CN117522325A

CN117522325A - Conference auxiliary method and device and related equipment

Info

Publication number: CN117522325A
Application number: CN202311524631.9A
Authority: CN
Inventors: 陈亚军
Original assignee: China Mobile Communications Group Co Ltd; MIGU Culture Technology Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; MIGU Culture Technology Co Ltd
Priority date: 2023-11-15
Filing date: 2023-11-15
Publication date: 2024-02-06

Abstract

The disclosure provides a conference auxiliary method, a conference auxiliary device and related equipment, and relates to the technical field of artificial intelligence, wherein the conference auxiliary method comprises the following steps: acquiring meeting materials of a target meeting; analyzing and reasoning the conference materials according to the large model to obtain a first conference manuscript, wherein the first conference manuscript comprises a plurality of conference test question groups, the conference test question groups are in one-to-one association with a plurality of conference contents of a target conference, the conference test question groups are used for testing the understanding degree of a first user on the associated conference contents, and the first user is a user participating in the target conference; the method comprises the steps of obtaining reply information of a first user to a plurality of conference test question sets, generating a second conference manuscript according to the reply information and the first conference manuscript, wherein the second conference manuscript comprises a plurality of first parameters, the plurality of first parameters are in one-to-one correspondence with a plurality of conference contents, and the first parameters are used for indicating conference resource duty ratio of the corresponding conference contents.

Description

Conference auxiliary method and device and related equipment

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to a conference assisting method, a conference assisting device and related equipment.

Background

During the conference, the conference talker can announce according to the talker manuscript.

In practice, a main speaking manuscript is generally formed by manual writing of a user, and is influenced by the working state and working experience of a manuscript writer, and certain fluctuation exists in the correlation between the content of the main speaking manuscript and a conference theme, so that the difficulty of speaking based on a main speaking material by a conference main speaker is increased, and the final speaking effect of a conference is poor; that is, the quality of the main presentation formed based on the related art is poor.

Disclosure of Invention

The disclosure aims to provide a conference assisting method, a conference assisting device and related equipment, which are used for solving the technical problem of poor quality of a main speaking manuscript formed based on related technologies.

In a first aspect, an embodiment of the present disclosure provides a conference assistance method, the method including:

acquiring meeting materials of a target meeting;

analyzing and reasoning the conference materials according to a large model to obtain a first conference manuscript, wherein the first conference manuscript comprises a plurality of conference test question groups, the conference test question groups are in one-to-one association with a plurality of conference contents of the target conference, the conference test question groups are used for testing the understanding degree of a first user on the associated conference contents, and the first user is a user participating in the target conference;

And obtaining the reply information of the first user to the plurality of conference test question sets, and generating a second conference manuscript according to the reply information and the first conference manuscript, wherein the second conference manuscript comprises a plurality of first parameters, the plurality of first parameters are in one-to-one correspondence with the plurality of conference contents, and the first parameters are used for indicating the conference resource duty ratio of the corresponding conference contents.

In one embodiment, the analyzing and reasoning the conference material according to the big model to obtain a first conference manuscript includes:

analyzing and reasoning the conference materials according to the large model to obtain an initial conference manuscript;

and according to the large model, based on the user attribute of the first user, analyzing and reasoning the initial conference manuscript to obtain the first conference manuscript, wherein the understanding difficulty of the first conference manuscript is lower than that of the initial conference manuscript.

In one embodiment, after the obtaining the reply information of the first user to the plurality of conference test question sets and forming a second conference document according to the reply information and the first conference document, the method further includes:

acquiring conference communication information, wherein the conference communication information is communication information of the first user aiming at the first conference manuscript;

And generating warning information indicating a meeting deviation problem under the condition that the content similarity between the corresponding content of the meeting communication information and the plurality of meeting contents is smaller than or equal to a preset threshold value.

In one embodiment, the forming a second conference document according to the reply information and the first conference document includes:

and analyzing and reasoning the reply information and the first conference manuscript according to the large model to obtain a second conference manuscript, wherein the second conference manuscript also comprises a plurality of parameter interpretation data, the plurality of parameter interpretation data are in one-to-one correspondence with the plurality of first parameters, the parameter interpretation data are used for guiding a second user to plan a corresponding first parameter associated conference content speaking mode, and the second user is a user hosting the target conference.

In one embodiment, the method further comprises:

acquiring target feedback information of the first user on associated target content, wherein the target content is one of the conference contents;

and analyzing and reasoning the target feedback information according to the large model to obtain meeting adjustment information, wherein the meeting adjustment information is used for guiding a second user to adjust the meeting declaration mode of the target content, and the second user is a user who hosts the target meeting.

In one embodiment, the method further comprises:

acquiring a conference conclusion of the first user on associated target content, wherein the target content is one conference content in the plurality of conference contents;

and analyzing and reasoning the conference conclusion according to the large model to obtain a task chain of the target content.

In one embodiment, the method further comprises:

acquiring meeting evaluation information of the first user on the target meeting;

and iterating the large model according to the conference evaluation information.

In a second aspect, embodiments of the present disclosure further provide a conference assistance apparatus, the apparatus including:

the material acquisition module is used for acquiring meeting materials of the target meeting;

the reasoning module is used for carrying out analysis and reasoning on the conference materials according to the large model to obtain a first conference manuscript, wherein the first conference manuscript comprises a plurality of conference test question groups, the conference test question groups are in one-to-one association with a plurality of conference contents of the target conference, the conference test question groups are used for testing the understanding degree of a first user on the associated conference contents, and the first user is a user participating in the target conference;

The manuscript generation module is used for acquiring the reply information of the first user to the conference test question groups, and generating a second conference manuscript according to the reply information and the first conference manuscript, wherein the second conference manuscript comprises a plurality of first parameters, the first parameters are in one-to-one correspondence with the conference contents, and the first parameters are used for indicating the conference resource duty ratio of the corresponding conference contents.

In a third aspect, an embodiment of the disclosure further provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program when executed by the processor implements the steps of the conference assistance method described above.

In a fourth aspect, the disclosed embodiments also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the conference assistance method described above.

In the embodiment of the disclosure, analysis and reasoning are performed on meeting materials by using a large model so as to avoid interference caused by human factors, a first meeting manuscript which is higher in quality and comprises a plurality of meeting test question groups is obtained, then users participating in a target meeting are tested based on the plurality of meeting test question groups, and the respective meeting resource occupation ratio of a plurality of meeting contents in the target meeting is determined according to response information fed back by the users in the test, so that a host user of the target meeting is guided to orderly develop meeting announcement work, actual meeting resources of the plurality of meeting contents are reasonably planned, and the meeting effect of the target meeting is improved.

Drawings

Fig. 1 is a schematic diagram of a conference assistance method provided in an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of an operation interface of a file upload module according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a first conference manuscript provided by an embodiment of the present disclosure;

FIG. 4 is a schematic illustration of a plurality of first parameters within a second conference manuscript provided by an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of another first conference manuscript provided by an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a meeting summary provided by an embodiment of the present disclosure;

fig. 7 is a schematic diagram of a conference system provided by an embodiment of the present disclosure;

fig. 8 is a schematic diagram of a conference flow provided by an embodiment of the present disclosure;

fig. 9 is a schematic diagram of a conference assistance apparatus provided by an embodiment of the present disclosure;

fig. 10 is a schematic diagram of an electronic device provided in an embodiment of the disclosure.

Detailed Description

The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are some embodiments of the present disclosure, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.

An embodiment of the present disclosure provides a conference assistance method, as shown in fig. 1, including:

step 101, acquiring meeting materials of a target meeting.

The method disclosed by the disclosure is applied to a conference system, the conference system at least comprises a large model reasoning module and a data transmission module, the large model reasoning module is used for running a large model required by a conference and iterating the large model, the data transmission module is used for receiving various data input by a user into the conference system, forwarding the various data to the large model reasoning module, and returning the reasoning result to the user after receiving the reasoning result fed back by the large model reasoning module.

In an example, the conference system may also support online conference reservation functions.

Illustratively, the meeting material may be material uploaded to the meeting system for users hosting the target meeting, such as: PPT files, word files, video files, audio files, etc.

It should be noted that, the target conference is a conference that multiple people participate, and at least one user of multiple users participating in the conference performs a hosting conference, which may be a conference corresponding to enterprise management content, for example: conference of business direction of the enterprise or company, conference of business purpose of the implementation enterprise or company; it may also be a meeting corresponding to educational or training content, such as: a teacher who is responsible for teaching can understand the conference learning the knowledge about the conic section, and the rest of the students can understand the users who are participating.

For example, if the target meeting is set as a meeting on "how to formulate AIGC development policy inside a company";

the conference material comprises a PPT file which is introduced from the current AIGC capacity condition, AIGC technical principle, AIGC application scene, AIGC industry application condition and the like;

the conference material also comprises a video for introducing AIGC application effects, and the application effects of AIGC character generation, picture generation and the like are roughly introduced;

the conference material further comprises a WORD file, and the specific policy scheme to be determined in the conference is indicated as follows: a. the AIGC is not developed, the AIGC is developed in an external purchasing mode, the AIGC is developed in a completely self-grinding mode, and the AIGC is developed in a partial purchasing and partial self-grinding mode; and the possible presence of binding points for AIGC and corporate traffic.

In this example, a presenter or presenter (i.e., a user who hosts a target conference) may upload conference materials through a "file upload module" of the conference system (i.e., the foregoing data transmission module), where the file upload module may upload files using HTTP protocol, and an operation interface of the file upload module may be as shown in fig. 2.

And 102, analyzing and reasoning the conference materials according to the large model to obtain a first conference manuscript.

The first conference manuscript comprises a plurality of conference test question groups, the conference test question groups are associated with a plurality of conference contents of the target conference one by one, the conference test question groups are used for testing the understanding degree of a first user on the associated conference contents, and the first user is a user participating in the target conference.

The large model of the present disclosure refers to a large-scale language model (large language model, LLM), which is a language model with a large number of parameters and computing resources, typically requiring a large amount of data and computing power during training, and with millions to billions of parameters, intended to understand and generate human language, through which training can be performed a wide range of tasks including text summarization, translation, emotion analysis, etc.

In application, training of preprocessing data can be performed based on a neural network architecture, so that an initial LLM with analysis and reasoning capability is obtained, after training of the initial LLM is completed, fine adjustment and evaluation are further required to be performed on the initial LLM so as to adapt to specific application scenes and reasoning tasks, for example, in the present disclosure, training and fine adjustment of a specific field are performed on the initial LLM through a large amount of preprocessing data of relevant corpus of conferences and the like, so that a large model for analysis and reasoning in step 102 is obtained.

After analyzing and reasoning the conference materials, the large model outputs key contents of the conference materials, matters to be decided and conference targets, wherein the key contents consist of a plurality of key content item chapters; a plurality of test questions (i.e. the conference test question group) corresponding to the key content item in each chapter are also output.

For example, the first conference manuscript output based on the big model may be as shown in fig. 3, referring to fig. 3, and the first conference manuscript may include a conference keyword, a conference to-be-decided item, a conference abstract, a plurality of conference chapters, and chapter contents of each conference chapter, in addition to a plurality of conference test question groups.

Compared with meeting materials, the first meeting manuscript has stronger logic, richer content and better visual effect, and can remarkably reduce the pre-meeting pre-learning difficulty of users participating in the target meeting.

Step 103, obtaining the reply information of the first user to the plurality of conference test question sets, and generating a second conference manuscript according to the reply information and the first conference manuscript.

The second conference manuscript comprises a plurality of first parameters, the first parameters and the conference contents are in one-to-one correspondence, and the first parameters are used for indicating conference resource duty ratio of the corresponding conference contents.

For example, the conference resource indicated by the conference resource ratio may be a speaking duration of the target conference, that is, if the conference resource ratio of the conference content a is higher than the conference resource ratio of the conference content b, the speaking duration occupied by the conference content a may be greater than the speaking duration occupied by the conference content b.

For example, if the answer information corresponding to a certain conference content is displayed, the user who correctly understands the conference content accounts for 20% of the number of users participating in the conference, which indicates that the conference content belongs to a content which is difficult to understand for most of the users participating in the conference.

For example, referring to fig. 4, fig. 4 illustrates a plurality of first parameters within a second conference manuscript.

In this embodiment, there are a plurality of first users of the target meeting, there are a plurality of first meeting documents, the plurality of first users and the plurality of first meeting documents are in one-to-one correspondence, and the process of generating the second meeting document according to the reply information and the first meeting document may be:

and generating the second conference manuscript according to the plurality of reply information of the plurality of first users and the plurality of first conference manuscripts.

The user attributes are acquired, and further analysis and reasoning are carried out on the initial conference manuscript so as to output customized manuscripts aiming at each first user, and the cognitive difference and the capability difference of different first users are adapted, so that the multiple first users participating in the conference can understand conference materials more efficiently, and further the conference effect of the target conference is improved.

Illustratively, the analytical reasoning performed by the large model on the initial conference manuscript comprises at least one of the following:

deleting redundant content in the initial conference manuscript;

supplementing the content of the initial conference manuscript to further explain or explain the concept or content which is not clearly expressed in the initial conference manuscript;

the order of the plurality of contents of the initial conference manuscript is adjusted.

The user attribute may be, for example, gender, age, marital status, work history, post, job rank, etc. of the first user, and the large model may identify, based on the user attribute, a cognitive level, a good business field, etc. of the corresponding first user, so as to purposefully correct the content in the initial conference manuscript, and provide a first conference manuscript easier to understand for the corresponding first user.

For example: referring to the foregoing examples, for users outside of strategic, human resources, financial, etc., since such users are not familiar with AIGC, a proper noun, or a large language model, the explanation and description of the concepts described above may be added to the first meeting manuscript to which such users correspond.

For example, referring to fig. 5, fig. 5 illustrates a first conference manuscript corresponding to a certain first user, and in the first conference manuscript illustrated in fig. 5, the english holonomy terms and the technical principles of the AIGC are complementary to the content based on the initial conference manuscript for the convenience of the first user to understand.

It should be noted that, the first meeting manuscript is a dedicated meeting manuscript of a corresponding first user, and is used for assisting the corresponding first user to understand related content of the target meeting before the meeting, and assisting the corresponding first user to pay attention to the meeting core issue in the meeting; the second conference manuscript is a conference manuscript for assisting the host in carrying out target conference announcement.

In this embodiment, in the process of performing the target conference, by acquiring the communication information of the first conference manuscript of the first user and analyzing the content similarity between the corresponding content of the communication information and the plurality of conference contents, whether the currently discussed content of the target conference is a topic or not is determined, if yes, the warning information is generated, and the participants are reminded to focus on the established topic of the target conference, so that the time and effort wasted by the participants of the target conference on irrelevant matters can be reduced, and the conference effect of the target conference is improved.

In the embodiment, the large model is applied to analyze and infer the reply information and the first conference manuscript so as to obtain a second conference manuscript with better quality, and the host (namely the second user) is assisted to quickly understand and apply the corresponding second parameters through a plurality of parameter interpretation data included in the second conference manuscript, so that the actual conference resources of a plurality of conference contents are planned better, and the conference effect of the target conference is optimized.

By way of example, the foregoing parameter interpretation data may be understood as "unusual advice emphasis" content shown in fig. 4.

In one embodiment, the method further comprises:

In this embodiment, the target feedback information of the first user on the associated target content is obtained, and the large model is applied to analyze and infer the target feedback information, so as to mine the understanding condition of the first user on the target content, the difficult matters existing in the process of the first user understanding the target content, and the expanded content of the first user on the target content, and accordingly, conference adjustment information is output, so that the second user can be guided to conduct targeted answering and selective thinking divergence in the process of declaring the target content, and further, the conference effect of the target conference is optimized.

It should be noted that the target feedback information may be generated before or during the target meeting.

For example, before the target conference is carried out, the host may remind a plurality of first users participating in the target conference to feed back for respective first conference manuscripts, where the feedback content includes subjective understanding information of each first user on the plurality of conference contents and objective response information of the plurality of conference test question sets;

in the process of developing the target conference, the first user participating in the target conference can directly feed back based on the current announced content, such as excessive redundancy of the feedback announced content, high understanding difficulty of the feedback announced content, or divergent content of the service aiming at the announced content, so that the talker can adjust the announced rhythm and content in real time.

In one embodiment, the method further comprises:

In the embodiment, the large model is applied to analyze and infer the conference conclusion, and a corresponding service system of the first user is connected in parallel, and a corresponding task chain is established in the service system, so that the task splitting and follow-up work aiming at target content in the target conference by the participants is facilitated, and the conference effect of the target conference is optimized.

It should be noted that, after the large model analyzes and infers a plurality of conference conclusions corresponding to the plurality of conference contents one by one, a conference summary of the target conference may also be obtained, where the conference summary may include: important content matters of the conference, conclusions corresponding to important discussion matters, to-do and corresponding responsible persons of the conference and the like, so that the writing efficiency of the conference summary can be improved, and the conference recording burden of participants can be reduced.

For example, the foregoing conference summary may be as shown in fig. 6.

In one embodiment, the method further comprises:

In the embodiment, the conference evaluation information of the participant user on the target conference is obtained, and the large model is iterated according to the conference evaluation information, so that the function optimization of the large model is promoted, the analysis reasoning capacity of the large model is improved, and the conference effect of the subsequent conference can be improved.

For example, the meeting evaluation information may include indicators of meeting efficiency, meeting effect, meeting time consumption, and the like.

For ease of understanding, examples are illustrated below:

the foregoing conference system may be as shown in fig. 7, and the conference flow performed based on the conference system may be as shown in fig. 8.

1.1 a presenter or presenter conferences on a predetermined line of a conference system (which may be a Web or APP client), and at the same time, the conference material (which may be in file formats such as PPT, word, video, etc. used in the conference, but not limited to these formats) is uploaded through a "file upload module" of the conference system, and the file upload module adopts the HTTP protocol.

1.2 after a conference link is generated by a preset conference, conference materials uploaded by a presenter are used as input contents and sent to an AI analysis reasoning module, and based on the input contents and the materials, AI reasoning analysis through LLM is firstly output:

a) The key content of the conference, matters to be decided and conference targets;

b) According to the main content item and chapter of the outputted conference, for each chapter and content item, a test question for the present part of the content is outputted (for example: the choice questions and/or judgment questions) are mainly used for objectively judging the understanding degree of the participant on the content;

c) And finally, outputting a detailed standard version conference content manuscript based on the two-point output contents of a) and b), wherein the detailed standard version conference content manuscript is mainly used for pre-meeting study and in-meeting check of the participants so as to facilitate the supplement follow-up of missing contents on the meeting by the participants.

1.3, a main speaker sends an online conference link to each participant, the participant logs in to a conference system through the link, the attribute (such as post, knowledge level, knowledge field and the like) of the participant is analyzed through a user data analysis module after logging in, then an AI analysis reasoning module takes the current conference standard edition content output based on a large model in 1.2 and the user attribute as a basis, and a customized edition conference content manuscript suitable for the user is generated for each participant, so that the participant can quickly understand the conference content, for example: when the participant is a non-technician, it may not understand what is the AIGC, and at this time, the concept of the AIGC may be explained based on the content of the conference standard version, so that PGC, UGC, etc. are introduced in an expanded manner.

1.4 after the user logs in the conference, the interface can display the content output by 1.2 and 1.3 so that the user can be familiar with the conference content in advance before the conference.

1.5 after the participants are familiar with the conference content, the feedback of the understanding condition of the conference content can be actively carried out through the feedback module of the conference system, and if no participant is fed back, the host can actively remind the corresponding participant to initiate feedback.

The feedback of the participant is mainly in two ways:

a. voting feedback self-understanding is performed based on the participant's subjective direction for each chapter and section (which may be matched to PPT page numbers or content chapters, etc.).

b. Based on feedback for each chapter and section of the test title, the conference system objectively evaluates the participant's content understanding based on user feedback.

1.6 before the meeting starts, the feedback condition of the understanding of the participant for each part of the content is displayed in a presenter or presenter interface, and subjective voting and objective testing are combined for each part of the content, for example, the proportion of the number of people understanding the content can be displayed, the list of participants with the understanding of the real objectivity is highlighted, and the feedback data of a feedback module is combined, the 'meeting content judgment suggestion' is output to the presenter based on the 'AI analysis reasoning module', and the visual conclusion is presented on each part of the content or each page of PPT (for example, only part of the people understand the concept of AIGC and the terms such as a large language model are slightly unintelligrated, and the like).

2.1 the presenter analyzes the understanding degree of the participant on each part of the content of the conference based on the feedback data and the conference content judging advice output in 1.6, and judges the understanding degree of the participant on each part of the content by combining the accuracy of the understanding of the key content fed back by the participant (for example, the participant is informed of the correct content and fed back, the participant is briefly taught or directly skipped, and important explanation is carried out on points where most of the participants do not understand or understand the deviation).

2.2 the participant can also feed back the understanding situation of the current speaking content in real time through a feedback module in the conference, and the AI analysis reasoning module outputs the participant understanding situation data and the conference content judgment suggestion in real time according to the feedback so as to enable the presenter to refer to and adjust the speaking rhythm and the content in real time.

2.3, aiming at the points to be discussed in the conference, the AI analysis reasoning module analyzes the conditions of the important matters and the target achievement of the important matters and the target in real time according to the contents of the discussion of the conference in real time and combines the important matters and the target achievement of the conference, and the points to be discussed and the bifurcation points are summarized and output in real time, so that the deviation of the discussion of the conference is avoided, and the conference contents are focused on the preset target of the conference.

3.1 after the conference is finished, the AI analysis reasoning module analyzes and outputs a conference summary based on conference records formed by conference materials and voice transfer capability and discussion records of people in the conference, wherein the summary mainly comprises the following steps: important content matters of the conference, conference conclusions corresponding to important discussion matters, backlog of the conference, corresponding responsible persons and the like. And the conference system can track and execute the task items corresponding to the task management system or the office system directly by converting the task management system or the office system where the participants are located.

3.2 the participants can evaluate the whole conference after the conference, and particularly give positive evaluation or negative evaluation in the aspects of efficiency, effect, whole duration and the like, so that the 'AI analysis reasoning module' bottom layer large model is subjected to feedback training through the evaluation of the participants, the evolution of the AI large model is reversely promoted, and the AI large model capacity is more intelligent and accurate.

Referring to fig. 9, fig. 9 is a conference assistance apparatus provided in an embodiment of the present disclosure, and as shown in fig. 9, the conference assistance apparatus 900 includes:

a material acquisition module 901, configured to acquire conference materials of a target conference;

the reasoning module 902 is configured to perform analysis reasoning on the conference material according to a big model to obtain a first conference manuscript, where the first conference manuscript includes a plurality of conference test question sets, the conference test question sets are associated with a plurality of conference contents of the target conference one by one, and the conference test question sets are used to test understanding degree of a first user on the associated conference contents, and the first user is a user participating in the target conference;

The manuscript generation module 903 is configured to obtain reply information of the first user to the plurality of conference test question sets, and generate a second conference manuscript according to the reply information and the first conference manuscript, where the second conference manuscript includes a plurality of first parameters, the plurality of first parameters are in one-to-one correspondence with the plurality of conference contents, and the first parameters are used to indicate a conference resource ratio of the corresponding conference contents.

In one embodiment, the inference module 902 is specifically configured to:

In one embodiment, the conference assistance apparatus 900 further includes:

the communication information acquisition module is used for acquiring conference communication information, wherein the conference communication information is communication information of the first user aiming at the first conference manuscript;

and the warning module is used for generating warning information indicating a meeting deviation problem under the condition that the content similarity between the corresponding content of the meeting communication information and the plurality of meeting contents is smaller than or equal to a preset threshold value.

In one embodiment, the document generation module 903 is specifically configured to:

In one embodiment, the conference assistance apparatus 900 further includes:

the feedback information acquisition module is used for acquiring target feedback information of the first user on the associated target content, wherein the target content is one conference content in the plurality of conference contents;

the adjustment information acquisition module is used for analyzing and reasoning the target feedback information according to the large model to obtain meeting adjustment information, the meeting adjustment information is used for guiding a second user to adjust the meeting declaration mode of the target content, and the second user is a user who hosts the target meeting.

In one embodiment, the conference assistance apparatus 900 further includes:

The task construction module is used for acquiring a conference conclusion of the first user on the associated target content, wherein the target content is one conference content in the plurality of conference contents; and analyzing and reasoning the conference conclusion according to the large model to obtain a task chain of the target content.

In one embodiment, the conference assistance apparatus 900 further includes:

the evaluation acquisition module is used for acquiring conference evaluation information of the first user on the target conference;

and the iteration module is used for iterating the large model according to the conference evaluation information.

The conference assistance apparatus 900 provided in the embodiments of the present disclosure can implement each process in the embodiments of the conference assistance method, and in order to avoid repetition, a description thereof is omitted here.

According to an embodiment of the disclosure, the disclosure further provides an electronic device, a readable storage medium.

Fig. 10 shows a schematic block diagram of an example electronic device 1000 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read-Only Memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access Memory (Random Access Memory, RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

Various components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and communication unit 1009 such as a network card, modem, wireless communication transceiver, etc. Communication unit 1009 allows device 1000 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.

The computing unit 1001 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1001 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphic Process Unit, GPU), various dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (Digital Signal Processing, DSP), and any suitable processors, controllers, microcontrollers, etc. The computing unit 1001 performs the respective methods and processes described above, such as a conference assistance method. For example, in some embodiments, the conference assistance method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1000 via ROM 1002 and/or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by computing unit 1001, one or more steps of the conference assistance method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the conference assistance method in any other suitable way (e.g., by means of firmware).

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuitry, field programmable gate arrays (Field-Programmable Gate Array, FPGA), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), application specific standard products (Application Specific Standard Product, ASSP), system On Chip (SOC), complex programmable logic devices (Complex Programmable Logic Device, CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A conference assistance method, the method comprising:

acquiring meeting materials of a target meeting;

2. The method of claim 1, wherein said analyzing and reasoning the conference material according to the big model to obtain a first conference manuscript comprises:

3. The method of claim 1, wherein after obtaining the reply information of the first user to the plurality of conference test question sets and forming a second conference document according to the reply information and the first conference document, the method further comprises:

4. The method of claim 1, wherein the forming a second conference document from the reply information and the first conference document comprises:

5. The method according to claim 1, wherein the method further comprises:

6. The method according to claim 1, wherein the method further comprises:

7. The method according to claim 1, wherein the method further comprises:

8. A conference assistance device, the device comprising:

9. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor performs the steps of the method according to any one of claims 1 to 7.

10. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the method according to any of claims 1 to 7.