CN112990794A - Video conference quality detection method, system, storage medium and electronic equipment - Google Patents
Video conference quality detection method, system, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112990794A CN112990794A CN202110513818.3A CN202110513818A CN112990794A CN 112990794 A CN112990794 A CN 112990794A CN 202110513818 A CN202110513818 A CN 202110513818A CN 112990794 A CN112990794 A CN 112990794A
- Authority
- CN
- China
- Prior art keywords
- conference
- data
- quality
- real
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a video conference quality detection method, a video conference quality detection system, a storage medium and electronic equipment, wherein the multi-level quality parameters of a conference to be detected are determined by acquiring conference basic data, conference associated data and conference real-time data of the conference to be detected and according to the conference real-time data, the conference associated data and the conference basic data; and further determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters. Basic data, real-time data and associated data of the conference are fully utilized, so that edge computing, cloud computing and artificial intelligence technologies can be applied to carry out real-time or off-line processing on data of the whole process of the video conference, systematic, objective, accurate and timely detection on the quality of the conference is realized, and an organizer of the video conference can adjust the video conference in time, so that the conference efficiency is improved, and the comprehensive cost of the conference is reduced.
Description
Technical Field
The present invention relates to the field of video communication technologies, and in particular, to a method and a system for detecting a quality of a video conference, a storage medium, and an electronic device.
Background
The rapid development of multimedia communication services brings great convenience to users, but the problems of high conference frequency and low efficiency of part of conferences also occur. Therefore, how to effectively detect the quality of the video conference so as to adjust the conference frequency, the conference content, the participant and the conference interaction mode and the like according to the quality of the video conference, thereby further bringing better user experience and becoming a very important work.
Currently, evaluation aiming at video conference quality is limited to the quality of video or audio, and is limited to hardware, networks, signals and other angles in a perception layer with a lower cognitive level. The detection and evaluation of the quality of the video conference is not objective enough, and the detection and evaluation result cannot objectively and accurately reflect the quality of the video conference.
Disclosure of Invention
The embodiment of the invention provides a video conference quality detection method, a video conference quality detection system, a storage medium and electronic equipment.
According to a first aspect of the present invention, there is provided a video conference quality detection method, the method comprising: acquiring conference basic data, conference associated data and conference real-time data of a conference to be detected; determining the multi-level quality parameters of the conference to be detected according to the conference real-time data, the conference associated data and the conference basic data; and determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters.
According to an embodiment of the present invention, the determining the multi-level quality parameters of the conference to be detected according to the conference real-time data, the conference associated data and the conference basic data includes: identifying the conference real-time data to obtain a data identification result; determining the multistage quality parameters according to the data identification result, the conference basic data and the conference associated data; wherein the multi-level quality parameter comprises at least one of: individual multi-level parameters, group multi-level parameters, and conference multi-level parameters.
According to an embodiment of the present invention, determining the multilevel quality parameter according to the data identification result, the conference basic data, and the conference associated data includes: determining a plurality of quality detection levels of the conference to be detected and the membership between the quality detection levels; determining a detection value vector of the conference to be detected according to the data identification result, the conference basic data and the conference associated data; and sequentially determining the multistage quality parameters of the conference to be detected according to the detection value vectors and the subordination relation.
According to an embodiment of the present invention, the determining the comprehensive conference quality of the conference to be detected according to the multi-stage quality parameters includes: determining a correction coefficient of the multilevel quality parameter; and obtaining the comprehensive conference quality by utilizing the correction coefficient and the multilevel quality parameters.
According to an embodiment of the invention, the method further comprises: and sending out reminding information under the condition that the multi-level quality parameters and the comprehensive conference quality meet set conditions.
According to an embodiment of the invention, the method further comprises: and adjusting the conference to be detected according to the reminding information.
According to a second aspect of the present invention, there is also provided a video conference quality detection system, the system comprising: a data layer for acquiring and storing the following data: meeting basic data, meeting associated data and meeting real-time data of the meeting to be detected; the processing layer is used for determining the multistage quality parameters of the conference to be detected according to the conference real-time data, the conference associated data and the conference basic data; and the optimization layer is used for determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters.
According to an embodiment of the present invention, the data layer includes: the data acquisition module is used for acquiring conference basic data, conference associated data and conference real-time data of the conference to be detected; the data identification module is used for identifying the conference real-time data to obtain a data identification result; and the data storage module is used for storing the data identification result, the conference basic data and the conference associated data in a data storage mode respectively matched with the data identification result, the conference basic data and the conference associated data.
According to a third aspect of the present invention, there is also provided a computer-readable storage medium comprising a set of computer-executable instructions which, when executed, are operable to perform any of the video conference quality detection methods described above.
According to the fourth aspect of the present invention, there is provided an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a memory for storing a computer program; and the processor is used for realizing the video conference quality detection method when executing the program stored in the memory.
According to the video conference quality detection method, the video conference quality detection system, the storage medium and the electronic equipment, the multi-stage quality parameters of the conference to be detected are determined by acquiring the conference basic data, the conference associated data and the conference real-time data of the conference to be detected and according to the conference real-time data, the conference associated data and the conference basic data; and further determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters. Basic data, real-time data and associated data of the conference are fully utilized, so that edge computing, cloud computing and artificial intelligence technologies can be applied to carry out real-time or off-line processing on data of the whole process of the video conference, systematic, objective, accurate and timely detection on the quality of the conference is realized, and an organizer of the video conference can adjust the video conference in time, so that the conference efficiency is improved, and the comprehensive cost of the conference is reduced.
It is to be understood that the teachings of the present invention need not achieve all of the above-described benefits, but rather that specific embodiments may achieve specific technical results, and that other embodiments of the present invention may achieve benefits not mentioned above.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Fig. 1 is a schematic diagram illustrating an implementation flow of a video conference quality detection method according to an embodiment of the present invention;
fig. 2 is a schematic implementation flow diagram of a specific application example of the video conference quality detection method according to the embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a configuration of a video conference quality detection system according to an embodiment of the present invention;
fig. 4 is a schematic diagram showing a composition structure of an electronic device according to an embodiment of the present invention.
Detailed Description
The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given only to enable those skilled in the art to better understand and to implement the present invention, and do not limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Firstly, an application scenario of the video conference quality detection method according to the embodiment of the present invention is briefly described, the video conference quality detection method according to the present invention needs to be operated based on a video conference quality detection system, and the video conference quality detection system will be described in detail with reference to fig. 3, which is only briefly described here. The video conference quality detection system comprises: a data layer for acquiring and storing the following data: meeting basic data, meeting associated data and meeting real-time data of the meeting to be detected; the processing layer is used for determining the multi-level quality parameters of the conference to be detected according to the real-time conference data, the conference associated data and the conference basic data; and the optimization layer is used for determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters. Wherein, the data layer can include: the device comprises a data acquisition module, a data identification module and a data storage module. The data identification module can identify conference real-time data of the video conference, for example, participant note data and conference whiteboard data in the conference real-time data can be identified by using an OCR recognition technology. The conference storage module adopts a distributed layered cloud storage architecture, and selects a proper storage mode to store different types of conference data according to the data type, the data use and the life cycle circulation stage of the data.
The technical solution of the present invention is further elaborated below with reference to the drawings and the specific embodiments.
Fig. 1 shows a schematic implementation flow diagram of a video conference quality detection method according to an embodiment of the present invention.
Referring to fig. 1, a method for detecting quality of a video conference according to an embodiment of the present invention at least includes the following operation flows: operation 101, acquiring conference basic data, conference associated data and conference real-time data of a conference to be detected; operation 102, determining a multi-level quality parameter of the conference to be detected according to the real-time conference data, the conference associated data and the conference basic data; and operation 103, determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters.
In operation 101, conference basic data, conference associated data, and conference real-time data of a conference to be detected are acquired.
In this embodiment of the present invention, the conference basic data may include a conference subject element, a conference content element, a conference spatio-temporal element, and other conference elements. The main conference element may include participants, conference levels, and the like. For example, the participants include all the personnel of the A Enterprise department 1 and department 3, and the conference level is of primary importance within the enterprise. The conference content elements may include conference issues, conference conclusions, and the like. The meeting spatiotemporal elements may include meeting time and location, and the like. Other meeting elements may include meeting forms, etc., e.g., meeting forms being an open discussion meeting or a speaker training form, etc.
Meeting associated data may include enterprise internal data and an industry repository. The internal data of the enterprise can include basic information of staff, enterprise products, project information, enterprise management information, enterprise interest related party information, enterprise competitor information and the like. The industry knowledge base may include a medical knowledge base, an emergency plan knowledge base, a judicial knowledge base, a party political public knowledge base, an educational knowledge base, and the like.
The conference real-time data mainly comprises conference video data, conference audio data, text data and identification data. The conference identification video data can comprise a full-field video, a participant video, a conference demonstration picture video and the like. The conference audio data may include background audio and participant spoken audio. The text data may include participant note data and meeting whiteboard data. The identification data may include a face, a fingerprint, a voiceprint, and the like.
In this embodiment of the present invention, the conference real-time data may be acquired by various types of acquisition devices, for example: the conference system comprises an audio and video acquisition device, an intelligent conference board, a video conference user terminal and other collectors, and exchanges and synchronizes conference basic data and conference associated data by utilizing a data exchange interface provided by the video conference device.
In operation 102, a multi-level quality parameter of the conference to be detected is determined according to the conference real-time data, the conference associated data and the conference basic data.
In this embodiment of the present invention, first, conference real-time data is identified to obtain a data identification result, and then, according to the data identification result, conference basic data, and conference associated data, a multi-stage quality parameter is determined, where the multi-stage quality parameter includes at least one of: individual multi-level parameters, group multi-level parameters, and conference multi-level parameters.
In the embodiment of the invention, the required target information can be extracted by means of various machine learning algorithms aiming at the data input by different collectors in an intelligent recognition engine mode, and edge calculation or cloud data center calculation can be intelligently selected according to the factors such as software and hardware equipment configuration, data types, data scale, calculation difficulty, scene adaptation and the like.
For example, when software and hardware devices for performing a video conference have a data processing configuration, operations such as real-time voice recognition, facial expression recognition, target detection, and the like can be performed on the device side by using an edge computing technology. And transmitting the structured conference real-time data obtained after the edge calculation to a cloud computing center of the video conference, and further computing and processing the conference data at the cloud. For example: identifying and extracting data such as facial expressions, actions and eyeball focus points of participants from a conference video; identifying valid speech content data of a specific person from the audio; text data and the like are recognized from a terminal input such as a tablet.
In this embodiment of the present invention, the following operation steps are adopted to determine the multi-stage quality parameters according to the data identification result, the conference basic data and the conference associated data: determining a plurality of quality detection levels of a conference to be detected and the membership between the plurality of quality detection levels; determining a detection value vector of the conference to be detected according to the data identification result, the conference basic data and the conference associated data; and sequentially determining the multi-stage quality parameters of the conference to be detected according to the detection value vectors and the subordination relation.
In the practical application process, aiming at the difference of conference indexes concerned by different users of a video conference, a plurality of quality detection levels and the affiliation among the quality detection levels of the conference to be detected can be firstly determined according to the requirements. For example: the multilevel quality parameters can be divided into individual multilevel parameters, group multilevel parameters and conference multilevel parameters according to the actual application scene. And dividing the video conference into three stages for conference quality detection. For example: the mid-session quality parameters of the video conference may be divided into a plurality of quality detection levels as shown in table 1 below for the individuals participating, and the affiliations between the plurality of quality detection levels are shown.
TABLE 1 multiple quality detection levels for individuals of participants during the mid-meeting phase
And determining the multi-level quality parameters of the conference to be detected in sequence according to the bottom-up sequence of the subordination relations at each quality detection level.
In this embodiment of the present invention, the following formula (1) may be used to determine the multilevel quality parameter of the conference to be detected:
FS,O,L=Wf(X) （1）
wherein, FS,O,LA quality parameter score representing a quality detection level for an object at a certain conference stage.
S represents a conference stage of the video conference;
l represents the quality parameter FS,O,LA quality detection level of;
x represents the calculation of the quality parameter score FS,O,LEach related quality parameter vector or an observation value vector corresponding to the quality parameter vector;
f denotes the function used in determining the value of the relevant quality parameter, for example: normalizing the function;
w represents a weight coefficient of each relevant quality parameter.
For example: fWill be middle/individual P/level= W (acceptance) × f (acceptance) + W (participation) × f (participation) + W (contribution) × f (contribution). The individual recognition of the participant can be determined by combining explicit recognition and data for automatically identifying recognition. And this quality parameter may be determined in conjunction with the hands-off voting and voting data for the display acceptance.
In this embodiment of the present invention, it is also possible to divide the quality parameters of the pre-meeting phase of the video conference into a plurality of quality detection levels as shown in table 2 below for the video conference itself, and show the affiliation between the plurality of quality detection levels.
TABLE 2
In this embodiment of the present invention, the mid-session quality parameters of the video conference can also be divided into a plurality of quality detection levels as shown in table 3 below for the participating groups, and the affiliations between the plurality of quality detection levels are shown.
TABLE 3
In this embodiment of the present invention, the mid-session quality parameters of the video conference can also be divided into a plurality of quality detection levels as shown in table 4 below for the conference itself of the video conference, and the affiliations between the plurality of quality detection levels are shown.
TABLE 4
In this embodiment of the present invention, it is also possible to divide the post-session quality parameters of the video conference into a plurality of quality detection levels as shown in table 5 below for the conference itself of the video conference, and show the affiliation among the plurality of quality detection levels.
TABLE 5
It should be noted that the above determination of the multi-level quality parameters and the dependencies between the multi-level quality parameters of the video conference is only an exemplary illustration, and in the practical application process, the determination may be processed as needed. The invention is not limited in this regard.
In operation 103, a comprehensive meeting quality of the meeting to be detected is determined based on the multi-level quality parameters.
In the embodiment of the invention, firstly, the correction coefficient of the multi-stage quality parameter is determined, and then the comprehensive conference quality is obtained by using the correction coefficient and the multi-stage quality parameter, so that the comprehensive conference quality of the conference to be detected is determined according to the multi-stage quality parameter.
In this embodiment of the present invention, the determined correction factor may be corrected for the quality of a particular individual, group or conference in the video conference quality detection process. For example: the participants of the video conference include an industry authority expert, which may cause a problem that the acceptance of the expert opinions is far different from that of other participants due to the expert effect. If the moderator of the video conference needs to correct his index score in order to find other talents with high opinion acceptance in the conference.
In this embodiment of the present invention, the reminding information is also sent out when the multi-level quality parameters and the comprehensive conference quality satisfy the setting conditions. And adjusting the conference to be detected according to the reminding information.
For example, for the whole process of the video conference, the data of the multi-level quality parameters and the comprehensive conference quality are obtained, and a structured database is formed for storage. For the specific scene meta-information of the video conference, the quality parameters can be selected from the structured database to evaluate the quality of the video conference.
For example: and when the group conflict parameter of the video conference exceeds a set threshold value, adjusting the conference topic or adjusting the question discussion mode aiming at the video conference.
Fig. 2 is a schematic implementation flow diagram of a specific application example of the video conference quality detection method according to the embodiment of the present invention.
Referring to fig. 2, a specific application example of the video conference quality detection method according to the embodiment of the present invention at least includes the following operation flows: data acquisition is carried out through an equipment acquisition mode or a direct data exchange process; intelligently identifying the data collected by the equipment; carrying out real-time or off-line data transmission on the data in the direct data exchange process and the conference data obtained through intelligent identification; and processing the conference data, and storing the data before and after processing, wherein the data storage mode can adopt a mode suitable for the data type. And finally, carrying out automatic calculation of the conference quality index and conference benefit evaluation according to the conference data, and carrying out decision support on the quality of the video conference.
Specifically, before the video conference is held, a conference organizer or a conference manager inputs conference basic data through a terminal, and meanwhile, the cloud computing center can access internal related data of an enterprise performing the video conference to serve as conference related data.
And in the process of meeting, starting to acquire real-time data in the meeting process through a plurality of acquisition devices. For example: and collecting the conference audio and video by audio and video collecting equipment such as a camera. The acquisition equipment of real-time data can have general and customized intelligent identification functions, an intelligent identification engine of the video conference quality detection system can utilize edge calculation based on the intelligent identification function of the equipment, audio and video structured data, text data and the like obtained through the edge calculation are transmitted to a data layer of the video conference quality detection system through a network, and conference original data which is not supported by the acquisition equipment or needs complex data processing is directly transmitted to the data layer. The processing efficiency of the real-time data of the conference is effectively improved.
And in the data processing process, various types of data gathered to the data center are cleaned and standardized in an off-line or real-time manner according to the service scene and requirements, and data organization is carried out according to the requirements of users on meeting quality indexes. For example: the conference can be monitored and intervened in real time according to the high attention of the user to the quality index of the conference in progress so as to effectively control the conference agenda to be carried out efficiently and smoothly. The user can select indexes of three aspects of individuals, groups and meetings in the middle stage of the meeting.
The data storage is to store the real-time data of the conference, the conference basic data and the conference associated data into a proper database according to the organization level, the category, the application and the like. For example: storing original video, snap pictures, audio, converted text data and the like of the conference by adopting objects; the method comprises the steps that a data warehouse is adopted to store massive audio and video structured data after original data processing; and storing the related data such as the speaking content of the user related to the topic in the conference by adopting a database, and storing the application-intensive result data by adopting a relational database or a cache database.
A quality indicator for the video conference can be determined from the data stored in the data repository. Based on a certain service purpose, a specific index set can be selected, or a preset index set is used, and a proper evaluation model is selected to evaluate the benefit of the video conference by combining the historical evaluation record of the service. Here, the benefit evaluation of the video conference may be a quantitative index, and the quantitative index calculation model may optimize model parameters in advance through a model training process, for example: and (3) adopting a neural network model to carry out a calculation model of the video conference benefit evaluation.
The calculation result of the video conference quality index and the benefit evaluation result can be carried out in real time and can be displayed in real time, and a user can use the calculation result of the video conference quality index and the benefit evaluation result as decision support. If some parameter in the calculation result of the video conference quality index and the benefit evaluation result is not in the preset range of the scene, the video conference parameter is abnormal, and real-time warning can be performed. For example: the concentration degree of the group Q1 in the video conference at a certain time is lower than the set concentration threshold, and information showing an option such as "whether to select a break in the conference" can be issued. When the user selects to have a rest midway, the related equipment of the video conference sends out a notice through voice, and meanwhile, the data in the previous round of conference is further analyzed in batches, indexes such as the achievement degree of an issue in conference benefits are summarized, and the follow-up conference arrangement of a conference organizer is facilitated.
And after the conference is finished, outputting the index calculation result and the benefit evaluation result of the video conference quality, wherein the index calculation result and the benefit evaluation result can comprise data in a preset sequence in the data of the individual concentration degree, the participation degree and the contribution degree, an opinion leader of the conference and the like, and sending information for reminding the participants of filling in a preset questionnaire.
The other specific implementation process in fig. 2 is similar to the operation steps related to the specific implementation process in the embodiment shown in fig. 1, and is not described here again.
Fig. 3 is a schematic diagram illustrating a composition structure of a video conference quality detection system according to an embodiment of the present invention.
Referring to fig. 3, the video conference quality detection system according to the embodiment of the present invention at least includes: a data layer for acquiring and storing the following data: meeting basic data, meeting associated data and meeting real-time data of the meeting to be detected; the processing layer is used for determining the multi-level quality parameters of the conference to be detected according to the real-time conference data, the conference associated data and the conference basic data; and the optimization layer is used for determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters.
In this embodiment of the present invention, the data layer includes: the data acquisition module is used for acquiring conference basic data, conference associated data and conference real-time data of the conference to be detected; the data identification module is used for identifying the real-time conference data to obtain a data identification result; and the data storage module is used for storing the data identification result, the conference basic data and the conference associated data in a data storage mode respectively matched with the data identification result, the conference basic data and the conference associated data.
It should be noted that fig. 3 is an optimized implementation of the video conference quality detection system according to the embodiment of the present invention, and in an actual application process, a module design therein may be simplified. The following briefly describes the video conference quality detection system according to this embodiment of the present invention with reference to fig. 3.
Firstly, the data acquisition module of the data layer exchanges and synchronizes data through various different acquisition devices or data exchange interfaces. The data collected by the data collecting device can comprise three categories of device collected data, meeting element data and external data. The equipment acquisition data is various conference data acquired by video conference equipment; the conference element data is obtained by video terminal user input and automatic generation; the external data refers to data which is not in a video conference software and hardware acquisition or recording mode, but has an important auxiliary effect on video conference benefit evaluation, the data in an enterprise is detailed, and knowledge bases of different industries are listed for video application in different industrial scenes.
The intelligent identification module of the data layer can extract target information aiming at data input by different collectors based on various machine learning algorithms. And according to the factors such as software and hardware equipment configuration, data type, data scale, calculation difficulty, scene adaptation and the like, edge calculation or cloud data center calculation is intelligently selected and adopted. Under the condition that the software and hardware equipment of the video conference meet the requirements, calculation such as real-time voice recognition, facial expression recognition and target detection can be carried out on the edge, the converted structured data is transmitted to the cloud computing center, and meanwhile, follow-up operation is continued according to the computing result. For example: identifying and extracting data such as facial expressions, actions and eyeball focus points of people from the conference video; identifying valid speech content data of a specific person from the audio; text data and the like are recognized from a terminal input such as a tablet.
The data storage module of the data layer adopts a distributed layered cloud storage architecture, and selects a proper storage mode according to the data type, the data use and the life cycle circulation stage of the data. Storing original videos, snap pictures, audios, converted text data and the like by adopting objects; the method comprises the steps that a data warehouse is adopted to store massive audio and video structured data after original data processing; and storing the related data such as the speaking content of the user related to the topic in the conference by adopting a database, and storing the application-intensive result data by adopting a relational database or a cache database.
And the data processing module of the processing layer supports an offline and real-time processing engine and data conversion aiming at different application scenes. For example: and converting the audio and video data into structured data comprising the information such as the actions, expressions, behaviors, speech contents and the like of the participants, and sending the structured data to the cloud data center. And cleaning and standardizing the data of the video conference, and processing and organizing the data according to the data use scene.
The data processing module of the processing layer intelligently selects according to a preset template of a specific scene, and loads required data to perform index calculation; and the calculation can be carried out by individually customizing a specific index as a self-defined template. And calculating the benefits of the individual participants, the groups of participants and the whole conference by classification. Individuals may be evaluated in terms of engagement, concentration, contribution, opinion acceptance, and the like. The overall conference benefit can be evaluated in terms of the conference achievement degree, the conference rate, the conference effective time ratio, the effective speech ratio, the total concentration degree and the like. The resulting data is stored in corresponding database tables.
Aiming at the scene meta-information, the quality determination module of the optimization layer intelligently analyzes and selects an optimal evaluation fusion model to perform benefit evaluation calculation according to a schema (mode) of data related to the whole life cycle of the video conference, an index set selected by a user, different points of interest of the video conference on the benefit and the like. The evaluation model may include expert evaluation methods, operational research and other mathematical methods, neural network methods, hybrid methods, and the like. The method specifically comprises qualitative and quantitative evaluation methods such as comprehensive adoption of a score card, AHP (Analytic Hierarchy Process), a grey correlation method, fuzzy comprehensive evaluation, DEA (Data environment Analysis), principal component Analysis, an event window method, evidence reasoning and the like.
The decision support module of the optimization layer provides decision support for different application scenarios, such as: inefficient participants are identified based on their personal benefit scores over historical meetings and subsequently restrictive measures may be taken. And (4) based on a certain important meeting, investigating task achievement conditions of the participants before and after the meeting and recording performance evaluation of the participants. According to the comprehensive performance of individuals in historical conferences, people are portrayed, and talent identification is performed through opinion leader identification, leadership analysis and the like. According to the analysis of the video conference data, the conference flow can be optimized, the conference benefit is improved, and the related experience can be transplanted to the offline conference. Various types of data accumulated in the video conference can extract valuable information from the data and promote the construction of enterprise knowledge management.
Therefore, the quality detection of the video conference in the embodiment of the invention runs through the whole life cycle of the video conference, and the organization of the conference before the video conference, the development of the video conference, the emotional experience of participants after the conference and the enhancement of the conference on cognition and behaviors are carried out; and make comprehensive assessment of the video conference benefit from individuals, groups and the conference itself. The method carries out the quality detection of the video conference from the background angles of multiple subjects such as management, psychology, statistics, system science and the like to obtain the multi-level quality parameters and the comprehensive conference quality of the video conference with objectivity, accuracy and higher reference value.
According to the video conference quality detection method, the video conference quality detection system, the storage medium and the electronic equipment, the multi-level quality parameters of the conference to be detected are determined by acquiring the conference basic data, the conference associated data and the conference real-time data of the conference to be detected and according to the conference real-time data, the conference associated data and the conference basic data; and further determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters. Basic data, real-time data and associated data of the conference are fully utilized, so that edge computing, cloud computing and artificial intelligence technologies can be applied to carry out real-time or off-line processing on data of the whole process of the video conference, systematic, objective, accurate and timely detection on the quality of the conference is realized, and an organizer of the video conference can adjust the video conference in time, so that the conference efficiency is improved, and the comprehensive cost of the conference is reduced.
Similarly, based on the foregoing video conference quality detection method, an embodiment of the present invention further provides a computer-readable storage medium, in which a program is stored, and when the program is executed by a processor, the processor at least performs the following operation steps: operation 101, acquiring conference basic data, conference associated data and conference real-time data of a conference to be detected; operation 102, determining a multi-level quality parameter of the conference to be detected according to the real-time conference data, the conference associated data and the conference basic data; and operation 103, determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters.
Further, based on the above, an electronic device is provided, fig. 4 shows a schematic structural diagram of the electronic device according to the embodiment of the present invention, and as shown in fig. 4, the electronic device 40 includes a processor 401, a communication interface 402, a memory 403, and a communication bus 404, where the processor 401, the communication interface 402, and the memory 403 complete communication with each other through the communication bus 404; a memory 403 for storing a computer program; the processor 401 is configured to implement any of the video conference quality detection methods described above when executing the program stored in the memory.
Here, it should be noted that: the above description of the embodiment of the video conference detection system and the electronic device is similar to the description of the embodiment of the method shown in fig. 1 to 3, and has similar beneficial effects to the embodiment of the method shown in fig. 1 to 3, and therefore, the description is omitted. For technical details that are not disclosed in the embodiment of the video conference detection system and the electronic device of the present invention, please refer to the description of the method embodiments shown in fig. 1 to fig. 3 of the present invention for understanding, and therefore, for brevity, will not be described again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of a unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for detecting video conference quality, the method comprising:
acquiring conference basic data, conference associated data and conference real-time data of a conference to be detected;
determining the multi-level quality parameters of the conference to be detected according to the conference real-time data, the conference associated data and the conference basic data;
and determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters.
2. The method according to claim 1, wherein the determining the multi-level quality parameters of the conference to be detected according to the conference real-time data, the conference associated data and the conference basic data comprises:
identifying the conference real-time data to obtain a data identification result;
determining the multistage quality parameters according to the data identification result, the conference basic data and the conference associated data;
wherein the multi-level quality parameter comprises at least one of: individual multi-level parameters, group multi-level parameters, and conference multi-level parameters.
3. The method of claim 2, wherein determining the multi-level quality parameter based on the data identification, the meeting base data, and the meeting correlation data comprises:
determining a plurality of quality detection levels of the conference to be detected and the membership between the quality detection levels;
determining a detection value vector of the conference to be detected according to the data identification result, the conference basic data and the conference associated data;
and sequentially determining the multistage quality parameters of the conference to be detected according to the detection value vectors and the subordination relation.
4. The method according to claim 1, wherein said determining the integrated meeting quality of the meeting to be detected according to the multi-level quality parameters comprises:
determining a correction coefficient of the multilevel quality parameter;
and obtaining the comprehensive conference quality by utilizing the correction coefficient and the multilevel quality parameters.
5. The method of claim 1, further comprising:
and sending out reminding information under the condition that the multi-level quality parameters and the comprehensive conference quality meet set conditions.
6. The method of claim 5, further comprising:
and adjusting the conference to be detected according to the reminding information.
7. A video conference quality detection system, the system comprising:
a data layer for acquiring and storing the following data: meeting basic data, meeting associated data and meeting real-time data of the meeting to be detected;
the processing layer is used for determining the multistage quality parameters of the conference to be detected according to the conference real-time data, the conference associated data and the conference basic data;
and the optimization layer is used for determining the comprehensive conference quality of the conference to be detected according to the multi-level quality parameters.
8. The system of claim 7, wherein the data layer comprises:
the data acquisition module is used for acquiring conference basic data, conference associated data and conference real-time data of the conference to be detected;
the data identification module is used for identifying the conference real-time data to obtain a data identification result;
and the data storage module is used for storing the data identification result, the conference basic data and the conference associated data in a data storage mode respectively matched with the data identification result, the conference basic data and the conference associated data.
9. A computer-readable storage medium comprising a set of computer-executable instructions that, when executed, perform the video conference quality detection method of any of claims 1-6.
10. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus; a memory for storing a computer program; a processor for implementing the video conference quality detection method of any one of claims 1-6 when executing the program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110513818.3A CN112990794B (en) | 2021-05-12 | 2021-05-12 | Video conference quality detection method, system, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110513818.3A CN112990794B (en) | 2021-05-12 | 2021-05-12 | Video conference quality detection method, system, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112990794A true CN112990794A (en) | 2021-06-18 |
| CN112990794B CN112990794B (en) | 2021-10-15 |
Family
ID=76337514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110513818.3A Active CN112990794B (en) | 2021-05-12 | 2021-05-12 | Video conference quality detection method, system, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990794B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113434663A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Conference summary generation method based on edge calculation and related equipment |
| CN114826804A (en) * | 2022-06-30 | 2022-07-29 | 天津大学 | Method and system for monitoring teleconference quality based on machine learning |
| CN116760653A (en) * | 2023-08-17 | 2023-09-15 | 北京博数智源人工智能科技有限公司 | Intelligent operation and maintenance method and system for remote video conference |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104581140A (en) * | 2014-12-26 | 2015-04-29 | 国家电网公司 | Method for estimating video quality of videoconference |
| CN106791579A (en) * | 2016-12-30 | 2017-05-31 | 唐常芳 | The processing method and system of a kind of Video Frequency Conference Quality |
| CN109994129A (en) * | 2017-12-29 | 2019-07-09 | 阿里巴巴集团控股有限公司 | Speech processing system, method and apparatus |
-
2021
- 2021-05-12 CN CN202110513818.3A patent/CN112990794B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104581140A (en) * | 2014-12-26 | 2015-04-29 | 国家电网公司 | Method for estimating video quality of videoconference |
| CN106791579A (en) * | 2016-12-30 | 2017-05-31 | 唐常芳 | The processing method and system of a kind of Video Frequency Conference Quality |
| CN109994129A (en) * | 2017-12-29 | 2019-07-09 | 阿里巴巴集团控股有限公司 | Speech processing system, method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 杜邦石: "视频会议***运行质量综合评估方法的研究与应用", 《中国硕士学位论文全文数据库》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113434663A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Conference summary generation method based on edge calculation and related equipment |
| CN114826804A (en) * | 2022-06-30 | 2022-07-29 | 天津大学 | Method and system for monitoring teleconference quality based on machine learning |
| CN114826804B (en) * | 2022-06-30 | 2022-09-16 | 天津大学 | Method and system for monitoring teleconference quality based on machine learning |
| CN116760653A (en) * | 2023-08-17 | 2023-09-15 | 北京博数智源人工智能科技有限公司 | Intelligent operation and maintenance method and system for remote video conference |
| CN116760653B (en) * | 2023-08-17 | 2023-10-20 | 北京博数智源人工智能科技有限公司 | Intelligent operation and maintenance method and system for remote video conference |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112990794B (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112990794B (en) | Video conference quality detection method, system, storage medium and electronic equipment | |
| Bahreini et al. | Towards multimodal emotion recognition in e-learning environments | |
| Sanchez-Cortes et al. | Emergent leaders through looking and speaking: from audio-visual data to multimodal recognition | |
| Hung et al. | Estimating cohesion in small groups using audio-visual nonverbal behavior | |
| CN111915148B (en) | Classroom teaching evaluation method and system based on information technology | |
| US20150189233A1 (en) | Facilitating user interaction in a video conference | |
| RU2673010C1 (en) | Method for monitoring behavior of user during their interaction with content and system for its implementation | |
| CN114187988A (en) | Data processing method, device, system and storage medium | |
| WO2020039250A1 (en) | Method and system for collecting data and detecting deception of a human using a multi-layered model | |
| CN112364234B (en) | Automatic grouping system for online discussion | |
| Gao | Research and implementation of intelligent evaluation system of teaching quality in universities based on artificial intelligence neural network model | |
| US20230011923A1 (en) | System for providing a virtual focus group facility | |
| Pesarin et al. | Conversation analysis at work: detection of conflict in competitive discussions through semi-automatic turn-organization analysis | |
| Kathan et al. | A personalised approach to audiovisual humour recognition and its individual-level fairness | |
| CN115641101A (en) | Intelligent recruitment method, device and computer readable medium | |
| Raducanu et al. | Inferring competitive role patterns in reality TV show through nonverbal analysis | |
| JP2023500974A (en) | Systems and methods for collecting behavioral data for interpersonal interaction support | |
| CN112417280A (en) | Recommendation method and system based on virtual reality moderator system | |
| US20220101262A1 (en) | Determining observations about topics in meetings | |
| CN111950381B (en) | Mental health on-line monitoring system | |
| Zhang et al. | Can Large Language Models Assess Personality from Asynchronous Video Interviews? A Comprehensive Evaluation of Validity, Reliability, Fairness, and Rating Patterns | |
| Boussalis et al. | Mad, sad, but mostly glad: how men and women in politics communicate using emotions in images | |
| Jackson et al. | An empirical approach to offender profiling | |
| Martinez Rebollar et al. | Automatic detection of social isolation based on human behavior analysis | |
| CN111209817A (en) | Assessment method, device and equipment based on artificial intelligence and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |