Method and apparatus for processing audio and video data, electronic device and medium
Patent Information
- Application Number
- CN202510429592.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-07
- Publication Date
- 2026-10-16
AI Technical Summary
[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the above-described method.
Smart Images
Figure CN122925316A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of computer technology, and more particularly to the fields of data processing, large modeling, and natural language processing, specifically to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for processing audio and video data. Background Technology
[0002] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.
[0003] A large model (also known as a foundation model) is a machine learning model with a large number of parameters and a complex structure. It is capable of processing massive amounts of data and completing various complex tasks, such as speech recognition and semantic recognition.
[0004] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention
[0005] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for processing audio and video data.
[0006] According to one aspect of this disclosure, a method for processing audio and video data is provided, comprising: acquiring a plurality of target files associated with a target topic, wherein each of the plurality of target files is an audio file or a video file; and processing the plurality of target files using a large model to obtain a content summary text, wherein the large model is used to identify a plurality of sub-topic contents corresponding to a plurality of sub-topics associated with the target topic from the plurality of target files, and to generate the content summary text based on the plurality of sub-topic contents.
[0007] According to another aspect of this disclosure, an audio / video data processing apparatus is provided, comprising: a first module configured to acquire a plurality of target files associated with a target topic, wherein each of the plurality of target files is an audio file or a video file; and a second module configured to process the plurality of target files using a large model to obtain a content summary text, wherein the large model is used to identify a plurality of sub-topic contents corresponding to a plurality of sub-topics associated with the target topic from the plurality of target files, and to generate the content summary text based on the plurality of sub-topic contents.
[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the methods described above.
[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the above-described method.
[0010] According to another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the above-described method.
[0011] According to one or more embodiments of this disclosure, a method for processing audio and video data is provided. By using a large model to simultaneously process multiple audio and video files related to the same target topic, the method identifies content in each audio and video file that is related to at least one sub-topic of the target topic. This enables the large model to extract content related to the target topic from multiple perspectives and to mutually supplement and verify the content during the understanding process. This provides the large model with richer information, enabling it to generate a complete and accurate summary text of the content of multiple audio and video files with the same topic.
[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0013] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.
[0014] Figure 1This is a schematic diagram illustrating an example system in which various methods described herein may be implemented according to exemplary embodiments;
[0015] Figure 2 A flowchart illustrating a method for processing audio and video data according to an embodiment of the present disclosure is shown;
[0016] Figure 3 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown;
[0017] Figure 4 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown;
[0018] Figure 5 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown;
[0019] Figure 6 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown;
[0020] Figure 7 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown;
[0021] Figure 8 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown;
[0022] Figure 9 A structural block diagram of an audio / video data processing apparatus according to embodiments of the present disclosure is shown; and
[0023] Figure 10 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation
[0024] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0025] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.
[0026] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.
[0027] In related technologies, large models can be used to process audio and video files in batches to generate content summaries.
[0028] However, the above method does not take into account the possible relationships between multiple audio and video files, resulting in the generated summary text containing independent summaries for each audio and video file, which can easily lead to content duplication or misunderstandings.
[0029] To address the aforementioned issues, this disclosure provides a method for processing audio and video data. By using a large model to simultaneously process multiple audio and video files related to the same target topic, the method identifies content in each audio and video file that is related to at least one sub-topic of the target topic. This allows the large model to extract content related to the target topic from multiple perspectives and to mutually supplement and verify the content during the understanding process. This provides the large model with richer information, enabling it to generate a complete and accurate summary text of the content of multiple audio and video files with the same topic.
[0030] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.
[0031] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1 The system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.
[0032] In embodiments of this disclosure, server 120 may run one or more services or software applications that enable the execution of methods for processing audio and video data.
[0033] In some embodiments, server 120 may also provide other services or software applications that may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, such as to users of client devices 101, 102, 103, 104, 105 and / or 106 under a Software as a Service (SaaS) model.
[0034] exist Figure 1 In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system for implementing the audio and video data processing methods described herein, and is not intended to be limiting.
[0035] Users can use client devices 101, 102, 103, 104, 105, and / or 106 to perform audio and video data processing methods. The client devices can provide an interface that allows users to interact with the client devices. The client devices can also output information to the user through this interface. Although... Figure 1 Only six client devices are described, but those skilled in the art will understand that this disclosure can support any number of client devices.
[0036] Client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices can run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or include various mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. Client devices are capable of executing various applications, such as various internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and can use various communication protocols.
[0037] Network 110 can be any type of network well known to those skilled in the art, and can use any of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.) to support data communication. By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, a token ring network, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.
[0038] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.
[0039] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.
[0040] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.
[0041] In some implementations, server 120 can be a server for a distributed system or a server integrated with blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.
[0042] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. Databases 130 may reside in various locations. For example, a database used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. Databases 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from and from the databases in response to commands.
[0043] In some embodiments, one or more of the databases 130 may also be used by an application to store application data. The databases used by the application may be of different types, such as key-value stores, object stores, or regular stores supported by a file system.
[0044] Figure 1 The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.
[0045] Figure 2 A flowchart illustrating a method for processing audio and video data according to an embodiment of the present disclosure is shown.
[0046] like Figure 2 As shown, the audio and video data processing method 200 includes:
[0047] Step 210: Obtain multiple target files from multiple related target topics, wherein each target file is an audio file or a video file; and
[0048] Step 220: Process multiple target files using a large model to obtain a content summary text, wherein the large model is used to identify multiple sub-topic contents corresponding to multiple sub-topics associated with the target topic from the multiple target files, and generate the content summary text based on the multiple sub-topic contents.
[0049] Therefore, by using a large model to process multiple audio and video files related to the same target topic simultaneously, and identifying at least one sub-topic related to the target topic in each audio and video file, the large model can extract content related to the target topic from multiple perspectives and verify the mutual supplementation between the content during the understanding process. This provides the large model with richer information, enabling it to generate a complete and accurate summary text of the content of multiple audio and video files with the same topic.
[0050] In step 210, the multiple target files can be, for example, input from the user. For instance, the user can directly input multiple audio / video files as multiple target files. Alternatively, the user can input multiple link addresses corresponding to the multiple target files to obtain the corresponding multiple audio / video files based on the multiple link addresses.
[0051] In step 210, for example, the multiple target files may be multiple audio files; for example, the multiple targets may be multiple video files; for example, the multiple target files may be partly audio files and partly video files.
[0052] In step 210, the target topic can be determined by the user's direct input, or it can be determined based on the titles of multiple target files.
[0053] In steps 210 and 220, the target topic can be a thing, and multiple target files can be multiple audio and video files describing different attributes of the same thing.
[0054] For example, target file 1 is a tutorial on jujube cultivation, target file 2 is a method for making jujube tea, and target file 3 is a documentary of the jujube cultivation process. In this case, the target topic can be jujube, and based on multiple target files, their corresponding subtopics can be identified, for example, as variety, production area, and consumption method.
[0055] Understandably, the type and number of subtopics here depend on the specific content described by the multiple target files, and there are no restrictions on this.
[0056] Based on this, since the number and type of sub-topic content included in each target file are uncertain, by processing target files 1 to 3 simultaneously, we can directly start from the relatively broad target topic of jujubes and extract all the more specific sub-topic content related to jujubes from multiple target files for summarization, so as to generate a complete and accurate summary text.
[0057] Furthermore, target file 1 and target file 3 may contain duplicate content (for example, both introduce the varieties and production areas of jujubes). The two files can be compared and verified against each other to help the large model check and correct errors, reduce the possibility of duplicate content in the summary text, and improve the understanding accuracy of the large model.
[0058] In steps 210 and 220, the target topic can also be an event, and multiple target files can be a series of audio and video files recorded for the same event at different time periods.
[0059] For example, multiple target files can be audio and video recordings of all math classes taught by students in the current semester. In this case, the target theme is the math course content of the current semester. Based on multiple target files, their corresponding sub-themes can be identified, for example, as theorem explanations, problem explanations, and review sessions.
[0060] Specifically, the explanation of theorems may span multiple lessons, and within the same lesson, theorem explanation, problem explanation, and review may be conducted simultaneously. Therefore, by processing multiple audio and video recordings corresponding to multiple lessons simultaneously, relevant content can be extracted from different audio and video recordings for each sub-topic. Based on the extracted content, these content can be used as context to provide richer information for the large model, thereby better generating a logically clear and complete summary text for the relevant content and improving the user experience.
[0061] It should be noted that the above examples are for illustrative purposes only and are not intended to limit the scope. Multiple target files can also be multiple audio and video recordings from meetings within the new product development cycle, with the target theme being new product development, and the corresponding sub-themes being, for example, development progress, problem summaries, and optimization measures, etc.
[0062] In step 220, the large model can be, for example, a multimodal large model, to enable simultaneous processing of multimodal data such as audio data, video data, and text data.
[0063] In step 220, the content summary text can be, for example, a verbatim transcript of the target topic, meeting minutes, or a smart summary.
[0064] Figure 3 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown.
[0065] According to some embodiments, such as Figure 3 As shown, in addition to steps 210 and 220 described above, method 200 further includes:
[0066] Step 310: Sort multiple target files according to their generation time; and
[0067] Step 320: Use a large model to process the sorted target files to obtain a summary text of the content.
[0068] In some cases, referring to the examples of classroom teaching audio and video mentioned above, multiple target files have a temporal relationship. For example, the first lesson explains theorems, the second lesson explains the corresponding exercises, and the third lesson reviews the first two lessons. Based on this, by considering the temporal order between target files, the overall logic between multiple target files can be clarified, allowing the extracted content to naturally form a continuous context. This enables the larger model to better understand the content and output a more complete and coherent summary text.
[0069] Figure 4 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown.
[0070] According to some embodiments, such as Figure 4 As shown, step 220 includes:
[0071] Step 410: Perform speech recognition on multiple target files to obtain multiple texts to be processed;
[0072] Step 420: For each of the multiple texts to be processed,
[0073] Step 421: Perform semantic recognition on the text to be processed based on the target topic to identify at least one subtopic associated with the target topic from the text to be processed; and
[0074] Step 422: For each subtopic in at least one subtopic, extract the text content associated with that subtopic from the text to be processed, as at least a portion of the subtopic content corresponding to that subtopic in the multiple subtopic contents; and
[0075] Step 430: Generate a summary text based on multiple sub-topics.
[0076] Therefore, by first transcribing audio and video files into text files and then performing semantic recognition on the text files, the content of the target files can be understood simply and efficiently. This allows for the accurate identification of the number and type of sub-topics associated with the target topic in each audio and video file, and the extraction of relevant content from the corresponding text files, thereby improving the efficiency and effectiveness of generating content summary texts.
[0077] Furthermore, most current semantic recognition models can only process text data. Text transcription can be effectively applied to most semantic recognition models, reducing the difficulty of implementation.
[0078] In step 410, exemplarily, the large model in step 220 includes a speech recognition model, which can process multiple target files separately to obtain multiple texts to be processed. The aforementioned speech recognition model can be constructed based on machine learning models such as UBM-GMM (Gaussian Mixture Model-Universal Background Model) and SVM (Support Vector Machine), or based on neural networks such as DNN (Deep Neural Networks), CNN (Convolutional Neural Networks), LSTM (Long Short-Term Memory), Conformer (Convolutional Attention Neural Network), and TDNN (Time Delay Neural Network). Understandably, the speech recognition model can employ other types of network structures, which are not limited here.
[0079] In step 420, for example, the large model in step 220 includes a semantic recognition model, which can process multiple texts to be processed separately to obtain multiple sub-topic contents. The aforementioned semantic recognition model can be constructed based on machine learning models such as UBM-GMM and SVM, or on neural networks such as DNN, CNN, LSTM, Conformer, and TDNN. Understandably, the semantic recognition model can adopt other types of network structures, which are not limited here.
[0080] Figure 5 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown.
[0081] According to some embodiments, such as Figure 5 As shown, step 430 includes:
[0082] Step 510: For each subtopic content within multiple subtopic contents, divide the subtopic content into multiple first parts, wherein each first part is associated with one target file among multiple target files; and
[0083] Step 520: Perform similarity comparison on multiple first parts to filter out texts with common content as content summary text, wherein at least a target number of first parts include texts with common content.
[0084] Therefore, for scenarios where key content needs to be extracted, the above method can identify the common content (key content) mentioned by multiple target documents in each sub-topic associated with the target topic as the summary text, effectively expanding the scope of applicable scenarios of this disclosure.
[0085] For example, referring to the classroom teaching scenario above, some key theorems may be repeatedly mentioned in problem-solving sessions and review sessions. Therefore, by identifying the theorems that are repeatedly mentioned in review sessions, we can determine that they are the key points of the math course this semester. Outputting them as summary texts can help users better understand the key points in multiple target files, thereby improving the user experience.
[0086] In step 510, the content portions from different target files within the same subtopic can be categorized to obtain multiple first portions.
[0087] In step 520, the similarity comparison can be, for example, based on key field similarity comparison or based on semantic understanding of content similarity comparison.
[0088] In step 520, the target quantity can be, for example, more than half of the quantity of the multiple first parts.
[0089] Figure 6 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown.
[0090] According to some embodiments, such as Figure 6 As shown, step 430 includes:
[0091] Step 610: For each subtopic content within multiple subtopic contents, divide that subtopic content into multiple second parts, wherein each of the multiple second parts is associated with one target file among multiple target files; and
[0092] Step 620: Generate a content comparison based on multiple subtopics and multiple second parts corresponding to the content of each subtopic, as a content summary text.
[0093] Therefore, for some scenarios that develop sequentially (e.g., chronologically), the above method can determine the similarities and differences of each sub-topic associated with the target topic in different target files, and generate summary text based on these similarities and differences to display to the user, effectively expanding the scope of applicable scenarios of this disclosure.
[0094] For example, in the product development meeting scenario mentioned above, the product development progress, problems encountered during the development process, and optimization measures involved in each meeting may change. By summarizing the changes in the aforementioned sub-topics in each meeting, users can better grasp the relevant situation of product development and improve their user experience.
[0095] In step 610, the content portions from different target files within the same subtopic can be categorized to obtain multiple second parts.
[0096] In step 620, referring to the above product development meeting scenario example, a content comparison table as a content summary text can be generated, for example, to be displayed to the user.
[0097]
[0098] Understandably, not every meeting audio (target file) includes all subtopics. Therefore, for subtopics for which no corresponding content has been extracted, the corresponding meeting audio section in the table (e.g., the "Current Issues" and "Optimization Measures" sections of meeting audio n) can be left blank.
[0099] It should be noted that the table above is for illustrative purposes only. The comparison of the contents in step 620 can also be generated in other non-tabular formats, and there are no restrictions on this.
[0100] Figure 7 A partial flowchart of another method for processing audio and video data according to an embodiment of the present disclosure is shown.
[0101] According to some embodiments, such as Figure 7 As shown, in addition to steps 210 and 220 described above, method 200 further includes:
[0102] Step 710: In response to the detection of historical content summary text related to the target topic, generate a prompt message to encourage the user to merge the text; and
[0103] Step 720: In response to user confirmation, perform text merging, using a large model to process multiple target files and historical content summary text to obtain content summary text.
[0104] Therefore, historical content summaries related to the target topic can be obtained as supplementary information to further improve the understanding accuracy of the large model. Furthermore, the processing of historical content summaries is relatively simple, effectively balancing the processing efficiency and effectiveness of generating the content summary text.
[0105] For example, referring to the product development meeting scenario mentioned above, the product may have already undergone a historical development process, but the development was stopped for some reason. Therefore, there is already a historical content summary text generated based on the audio and video of the historical product development meeting. If the development of the product needs to be restarted, the corresponding historical content summary text can be obtained and used as input to the large model, so that the large model can obtain richer related information, thereby making the content summary text generated by it more complete and accurate.
[0106] According to some embodiments, such as Figure 8 As shown, step 210 includes:
[0107] Step 810: Obtain multiple initial files, where each initial file is either an audio file or a video file; and
[0108] Step 820: In response to the total duration of multiple initial files being less than the duration threshold, the multiple initial files are treated as multiple target files.
[0109] Most current large models have time processing limitations. Based on this, by limiting the total time of multiple target files, the requirements of most large models can be better met, thereby expanding the scope of application.
[0110] In step 820, the duration threshold can be determined, for example, based on the specific requirements of the large model.
[0111] For example, when multiple initial files are detected to have a duration exceeding a duration threshold, a prompt message can be generated to encourage the user to filter and exclude the multiple initial files so that the total duration of the remaining multiple initial files after filtering meets the requirements.
[0112] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0113] According to another aspect of this disclosure, an apparatus for processing audio and video data is provided. For example... Figure 9 As shown, the audio and video data processing apparatus 900 includes: a first module 910 configured to acquire multiple target files associated with a target topic, wherein each target file is an audio file or a video file; and a second module 920 configured to process the multiple target files using a large model to obtain a content summary text, wherein the large model is used to identify multiple sub-topic contents corresponding to multiple sub-topics associated with the target topic from the multiple target files, and to generate a content summary text based on the multiple sub-topic contents.
[0114] According to another aspect of this disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the aforementioned method.
[0115] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause the computer to perform the aforementioned method.
[0116] According to another aspect of this disclosure, a computer program product is also provided, including a computer program, wherein the computer program implements the aforementioned method when executed by a processor.
[0117] like Figure 10 As shown, the electronic device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of the electronic device 1000. The computing 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.
[0118] Multiple components in electronic device 1000 are connected to I / O interface 1005, including: input unit 1006, output unit 1007, storage unit 1008, and communication unit 1009. Input unit 1006 can be any type of device capable of inputting information to electronic device 1000. Input unit 1006 can receive input digital or character information and generate key signal input related to user settings and / or function control of electronic device, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 1007 can be any type of device capable of presenting information, and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1008 may include, but is not limited to, disk and optical disk. Communication unit 1009 allows electronic device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth. TM Devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices and / or the like.
[0119] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as methods for processing audio and video data. For example, in some embodiments, the methods for processing audio and video data can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the audio and video processing methods described above can be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform audio and video data processing methods by any other suitable means (e.g., by means of firmware).
[0120] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0121] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0122] 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.
[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0124] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0125] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.
[0126] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0127] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.
Claims
1. A method for processing audio and video data, comprising: Obtain multiple target files associated with a target topic, wherein each of the multiple target files is an audio file or a video file; and The multiple target files are processed using a large model to obtain a content summary text. The large model is used to identify multiple sub-topic contents corresponding to multiple sub-topics associated with the target topic from the multiple target files, and to generate the content summary text based on the multiple sub-topic contents.
2. The method according to claim 1, further comprising: The target files are sorted according to their generation time; as well as The sorted target files are processed using a large model to obtain the content summary text.
3. The method according to claim 1 or 2, wherein, The process of using a large model to process the multiple target files includes: Speech recognition is performed on the multiple target files to obtain multiple texts to be processed; For each of the plurality of texts to be processed, Based on the target topic, semantic recognition is performed on the text to be processed to identify at least one subtopic associated with the target topic from the text to be processed; and For each subtopic in the at least one subtopic, extract the text content associated with that subtopic from the text to be processed, as at least a portion of the subtopic content corresponding to that subtopic in the plurality of subtopic contents; and The content summary text is generated based on the multiple sub-topics.
4. The method according to claim 3, wherein, in, The generation of the content summary text based on the multiple sub-topic contents includes: For each subtopic content among the plurality of subtopic contents, the subtopic content is divided into a plurality of first parts, wherein each of the plurality of first parts is associated with a target file among the plurality of target files; and The plurality of first parts are compared for similarity to select common content text as the content summary text, wherein at least a target number of the plurality of first parts include the common content text.
5. The method according to claim 3, wherein, The generation of the content summary text based on the multiple sub-topic contents includes: For each of the plurality of subtopic contents, the subtopic content is divided into a plurality of second parts, wherein each of the plurality of second parts is associated with a target file among the plurality of target files; and Based on the multiple subtopics and the multiple second parts corresponding to the content of each subtopic, a content comparison is generated as the content summary text.
6. The method according to any one of claims 1-5, further comprising: In response to the detection of historical content summary text related to the target topic, a prompt message is generated to prompt the user to merge the text. as well as In response to the user's confirmation to merge the text, the large model is used to process the multiple target files and the historical content summary text to obtain the content summary text.
7. The method according to any one of claims 1-6, wherein, The process of obtaining multiple target files associated with a target topic includes: Obtain multiple initial files, wherein each of the multiple initial files is an audio file or a video file; and In response to the fact that the total duration of the plurality of initial files is less than the duration threshold, the plurality of initial files are used as the plurality of target files.
8. A device for generating a listening transcript, comprising: The first module is configured to acquire multiple target files associated with a target topic, wherein each of the multiple target files is an audio file or a video file; and The second module is configured to process the multiple target files using a large model to obtain a content summary text, wherein the large model is used to identify multiple sub-topic contents corresponding to multiple sub-topics associated with the target topic from the multiple target files, and generate the content summary text based on the multiple sub-topic contents.
9. An electronic device, comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.
11. A computer program product comprising a computer program, wherein, The computer program, when executed by a processor, implements the method of any one of claims 1-7.