Real-time conference abstract generation method, apparatus, device, medium, and computer program product

Abstract

This invention discloses a method, apparatus, device, medium, and computer program product for generating real-time meeting summaries, relating to the field of natural language processing technology and applicable to the fintech sector. The method involves: acquiring the real-time cumulative meeting content of a target meeting; truncating the real-time cumulative meeting content to obtain fixed meeting content for at least one round of meetings, each round including at least one interval meeting; and summarizing the fixed meeting content and the interval meeting content to obtain a real-time meeting summary of the target meeting. This technical solution, by truncating the meeting content, generates a real-time meeting summary that accurately reflects the key points of the meeting, ensuring accurate generation of real-time meeting summaries in various meeting scenarios.

Description

Technical Field

[0001] This invention relates to the field of natural language processing technology, and can be applied to the field of financial technology. In particular, it relates to a method, apparatus, device, medium, and computer program product for generating real-time meeting summaries. Background Technology

[0002] The development of abstract generation technology involves progress in multiple fields. There is currently very little research on conference abstract generation technology. Unlike general document abstracts, conference abstracts require comprehensive consideration of dialogue context information. Due to the high real-time requirements, the technical difficulty and detail requirements for conference abstracts are also more stringent.

[0003] Existing summary generation methods often rely on rule-based approaches, which extract key sentences from text content to generate summaries through predefined rules and keyword matching; or identify important sentences by analyzing word frequency and word co-occurrence relationships in the text to generate summaries; or train models to learn how to generate summaries from a large amount of labeled data.

[0004] For complex sentence structures or texts involving technical terms, the model may fail to correctly understand and generate summaries, and key information may be missed during the summarization process, resulting in incomplete summaries or the loss of important details. While the model may perform well in a specific domain, its generalization ability across different domains is limited. The model's performance is highly dependent on the quality and diversity of the training data; insufficient or domain-specific training data may lead to biased conference summaries. Summary of the Invention

[0005] This invention provides a method, apparatus, device, storage medium, and computer program product for generating real-time meeting summaries. By truncating the meeting content into text, it summarizes the content of fixed meetings and interval meetings, accurately reflecting the key points of the meeting and ensuring accurate generation of real-time meeting summaries in various meeting scenarios.

[0006] According to one aspect of the present invention, a method for generating real-time meeting summaries is provided, comprising:

[0007] Obtain the real-time cumulative meeting content of the target meeting;

[0008] The real-time cumulative meeting content is truncated to obtain fixed meeting content for at least one round of meetings, each round of meetings including at least one time interval meeting;

[0009] This is used to summarize the content of the fixed meeting and the content of the interval meetings to obtain a real-time meeting summary of the target meeting.

[0010] According to another aspect of the present invention, a real-time meeting summary generation apparatus is provided, comprising:

[0011] The meeting content acquisition module is used to acquire the real-time cumulative meeting content of the target meeting;

[0012] The fixed meeting content acquisition module is used to truncate the real-time accumulated meeting content to obtain fixed meeting content for at least one round of meetings, each round of meetings including at least one time interval meeting.

[0013] The real-time meeting summary determination module is used to summarize the content of the fixed meeting and the content of the interval meetings to obtain the real-time meeting summary of the target meeting.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform any of the real-time conference summary generation methods described in this invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement any of the real-time conference summary generation methods of the present invention.

[0019] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the real-time conference summary generation method according to any of the present invention.

[0020] The technical solution of this invention solves the problem of generating real-time meeting summaries by truncating the target meeting content and summarizing it based on fixed meeting content and interval meeting content. This allows users to review and grasp the key points in a timely manner and ensures that they can keep up with the meeting pace when they rejoin the meeting after leaving it.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a real-time meeting summary generation method provided by an embodiment of the present invention;

[0024] Figure 2 This is a logic design diagram for generating conference summaries at various intervals according to an embodiment of the present invention;

[0025] Figure 3 This is a flowchart of a real-time meeting summary generation method provided by an embodiment of the present invention;

[0026] Figure 4 This is a structural block diagram of a real-time meeting summary generation device provided according to an embodiment of the present invention;

[0027] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] Large models are large neural network models of deep learning with a large number of parameters and high-performance computing capabilities. They can leverage the powerful understanding capabilities of large models to avoid technical problems such as poor generalization, difficulty in collecting training data, and high training costs of small models.

[0030] Figure 1 This is a flowchart of a real-time meeting summary generation method according to an embodiment of the present invention. The present invention is applicable to situations requiring real-time generation of meeting summaries. This method can be executed by a real-time meeting summary generation device provided in this embodiment. This device can be implemented in hardware and / or software and can be integrated into an electronic device that carries the meeting summary generation function, such as a server. Figure 1 As shown, the method specifically includes the following steps:

[0031] S110. Obtain the real-time cumulative meeting content of the target meeting.

[0032] The target meeting is the meeting that is currently in progress and requires the generation of a meeting summary; the real-time accumulated meeting content is the text content of the meeting audio converted into text and accumulated in chronological order during the target meeting.

[0033] Specifically, after the target meeting begins, the meeting audio is converted into text content in real time using natural language processing technology, and the text content is accumulated and stored in chronological order. Preferably, the natural language processing technology can be an Automatic Speech Recognition (ASR) engine to convert speech into text. It should be noted that those skilled in the art can use other natural language processing technologies for speech conversion, and this embodiment of the invention does not specifically limit this.

[0034] S120. Truncate the real-time cumulative meeting content to obtain fixed meeting content for at least one round of meetings, each round of meetings including at least one time interval meeting.

[0035] The text truncation can be used to split the accumulated meeting content within a certain time interval or a certain number of words; then a certain time interval or a certain number of words constitutes a round of meetings, and the corresponding meeting content is the fixed meeting content of that round of meetings; the time interval is preset; a round of meetings can consist of at least one time interval.

[0036] Specifically, the real-time accumulated meeting content is acquired at preset time intervals. When the accumulated meeting content reaches a text truncation condition, it is truncated, and the current accumulated meeting content is used as the fixed content for one round of meetings and stored in the database, continuing to accumulate from the next time interval. It is understandable that by setting a text truncation condition to truncate the accumulated meeting content, the model's input limitations of tens of billions of data points are accommodated, preventing the input meeting content from exceeding the maximum capacity and affecting the model's output quality.

[0037] Optionally, the text truncation condition is a word limit for the real-time accumulated meeting content, which can be two thousand, three thousand, four thousand, or five thousand words, etc. Preferably, in this embodiment of the invention, the text truncation condition is that when the real-time accumulated meeting content reaches four thousand words, the current accumulated meeting content is stored as the fixed meeting content for that round. It is understood that when meeting content of around four thousand words is fed into the large model to output a meeting summary, the adoption rate and usability indicators of the generated summary are optimal, and the topics conveyed by the meeting content are relatively stable at this time.

[0038] It should be noted that the time interval is preset by relevant technical personnel based on experience according to the specific meeting scenario, the speaker's speaking habits, speaking frequency and word count. The time interval can be set to one minute, two minutes or five minutes. This invention does not limit the specific time interval setting.

[0039] For example, at the start of the meeting, after acquiring the meeting content for the first time interval, the meeting content for the next time interval is acquired and accumulated as real-time cumulative meeting content. When the real-time cumulative meeting content reaches four thousand words, the real-time cumulative meeting content from the start of the first time interval to four thousand words is taken as the fixed meeting content for the first round of the meeting, and the accumulation of meeting content for the next time interval continues, and so on, until the target meeting ends. It can be seen that, depending on different meeting scenarios and the speaker's speaking frequency, the time required for each round of fixed meeting content to be spoken varies, so a round of fixed meeting can have at least one interval of interval meetings.

[0040] S130. Summarize the content of fixed meetings and the content of interval meetings to obtain the real-time meeting summary of the target meeting.

[0041] Each interval meeting corresponds to a meeting summary; each round of meetings includes at least one meeting summary.

[0042] Specifically, the system acquires the real-time cumulative meeting content, inputs the interval meeting content for one time interval into the large model to obtain the interval meeting summary. When the word count of the current interval meeting content meets the text truncation condition, the 4,000 words preceding the truncation condition are taken as a fixed round of meeting content. This fixed round of meeting content is input into the large model to obtain and save the fixed meeting summary for that round. The system then acquires the interval meeting content for the next time interval, inputs it into the large model, and outputs the interval meeting summary corresponding to the current interval meeting content. This process continues until, after N minutes, the real-time cumulative meeting content again reaches 4,000 words. A new fixed meeting summary is then generated by combining the previous fixed summary and the interval meeting summary corresponding to the current N-minute interval meeting content. Here, N is a natural number greater than 0.

[0043] In one optional embodiment of the present invention, before generating the interval meeting summary, it is necessary to determine whether the interval meeting content within the current time interval meets the summary generation conditions:

[0044] Determine whether the word count of the meeting content in the current time interval meets the conditions for abstract generation;

[0045] If the conditions are met, the content of the meeting at the current time interval will be input into the large model to generate a meeting summary;

[0046] If the condition is not met, a prompt message will be returned.

[0047] The summary generation condition is that the number of words in the interval meeting content is greater than 200; the prompt message is "There are few transcribed text records at present, and there is no intelligent summary text available."

[0048] like Figure 2 As shown, the ASR engine obtains the content of the interval meeting at the current time interval, and determines whether the number of words in the interval meeting content is greater than 200. If the number of words in the interval meeting content is greater than 200, it is input into the large model and the corresponding interval meeting summary is output; if the number of words in the interval meeting content is less than 200, it directly returns "There are few transcribed text records at present, and there is no intelligent summary text available".

[0049] Understandably, by judging the number of words in the meeting content within a time interval, it is possible to avoid the inability to accurately summarize the meeting summary when the number of words is too small, thus ensuring the completeness and richness of the data required for generating the meeting summary.

[0050] Optionally, summaries can be generated from the fixed meeting content and the interval meeting content to obtain a real-time meeting summary of the target meeting, including:

[0051] For each round of meetings:

[0052] For each interval meeting in this round of meetings, determine the content of the corresponding interval meeting;

[0053] Based on a large model, summaries of interval and fixed meeting content are generated to determine the real-time meeting summary for the target meeting.

[0054] The interval meeting content refers to the meeting content from the start to the end of the current time interval in this round of meetings; the real-time meeting summary may include interval meeting summaries and fixed meeting summaries.

[0055] Specifically, for each round of meetings, each interval meeting is obtained, and the corresponding interval meeting content is obtained. The interval meeting content is input into the large model to obtain the corresponding interval meeting summary. The fixed meeting content is input into the large model to output the corresponding fixed meeting summary. Based on the interval meeting summary and the fixed meeting summary, the real-time meeting summary of the target meeting is summarized.

[0056] Understandably, using a large model to output meeting summaries corresponding to the meeting content ensures the accuracy and efficiency of generating the target meeting summaries.

[0057] Optionally, based on a large model, summarize the content of interval meetings and fixed meetings to determine the real-time meeting summary of the target meeting, including:

[0058] Based on the large model, a summary of the fixed meeting content of the previous round of meetings is obtained.

[0059] Based on the large model, a summary is made of the fixed meeting summary based on the content of the interval meetings and the previous round of meetings to determine the real-time meeting summary of the target meeting.

[0060] Specifically, when the meeting content reaches the first 4,000 words, the fixed meeting content of that round is input into the large model for summary, and the fixed meeting summary of that round is output. Continue to obtain the meeting content of the next time interval. After the interval ends, the meeting content of the interval and the fixed meeting summary of the previous round are input into the large model, and the interval meeting summary corresponding to the current interval meeting is output. The generation logic of subsequent meeting summaries is similar.

[0061] Understandably, by using the content of the current interval meeting and the summary of the previous fixed meeting as input to the large model, the output meeting summary is ensured to fully learn the context, achieve a deep understanding and accurate expression of the meeting content, and thus accurately reflect the key points of the meeting.

[0062] This invention provides an embodiment of obtaining the real-time cumulative meeting content of a target meeting; truncating the real-time cumulative meeting content to obtain fixed meeting content for at least one round of meetings, each round including at least one interval meeting; and summarizing the fixed meeting content and the interval meeting content to obtain a real-time meeting summary of the target meeting. This technical solution solves the problem of generating real-time meeting summaries in various meeting scenarios, ensuring accurate generation of real-time meeting summaries. By truncating the real-time meeting content and generating real-time meeting summaries based on fixed and interval meeting content, it effectively understands long texts or complex contextual relationships, ensuring the overall coherence of the meeting summary and further ensuring that it accurately reflects the intent and semantics of the original text in various meeting scenarios across different fields.

[0063] Optionally, after summarizing the content of fixed meetings and interval meetings to obtain the real-time meeting summary of the target meeting, the following steps are also included:

[0064] The real-time meeting summary of the target meeting is optimized by merging the meeting summaries of two adjacent rounds based on a large model.

[0065] The meeting summaries for two consecutive rounds of meetings include the summaries of the last two intervals of the previous round and the summaries of the first two intervals of the subsequent round.

[0066] Specifically, based on the aforementioned text truncation processing of a round of meetings, and the acquisition of interval meeting content for a single time interval based on a preset time interval, after the target meeting concludes, the summaries of two adjacent fixed rounds of meetings are merged. This includes: inputting the last two topics of the first round summary, the first two topics of the second round summary, the last two topics of the second round summary, and the first two round summaries of the third round summary, etc., into a large model for summary merging, until all rounds of meetings of the target meeting have been merged. It should be noted that merging multiple summaries in the large model can be done using different prompt words, or by vectorizing each summary, or by calculating the similarity of each summary; this invention does not specifically limit the method of summary merging.

[0067] It is understandable that since each round of meetings is truncated to 4,000 characters, the same topic may appear in different rounds of meetings. Therefore, by merging the meeting summaries of each round of the target meeting, redundant topics can be eliminated, the number of topics can be simplified, and the readability and accuracy of the meeting summaries can be further increased.

[0068] Figure 3 This is a flowchart of a real-time meeting summary generation method according to an embodiment of the present invention. Based on the above embodiments, this embodiment optimizes the specific method for determining the real-time meeting summary of the target meeting by summarizing the content of interval meetings and fixed meetings using a large model. It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 3 As shown, the method includes:

[0069] S210. Obtain the real-time cumulative meeting content of the target meeting.

[0070] S220. Truncate the real-time cumulative meeting content to obtain fixed meeting content for at least one round of meetings, each round of meetings including at least one time interval meeting.

[0071] S230. For each round of meetings, for each interval meeting in that round of meetings, determine the content of the interval meeting corresponding to that interval meeting.

[0072] S240. Determine whether the word count of the interval meeting content meets the word count threshold.

[0073] The word count threshold is preset and represents the word limit for each round of meetings. A preferred threshold is 4,000 words. It should be noted that those skilled in the art can set a corresponding word count threshold according to actual needs; this embodiment of the invention does not impose a specific limitation on this.

[0074] Specifically, after a round of meetings ends, the content of the next time interval meeting is obtained, and the meeting content is recalculated to determine whether the content of the next time interval meeting reaches four thousand words.

[0075] For example, after the first round of meetings ends, the content of the interval meetings in the first time interval is obtained and recalculated, and it is determined whether the content of the interval meetings in the first time interval reaches four thousand words. After completing the corresponding interval meeting summary, the content of the interval meetings in the second time interval is obtained and accumulated with the content of the interval meetings in the first time interval to determine the number of words of the accumulated interval meeting content. It is then determined whether the number of words of the accumulated interval meeting content reaches the four thousand word threshold, and so on... until the accumulated interval meeting content reaches four thousand words and then it is recalculated again.

[0076] S250. If not satisfied, input the interval meeting content of the interval meeting into the large model to obtain the interval meeting summary, and determine the real-time meeting summary of the target meeting based on the interval meeting summary and the fixed meeting summary of the previous round of meetings.

[0077] If the cumulative number of words in the current interval meeting is less than 4,000, then the interval meeting content of the current interval meeting is input into the large model, the interval meeting summary of the current interval meeting is output, and a new summary is obtained based on the interval meeting summary of the current interval meeting and the fixed meeting summary of the previous round of meetings in the current round, which is used as the interval meeting summary of the current interval meeting content.

[0078] It is understandable that generating a new meeting summary by combining the current interval meeting summary with the fixed meeting summary of the previous round ensures that the expression style and form of the input content of the large model are on the same dimension, and guarantees that the large model can accurately learn and fully follow the style of the summary.

[0079] S260. If satisfied, input the fixed meeting content of this round of meetings into the large model to obtain the fixed meeting summary of this round of meetings, and determine the real-time meeting summary of the target meeting based on the fixed meeting summary of this round of meetings and the fixed meeting summary of the previous round of meetings.

[0080] If the cumulative number of words in the content of the current interval meeting reaches four thousand words, then the fixed meeting content of this round of meetings is input into the large model to obtain the fixed meeting summary of this round of meetings. Furthermore, the fixed meeting summary of this round of meetings and the fixed meeting summary of the previous round of meetings are used as inputs to the large model to further determine the fixed meeting summary of this round of meetings.

[0081] Understandably, by using the fixed meeting summaries from the two rounds of meetings to further determine the fixed meeting summary for the current round, we can avoid the same topic being split into fixed meeting content for two rounds of meetings due to text truncation, which would lead to duplicate summaries. Furthermore, by summarizing based on the fixed meeting summary from the previous round, we can improve the adoption rate and usability of the meeting summary output by the large model, and further ensure that the large model can understand long texts and contextual relationships, thus guaranteeing the overall coherence of the meeting summary.

[0082] This invention, through a method of judging the word count of the interval meeting content, summarizes the interval summary of the current time interval and the fixed meeting summary of the previous round during a meeting round; at the end of a meeting round, it summarizes the fixed meeting summaries of the two adjacent rounds; ensuring that the expression style and form of the input content of the large model are on the same dimension, accurately learning and following the summary style, avoiding omission of topic content, and further ensuring that when the content of two fixed meetings is the same topic, the context can be accurately understood to summarize the summary, ensuring that real-time meeting summaries can be accurately generated in various meeting scenarios.

[0083] Figure 4 This is a structural block diagram of a real-time meeting summary generation device according to an embodiment of the present invention. The present invention is applicable to situations requiring real-time generation of meeting summaries. This method can be executed by the real-time meeting summary generation device provided in this embodiment, which can be implemented in hardware and / or software and integrated into an electronic device carrying summary generation functionality, such as a server. Figure 4 As shown, the real-time meeting summary generation device 300 includes a meeting content acquisition module 310, a fixed meeting content acquisition module 320, and a real-time meeting summary determination module 330.

[0084] The meeting content acquisition module 310 is used to acquire the real-time cumulative meeting content of the target meeting;

[0085] The fixed meeting content acquisition module 320 is used to truncate the real-time accumulated meeting content to obtain the fixed meeting content of at least one round of meetings, each round of meetings including at least one time interval meeting.

[0086] The real-time meeting summary determination module 330 is used to summarize the content of fixed meetings and the content of interval meetings to obtain the real-time meeting summary of the target meeting.

[0087] This invention provides an embodiment of obtaining the real-time cumulative meeting content of a target meeting; truncating the real-time cumulative meeting content to obtain fixed meeting content for at least one round of meetings, each round including at least one interval meeting; and summarizing the fixed meeting content and the interval meeting content to obtain a real-time meeting summary of the target meeting. This technical solution solves the problem of generating real-time meeting summaries in various meeting scenarios, ensuring accurate generation of real-time meeting summaries. By truncating the real-time meeting content and generating real-time meeting summaries based on fixed and interval meeting content, it effectively understands long texts or complex contextual relationships, ensuring the overall coherence of the meeting summary and further ensuring that it accurately reflects the intent and semantics of the original text in various meeting scenarios across different fields.

[0088] Optionally, the real-time meeting summary determination module 330 is specifically used for each round of meetings: for each interval meeting in the round of meetings, to determine the interval meeting content corresponding to that interval meeting; and to summarize the interval meeting content and fixed meeting content based on the large model to determine the real-time meeting summary of the target meeting.

[0089] Optionally, the real-time meeting summary determination module 330 is specifically used to determine whether the number of words in the interval meeting content of the current interval meeting meets the word count threshold; if it does not meet the threshold, the interval meeting content of the current interval meeting is input into the large model to obtain the interval meeting summary, and the real-time meeting summary of the target meeting is determined based on the interval meeting summary and the fixed meeting summary of the previous round of meetings; if it meets the threshold, the fixed meeting content of the current round of meetings is input into the large model to obtain the fixed meeting summary of the current round of meetings, and the real-time meeting summary of the target meeting is determined based on the fixed meeting summary of the current round of meetings and the fixed meeting summary of the previous round of meetings.

[0090] Optionally, the real-time meeting summary determination module 330 is specifically used to summarize the fixed meeting content of the previous round of meetings based on the large model to obtain the fixed meeting summary of the previous round of meetings; and based on the large model, to summarize the meeting content based on the interval meetings and the fixed meeting summary of the previous round of meetings to determine the real-time meeting summary of the target meeting.

[0091] Each interval meeting corresponds to a meeting summary; each round of meetings includes at least one meeting summary.

[0092] Optionally, the device also includes a meeting summary merging module, used to merge meeting summaries from two adjacent rounds of meetings based on a large model, thereby optimizing the real-time meeting summary of the target meeting.

[0093] The automated test case processing device provided in the embodiments of the present invention can execute the automated test case processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0094] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0095] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0096] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0097] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0098] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 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 processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as real-time meeting summary generation methods.

[0099] In some embodiments, the real-time meeting summary generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the automated test case processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the real-time meeting summary generation method by any other suitable means (e.g., by means of firmware).

[0100] 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), payload-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.

[0101] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0102] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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 thereof.

[0103] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. 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).

[0104] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations 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., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0105] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0106] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0107] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for real-time meeting summarization, the method comprising: include: Obtain the real-time cumulative meeting content of the target meeting; When the accumulated meeting content reaches the text truncation condition, the real-time accumulated meeting content is truncated to obtain fixed meeting content for at least one round of meetings. Each round of meetings includes at least one time interval meeting. The text truncation condition is the word count limit of the accumulated meeting content. The content of the fixed meeting and the content of the interval meetings are summarized to obtain the real-time meeting summary of the target meeting, including: For each round of meetings: For each interval meeting in this round of meetings, determine the content of the corresponding interval meeting; Based on a large model, summaries are generated of the content of the interval meetings and the content of the fixed meetings to determine the real-time meeting summary of the target meeting, including: Determine whether the word count of the content of the interval meeting meets the word count threshold; If not satisfied, the content of the interval meeting is input into the large model to obtain the interval meeting summary, and the real-time meeting summary of the target meeting is determined based on the interval meeting summary and the fixed meeting summary of the previous round of meetings. If the conditions are met, the fixed meeting content of this round of meetings is input into the large model to obtain the fixed meeting summary of this round of meetings. Based on the fixed meeting summary of this round of meetings and the fixed meeting summary of the previous round of meetings, the real-time meeting summary of the target meeting is determined. or, Based on the large model, a summary of the fixed meeting content of the previous round of meetings is obtained. Based on the large model, a summary is made of the fixed meeting summary of the target meeting based on the content of the interval meeting and the previous round meeting, and the real-time meeting summary is determined.

2. The method according to claim 1, characterized in that, Each interval meeting corresponds to one meeting summary; each round of meetings includes at least one meeting summary.

3. The method according to claim 2, characterized in that, After summarizing the fixed meeting content and the interval meeting content to obtain the real-time meeting summary of the target meeting, the following steps are also included: The real-time meeting summary of the target meeting has been optimized by merging the meeting summaries of two adjacent rounds of meetings based on a large model.

4. A real-time meeting summary generation device, characterized in that, include: The meeting content acquisition module is used to acquire the real-time cumulative meeting content of the target meeting; A fixed meeting content acquisition module is used to truncate the real-time accumulated meeting content when the accumulated meeting content reaches the text truncation condition, so as to obtain fixed meeting content for at least one round of meetings, each round of meetings including at least one time interval meeting; the text truncation condition is the word count limit of the accumulated meeting content; The real-time meeting summary determination module is used to summarize the content of the fixed meeting and the content of the interval meetings to obtain the real-time meeting summary of the target meeting. The real-time meeting summary determination module is specifically used for each round of meetings: for each interval meeting in the round of meetings, to determine the content of the interval meeting corresponding to that interval meeting; and to summarize the content of the interval meetings and the content of fixed meetings based on a large model to determine the real-time meeting summary of the target meeting. The real-time meeting summary determination module is specifically used to determine whether the word count of the interval meeting content meets the word count threshold; if it does not meet the threshold, the interval meeting content is input into the large model to obtain the interval meeting summary, and the real-time meeting summary of the target meeting is determined based on the interval meeting summary and the fixed meeting summary of the previous round of meetings; if it meets the threshold, the fixed meeting content of the previous round of meetings is input into the large model to obtain the fixed meeting summary of the previous round of meetings, and the real-time meeting summary of the target meeting is determined based on the fixed meeting summary of the previous round of meetings. The real-time meeting summary determination module is specifically used to summarize the fixed meeting content of the previous round of meetings based on the large model, so as to obtain the fixed meeting summary of the previous round of meetings. Based on the large model, a summary is made of the fixed meeting summary of the target meeting based on the content of the interval meeting and the previous round meeting, and the real-time meeting summary is determined.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the real-time conference summary generation method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the real-time conference summary generation method according to any one of claims 1-3.

7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the real-time conference summary generation method according to any one of claims 1-3.

Images