An abstract generation method, apparatus, device, and medium

Abstract

The application discloses a summary generation method and device applied to the technical field of data processing, equipment and a medium. In the method, content data of each sub-content included in media content is acquired, and summaries of the sub-contents are determined based on the content data of the sub-contents. The summaries of the sub-contents can describe the main content of the sub-contents. Extracting the summaries of the sub-contents first can reduce the difficulty of generating a total summary of the media content. The summaries of the sub-contents are fused based on the weights of the sub-contents to obtain a summary of the media content. The weight of a sub-content can reflect the importance of the sub-content in the media content. In this way, the summaries of the sub-contents are fused with reference to the importance of each sub-content in the media content, which can reduce the omission of important content, avoid excessive description of unimportant content, and obtain a summary of the media content which can accurately describe the main content of the media content, so that a user can understand the media content through the summary.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method, apparatus, device, and medium for generating abstracts. Background Technology

[0002] For some media content, users need to quickly understand the specific content. For example, in a video playback scenario, users may need to understand the general content of the video to decide whether to continue watching. Similarly, in a meeting scenario, after the meeting ends, users may need to review the meeting minutes to understand what was discussed.

[0003] Currently, users can quickly understand media content through summaries. However, these summaries often fail to accurately capture the main points of the content, hindering users' comprehension. Summary of the Invention

[0004] In view of this, this application provides a summary generation method, apparatus, device and medium, which aims to generate a summary that accurately describes the main content of the media content, so that users can understand the media content through the summary.

[0005] Based on this, the technical solution provided in this application is as follows:

[0006] In a first aspect, this application provides a summary generation method, the method comprising: acquiring content data of various sub-contents included in media content, wherein the sub-contents are obtained by dividing the media content; determining a summary of the sub-contents based on the content data of each sub-content; and fusing the summaries of each sub-content based on the weights of each sub-content to obtain a summary of the media content, wherein the weights of the sub-contents are used to represent the importance of the sub-contents in the media content.

[0007] In one possible implementation, the weight of the sub-content is determined based on the content information of the sub-content, which is determined based on the time information of the sub-content in the media content and the content data of the sub-content.

[0008] In one possible implementation, the weight of the sub-content is determined based on the sub-weights corresponding to the sub-information included in the content information of the sub-content.

[0009] In one possible implementation, the content information includes one or more of the following sub-information: the duration of the sub-content, the number of people involved in the sub-content, and the position of the time period of the sub-content within the time period of the media content.

[0010] In one possible implementation, the weights of the sub-contents are determined based on an artificial intelligence model, which outputs weights based on the input content information.

[0011] In one possible implementation, fusing the summaries of each sub-content based on the weights of each sub-content to obtain the summary of the media content includes: processing the weights of each sub-content and the summaries of each sub-content based on a first language processing model to obtain the summary of the media content.

[0012] In one possible implementation, the content data is text data, and determining the summary of each sub-content based on its content data includes: processing the content data of each sub-content using a second language processing model to obtain a summary of each sub-content.

[0013] In one possible implementation, the media content is the content of the meeting, the sub-content is the content of the sub-meetings obtained by dividing the meeting, or the meeting is a recurring schedule meeting, and the sub-content is the content of at least one schedule meeting included in the recurring schedule meeting.

[0014] In one possible implementation, the sub-conferences are obtained by dividing the conference based on the conference type and the conference content.

[0015] In one possible implementation, the sub-meetings are obtained by dividing the meeting based on at least two content dimensions.

[0016] Secondly, this application provides a summary generation apparatus, the apparatus comprising: an acquisition unit, configured to acquire content data of various sub-contents included in media content, wherein the sub-contents are obtained by dividing the media content; a determination unit, configured to determine a summary of the sub-contents based on the content data of each sub-content; and a generation unit, configured to fuse the summaries of each sub-content based on the weights of each sub-content to obtain a summary of the media content, wherein the weights of the sub-contents are used to represent the importance of the sub-contents in the media content.

[0017] In one possible implementation, the weight of the sub-content is determined based on the content information of the sub-content, which is determined based on the time information of the sub-content in the media content and the content data of the sub-content.

[0018] In one possible implementation, the weight of the sub-content is determined based on the sub-weights corresponding to the sub-information included in the content information of the sub-content.

[0019] In one possible implementation, the content information includes one or more of the following sub-information: the duration of the sub-content, the number of people involved in the sub-content, and the position of the time period of the sub-content within the time period of the media content.

[0020] In one possible implementation, the weights of the sub-contents are determined based on an artificial intelligence model, which outputs weights based on the input content information.

[0021] In one possible implementation, the generation unit is specifically used to process the weights of each of the sub-contents and the summaries of each of the sub-contents based on a first language processing model to obtain a summary of the media content.

[0022] In one possible implementation, the content data is text data, and the determining unit is used to process the content data of each sub-content based on a second language processing model to obtain a summary of each sub-content.

[0023] In one possible implementation, the media content is the content of the meeting, the sub-content is the content of the sub-meetings obtained by dividing the meeting, or the meeting is a recurring schedule meeting, and the sub-content is the content of at least one schedule meeting included in the recurring schedule meeting.

[0024] In one possible implementation, the sub-conferences are obtained by dividing the conference based on the conference type and the conference content.

[0025] In one possible implementation, the sub-meetings are obtained by dividing the meeting based on at least two content dimensions.

[0026] Thirdly, this application provides an electronic device, comprising:

[0027] One or more processors;

[0028] Storage device, on which one or more programs are stored,

[0029] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described in the first aspect.

[0030] Fourthly, this application provides a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in the first aspect or any implementation thereof.

[0031] Fifthly, this application provides a computer program product that, when run on a device, causes the device to perform the method described in the first aspect or any implementation thereof.

[0032] Therefore, this application has the following beneficial effects:

[0033] This application provides a summary generation method, apparatus, device, and medium. In this method, content data of each sub-content included in media content is acquired, and a summary for each sub-content is determined based on the content data of each sub-content. The summary of each sub-content describes its main content. Extracting the summaries of the sub-contents first reduces the difficulty of generating a comprehensive summary of the media content. Based on the weights of each sub-content, the summaries of each sub-content are merged to obtain a summary of the media content. The weights of the sub-contents reflect their importance within the media content. Thus, by merging the summaries of each sub-content according to their importance within the media content, the omission of important content is reduced, and excessive description of unimportant content is avoided. The resulting summary of the media content accurately describes its main content, making it easier for users to understand the media content through the summary. Attached Figure Description

[0034] Figure 1 A flowchart illustrating a method for generating an abstract, as provided in an embodiment of this application;

[0035] Figure 2 This is a schematic diagram of the structure of an abstract generation device provided in an embodiment of this application;

[0036] Figure 3 This is a schematic diagram of the basic structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0037] To facilitate understanding and explanation of the technical solutions provided in the embodiments of this application, the background technology of this application will be described first.

[0038] Media content refers to content expressed through various means of dissemination. Media content includes one or more of the following: video content, image content, audio content, and text content. Media content can be disseminated via the internet, making it convenient for users to view it online. Currently, users have access to a large amount of media content, and some media content is quite comprehensive. To facilitate user viewing, summaries describing the main points of the media content can be provided. By viewing these summaries, users can quickly understand the specific content included in the media, making it easier for them to select the media content they need or to enhance their understanding of the content. However, current media content summaries often fail to accurately describe the main points of the media content.

[0039] Based on this, embodiments of this application provide a summary generation method, apparatus, device, and medium. In this method, content data of each sub-content included in the media content is obtained, and a summary of each sub-content is obtained based on the content data of each sub-content. The summary of each sub-content can describe the main content of the sub-content. Extracting the summaries of the sub-contents first reduces the difficulty of generating a summary of the media content. Based on the weight of each sub-content, the summaries of each sub-content are merged to obtain a summary of the media content. The weight of each sub-content reflects its importance within the media content. Thus, by referring to the importance of each sub-content within the media content and merging the summaries of the sub-contents, the omission of important content can be reduced, and excessive description of unimportant content can be avoided. The resulting summary of the media content can accurately describe the main content of the media content, making it easier for users to understand the media content through the summary.

[0040] This application provides a summary generation method that can be applied to electronic devices with data processing capabilities. The electronic device can be, for example, a server or a terminal. The terminal includes, but is not limited to, smartphones, tablets, laptops, personal digital assistants (PDAs), or smart wearable devices. The server can be a cloud server, such as a central server in a central computing cluster or an edge server in an edge computing cluster. Alternatively, the server can be a server in a local data center. A local data center refers to a data center directly controlled by the user.

[0041] Electronic devices acquire content data from the various sub-contents within the media content. Based on this data, a summary of each sub-content is generated. Then, based on the weights of each sub-content, these summaries are merged to obtain a summary of the media content. The weights of the sub-contents represent their importance within the overall media content. Extracting sub-content summaries first and then merging them to obtain the media content summary reduces the difficulty of generating a summary and facilitates its creation. Merging the sub-content summaries according to their importance within the media content minimizes the omission of important content and avoids excessive description of unimportant information. The resulting summary accurately encapsulates the main content of the media content, meeting the needs of users viewing a summary of the media content.

[0042] Those skilled in the art will understand that the above application scenarios are merely one example of how the embodiments of this application can be implemented. The scope of application of the embodiments of this application is not limited by any aspect of this framework.

[0043] To facilitate understanding of the technical solutions provided in the embodiments of this application, the abstract generation method provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0044] See Figure 1 As shown, this figure is a flowchart of an abstract generation method provided in an embodiment of this application. Figure 1 As shown, the method may include S101-S103:

[0045] S101: Obtain the content data of each sub-content included in the media content.

[0046] Media content includes one or more of the following: video content, image content, audio content, and text content. This application does not limit the specific types of media content.

[0047] Sub-content refers to a portion of media content that has been divided into sub-contents. Media content includes at least two sub-contents.

[0048] This application does not limit the method of dividing sub-content. In one possible implementation, the media content is divided into sub-contents by average duration. For example, if the media content is video content, it can be divided into multiple sub-contents in 20-minute intervals. In another possible implementation, the content included in the media content is analyzed, and the content is clustered to divide the media content based on similar content types. In this way, highly relevant parts of the content can be grouped into one sub-content. The sub-contents obtained in this way conform to the actual content structure of the media content, enabling the extraction of more accurate sub-content summaries, and thus generating a more accurate summary of the media content.

[0049] In one possible implementation, the media content is the content of the meeting. For example, the sub-content is the content of the sub-meetings obtained by dividing the meeting.

[0050] The embodiments of this application do not limit the way of dividing the meeting into sub-meetings.

[0051] As an example, meetings can be divided into sub-meetings based on their meeting type and content. The meeting type can be determined based on the meeting's communication information. This communication information may include one or more of the following: information representing the number of participants, information representing the communication format, and information representing the communication content. Sub-meetings can be obtained by using a partitioning model corresponding to the meeting type. Alternatively, sub-meetings can be determined by using partitioning rules corresponding to the meeting type.

[0052] As another example, the meeting content includes content from at least two dimensions. The meeting is divided into sub-meetings based on these content dimensions. In one possible implementation, a division method corresponding to the content dimensions is used to determine candidate segmentation points and their segmentation confidence levels. Target segmentation points are determined based on the segmentation confidence levels, and the meetings are then divided using these target segmentation points to obtain sub-meetings. In another possible implementation, the meetings are divided using a division method corresponding to the content dimensions to obtain meeting segments. Meeting segments that meet certain criteria are then merged to obtain sub-meetings. Qualifying meeting segments include, for example, those with adjacent time periods within the meeting and a content similarity greater than a similarity threshold.

[0053] Alternatively, the meeting is a recurring scheduled meeting. The sub-content consists of the content of at least one scheduled meeting included in the recurring scheduled meeting. For example, the meeting is a weekly meeting held every Monday afternoon. The sub-content consists of at least one Monday afternoon meeting included in that weekly meeting.

[0054] The content data of a sub-content is data related to the sub-content. Taking a sub-meeting as an example, the content data of the sub-meeting is the meeting data. This application does not limit the specific type of the content data of the sub-content. As an example, the content data of the sub-content may be one or more of audio data, video data, image data, and text data.

[0055] S102: Based on the content data of each sub-content, determine the summary of each sub-content.

[0056] The summary of a sub-content is used to describe the main content of the sub-content. This application does not limit the implementation method of determining the summary of each sub-content based on its content data. In one possible implementation, keywords of the sub-content are determined by analyzing its content data. A summary of the sub-content is then generated based on these keywords. In another possible implementation, the content data of the sub-content is processed using a second language processing model to obtain a summary. This second language processing model has natural language processing capabilities. The second language processing model can analyze the input content data and output a summary.

[0057] The content data of each sub-content within the media content is relatively small, making it easier to process the sub-content data to obtain a summary of the sub-content. Generating summaries of sub-content is inexpensive and provides a high degree of accuracy in summarizing the sub-content, thereby improving the accuracy of the resulting media content summary.

[0058] S103: The summaries of each sub-content are merged based on the weight of each sub-content to obtain a summary of the media content.

[0059] Different sub-contents have varying degrees of importance within the overall media content. The importance of a sub-content within the media content is represented by its weight.

[0060] The embodiments of this application do not limit the method for determining the weight of sub-content.

[0061] In one possible implementation, the weights of sub-contents can be set by the content creator. For example, if the media content is generated based on a web conference, the weights of each sub-content within the media content can be set by the web conference organizer, host, or other personnel with conference management authority.

[0062] In another possible implementation, the weight of sub-content is determined based on its content information. As an example, the content information of sub-content is determined by its temporal information within the media content, as well as content data. For instance, the content information includes the temporal information of the sub-content within the media content, and relevant information about the specific content determined by the content data. The temporal information of sub-content within the media content can reflect its importance to some extent. For example, sub-content at the beginning of the media content, typically the introductory section, has lower importance. Conversely, sub-content at the end of the media content, typically the summary section, has higher importance. Analyzing the content data allows us to obtain the specific content of the sub-content, thereby determining its importance and weight.

[0063] As one example, an AI model is pre-trained to determine the weights of sub-content. For instance, the AI ​​model is trained using training data that includes training content information and its labels. The labels of the training content information serve as its weights. The trained AI model can then determine the weights of sub-content based on its content information. As another example, the labels of the training content information serve as its importance values. These importance values ​​measure the significance of the training content information. The trained AI model can then determine the importance values ​​of the sub-content based on its content information. Finally, it determines the weights of the sub-content based on the weights corresponding to these importance values.

[0064] As another example, the content information of the sub-content is analyzed to obtain at least one dimension of sub-information that can determine the weight of the sub-content. This application does not limit the way the dimensions of the content information are divided. For example, the content information may include one or more of the following: the duration of the sub-content, the number of people involved in the sub-content, and the position of the sub-content's time period within the time period of the media content. The duration of the sub-content and the position of its time period within the time period of the media content can be determined by analyzing the sub-content's time information within the media content. The number of people involved in the sub-content can be obtained through analysis of the sub-content's content data. In another possible implementation, for scenarios where the media content is the content of a meeting, the people involved in the sub-content are the participants, and the sub-information also includes the participants' meeting identities. Meeting identities can be determined based on the participants' speaking styles, speaking frequencies, and other speaking characteristics included in the content data of the sub-content. For example, for a speaking style that summarizes events and a high speaking frequency, the participant is identified as a main speaker. For a speaking style that promotes the process and a high speaking frequency, the participant is identified as a moderator.

[0065] Each piece of information has a corresponding sub-weight. The sub-weight of a piece of information can be determined, for example, based on pre-set rules for determining sub-weights. For example, sub-content at the initial stage of media content has a lower sub-weight value, while sub-content at the end stage of media content has a higher sub-weight value.

[0066] When meeting information includes multiple sub-information items with different dimensions, the weight of each sub-item is determined based on its sub-weight. As an example, the statistical value of the sub-weight of each sub-item within the sub-content is calculated and used as the weight of the sub-content. Statistical values ​​can be, for example, averages, weighted averages, and medians obtained using statistical methods.

[0067] The weight of each sub-content affects the proportion of sub-content summaries included in the media content summary. Based on the weight of each sub-content, the summaries of each sub-content are merged to obtain the media content summary.

[0068] This application does not limit the implementation method of fusing the summaries of each sub-content based on their weights to obtain a summary of the media content. In one possible implementation, a first language processing model is used to process the weights and summaries of each sub-content to obtain a summary of the media content. The first language processing model has natural language processing capabilities. It can be used to fuse summaries based on their weights and output a summary. In another possible implementation, rules for fusing the summaries are pre-defined. These rules define how summaries with different weights are fused. Based on these rules, the summaries of each sub-content are processed to obtain a summary of the media content.

[0069] Based on the above S101-S103, it is clear that extracting summaries from sub-contents first, and then merging these summaries to obtain a summary of the media content, reduces the difficulty of generating a summary and facilitates its creation. By considering the importance of each sub-content within the media content, merging the summaries reduces the omission of important content and avoids excessive description of unimportant content. The resulting summary accurately encapsulates the main content of the media content, meeting users' needs for viewing summaries and improving user experience.

[0070] Based on the summary generation method provided in the above-described embodiments, this application also provides a summary generation apparatus, which will be described below with reference to the accompanying drawings.

[0071] See Figure 2 As shown, this figure is a schematic diagram of the structure of an abstract generation device provided in an embodiment of this application. Figure 2 As shown, the abstract generation apparatus includes:

[0072] The acquisition unit 201 is used to acquire the content data of each sub-content included in the media content, wherein the sub-content is obtained by dividing the media content;

[0073] The determining unit 202 is used to determine a summary of the sub-content based on the content data of each sub-content;

[0074] The generation unit 203 is used to fuse the summaries of each sub-content based on the weight of each sub-content to obtain a summary of the media content, wherein the weight of each sub-content is used to represent the importance of the sub-content in the media content.

[0075] In one possible implementation, the weight of the sub-content is determined based on the content information of the sub-content, which is determined based on the time information of the sub-content in the media content and the content data of the sub-content.

[0076] In one possible implementation, the weight of the sub-content is determined based on the sub-weights corresponding to the sub-information included in the content information of the sub-content.

[0077] In one possible implementation, the content information includes one or more of the following sub-information: the duration of the sub-content, the number of people involved in the sub-content, and the position of the time period of the sub-content within the time period of the media content.

[0078] In one possible implementation, the weights of the sub-contents are determined based on an artificial intelligence model, which outputs weights based on the input content information.

[0079] In one possible implementation, the generation unit 203 is specifically used to process the weights of each sub-content and the summaries of each sub-content based on a first language processing model to obtain a summary of the media content.

[0080] In one possible implementation, the content data is text data, and the determining unit 202 is used to process the content data of each sub-content based on a second language processing model to obtain a summary of each sub-content.

[0081] In one possible implementation, the media content is the content of the meeting, the sub-content is the content of the sub-meetings obtained by dividing the meeting, or the meeting is a recurring schedule meeting, and the sub-content is the content of at least one schedule meeting included in the recurring schedule meeting.

[0082] In one possible implementation, the sub-conferences are obtained by dividing the conference based on the conference type and the conference content.

[0083] In one possible implementation, the sub-conferences are obtained by dividing the conference based on at least two content dimensions.

[0084] Based on the summary generation method provided in the above embodiments, this application also provides an electronic device, including: one or more processors; a storage device storing one or more programs thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the summary generation method as described in any of the above embodiments.

[0085] The following is for reference. Figure 3This document illustrates a structural schematic diagram of an electronic device 300 suitable for implementing embodiments of this application. The terminal devices in these embodiments may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Android Devices), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs (televisions), desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0086] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0087] Typically, the following devices can be connected to I / O interface 305: input devices 308 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0088] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. When the computer program is executed by the processing device 301, it performs the functions defined in the methods of the embodiments of this application.

[0089] The electronic device provided in this application embodiment and the abstract generation method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0090] Based on the summary generation method provided in the above embodiments, this application provides a computer storage medium storing a computer program thereon, wherein the program, when executed by a processor, implements the summary generation method as described in any of the above embodiments.

[0091] It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0092] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0093] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0094] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned digest generation method.

[0095] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The units described in the embodiments of this application can be implemented in software or in hardware. The name of the unit / module does not necessarily limit the unit itself; for example, a voice data acquisition module can also be described as a "data acquisition module".

[0098] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0099] In the context of this application, 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. Machine-readable media 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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0100] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0101] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0102] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0103] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An abstract generation method characterized by comprising: The method comprises: obtaining content data of each sub-content included in media content, the sub-content being obtained by dividing the media content, the media content being content of a conference, the sub-content being content of a sub-conference obtained by dividing the conference, or the conference being a repetitive schedule conference, and the sub-content being content of at least one schedule conference included in the repetitive schedule conference, the media content including one or more of video content, image content, audio content, and text content; determining an abstract of each sub-content based on the content data of each sub-content; fusing the abstracts of the sub-contents based on weights of the sub-contents to obtain an abstract of the media content, the weights of the sub-contents being used to represent the importance of the sub-contents in the media content; The sub-conference is obtained by dividing the conference in the following manner: dividing the conference based on a conference type of the conference and conference content of the conference to obtain the sub-conference; or dividing the conference based on at least two content dimensions of the conference to obtain the sub-conference; The weight of the sub-content is determined according to content information of the sub-content, the content information being determined based on time information of the sub-content in the media content and content data of the sub-content; The weight of the sub-content is determined based on a sub-weight corresponding to sub-information included in the content information of the sub-content.

2. The method of claim 1, wherein, The content information includes one or more of the following sub-information: a duration of the sub-content, a number of characters involved in the sub-content, and a position of a time period of the sub-content in a time period of the media content.

3. The method of claim 1, wherein, The weight of the sub-content is determined based on an artificial intelligence model, the artificial intelligence model being used to output a weight based on input content information.

4. The method of claim 1, wherein, The fusing of the abstracts of the sub-contents based on the weights of the sub-contents to obtain the abstract of the media content comprises: processing the weights of the sub-contents and the abstracts of the sub-contents based on a first language processing model to obtain the abstract of the media content.

5. The method of claim 1, wherein, The content data is text data, and the determining of the abstract of each sub-content based on the content data of each sub-content comprises: processing the content data of each sub-content based on a second language processing model to obtain the abstract of each sub-content.

6. An abstract generation apparatus characterized by comprising: The apparatus comprises: an obtaining unit configured to obtain content data of each sub-content included in media content, the sub-content being obtained by dividing the media content, the media content being content of a conference, the sub-content being content of a sub-conference obtained by dividing the conference, or the conference being a repetitive schedule conference, and the sub-content being content of at least one schedule conference included in the repetitive schedule conference, the media content including one or more of video content, image content, audio content, and text content; a determining unit configured to determine an abstract of each sub-content based on the content data of each sub-content; and The generating unit is configured to fuse the summaries of the sub-contents according to the weights of the sub-contents, to obtain the summary of the media content, wherein the weight of the sub-content represents the importance of the sub-content in the media content; The sub-conference adopts the following method to divide the conference: The conference is divided based on the conference type and the conference content of the conference to obtain the sub-conference; or, The conference is divided based on at least two content dimensions of the conference to obtain the sub-conference; The weight of the sub-content is determined according to content information of the sub-content, wherein the content information is determined based on time information of the sub-content in the media content and content data of the sub-content; The weight of the sub-content is determined based on a sub-weight corresponding to sub-information included in the content information of the sub-content.

7. An electronic device, comprising: Comprise: One or more processors; A storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-5.

8. A computer readable medium characterized by A computer program is stored thereon, wherein the program is executed by the processor to implement the method of any one of claims 1-5.

Images