Multimedia editing method and device

Abstract

The embodiment of the invention provides a multimedia editing method. The multimedia editing method comprises the following steps: acquiring a plurality of first materials; generating material information respectively corresponding to the plurality of first materials; and editing the plurality of first materials according to the material information corresponding to the plurality of first materials to obtain a second material. According to the technical scheme, the editing efficiency can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of multimedia technology, and in particular, to a multimedia editing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the popularization of mobile Internet, multimedia has become an important driving force for information dissemination, entertainment consumption, etc. As the basic elements of content creation, multimedia materials such as pictures and videos have a direct impact on the speed and quality of content output due to their processing and editing efficiency.

[0003] However, when faced with large amounts of material, traditional editing methods suffer from low efficiency and video quality.

[0004] It should be noted that the above content is not necessarily prior art, nor is it intended to limit the scope of patent protection of this application. Summary of the invention

[0005] Embodiments of the present application provide a multimedia editing method, apparatus, computer device, computer-readable storage medium, and computer program product to solve or alleviate one or more of the technical problems raised above.

[0006] One aspect of an embodiment of the present application provides a multimedia editing method, the method comprising: Acquire multiple first materials; generating material information corresponding to each of the plurality of first materials; and The plurality of first materials are edited according to the material information corresponding to each of the plurality of first materials to obtain a second material.

[0007] Optionally, the material information includes material text information; generating a plurality of material information corresponding to each of the first materials includes: Obtaining keywords of the first material; According to the keyword of the first material, the material text information of the first material is obtained; wherein the material text information includes the keyword. Optionally, according to the keyword of the first material, the material text information of the first material is obtained, including: Inputting the keywords of the first material into a text generation model to obtain initial text information; The sensitive words in the initial text information are removed to obtain the material text information.

[0008] Optionally, the method further comprises: When the material text information is obtained, the material text information and the first material are matched according to the keywords in the material text information and the keywords of the first material to form a matching relationship.

[0009] Optionally, obtaining keywords of the first material includes: Acquire the time length of the first material; When the time length is less than a preset value, identifying keywords in the first material by using a local recognition model; When the time length is not less than a preset value, keywords in the first material are identified through a cloud recognition model.

[0010] Optionally, the method further comprises: Acquire new material information from the material library, where the new material information includes a material identification code and a placement location; The material corresponding to the newly added material information is loaded into the second material as a decorative material.

[0011] Optionally, editing the plurality of first materials to obtain a second material according to material information corresponding to each of the plurality of first materials includes: According to a pre-configured processing logic code and material information corresponding to each of the plurality of first materials, the plurality of first materials are edited to obtain the second material; the processing logic code is used to indicate material processing logic.

[0012] Optionally, for use in an editing processing toolkit; The editing and processing toolkit includes: risk management module, matching module, and positioning module; The risk management module is used to remove sensitive words in the initial text information to obtain the material text information.

[0013] The matching module is used to match the material text information with the first material according to the keywords in the material text information and the keywords of the first material to form a matching relationship; The positioning module is used to obtain the newly added material information from the material library, and the newly added material information includes a material identification code and a placement position; wherein the material corresponding to the newly added material information is loaded into the second material as a decorative material.

[0014] Another aspect of the embodiments of the present application provides a multimedia editing device, the device comprising: An acquisition module, used for acquiring a plurality of first materials; A generating module, configured to generate material information corresponding to each of the plurality of first materials, wherein the material information includes material text information; The editing module is used to edit the multiple first materials to obtain the second material according to the material information corresponding to each of the multiple first materials.

[0015] Another aspect of an embodiment of the present application provides a computer device, including: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein: the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0016] Another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method described above is implemented.

[0017] Another aspect of an embodiment of the present application provides a computer program product, including a computer program, which implements the method described above when executed by a processor.

[0018] The above technical solution adopted in the embodiment of the present application may have the following advantages: Multiple selected first materials (e.g., images or videos to be processed) can be automatically generated into multiple material information (e.g., titles, plot texts, tags, etc.). The material information is integrated with the first material to obtain a second material (e.g., a video with plot texts), thereby improving editing efficiency and video editing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0020] Figure 1 The operating environment diagram of the multimedia editing method according to the first embodiment of the present application is schematically shown; Figure 2 The flowchart of the multimedia editing method according to the first embodiment of the present application is schematically shown; Figure 3 Schematically shows Figure 2 Flow chart of sub-steps of step S202; Figure 4 Schematically shows Figure 3 Flow chart of sub-steps of step S300; Figure 5Schematically shows Figure 3 Flow chart of sub-steps of step S300; Figure 6 The arrangement diagram of the material text information and the first material is schematically shown; Figure 7 Schematically shows an exemplary application diagram of the present application; Figure 8 Schematically shows an exemplary application flow chart of the present application Fig. 9 A block diagram schematically shows a multimedia editing device according to the second embodiment of the present application; and Fig.10 The hardware architecture diagram of the computer device according to the third embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0022] It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0023] In the description of the present application, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are executed, but are only used to facilitate the description of the present application and to distinguish each step, and therefore should not be understood as a limitation on the present application.

[0024] First, the following terms are explained: KMP (Kotlin Multiplatform, a cross-platform framework based on the Kotlin language): Kotlin Multiplatform is a cross-platform framework for mobile development, written in the Kotlin language, which can share code and logic on multiple platforms. With the KMP framework, you can write code once and then deploy and run it on different platforms.

[0025] For ease of understanding, an exemplary operating environment is provided below.

[0026] like Figure 1 As shown, the operating environment diagram includes: a service platform 2, and clients (4A, 4B, ..., 4N).

[0027] The service platform 2 can be connected to the client terminals ( 4A, 4B, ..., 4N) via the network.

[0028] The service platform 2 may be a single server, a server cluster or a cloud computing service center.

[0029] The service platform 2 can provide the client with services such as storing sensitive word libraries and storing material.

[0030] The service platform 2 may be located in a data center such as a single location, or distributed in different geographical locations (e.g., in multiple locations). The service platform 2 may provide services via a network. The network includes various network devices such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and / or the like. The network may include physical links such as coaxial cable links, twisted pair cable links, optical fiber links, combinations thereof, and the like, or wireless links such as cellular links, satellite links, Wi-Fi links, and the like.

[0031] The client (4A, 4B, ..., 4N) may be configured to access the content and services of the service platform 2. The client (4A, 4B, ..., 4N) may include an electronic device carrying or externally connected to a display panel, such as a mobile device, a tablet device, a laptop computer, a workstation, a virtual reality device, a gaming device, a digital streaming device, a vehicle terminal, a smart TV, a set-top box, etc., and may also include a virtualized computing instance. The virtualized computing instance may include a virtual machine, such as a simulation of a computer system, an operating system, a server, etc. The computing device may load a virtual machine based on a virtual image and / or other data defining specific software (e.g., an operating system, a dedicated application, a server) for simulation. As the demand for different types of processing services changes, different virtual machines may be loaded and / or terminated on one or more computing devices.

[0032] The client (4A, 4B, ..., 4N) may be associated with one or more users. A single user may also use one or more of the clients (4A, 4B, ..., 4N) to access the service platform 2. The client (4A, 4B, ..., 4N) may travel to various locations and use different networks to access the service platform 2.

[0033] The client (4A, 4B, ..., 4N) may include an interface. The interface may include a touch pad, a touch screen, a mouse, a keyboard, or other sensing elements. For example, the input element may be configured to receive user instructions, which may enable the client (4A, 4B, ..., 4N) to perform various operations, such as uploading and downloading materials, video editing, etc.

[0034] It should be noted that the above devices are exemplary, and the number and type of devices are adjustable in different scenarios or according to different needs.

[0035] The following describes the technical solution of the present application through multiple embodiments, taking the client as the execution subject. It should be noted that these embodiments can be implemented in a variety of different forms and should not be interpreted as being limited to the embodiments described here.

[0036] Embodiment 1 Figure 2 The flowchart of the multimedia editing method according to the first embodiment of the present application is schematically shown.

[0037] like Figure 2 As shown, the multimedia editing method may include steps S200 to S204, wherein: Step S200: acquiring a plurality of first materials.

[0038] Step S202: Generate material information corresponding to each of the plurality of first materials.

[0039] Step S204: Edit the plurality of first materials to obtain a second material according to the material information corresponding to each of the plurality of first materials.

[0040] The multimedia editing method provided in this embodiment can be applied to a client (e.g., 4A), and automatically generates multiple material information (e.g., material titles, plot texts, tags, etc.) according to multiple first materials (e.g., materials such as pictures or videos to be processed) selected by a user. The material information is integrated with the first material to obtain a second material (e.g., a video with a plot text), thereby improving editing efficiency and video editing quality.

[0041] The following combination Figure 2 , each step in steps S200~S204 and other optional steps are explained in detail.

[0042] Step S200 , obtain multiple first materials.

[0043] The user selects multiple first materials for editing the video. The first materials can be local materials, materials from the Internet, materials stored in the cloud, etc. The first materials can be videos, pictures, etc. to be processed.

[0044] Videos can be educational videos, advertising videos, entertainment videos (such as animated shorts, movie clips, music videos, etc.), live broadcast playbacks, surveillance videos, game videos, etc. Videos can be in various formats such as MPEG, FLV, AVI, MP4, etc. Images can be photographs (such as landscape photos, portrait photos, still life photos, etc.), screenshots, etc.

[0045] In some embodiments, after acquiring the first material, the first material may be subjected to image preprocessing, such as denoising, contrast enhancement, color balance adjustment, etc., to improve the quality of the first material.

[0046] In some embodiments, the sizes of the multiple first materials may be adjusted by using a cropping tool or calling an online cropping website, so that the multiple first materials are scaled to a uniform size to improve subsequent video synthesis effects.

[0047] Step S202 , generating material information corresponding to each of the plurality of first materials.

[0048] When the first material is a picture, the picture can be recognized by a pre-trained recognition model, for example, objects (such as people, animals, scenery, products, etc.), scenes (such as indoors, outdoors, cities, nature, etc.) in the picture, etc.

[0049] When the first material is a video, multiple key frames can be extracted from the video and input into the recognition model.

[0050] The recognition model can be a machine learning model, a deep learning network model, such as an object detection model, a multimodal learning model, a scene recognition model, etc.

[0051] Generate corresponding material information according to the image recognition result of the first material. The generated material information may be a label, text, etc. For example, if the subject recognized in the image is a dog, labels such as "puppy", "golden retriever", "pet", or descriptive text such as "a cute golden retriever playing in the sun" may be generated.

[0052] In some embodiments, the overall atmosphere of the first material (such as warmth, excitement, mystery, etc.) can be identified. According to the identification result, music corresponding to the atmosphere of the first material is obtained from a local music library or a cloud music library as material information.

[0053] In an optional embodiment, if Figure 3 As shown, the material information includes material text information, and step S202 may include: Step S300, obtaining keywords of the first material; Step S302: acquiring material text information of the first material according to the keyword of the first material; wherein the material text information includes the keyword.

[0054] Through image recognition or video analysis technology, key information such as objects, scenes, actions, etc. are extracted from the first material (such as the video or picture to be processed) and converted into one or more keywords.

[0055] In some embodiments, when the video contains an audio track, the audio can be converted into text through speech recognition technology, and the text can be used as keywords, or natural language processing technology, such as TF-IDF, Word2Vec and other algorithms, can be used to evaluate the importance of vocabulary in the text to extract keywords from the text.

[0056] In some embodiments, the identified keywords may be processed, such as deduplication, filtering, etc., to improve the usability of the identification results.

[0057] After extracting keywords from the image or video, you can generate longer descriptive text or a short story as material text information based on the keywords while retaining at least one keyword. For example, describe the scene in the picture, the relationship between characters, the development of events, etc.

[0058] In this embodiment, richer material text information is generated according to the keywords of the first material, thereby improving editing efficiency and content creation efficiency.

[0059] In an optional embodiment, if Figure 4 As shown, step S300 may include: Step S400, obtaining the time length of the first material; Step S402, when the time length is less than a preset value, identifying keywords in the first material by using a local recognition model; Step S404: When the time length is not less than a preset value, the keywords in the first material are identified by a cloud recognition model.

[0060] When the first material is a local material and its time length is lower than a preset value (e.g., 10 seconds), the local material is identified by a local recognition model to obtain its corresponding keywords. When the time length of the local material is higher than the preset value, the local material is identified by a cloud recognition model. When the first material is a cloud material, the cloud material is directly identified by a cloud recognition model to obtain its corresponding keywords. The preset value can also be dynamically adjusted according to the system load, network conditions, or user behavior to achieve better results. For example, when the local system load is high, the preset value can be lowered accordingly, so that the local material can be identified by the cloud even when the time length is short, so as to reduce the system burden caused by local processing.

[0061] In this embodiment, a specific recognition model (eg, a local recognition model or a cloud recognition model) is selected based on a comparison between the time length of the first material and a preset value to identify keywords in the first material, thereby improving processing efficiency and optimizing resource utilization.

[0062] In an optional embodiment, if Figure 5 As shown, step S302 may include: Step S500, inputting the keywords of the first material into a text generation model to obtain initial text information; Step S502: removing sensitive words from the initial text information to obtain the material text information.

[0063] The keywords of the first material can be input into text generation models such as ChatGPT and Wenxinyiyan. The text generation model can generate an initial text message based on the input keywords and business instructions (for example, requiring a story to be generated based on the keywords). The initial text message can be a detailed description of the keywords, an extended discussion, or a related story.

[0064] A sensitive word library may be preset in a local client (such as 4A) or in the service platform 2. The sensitive word library may include words that are illegal or violate public order and good morals. After the initial text information is generated, the initial text information may be compared with the sensitive words in the sensitive word library to determine and remove the sensitive words in the initial text information, thereby obtaining the material text information.

[0065] In this embodiment, the keywords of the first material are polished and expanded through the text generation model to obtain the initial text information. Then, the initial text information is filtered for sensitive words to generate the final material text information, thereby improving the efficiency and quality of editing the material text information and improving the compliance of the content of the material text information.

[0066] Step S204, editing the plurality of first materials to obtain a second material according to the material information corresponding to each of the plurality of first materials.

[0067] The material information can be analyzed by deep learning algorithms and automatically edited. For example, the text information, tags, music, etc. contained in the material information can be automatically added to the first material to generate the second material. In addition, according to the type of material information (such as theme, etc.), a suitable editing template can be automatically selected from the preset editing templates, and the first material can be automatically filled into the template to obtain the second material. For example, if the recognized material is "food", a food introduction template is automatically selected and applied.

[0068] In this embodiment, a plurality of material information (eg, plot text) is automatically generated based on the first material, and the material information is integrated with the first material to obtain the second material (eg, video with plot text), thereby improving editing efficiency and video quality.

[0069] In an optional embodiment, step S204 may include: According to a pre-configured processing logic code and material information corresponding to each of the plurality of first materials, the plurality of first materials are edited to obtain the second material; the processing logic code is used to indicate material processing logic.

[0070] The material processing logic is a set of logical implementations of "how to synthesize a video (with a plot) based on multiple first materials and material information".

[0071] In this embodiment, the processing logic code may be in Json format or other formats.

[0072] The processing logic code is used to automatically add corresponding material information (such as labels, subtitles, music, etc.) to the first material (such as the video or picture to be processed). For example, if a frame in the recognized picture or video is a "beach" scene, the blue sky and waves can be automatically added, and the relaxing sound of the waves can be used as background music, and subtitles can be added in appropriate locations, such as "Sunny beach, leisurely vacation" and other words. At the same time, the processing logic code is also used to combine multiple first materials together to form a video with a plot.

[0073] In this embodiment, a plurality of first materials are automatically edited to generate a second material through a pre-configured processing logic code, thereby improving the editing efficiency and the quality of the finished film. The quality of the finished film refers to the content quality of a single video.

[0074] In an optional embodiment, the multimedia editing method may further include: When the material text information is obtained, the material text information and the first material are matched according to the keywords in the material text information and the keywords of the first material to form a matching relationship.

[0075] Matching rules can be preset, for example, requiring at least one keyword to be fully matched. When the preset matching rules are met, the material text information and the first material are matched. For example, keywords such as "puppy", "grass", and "play" are extracted from a picture containing a puppy (the first material). In the process of generating corresponding material text information based on these keywords, at least one keyword is retained. For example, the generated material text information can be "the puppy's hair shines with a healthy luster in the sun, and it sometimes runs happily", retaining the keyword "puppy". Based on the complete match between the keyword "puppy" in the first material and the keyword "puppy" in the material text information, the material text information is matched to the picture containing the puppy. In addition, the semantic similarity calculation of the keyword of the first material and the material text information can be performed by natural language processing technology. According to the similarity calculation result, if the similarity exceeds a preset threshold (such as 0.7), it is determined that the material text information and the keyword of the first material are highly semantically related, and therefore, a corresponding relationship between the two is established. Then, the material text information and the first material are matched according to the corresponding relationship between the keyword and the material text information.

[0076] In some embodiments, there may be a situation where the keyword in the initial text information is a sensitive word. In this case, the keyword in the initial text information can be directly deleted to generate the material text information. In addition to directly deleting the keyword in the initial text information, the material text information corresponding to the keyword can also be deleted. Specifically, when generating the initial text information based on the keyword, it is necessary to establish a correspondence between the keyword and the initial text information generated based on the keyword. After the keyword in the initial text information is removed as a sensitive word, the material text information corresponding to the initial text information can be located and deleted (the material text information here is the initial text information remaining after deleting the keyword), thereby ensuring that the material text information and the first material can always match.

[0077] like Figure 6 As shown, the material text information and the first material can be arranged and combined in a certain form (such as mixed text and image, video superimposed with subtitles, etc.) according to the matching relationship between the material text information and the first material to generate video content.

[0078] In this embodiment, by matching the material text information with the keywords in the first material (such as a picture or a video), the material text information can be matched with its corresponding picture or video, thereby improving the quality of the video content.

[0079] In an optional embodiment, the multimedia editing method may further include: Newly added material information is acquired from the material library, wherein the newly added material information includes a material identification code and a placement position; wherein the material corresponding to the newly added material information is loaded into the second material as a decorative material.

[0080] The material library can be a local material library, a cloud material library, an online community shared material library, etc.

[0081] Decorative materials can be stickers (pictures, GIFs), filters, decorative text, etc. In addition to obtaining decorative materials from the material library, artificial intelligence technology can also be used to automatically generate corresponding decorative materials based on user input (such as text descriptions, keywords, style requirements, etc.).

[0082] The decorative material can be placed at the best position of the second material according to the content, layout and color of the second material, so that the user does not need to adjust it manually. Of course, the user can also drag and adjust when he wants to adjust it.

[0083] In this embodiment, the decorative material is obtained from the material library to modify the second material, so that the content of the second material is more vivid and interesting.

[0084] In an optional embodiment, the implementation code corresponding to the above method is located in an editing and processing toolkit; the editing and processing toolkit includes: a risk management module, a matching module, and a positioning module; The risk management module is used to remove sensitive words from the initial text information to obtain the material text information. The matching module is used to match the material text information with the first material according to the keywords in the material text information and the keywords of the first material to form a matching relationship. The positioning module is used to obtain the newly added material information from the material library, and the newly added material information includes a material identification code and a placement position; wherein the material corresponding to the newly added material information is loaded into the second material as a decorative material.

[0085] Exemplarily, the editing processing toolkit may be KMP SDK (Kotlin Multiplatform software development kit, multi-platform software development kit) or the like.

[0086] KMP SDK includes risk management module, matching module, positioning module, etc. KMP SDK can process the first material through risk management module, matching module and positioning module. By processing the first material through KMP SDK, developers can use a set of codes to run on various operating systems such as Android, iOS, and Hongmeng, which not only reduces development costs, but also reduces the differences in multi-terminal business logic and improves the consistency of multi-terminal experience.

[0087] In order to make this application easier to understand, the following Figure 7 and Figure 8 An exemplary application is provided.

[0088] In this exemplary application, KMP SDK is an editing and processing toolkit with cross-platform capabilities. KMP SDK includes an interface layer, a local recognition model, a risk management module, a matching module, a positioning module, and the like.

[0089] S600: The KMP SDK obtains the first material (or material ID).

[0090] S602: Compare the time length of the first material with a preset value (eg, 10 seconds).

[0091] S604: When the time length of the first material is less than a preset value, the first material is input into the local recognition model. When the time length of the first material is greater than the preset value, the first material is input into the cloud recognition model via the Interface layer to identify the keywords of the first material, and the first material and the keywords are returned to the KMP SDK.

[0092] S606, KMP SDK inputs the identified keywords into text generation models such as ChatGPT. ChatGPT processes the keywords according to business instructions (for example, requiring to generate a story based on the keywords) to generate initial text information that meets the business instructions.

[0093] S608, returning the initial text information to the risk management module in the KMP SDK.

[0094] S610, the risk management module retrieves a preset sensitive word library from the service platform 2 or locally, and compares the initial text information with the sensitive word library to remove sensitive words in the initial text information to obtain material text information.

[0095] S612: Input the material text information into the matching module.

[0096] S614: The matching module matches the material text information with the first material according to the keywords in the material text information and the keywords of the first material.

[0097] S616, obtaining new material information from the material library of the server through the positioning module, where the new material information includes a material identification code and a placement location.

[0098] S618, providing the first material, material text information, decorative material, newly added material information, and processing logic code and other information to the editor, and the editor processes the material-related information through the processing logic code to generate the second material.

[0099] Embodiment 2 Fig. 9 The block diagram of a multimedia editing device according to the second embodiment of the present application is schematically shown. The device can be divided into one or more program modules, one or more program modules are stored in a storage medium, and are executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Fig. 9 As shown, the device 1000 may include: an acquisition module 1100, a generation module 1200, and an editing module 1300, wherein: An acquisition module, used for acquiring a plurality of first materials; A generating module, configured to generate material information corresponding to each of the plurality of first materials, wherein the material information includes material text information; The editing module is used to edit the multiple first materials to obtain the second material according to the material information corresponding to each of the multiple first materials.

[0100] As an optional embodiment, the material information includes material text information; generating a plurality of material information corresponding to each of the first materials includes: Obtaining keywords of the first material; According to the keyword of the first material, the material text information of the first material is obtained; wherein the material text information includes the keyword. As an optional embodiment, according to the keyword of the first material, the material text information of the first material is obtained, including: Inputting the keywords of the first material into a text generation model to obtain initial text information; The sensitive words in the initial text information are removed to obtain the material text information.

[0101] As an optional embodiment, the device further includes: When the material text information is obtained, the material text information and the first material are matched according to the keywords in the material text information and the keywords of the first material to form a matching relationship.

[0102] As an optional embodiment, obtaining the keyword of the first material includes: Acquire the time length of the first material; When the time length is less than a preset value, identifying keywords in the first output by using a local recognition model; When the time length is not less than a preset value, the keywords in the first output are identified by a cloud recognition model.

[0103] As an optional embodiment, the device further includes: Acquire new material information from the material library, where the new material information includes a material identification code and a placement location; The material corresponding to the newly added material information is loaded into the second material as a decorative material.

[0104] As an optional embodiment, editing the plurality of first materials to obtain a second material according to material information corresponding to each of the plurality of first materials includes: According to a pre-configured processing logic code and material information corresponding to each of the plurality of first materials, the plurality of first materials are edited to obtain the second material; the processing logic code is used to indicate material processing logic.

[0105] As an optional embodiment, used in an editing processing toolkit; The editing and processing toolkit includes: risk management module, matching module, and positioning module; The risk management module is used to remove sensitive words in the initial text information to obtain the material text information.

[0106] The matching module is used to match the material text information with the first material according to the keywords in the material text information and the keywords of the first material to form a matching relationship; The positioning module is used to obtain the newly added material information from the material library, and the newly added material information includes a material identification code and a placement position; wherein the material corresponding to the newly added material information is loaded into the second material as a decorative material.

[0107] Embodiment 3 Fig.10The schematic diagram of the hardware architecture of a computer device 10000 suitable for implementing a multimedia editing method according to the third embodiment of the present application is shown schematically. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle-mounted terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a server cluster composed of multiple servers), etc. Fig.10 As shown, the computer device 10000 includes but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them: The memory 10010 includes at least one type of computer-readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10010 can be an internal storage module of the computer device 10000, such as a hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 can also be an external storage device of the computer device 10000, such as a plug-in hard disk equipped on the computer device 10000, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10010 can also include both the internal storage module of the computer device 10000 and its external storage device. In this embodiment, the memory 10010 is generally used to store an operating system and various application software installed in the computer device 10000, such as program codes of a multimedia editing method, etc. In addition, the memory 10010 can also be used to temporarily store various data that have been output or are to be output.

[0108] In some embodiments, the processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0109] The network interface 10030 may include a wireless network interface or a wired network interface, and the network interface 10030 is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal through a network, and to establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network may be a wireless or wired network such as an intranet, the Internet, the Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0110] It should be pointed out that Fig.10 Only a computer device having components 10010 - 10030 is shown, but it should be understood that implementation of all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0111] In this embodiment, the multimedia editing method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as processor 10020) to complete the embodiment of the present application.

[0112] Embodiment 4 An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the multimedia editing method in the embodiment are implemented.

[0113] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on the computer device, such as the program code of the multimedia editing method in the embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0114] Embodiment 5 An embodiment of the present application also provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0115] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented by general-purpose computer devices, they can be concentrated on a single computer device, or distributed on a network composed of multiple computer devices, optionally, they can be implemented by executable program codes of computer devices, so that they can be stored in a storage device and executed by the computer device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0116] It should be noted that the above are only preferred embodiments of the present application, and the patent protection scope of the present application is not limited thereto. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A multimedia editing method, characterized in that: The method comprises: Acquire multiple first materials; generating material information corresponding to each of the plurality of first materials; and The plurality of first materials are edited according to the material information corresponding to each of the plurality of first materials to obtain a second material.

2. The method according to claim 1, characterized in that The material information includes material text information; generating a plurality of material information corresponding to each of the first materials, including: Obtaining keywords of the first material; According to the keyword of the first material, material text information of the first material is acquired; wherein the material text information includes the keyword.

3. The method according to claim 2, characterized in that Acquiring material text information of the first material according to the keyword of the first material includes: Inputting the keywords of the first material into a text generation model to obtain initial text information; The sensitive words in the initial text information are removed to obtain the material text information.

4. The method according to claim 3, characterized in that The method further comprises: When the material text information is obtained, the material text information and the first material are matched according to the keywords in the material text information and the keywords of the first material to form a matching relationship.

5. The method according to claim 2, characterized in that: Obtaining keywords of the first material includes: Acquire the time length of the first material; When the time length is less than a preset value, identifying keywords in the first material by using a local recognition model; When the time length is not less than a preset value, keywords in the first material are identified through a cloud recognition model.

6. The method according to claim 1, characterized in that The method further comprises: Acquire new material information from the material library, where the new material information includes a material identification code and a placement location; The material corresponding to the newly added material information is loaded into the second material as a decorative material.

7. The method according to claim 1, characterized in that Editing the plurality of first materials to obtain a second material according to material information corresponding to each of the plurality of first materials includes: According to a pre-configured processing logic code and material information corresponding to each of the plurality of first materials, the plurality of first materials are edited to obtain the second material; the processing logic code is used to indicate material processing logic.

8. The method according to claim 1, characterized in that: Used in the editing toolkit; The editing and processing toolkit includes: risk management module, matching module, and positioning module; The risk management module is used to remove sensitive words in the initial text information to obtain the material text information. The matching module is used to match the material text information with the first material according to the keywords in the material text information and the keywords of the first material to form a matching relationship; The positioning module is used to obtain the newly added material information from the material library, and the newly added material information includes a material identification code and a placement position; wherein the material corresponding to the newly added material information is loaded into the second material as a decorative material.

9. A multimedia editing device, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of first materials; A generating module, configured to generate material information corresponding to each of the plurality of first materials, wherein the material information includes material text information; The editing module is used to edit the multiple first materials to obtain the second material according to the material information corresponding to each of the multiple first materials.

10. A computer device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claims 1 to 8 are implemented.

Images