Conference recording method and system, storage medium and program product

Abstract

The invention provides a conference recording method and system, a storage medium and a program product. The conference recording method comprises the following steps: a mobile terminal starts a recording function in response to a conference mode starting operation, and requests to establish connection with a cloud; the mobile terminal uploads conference audio data recorded through the recording function to the cloud in real time under the condition that the mobile terminal establishes connection with the cloud; the cloud performs data processing on the conference audio data to generate a conference content text; and the cloud uses an abstract generation model to generate conference key information based on the conference content text, and generates a conference content abstract based on the conference key information.

Description

Technical Field

[0001] The present disclosure generally relates to the field of data processing, and more specifically, to a conference recording method, system, storage medium and program product. Background Art

[0002] In today’s fast-paced work environment, effective meeting management can effectively improve team collaboration and productivity. For example, effective meeting management can be achieved through professional meeting recording services.

[0003] Professional meeting recording service: Professionals provide on-site or remote meeting recording services, which can record the meeting content in real time, even including non-verbal information such as gestures and expressions. However, there are the following main problems:

[0004] High cost. Hiring a professional meeting recorder usually requires a high fee, which may become a significant expense, especially for long-term or frequent meeting needs;

[0005] Reliance on manpower: Professional meeting record-keeping services rely on the recorder's personal skills and concentration. There may be errors in recording due to fatigue, negligence or misunderstanding. In addition, the recorder's availability may be limited by time, location and health conditions.

[0006] Subsequent collation and distribution: The collation, editing and distribution of meeting minutes usually takes additional time and manpower, which may affect the immediate availability of information and the efficiency of team collaboration;

[0007] Lack of intelligent analysis: Traditional manual recording methods usually cannot provide in-depth analysis, and the understanding and use of meeting content may remain at a superficial level. Summary of the invention

[0008] The exemplary embodiments of the present disclosure provide a conference recording method, system, storage medium and program product, which can solve the above-mentioned problems existing in the prior art.

[0009] According to an exemplary embodiment of the present disclosure, a conference recording method is provided, including: a mobile terminal starts a recording function in response to a conference mode activation operation, and requests to establish a connection with a cloud; when the mobile terminal establishes a connection with the cloud, the mobile terminal uploads conference audio data recorded by the recording function to the cloud in real time; the cloud processes the conference audio data to generate a conference content text; the cloud uses a summary generation model to generate conference key information based on the conference content text, and generates a conference content summary based on the conference key information.

[0010] Optionally, the key conference information includes: summary information of each speaker's speech, summary information of conference sections, and emphasis information of each speaker's speech.

[0011] Optionally, it also includes: the cloud uses a to-do generation model to extract to-do related information from the meeting content text, and generates a post-meeting to-do list based on the extracted to-do related information; wherein the to-do related information includes: information on matters mentioned in the meeting content text that are currently unfinished and need to be completed in the future; wherein the to-do list includes: the content, requirements, time limit, and person in charge of each to-do item.

[0012] Optionally, the cloud performs data processing on the conference audio data to generate a conference content text, including the steps of: the cloud dividing the conference audio data into multiple audio data segments according to the pause intervals when no speaker is speaking; the cloud determining the audio data segments corresponding to each speaker according to the characteristics of the multiple audio data segments; the cloud generating the conference content text based on the audio data segments corresponding to each speaker; wherein the conference content text includes: the identification information of each speaker, the speaking time period and the speech content.

[0013] Optionally, the step of the cloud determining the audio data segments corresponding to each speaker based on the characteristics of the multiple audio data segments includes: the cloud clustering the multiple audio data segments based on the characteristics of the multiple audio data segments to obtain the audio data segments corresponding to the each speaker; wherein the audio data segments included in each category obtained by clustering correspond to the same speaker.

[0014] Optionally, the cloud determines the audio data segment corresponding to each speaker based on the characteristics of the multiple audio data segments, including: the cloud obtains the voice characteristics of each speaker; the cloud obtains the audio data segment corresponding to each speaker based on the similarity between the characteristics of each audio data segment and the voice characteristics of each speaker.

[0015] Optionally, the step of the cloud obtaining the voice characteristics of each speaker includes: the cloud obtaining the time point corresponding to each speaker marked by the mobile terminal in response to the user operation; the cloud determines the audio data segment corresponding to the time point of each speaker from the multiple audio data segments; the cloud uses the characteristics of the audio data segment corresponding to the time point of each speaker as the voice characteristics of the speaker; wherein the user operation includes: marking the speaker at the current time point through the mobile terminal when each speaker speaks.

[0016] Optionally, the step of the cloud acquiring the voice characteristics of each speaker includes: the cloud receiving the audio data of each speaker recorded by the mobile terminal before entering the conference mode; the cloud using the characteristics of the audio data of each speaker as the voice characteristics of each speaker.

[0017] Optionally, the features of the audio data segment include at least one of the following items: Mel-frequency cepstral coefficients, pitch features, and volume features.

[0018] Optionally, the type of the mobile terminal includes at least one of the following items: a smart mouse, a smart wearable device, and a smart communication terminal.

[0019] Optionally, it also includes: the cloud provides the meeting content text, the meeting content summary, the meeting key information, identification information of each speaker and the total speaking time of each speaker.

[0020] According to an exemplary embodiment of the present disclosure, a conference recording system is provided, comprising: a mobile terminal and a cloud, wherein the mobile terminal comprises: a recording unit; a conference mode activation unit, configured to start the recording function of the recording unit in response to a conference mode activation operation, and request to establish a connection with the cloud; a data upload unit, configured to upload conference audio data recorded by the recording function to the cloud in real time when a connection is established with the cloud; the cloud comprises: a conference content generation unit, configured to perform data processing on the conference audio data and generate a conference content text; a conference summary generation unit, configured to use a summary generation model to generate conference key information based on the conference content text, and to generate a conference content summary based on the conference key information.

[0021] Optionally, the key conference information includes: summary information of each speaker's speech, summary information of conference sections, and emphasis information of each speaker's speech.

[0022] Optionally, the cloud also includes: a to-do list generation unit, configured to use a to-do generation model to extract to-do related information from the meeting content text, and generate a post-meeting to-do list based on the extracted to-do related information; wherein the to-do related information includes: information on matters mentioned in the meeting content text that are currently unfinished and need to be completed in the future; wherein the to-do list includes: the content, requirements, time limit, and person in charge of each to-do item.

[0023] Optionally, the conference content generation unit is configured to: divide the conference audio data into multiple audio data segments according to the pause intervals when no speaker is speaking; determine the audio data segments corresponding to each speaker according to the characteristics of the multiple audio data segments; and generate the conference content text based on the audio data segments corresponding to each speaker; wherein the conference content text includes: the identification information, speaking time period and speech content of each speaker.

[0024] Optionally, the conference content generation unit is configured to: cluster the multiple audio data segments according to the characteristics of the multiple audio data segments to obtain the audio data segments corresponding to the respective speakers; wherein the audio data segments included in each category obtained by clustering correspond to the same speaker.

[0025] Optionally, the conference content generating unit is configured to: obtain voice features of the respective speakers; and obtain audio data segments corresponding to the respective speakers based on similarities between features of the respective audio data segments and the voice features of the respective speakers.

[0026] Optionally, the conference content generation unit is configured to: obtain the time point corresponding to each speaker marked by the mobile terminal in response to a user operation; determine the audio data segment at the time point corresponding to each speaker from the multiple audio data segments; and use the features of the audio data segment at the time point corresponding to each speaker as the voice features of the speaker; wherein the user operation includes: marking the speaker at the current time point through the mobile terminal when each speaker speaks.

[0027] Optionally, the conference content generating unit is configured to: receive audio data of each speaker recorded by the mobile terminal before entering the conference mode; and use features of the audio data of each speaker as voice features of each speaker.

[0028] Optionally, the features of the audio data segment include at least one of the following items: Mel-frequency cepstral coefficients, pitch features, and volume features.

[0029] Optionally, the type of the mobile terminal includes at least one of the following items: a smart mouse, a smart wearable device, and a smart communication terminal.

[0030] Optionally, the cloud further includes: a providing unit configured to provide the conference content text, the conference content summary, the conference key information, identification information of each speaker, and the total speaking time of each speaker.

[0031] According to an exemplary embodiment of the present disclosure, a system is provided, including at least one computing device and at least one storage device storing instructions, wherein when the instructions are executed by the at least one computing device, the at least one computing device is prompted to execute the meeting recording method as described above.

[0032] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing instructions is provided, wherein when the instructions are executed by at least one computing device, the at least one computing device is prompted to perform the meeting recording method as described above.

[0033] According to an exemplary embodiment of the present disclosure, a computer program product is provided, including computer executable instructions, wherein the computer executable instructions implement the above-mentioned meeting recording method when executed by at least one processor.

[0034] The meeting recording method, system, storage medium and program product according to the exemplary embodiments of the present disclosure can support the recording of online and offline meetings, can help users save a lot of time in organizing meeting minutes, and facilitate users to use meeting information more efficiently.

[0035] Additional aspects and / or advantages of the present general inventive concept will be set forth in part in the following description and in part will be apparent from the description or may be learned through practice of the present general inventive concept. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and other objects and features of the exemplary embodiments of the present disclosure will become more apparent through the following description in conjunction with the accompanying drawings which exemplarily illustrate the embodiments, in which:

[0037] Figure 1 A flowchart showing a conference recording method according to an exemplary embodiment of the present disclosure;

[0038] Figure 2 A flowchart showing a method for processing conference audio data in the cloud to generate conference content text according to an exemplary embodiment of the present disclosure;

[0039] Figure 3 A flowchart showing a conference recording method according to another exemplary embodiment of the present disclosure;

[0040] Figure 4 A structural block diagram of a conference recording system according to an exemplary embodiment of the present disclosure is shown;

[0041] Figure 5 A structural block diagram of a conference recording system according to another exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0042] Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like parts throughout. The embodiments will be described below with reference to the drawings in order to explain the present disclosure.

[0043] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0044] It should be noted that the phrase "at least one of the items" in the present disclosure includes three types of parallel situations: "any one of the items", "a combination of any number of the items", and "all of the items". For example, "including at least one of A and B" includes the following three parallel situations: (1) including A; (2) including B; (3) including A and B. Another example is "executing at least one of step 1 and step 2" which means the following three parallel situations: (1) executing step 1; (2) executing step 2; (3) executing step 1 and step 2.

[0045] Figure 1 A flowchart of a conference recording method according to an exemplary embodiment of the present disclosure is shown. The conference recording method according to an exemplary embodiment of the present disclosure supports not only online conferences, but also offline conference recording, for example, daily meetings, ad hoc discussion meetings and other offline meetings.

[0046] Reference Figure 1 In step S101, the mobile terminal responds to the conference mode start operation, starts the recording function, and requests to establish a connection with the cloud.

[0047] As an exemplary embodiment, the type of the mobile terminal may include, but is not limited to, at least one of the following: a smart mouse, a smart wearable device (eg, a smart watch), a smart communication terminal (eg, a smart phone).

[0048] As an exemplary embodiment, the conference mode activation operation can be implemented by operating a mechanical button of the mobile terminal, for example, the conference mode can be activated by clicking a mechanical button on an intelligent mouse. In addition, the conference mode activation operation can also be implemented by operating a control (for example, a virtual button) on an interface displayed by the mobile terminal.

[0049] In step S102, when the mobile terminal is connected to the cloud, the conference audio data recorded by the recording function is uploaded to the cloud in real time.

[0050] As an exemplary embodiment, after the mobile terminal enters the conference mode in response to the conference mode activation operation, the mobile terminal continuously records through the recording function to obtain conference audio data (i.e., real-time recording data of the conference). When the mobile terminal is not connected to the cloud, the conference audio data will be saved in the mobile terminal, and uploaded to the cloud after the connection with the cloud is established.

[0051] As an exemplary embodiment, the mobile terminal supports online mode and offline mode. In online mode, during the meeting, the most recently recorded meeting audio data will be uploaded to the cloud in real time at regular intervals. In offline mode, all meeting audio data will be uploaded to the cloud in real time after the meeting.

[0052] As an exemplary embodiment, the mobile terminal may perform noise reduction processing (e.g., removing background noise and other abnormal sounds) and / or compression processing on the conference audio data before uploading it to the cloud.

[0053] According to an exemplary embodiment of the present application, the smart mouse not only has the control function of a traditional mouse, but also has a high-precision microphone array, which can capture clear voice signals in a meeting and maintain a good recording effect even in a noisy environment. In addition, the smart mouse can also have audio noise reduction function, audio data compression function, audio data storage function, and audio data upload function.

[0054] In step S103, the cloud processes the conference audio data to generate a conference content text.

[0055] As an exemplary embodiment, the conference content text may include, but is not limited to: identification information of each speaker, speech time period, and speech content.

[0056] As an example, the meeting content text may look like this:

[0057] Speaker A, speaking time: 3 minutes 15 seconds to 4 minutes 2 seconds, speech content: ...;

[0058] Speaker B, speaking time: 4 minutes 5 seconds to 4 minutes 20 seconds, speech content: ...;

[0059] Speaker A, speaking time: 4 minutes 23 seconds to 4 minutes 40 seconds, speech content: ...;

[0060] Speaker C, speaking time: 4 minutes 45 seconds to 5 minutes 2 seconds, speech content: ……

[0061] As an exemplary embodiment, the cloud can process the conference audio data through speaker recognition technology and speech recognition technology to generate conference content text. As an example, deep learning technology can be used to ensure accurate speech recognition in various conference scenarios, and maintain a high recognition rate even at a long distance or in a noisy environment.

[0062] As an exemplary embodiment, the cloud can verify and modify the initially generated meeting content text through natural language processing (NLP) technology to obtain the best meeting content text to improve the accuracy of the meeting content text.

[0063] The following will be combined Figure 2 An exemplary embodiment of step S103 is described below, which will not be expanded here.

[0064] In step S104, the cloud uses a summary generation model to generate key meeting information based on the meeting content text, and generates a meeting content summary based on the key meeting information.

[0065] As an exemplary embodiment, the key conference information may include, but is not limited to: summary information of each speaker's speech, summary information of conference sections, and emphasis information of each speaker's speech (ie, the content emphasized by each speaker during his speech).

[0066] As an exemplary embodiment, the summary generation model may utilize natural language understanding (NLU) and natural language generation (NLG) technologies to automatically analyze meeting content, extract and generate key meeting information, and further generate a structured summary.

[0067] In addition, as an exemplary embodiment, the meeting recording method according to the exemplary embodiment of the present disclosure may also include: using a to-do generation model in the cloud to extract to-do related information from the meeting content text, and generating a post-meeting to-do list based on the extracted to-do related information.

[0068] As an example, the to-do item related information may include: information about items mentioned in the meeting content text that are not yet completed but need to be completed in the future.

[0069] As an example, the to-do list may include: the content, requirements, deadline, and person in charge of each to-do item.

[0070] In addition, as an exemplary embodiment, the meeting recording method according to the exemplary embodiment of the present disclosure may also include: providing meeting content text, meeting content summary, meeting key information, identification information of each speaker and the total speaking time of each speaker in the cloud.

[0071] As an example, a user may view the meeting content text, meeting content summary, meeting key information, identification information of each speaker, and the total speaking time of each speaker provided by the cloud by accessing a web page provided by the cloud.

[0072] According to an exemplary embodiment of the present application, it is convenient for users to use conference information more efficiently.

[0073] Figure 2 A flowchart is shown of a method for processing conference audio data in the cloud to generate conference content text according to an exemplary embodiment of the present disclosure.

[0074] Reference Figure 2 In step S201, the cloud divides the conference audio data into multiple audio data segments according to the pause intervals when no speaker speaks. As an example, the pause interval threshold can be set according to the actual situation and specific needs. When the pause interval exceeds the pause interval threshold (for example, 0.2 seconds), the pause interval will be used as an audio data segmentation point.

[0075] In step S202, the cloud determines the audio data segment corresponding to each speaker according to the characteristics of the multiple audio data segments.

[0076] This application supports offline meetings, but it is difficult to accurately distinguish the voices of different speakers in offline multi-person meetings, which causes trouble for the subsequent organization and analysis of the meeting content. Therefore, this application proposes that the cloud determines the audio data segments corresponding to each speaker based on the characteristics of the multiple audio data segments.

[0077] As an exemplary embodiment, the features of the audio data segment may include, but are not limited to, at least one of the following items: Mel-frequency cepstral coefficients, pitch features, and volume features.

[0078] As an exemplary embodiment, the cloud clusters the multiple audio data segments according to the characteristics of the multiple audio data segments to obtain audio data segments corresponding to each speaker; wherein the audio data segments included in each category obtained by clustering correspond to the same speaker.

[0079] As another exemplary embodiment, the cloud obtains the voice features of each speaker; the cloud obtains the audio data segments corresponding to each speaker based on the similarity between the features of each audio data segment and the voice features of each speaker. As an example, when the similarity or distance between the features of the audio data segment and the voice features of the speaker meets a preset condition, the audio data segment is considered to correspond to the speaker.

[0080] An exemplary embodiment of obtaining the voice characteristics of each speaker in the cloud is shown below.

[0081] As an exemplary embodiment, the cloud can obtain the time point corresponding to each speaker marked by the mobile terminal in response to the user operation; the cloud determines the audio data segment corresponding to the time point of each speaker from the multiple audio data segments; the cloud uses the characteristics of the audio data segment corresponding to the time point of each speaker as the voice characteristics of the speaker. As an example, the user operation may include: marking the speaker at the current time point through the mobile terminal when each speaker speaks, thereby marking the speaker (for example, the speaker's name) once when each speaker speaks, and then determining the speaker's speaking time point, and then determining the speaker's voice characteristics based on the audio data segment corresponding to the speaking time point, which is used to determine all audio data segments corresponding to the speaker.

[0082] As another exemplary embodiment, the cloud receives the audio data of each speaker recorded by the mobile terminal before entering the conference mode; the cloud uses the characteristics of the audio data of each speaker as the voice characteristics of each speaker. As an example, the audio data of each participant can be recorded and marked (for example, the name of the participant is marked) when the participant enters the meeting. As another example, the audio data of each speaker can be obtained from the audio data of employees collected uniformly by the company (for example, the audio data collected when the employee joins the company).

[0083] In step S203, the cloud generates a conference content text based on the audio data segments corresponding to each speaker.

[0084] Figure 3 A flowchart showing a conference recording method according to another exemplary embodiment of the present disclosure is shown. Figure 4 A structural block diagram of a conference recording system according to an exemplary embodiment of the present disclosure is shown. The conference recording system includes: an intelligent mouse and an intelligent conference recording cloud.

[0085] like Figure 3 and Figure 4 As shown, at the beginning of the meeting, the meeting mode is entered by clicking the mechanical button on the smart mouse. At this time, the smart mouse will automatically turn on the recording function and noise reduction function (realized by the noise removal module of the smart mouse terminal) to follow the progress of the meeting and record the meeting. The recording data is uploaded in real time. The recording file can be compressed by the built-in audio compression module of the smart mouse and uploaded to the smart meeting record cloud with the corresponding name.

[0086] The intelligent conference record cloud will store the received recording files in the voice data storage module, and perform speaker identification through the speaker identification module. Specifically, the compressed recording files are first decompressed, and the recording data is segmented according to the pause duration. Then, the Mel-frequency cepstral coefficients, pitch and volume features in each recording data segment are extracted, and the audio data segments are clustered according to the extracted features to determine the audio time periods and durations corresponding to different speakers. The generated speaker identification data is stored in the intelligent conference record cloud; speech recognition is performed on the specific audio data of different speakers to generate text data corresponding to the speech data, and the result text is verified and modified through NLP technology; according to the meeting content text, the key information of the meeting is generated using the large model technology, and the meeting summary text is generated based on the key information of the meeting; the structured data of the meeting is stored, and the structured data may include but is not limited to: meeting content text, meeting content summary, meeting key information, identification information of each speaker (for example, name) and the total speaking time of each speaker; users can see the detailed information of the meeting record through the interface provided by the intelligent conference record cloud.

[0087] The application scenarios of this application may include but are not limited to:

[0088] Enterprise meetings: Applicable to meetings of all sizes, helping teams quickly generate meeting minutes and improve meeting efficiency;

[0089] Academic lectures: record and summarize the contents of academic lectures to facilitate subsequent research and review;

[0090] Personal learning: When used personally, you can record learning notes and automatically generate learning summaries to improve learning efficiency.

[0091] In addition, this application supports real-time synchronization with a variety of conference software and cloud storage services to ensure the immediate availability of meeting records. This application also supports docking with existing video conferencing systems to better support online conference scenarios.

[0092] Figure 5 A structural block diagram of a conference recording system according to another exemplary embodiment of the present disclosure is shown.

[0093] Reference Figure 5 According to another exemplary embodiment of the present disclosure, a conference recording system includes: a mobile terminal 100 and a cloud 200. The mobile terminal 100 includes: a recording unit 101, a conference mode activation unit 102, and a data upload unit 103. The cloud 200 includes: a conference content generation unit 201 and a conference summary generation unit 202.

[0094] Specifically, the conference mode activation unit 102 is configured to activate the recording function of the recording unit in response to the conference mode activation operation, and request to establish a connection with the cloud 200 .

[0095] The data uploading unit 103 is configured to upload the conference audio data recorded by the recording function to the cloud 200 in real time when a connection is established with the cloud 200 .

[0096] The conference content generating unit 201 is configured to perform data processing on the conference audio data to generate conference content text.

[0097] The conference summary generating unit 202 is configured to generate conference key information based on the conference content text using a summary generating model, and to generate a conference content summary based on the conference key information.

[0098] As an exemplary embodiment, the key conference information may include: summary information of each speaker's speech, summary information of conference sections, and emphasis information of each speaker's speech.

[0099] As an exemplary embodiment, the cloud 200 may also include: a to-do list generation unit (not shown), which is configured to use a to-do generation model to extract to-do related information from the meeting content text, and generate a post-meeting to-do list based on the extracted to-do related information; wherein the to-do related information includes: information on matters mentioned in the meeting content text that are not yet completed and need to be completed in the future; wherein the to-do list includes: the content, requirements, time limit, and person in charge of each to-do item.

[0100] As an exemplary embodiment, the conference content generation unit 201 can be configured to: divide the conference audio data into multiple audio data segments according to the pause intervals when no speaker is speaking; determine the audio data segments corresponding to each speaker according to the characteristics of the multiple audio data segments; generate the conference content text based on the audio data segments corresponding to each speaker; wherein the conference content text includes: the identification information of each speaker, the speaking time period and the speech content.

[0101] As an exemplary embodiment, the conference content generation unit 201 can be configured to: cluster the multiple audio data segments according to the characteristics of the multiple audio data segments to obtain the audio data segments corresponding to the respective speakers; wherein the audio data segments included in each category obtained by clustering correspond to the same speaker.

[0102] As an exemplary embodiment, the conference content generating unit 201 may be configured to: obtain the voice features of the respective speakers; and obtain the audio data segments corresponding to the respective speakers based on the similarity between the features of the respective audio data segments and the voice features of the respective speakers.

[0103] As an exemplary embodiment, the conference content generation unit 201 can be configured to: obtain the time point corresponding to each speaker marked by the mobile terminal in response to the user operation; determine the audio data segment where the time point corresponding to each speaker is located from the multiple audio data segments; use the characteristics of the audio data segment where the time point corresponding to each speaker is located as the voice characteristics of the speaker; wherein the user operation includes: marking the speaker at the current time point through the mobile terminal when each speaker speaks.

[0104] As an exemplary embodiment, the conference content generating unit 201 may be configured to: receive the audio data of the speakers recorded by the mobile terminal before entering the conference mode; and use the features of the audio data of the speakers as the voice features of the speakers.

[0105] As an exemplary embodiment, the feature of the audio data segment may include at least one of the following items: Mel-frequency cepstral coefficients, pitch features, and volume features.

[0106] As an exemplary embodiment, the type of the mobile terminal may include at least one of the following items: a smart mouse, a smart wearable device, and a smart communication terminal.

[0107] As an exemplary embodiment, the cloud 200 may further include: a providing unit (not shown), which is configured to provide the meeting content text, the meeting content summary, the meeting key information, identification information of each speaker, and the total speaking time of each speaker.

[0108] It should be understood that the specific implementation of the conference recording system according to the exemplary embodiment of the present disclosure can refer to the Figures 1 to 4 The relevant specific implementation methods described are implemented and will not be repeated here.

[0109] The units included in the conference record system according to the exemplary embodiment of the present disclosure may be configured as software, hardware, firmware or any combination of the above items to perform specific functions. For example, these units may correspond to a dedicated integrated circuit, or may correspond to pure software code, or may correspond to a module combining software and hardware. In addition, one or more functions implemented by these units may also be uniformly executed by components in a physical entity device (e.g., a processor, a client or a server, etc.).

[0110] It should be understood that the meeting recording method according to the exemplary embodiment of the present disclosure can be implemented by a program recorded on a computer-readable medium. For example, according to the exemplary embodiment of the present disclosure, a computer-readable medium can be provided, wherein the computer-readable medium records a program for executing the meeting recording method as described in the above exemplary embodiment.

[0111] The computer program in the computer-readable medium can be run in an environment deployed in a computer device such as a client, a host, an agent device, a server, etc. It should be noted that the computer program can also be used to perform additional steps in addition to the above steps or perform more specific processing when performing the above steps. The contents of these additional steps and further processing have been referred to in Figures 1 to 4 The description has been made, and will not be repeated here to avoid repetition.

[0112] It should be noted that the meeting recording system according to the exemplary embodiment of the present disclosure can completely rely on the operation of the computer program to realize the corresponding functions, that is, each unit corresponds to each step in the functional architecture of the computer program, so that the entire system is called through a special software package (for example, lib library) to realize the corresponding function.

[0113] On the other hand, the various units included in the conference recording system according to the exemplary embodiment of the present disclosure may also be implemented by hardware, software, firmware, middleware, microcode or any combination thereof. When implemented by software, firmware, middleware or microcode, the program code or code segment for performing the corresponding operation may be stored in a computer-readable medium such as a storage medium, so that the processor can perform the corresponding operation by reading and running the corresponding program code or code segment.

[0114] For example, an exemplary embodiment of the present disclosure may also be implemented as a computing device, which includes a storage component and a processor, wherein a set of computer executable instructions is stored in the storage component, and when the set of computer executable instructions is executed by the processor, the meeting recording method described in the above exemplary embodiment is executed.

[0115] Specifically, the computing device may be deployed in a server or client, or may be deployed on a node device in a distributed network environment. In addition, the computing device may be a PC, a tablet device, a personal digital assistant, a smart phone, a web application, or other device capable of executing the above instruction set.

[0116] Here, the computing device is not necessarily a single computing device, but may be any device or circuit collection that can execute the above instructions (or instruction sets) individually or jointly. The computing device may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that is interconnected with a local or remote (e.g., via wireless transmission) interface.

[0117] In the computing device, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. By way of example and not limitation, the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0118] According to the exemplary embodiment of the present disclosure, some operations described in the conference recording method can be implemented by software, some operations can be implemented by hardware, and furthermore, these operations can be implemented by a combination of software and hardware.

[0119] The processor may execute instructions or codes stored in one of the storage components, which may also store data. Instructions and data may also be sent and received over a network via a network interface device, which may employ any known transmission protocol.

[0120] The storage component may be integrated with the processor, for example, RAM or flash memory is arranged within an integrated circuit microprocessor, etc. In addition, the storage component may include a separate device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system. The storage component and the processor may be operatively coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the processor can read files stored in the storage component.

[0121] In addition, the computing device may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the computing device may be connected to each other via a bus and / or a network.

[0122] The operations involved in the conference recording method according to the exemplary embodiment of the present disclosure can be described as various interconnected or coupled functional blocks or functional diagrams. However, these functional blocks or functional diagrams can be equally integrated into a single logical device or operate according to non-precise boundaries.

[0123] For example, as described above, a computing device according to an exemplary embodiment of the present disclosure may include a storage component and a processor, wherein a set of computer executable instructions is stored in the storage component, and when the set of computer executable instructions is executed by the processor, the meeting recording method described in the above exemplary embodiment is executed.

[0124] The above describes various exemplary embodiments of the present disclosure, and it should be understood that the above description is only exemplary and not exhaustive, and the present disclosure is not limited to the disclosed exemplary embodiments. Without departing from the scope and spirit of the present disclosure, many modifications and changes are obvious to those of ordinary skill in the art. Therefore, the scope of protection of the present disclosure should be based on the scope of the claims.

Claims

1. A conference recording method, characterized in that: include: The mobile terminal responds to the conference mode start operation, starts the recording function, and requests to establish a connection with the cloud; When the mobile terminal is connected to the cloud, the mobile terminal uploads the conference audio data recorded by the recording function to the cloud in real time; The cloud performs data processing on the conference audio data to generate a conference content text; The cloud uses a summary generation model to generate key meeting information based on the meeting content text, and generates a meeting content summary based on the key meeting information.

2. The conference recording method according to claim 1, characterized in that: The key information of the meeting includes: Summary information of each speaker's speech, summary information of conference chapters, and emphasis information of each speaker's speech.

3. The conference recording method according to claim 1, characterized in that: Also includes: The cloud uses a to-do item generation model to extract to-do item related information from the meeting content text, and generates a to-do item list after the meeting based on the extracted to-do item related information; The to-do items related information includes: information on items mentioned in the meeting content text that are not yet completed and need to be completed in the future; The to-do list includes: the content, requirements, time limit, and person in charge of each to-do item.

4. The conference recording method according to claim 1, characterized in that: The cloud performs data processing on the conference audio data to generate a conference content text, including: The cloud divides the conference audio data into a plurality of audio data segments according to pause intervals when no speaker speaks; The cloud determines the audio data segment corresponding to each speaker according to the characteristics of the multiple audio data segments; The cloud generates the conference content text based on the audio data segments corresponding to the speakers; The conference content text includes: identification information of each speaker, speech time period and speech content.

5. The conference recording method according to claim 4, characterized in that: The step of determining, by the cloud, the audio data segments corresponding to each speaker according to the characteristics of the multiple audio data segments comprises: The cloud clusters the multiple audio data segments according to the features of the multiple audio data segments to obtain the audio data segments corresponding to the respective speakers; The audio data segments included in each category obtained by clustering correspond to the same speaker.

6. The conference recording method according to claim 4, characterized in that: The step of determining, by the cloud, the audio data segments corresponding to each speaker according to the characteristics of the multiple audio data segments comprises: The cloud obtains the voice characteristics of each speaker; The cloud obtains the audio data segments corresponding to the respective speakers according to the similarity between the features of the respective audio data segments and the voice features of the respective speakers.

7. The conference recording method according to claim 6, characterized in that: The step of obtaining the voice features of each speaker in the cloud comprises: The cloud obtains the time point corresponding to each speaker marked by the mobile terminal in response to the user operation; The cloud determines, from the plurality of audio data segments, an audio data segment at a time point corresponding to each speaker; The cloud uses the features of the audio data segment at the time point corresponding to each speaker as the voice features of the speaker; The user operation includes: marking the speaker at the current time point through the mobile terminal when each speaker speaks.

8. The conference recording method according to claim 6, characterized in that: The step of obtaining the voice features of each speaker in the cloud comprises: The cloud receives the audio data of each speaker recorded by the mobile terminal before entering the conference mode; The cloud uses the features of the audio data of each speaker as the voice features of each speaker.

9. A conference recording system, characterized in that: include: Mobile terminals and cloud, including: The mobile terminal comprises: Recording unit; a conference mode activation unit, configured to activate the recording function of the recording unit in response to the conference mode activation operation, and request to establish a connection with the cloud; A data uploading unit, configured to upload the conference audio data recorded by the recording function to the cloud in real time when a connection is established with the cloud; The cloud comprises: A conference content generating unit, configured to perform data processing on the conference audio data to generate a conference content text; The conference summary generating unit is configured to generate conference key information based on the conference content text using a summary generating model, and to generate a conference content summary based on the conference key information.

10. A computer-readable storage medium storing instructions, wherein: When the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the meeting recording method according to any one of claims 1 to 8.

Images