relationship between the initial word segment and the second word segment is a dependency relationship in the second dependency relationship set;

[0223] If so, the second segment and the starting segment are combined to obtain the intended phrase;

[0224] If not, then obtain the preset word segmentation with the part of speech of a verb, and combine the preset word segmentation and the starting word segmentation to obtain the intention phrase.

[0225] According to one or more embodiments of this disclosure, after combining the second word segment and the starting word segment to obtain the intent phrase, the method further includes:

[0226] Based on the dependency relationship, determine whether there are candidate segmentations that are parallel to the starting segmentation among the multiple segmentations;

[0227] If so, the second word segment and the candidate word segment are combined to obtain other intention phrases.

[0228] According to one or more embodiments of this disclosure, determining the parameter phrase among the plurality of word segments based on the part-of-speech tag of the initial word segment, the dependency relation, and the part-of-speech tags of the plurality of word segments includes:

[0229] Based on the part-of-speech of the initial word segment and the dependency relationship, determine the first-level search term among the multiple word segments;

[0230] If a second-level search term corresponding to the first-level search term exists among the multiple word segments, then the first search term and the second search term are combined to obtain the parameter phrase;

[0231] If there is no second-level search term corresponding to the first-level search term among the multiple word segments, then the first-level search term is determined as the parameter phrase.

[0232] According to one or more embodiments of this disclosure, a first-level search term is determined from the plurality of word segments based on the part-of-speech tag of the initial word segment and the dependency relationship, including:

[0233] If the part of speech of the starting word is a noun, then the word whose dependency relationship with the starting word is a dependency relationship in the third dependency relationship set is determined as the first-level search word.

[0234] If the part of speech of the starting word is a verb, then the word whose dependency relationship with the starting word is a dependency relationship in the fourth dependency relationship set is determined as the first-level search term, or the noun among the multiple words is determined as the first-level search term.

[0235] According to one or more embodiments of this disclosure, determining the operation type based on the intent phrase includes:

[0236] Based on the intent phrase, a target intent phrase is determined in the intent database, which includes multiple preset intent phrases and a preset operation type corresponding to each preset intent phrase. The target intent phrase has the highest similarity to the intent phrase.

[0237] The preset operation type corresponding to the target intent phrase is determined as the operation type corresponding to the intent phrase.

[0238] According to one or more embodiments of this disclosure, the step of editing the first video to obtain a second video based on the operation type and the operation parameters includes:

[0239] Based on the operation type and the operation parameters, a target script is generated, the target script including the code corresponding to the operation type and the parameter phrase;

[0240] The target script is executed on the first video to edit and process it, resulting in a second video.

[0241] Secondly, according to one or more embodiments of this disclosure, this disclosure provides a video processing apparatus, which includes an acquisition module, a first determination module, a second determination module, and a processing module, wherein:

[0242] The acquisition module is used to acquire indication information corresponding to the first video, and the indication information is used to indicate the editing effect on the first video;

[0243] The first determining module is used to determine multiple word segments associated with the indication information, the part-of-speech tag of each word segment, and the dependency relationships between the multiple word segments;

[0244] The second determining module is used to determine the operation type and operation parameters associated with the editing operation based on the part-of-speech of each word, the dependency relationship between the multiple words, and the multiple words.

[0245] The processing module is used to edit the first video according to the operation type and the operation parameters to obtain the second video.

[0246] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0247] Based on the dependency relationship and the part-of-speech tags of the multiple word segments, a starting word segment is determined among the multiple word segments, and the part-of-speech tag of the starting word segment is the part-of-speech tag in a preset part-of-speech tag set;

[0248] Based on the part-of-speech of the initial word segment, the dependency relationship, and the part-of-speech of the multiple word segments, the intention phrase and the parameter phrase are determined from the multiple word segments;

[0249] Based on the intent phrase, the operation type is determined, and based on the parameter phrase, the operation parameters are determined.

[0250] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0251] Based on the starting word segment and the dependency relationship, at least one first word with a noun part of speech is determined from the plurality of word segments, and the dependency relationship between the starting word and the first word segment is a dependency relationship in the first dependency relationship set;

[0252] If the number of the first word segment is 1, then the starting word segment and the first word segment are combined to obtain the intent phrase;

[0253] If the number of the first word segment is greater than 1, then the type of dependency relationship between the starting word and each first word is obtained, and the intention phrase is determined among the multiple words according to the type of dependency relationship between the starting word and each first word.

[0254] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0255] The priority of each first word is determined based on the type of dependency relationship between the starting word and each first word.

[0256] Based on the priority of each first word segment, determine the target word with the highest priority among the at least one first word segment;

[0257] The initial word segment and the target word segment are combined to obtain the intent phrase.

[0258] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0259] Based on the initial word segment and the dependency relationship, determine whether there is a second word with a verb part of speech among the multiple word segments, and the dependency relationship between the initial word segment and the second word segment is a dependency relationship in the second dependency relationship set;

[0260] If so, the second segment and the starting segment are combined to obtain the intended phrase;

[0261] If not, then obtain the preset word segmentation with the part of speech of a verb, and combine the preset word segmentation and the starting word segmentation to obtain the intention phrase.

[0262] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0263] Based on the dependency relationship, determine whether there are candidate segmentations that are parallel to the starting segmentation among the multiple segmentations;

[0264] If so, the second word segment and the candidate word segment are combined to obtain other intention phrases.

[0265] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0266] Based on the part-of-speech of the initial word segment and the dependency relationship, determine the first-level search term among the multiple word segments;

[0267] If a second-level search term corresponding to the first-level search term exists among the multiple word segments, then the first search term and the second search term are combined to obtain the parameter phrase;

[0268] If there is no second-level search term corresponding to the first-level search term among the multiple word segments, then the first-level search term is determined as the parameter phrase.

[0269] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0270] If the part of speech of the starting word is a noun, then the word whose dependency relationship with the starting word is a dependency relationship in the third dependency relationship set is determined as the first-level search word.

[0271] If the part of speech of the starting word is a verb, then the word whose dependency relationship with the starting word is a dependency relationship in the fourth dependency relationship set is determined as the first-level search term, or the noun among the multiple words is determined as the first-level search term.

[0272] According to one or more embodiments of this disclosure, the second determining module is specifically used for:

[0273] Based on the intent phrase, a target intent phrase is determined in the intent database, which includes multiple preset intent phrases and a preset operation type corresponding to each preset intent phrase. The target intent phrase has the highest similarity to the intent phrase.

[0274] The preset operation type corresponding to the target intent phrase is determined as the operation type corresponding to the intent phrase.

[0275] According to one or more embodiments of this disclosure, the processing module is specifically used for:

[0276] Based on the operation type and the operation parameters, a target script is generated, the target script including the code corresponding to the operation type and the parameter phrase;

[0277] The target script is executed on the first video to edit and process it, resulting in a second video.

[0278] Thirdly, embodiments of this disclosure provide an electronic device including: a processor and a memory;

[0279] The memory stores computer-executed instructions;

[0280] The processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the video processing methods described in the first aspect above and various possible aspects of the first aspect.

[0281] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the video processing methods described in the first aspect and various possible aspects thereof.

[0282] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0283] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0284] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A video processing method, characterized in that, include: Obtain the instruction information corresponding to the first video, the instruction information being used to indicate the editing effect on the first video; Determine the multiple word segments associated with the indicated information, the part-of-speech tag of each word, and the dependency relationships between the multiple word segments; Based on the dependency relationship and the part-of-speech tags of the multiple word segments, a starting word segment is determined among the multiple word segments, and the part-of-speech tag of the starting word segment is the part-of-speech tag in a preset part-of-speech tag set; Based on the part-of-speech of the starting word, the dependency relationship, and the part-of-speech of the multiple words, an intent phrase is determined from the multiple words, and based on the part-of-speech of the starting word and the dependency relationship, a first-level search term is determined from the multiple words; If a second-level search term corresponding to the first-level search term exists among the multiple word segments, then the first-level search term and the second-level search term are combined to obtain a parameter phrase; If there is no second-level search term corresponding to the first-level search term among the multiple word segments, then the first-level search term is determined as the parameter phrase; Based on the intent phrase, determine the operation type associated with the editing operation, and based on the parameter phrase, determine the operation parameters associated with the editing operation; Based on the operation type and the operation parameters, the first video is edited to obtain the second video.

2. The method according to claim 1, characterized in that, The part of speech of the starting word is a verb; based on the part of speech of the starting word, the dependency relationship, and the parts of speech of the multiple words, the intention phrase is determined from the multiple words, including: Based on the starting word segment and the dependency relationship, at least one first word with a noun part of speech is determined from the plurality of word segments, and the dependency relationship between the starting word and the first word segment is a dependency relationship in the first dependency relationship set; If the number of the first word segment is 1, then the starting word segment and the first word segment are combined to obtain the intent phrase; If the number of the first word segment is greater than 1, then the type of dependency relationship between the starting word and each first word is obtained, and the intention phrase is determined among the multiple words according to the type of dependency relationship between the starting word and each first word.

3. The method according to claim 2, characterized in that, Based on the type of dependency relationship between the starting word and each first word, the intent phrase is determined from the plurality of words, including: The priority of each first word is determined based on the type of dependency relationship between the starting word and each first word. Based on the priority of each first word segment, determine the target word with the highest priority among the at least one first word segment; The initial word segment and the target word segment are combined to obtain the intent phrase.

4. The method according to claim 1, characterized in that, The initial word segment is a noun; based on the part of speech of the initial word segment, the dependency relationship, and the part of speech of the multiple word segments, the intention phrase is determined from the multiple word segments, including: Based on the initial word segment and the dependency relationship, determine whether there is a second word with a verb part of speech among the multiple word segments, and the dependency relationship between the initial word segment and the second word segment is a dependency relationship in the second dependency relationship set; If so, the second segment and the starting segment are combined to obtain the intended phrase; If not, then obtain the preset word segmentation with the part of speech of a verb, and combine the preset word segmentation and the starting word segmentation to obtain the intention phrase.

5. The method according to claim 4, characterized in that, After combining the second word segment and the initial word segment to obtain the intent phrase, the method further includes: Based on the dependency relationship, determine whether there are candidate segmentations that are parallel to the starting segmentation among the multiple segmentations; If so, the second word segment and the candidate word segment are combined to obtain other intention phrases.

6. The method according to claim 1, characterized in that, Based on the part-of-speech of the initial word segment and the dependency relationship, the first-level search terms are determined from the plurality of word segments, including: If the part of speech of the starting word is a noun, then the word whose dependency relationship with the starting word is a dependency relationship in the third dependency relationship set is determined as the first-level search word. If the part of speech of the starting word is a verb, then the word whose dependency relationship with the starting word is a dependency relationship in the fourth dependency relationship set is determined as the first-level search term, or the noun among the multiple words is determined as the first-level search term.

7. The method according to any one of claims 1-4, characterized in that, Determining the operation type based on the intent phrase includes: Based on the intent phrase, a target intent phrase is determined in the intent database, which includes multiple preset intent phrases and a preset operation type corresponding to each preset intent phrase. The target intent phrase has the highest similarity to the intent phrase. The preset operation type corresponding to the target intent phrase is determined as the operation type corresponding to the intent phrase.

8. The method according to any one of claims 1-4, characterized in that, The step of editing the first video according to the operation type and the operation parameters to obtain the second video includes: Based on the operation type and the operation parameters, a target script is generated, the target script including the code corresponding to the operation type and the parameter phrase; The target script is executed on the first video to edit and process it, resulting in a second video.

9. A video processing apparatus, characterized in that, It includes 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, and the indication information is used to indicate the editing effect on the first video; The first determining module is used to determine multiple word segments associated with the indication information, the part-of-speech tag of each word segment, and the dependency relationships between the multiple word segments; The second determining module is used to determine the starting segment from the multiple segmented words based on the dependency relationship and the part-of-speech tags of the multiple segmented words, wherein the part-of-speech tag of the starting segmented word is a part-of-speech tag from a preset set of part-of-speech tags; Based on the part-of-speech of the starting word, the dependency relationship, and the part-of-speech of the multiple words, an intent phrase is determined from the multiple words, and based on the part-of-speech of the starting word and the dependency relationship, a first-level search term is determined from the multiple words; If a second-level search term corresponding to the first-level search term exists among the multiple word segments, then the first-level search term and the second-level search term are combined to obtain a parameter phrase; if a second-level search term corresponding to the first-level search term does not exist among the multiple word segments, then the first-level search term is determined as the parameter phrase. Based on the intent phrase, determine the operation type associated with the editing operation, and based on the parameter phrase, determine the operation parameters 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 the second video.

10. A terminal device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the video processing method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the video processing method as described in any one of claims 1-8.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the video processing method as described in any one of claims 1-8.

Images