CN116647635A - Remote desktop conference system and method based on deep learning - Google Patents
Remote desktop conference system and method based on deep learning Download PDFInfo
- Publication number
- CN116647635A CN116647635A CN202310926555.8A CN202310926555A CN116647635A CN 116647635 A CN116647635 A CN 116647635A CN 202310926555 A CN202310926555 A CN 202310926555A CN 116647635 A CN116647635 A CN 116647635A
- Authority
- CN
- China
- Prior art keywords
- data
- conference
- user
- module
- deep learning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000013135 deep learning Methods 0.000 title claims abstract description 41
- 230000005540 biological transmission Effects 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000002708 enhancing effect Effects 0.000 claims abstract description 11
- 238000012795 verification Methods 0.000 claims abstract description 11
- 238000007726 management method Methods 0.000 claims description 33
- 230000008569 process Effects 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000008451 emotion Effects 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 13
- 238000013075 data extraction Methods 0.000 claims description 12
- 238000013144 data compression Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 7
- 238000007781 pre-processing Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/15—Conference systems
-
- 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
- G06F9/452—Remote windowing, e.g. X-Window System, desktop virtualisation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/08—Protocols specially adapted for terminal emulation, e.g. Telnet
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/04—Protocols for data compression, e.g. ROHC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/40—Network security protocols
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a remote desktop conference system and method based on deep learning. The system comprises a data transmission unit, a user verification unit, a conference management unit, a conference recording unit and an encryption protection unit; the data transmission unit is used for compressing data transmission and enhancing the compressed data; the user verification unit is used for collecting conference user data and distributing corresponding conference management authorities for users; according to the invention, network transmission is optimized through the deep learning algorithm, so that the data transmission amount can be reduced, the transmission speed is improved, the communication delay is reduced, the remote desktop picture is enhanced and optimized through the deep learning image processing algorithm, the definition and detail restoring capability of the image are improved, a participant can obtain a clearer and more real remote desktop picture, the conference content is recorded in real time through the deep learning algorithm, and the conference content is analyzed and abstracted.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a remote desktop conference system and method based on deep learning.
Background
The current remote conference system has the defects of fuzzy pictures and insufficient interactivity among participants due to high communication delay in the long-time conversation process, and needs to assist in cutting and encrypting videos after the conference is stored, so that important parts of the videos are prevented from being leaked, the trouble is caused, meanwhile, an administrator is required to assist in controlling the time management of the conference, the situation that the conference data is displayed incompletely when the time exceeds the preset time easily occurs, and therefore, the remote desktop conference system and the remote desktop conference method based on the deep learning are provided.
Disclosure of Invention
The invention aims to provide a remote desktop conference system and a remote desktop conference method based on deep learning, which are used for solving the problems in the background technology.
In order to solve the above technical problems, one of the purposes of the present invention is to provide a remote desktop conference system based on deep learning, which includes a data transmission unit, a user verification unit, a conference management unit, a conference recording unit, and an encryption protection unit;
the data transmission unit is used for compressing data transmission and enhancing the compressed data;
the user verification unit is used for collecting conference user data and distributing corresponding conference management authorities for users;
the conference management unit is used for collecting information which is needed to be displayed in a conference by a user and distributing time for the user by combining with conference management authority;
the conference recording unit is used for collecting conference process data and analyzing and extracting the process data;
the encryption protection unit is used for encrypting according to the data analyzed and extracted by the conference recording unit and classifying according to the conference management authority of the user.
As a further improvement of the technical scheme, the data transmission unit comprises a data compression module and a video enhancement module;
the data compression module is used for collecting the data type of the conference and establishing a network data transmission optimization data channel according to the data type;
the video enhancement module is used for enhancing the conference picture by using a deep learning image processing algorithm according to the data type acquired by the data compression module.
As a further improvement of the technical scheme, the user authentication unit comprises a user acquisition module and a right distribution module;
the user acquisition module is used for acquiring the user data of the meeting and classifying the user data according to the user grade;
the right distribution module is used for distributing the management rights corresponding to the conference to the user according to the user data classified by the user acquisition module.
As a further improvement of the technical scheme, the conference management unit comprises a data uploading module and a time distribution module;
the data uploading module is used for collecting the display data of the conference required by the user and backing up the display data;
the time distribution module is used for analyzing the management rights distributed by the user according to the rights distribution module and the display data acquired by the data uploading module, so as to acquire a user time management scheme.
As a further improvement of the technical scheme, the time distribution module analyzes the collected display data by using an emotion analysis algorithm in combination with the performance of the corresponding user so as to judge the contribution and influence of each user, and the corresponding time is distributed to the user.
As a further improvement of the technical scheme, the conference recording unit comprises a file identification module and a data extraction module;
the file identification module is used for recording conference process data in real time and carrying out unified visual conversion on the conference process data;
the data extraction module is used for analyzing and extracting the data converted by the file identification module and classifying the data according to the extraction result.
As a further improvement of the technical scheme, the data extraction module uses a deep learning algorithm to analyze the converted conference process data, extract key information and generate conference summary.
As a further improvement of the technical scheme, the encryption protection unit comprises an information encryption module and a data display module;
the information encryption module is used for encrypting the data classified by the data extraction module and the user data classified by the user acquisition module;
the data display module is used for verifying the user accessing the record and displaying the corresponding conference process data according to the verification result.
The second object of the present invention is to provide a deep learning-based remote desktop conference method, including any one of the above deep learning-based remote desktop conference systems, comprising the following steps:
s1, compressing data transmission and enhancing the compressed data;
s2, collecting conference user data and distributing corresponding conference management authorities for users;
s3, collecting information which needs to be displayed in the conference by the user, and distributing time for the user by combining with conference management authority;
s4, collecting conference process data, and analyzing and extracting the process data;
s5, encrypting according to the analyzed and extracted data, and classifying according to the conference management authority of the user.
Compared with the prior art, the invention has the beneficial effects that:
the network transmission is optimized through the deep learning algorithm, the data transmission amount can be reduced, the transmission speed is improved, the communication delay is reduced, the remote desktop images are enhanced and optimized through the deep learning image processing algorithm, the definition and detail restoring capability of the images are improved, the participants can obtain clearer and more real remote desktop images, the conference content is recorded in real time through the deep learning algorithm, the conference content is analyzed and abstracted, the abstract of conference summary and key information is automatically generated, the efficiency of conference recording and arrangement is improved, meanwhile, the accuracy and the integrity of conference information are ensured, corresponding time is allocated for each user through the emotion analysis algorithm, the conference quality is improved, and the users are ensured to be capable of displaying the data to be displayed.
Drawings
FIG. 1 is a schematic diagram of the overall structure of the present invention;
fig. 2 is a schematic diagram of a data transmission unit according to the present invention;
FIG. 3 is a schematic diagram of a user authentication unit according to the present invention;
fig. 4 is a schematic structural diagram of a conference management unit of the present invention;
fig. 5 is a schematic structural diagram of a conference recording unit of the present invention;
FIG. 6 is a schematic diagram of the structure of the encryption protection unit of the present invention;
fig. 7 is a schematic diagram of the structure of the present invention for enhancing compressed data.
The meaning of each reference sign in the figure is:
10. a data transmission unit; 11. a data compression module; 12. a video enhancement module;
20. a user authentication unit; 21. a user acquisition module; 22. a rights allocation module;
30. a conference management unit; 31. a data uploading module; 32. a time distribution module;
40. a conference recording unit; 41. a file identification module; 42. a data extraction module;
50. an encryption protection unit; 51. an information encryption module; 52. and the data display module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: as shown in fig. 1 to 7, it is an object of the present invention to provide a deep learning-based remote desktop conference system including a data transmission unit 10, a user authentication unit 20, a conference management unit 30, a conference recording unit 40, and an encryption protection unit 50;
the data transmission unit 10 is used for compressing data transmission and enhancing compressed data;
the data transmission unit 10 includes a data compression module 11 and a video enhancement module 12;
the data compression module 11 is used for collecting the conference data type and establishing a network data transmission optimization data channel according to the data type; the network transmission is optimized through the deep learning algorithm, so that the data transmission quantity can be reduced, the transmission speed can be improved, and the communication delay can be reduced. This advantage enables a remote desktop conferencing system to maintain stable conference quality in a low bandwidth and high latency network environment; the method comprises the following steps:
identifying a data type: identifying the type of data that needs to be transmitted in the meeting, such as meeting agenda, meeting manuscript, presentation manuscript, audio and video streams, etc.;
analysis of data volume: estimating the transmitted data quantity according to the data type, analyzing network flow bottleneck, and determining a network data communication protocol and a stable transmission rate so as to achieve the stability of data transmission;
selecting a suitable network transmission protocol: since conference data generally needs to be transferred quickly and stably, a reliable data transfer technique based on UDP or a streaming media data transfer protocol of RTP protocol can be selected. The method can also be selected according to the data size, the real-time performance, the network bandwidth and the like;
establishing a network data transmission channel: the network data transmission channel can be established by VPN, qoS or establishing special network. Selecting a proper network transmission protocol and a network communication mode, and establishing a rapid and stable data communication channel so as to ensure timely and stable transmission of conference data;
configuring network optimization settings: the aim of optimizing the conference data network is achieved through means of configuration of a wireless network and a router, network topology optimization, network bandwidth management and the like. Optimizing the network configuration can effectively reduce network loss and improve the rate, stability and efficiency of data transmission.
By establishing the network data transmission optimization channel through the steps, the transmission quality of conference data can be improved, timely transmission and processing of conference data are ensured, and conference efficiency and successful holding possibility are increased.
The video enhancement module 12 is used for enhancing the conference picture by using a deep learning image processing algorithm according to the data type acquired by the data compression module 11. And the remote desktop picture is enhanced and optimized through a deep learning image processing algorithm, so that the definition and detail restoring capability of the image are improved. Therefore, the participants can obtain clearer and more real remote desktop pictures, and the communication and understanding capabilities of the participants are improved; the method comprises the following steps:
collecting conference videos: conference video is captured by a camera during a conference. The relative balance of the quality of the video is ensured as much as possible, and the shaking and the jitter should be prevented in the recording process;
preparing a training data set: a training dataset is prepared for a deep learning image processing algorithm. A large number of image samples needed by the algorithm are acquired, including a good clear picture and a picture under the conditions of noise interference, low luminosity, blurring and the like;
data preprocessing: preprocessing the images of the training set to eliminate the difference between input and output. Common pretreatment methods include subtracting means, normalization, resize, etc.;
training a deep learning model: a deep learning model, such as a convolutional neural network, is trained from the prepared data. During the training process, super-parameter adjustment and verification set test are required to be carried out so as to improve the generalization capability and robustness of the algorithm; the expression of the convolutional neural network is as follows:
assuming that an mtimesn image RGB image is mtimentimes 3, the filter size is ftimesf, and the convolution layer has k filters. Then the convolution operation of the ith filter and the input jth channel RGB image with 3 channels, only one channel of the gray scale image, can be expressed as:
；
where p and q are the steps of the filter in the horizontal and vertical directions.Typically an activation function such as a ReLU function or the like. />Weights, which are filter convolution kernels, +.>Is a bias item->Is the output from the neuron of the input layer or the upper layer. Output of convolution operation->Can be expressed as:
；
wherein the method comprises the steps ofIs the number of neurons in the upper layer. Output->Typically as input to subsequent layers.
The algorithm is applied: applying the trained deep learning image processing algorithm to the conference video, and carrying out edge enhancement, sharpening, noise reduction and other treatments on the conference picture through the algorithm, thereby improving the picture quality and highlighting key contents;
outputting optimized video: and outputting the processed picture as an optimized video, and storing the optimized video in a format which can be used for replay or transmission of the conference.
The user verification unit 20 is used for collecting conference user data and distributing corresponding conference management rights to users;
the user authentication unit 20 includes a user acquisition module 21 and a rights allocation module 22;
the user acquisition module 21 is used for acquiring the user data of the meeting and classifying the user data according to the user grade; the method comprises the following steps:
confirm the type of user data collected: determining the type of user data to be collected, such as name, email address, job position, department, telephone number, etc., for better user classification;
selecting a suitable data acquisition tool: a suitable data acquisition tool, such as an online questionnaire tool or acquisition software, is selected. For the acquisition of the related privacy information, the user needs to be informed in advance and clear consent is obtained;
design questionnaires or data acquisition tables: designing a questionnaire or a data acquisition table according to the type of user data to be acquired;
acquiring user data through a survey or data acquisition table: sending a questionnaire or a data acquisition table to users participating in the conference to acquire user data;
the rights allocation module 22 is configured to allocate the management rights corresponding to the conference to the user according to the user data classified by the user acquisition module 21. The method comprises the following steps:
classifying users according to user grades: and classifying the users according to the acquired user data. Can be according to the position, department;
corresponding conference management rights are allocated: and according to the user grade, corresponding meeting management rights are allocated to the user. For example, higher conference management rights may be assigned to high-level users, including rights for conference hosting, summary writing, and the like; while a common user is assigned less rights, such as viewing a meeting schedule or participating in a discussion.
The conference management unit 30 is used for collecting the information that the user needs to display in the conference, and distributing time to the user in combination with the conference management authority;
the conference management unit 30 includes a data upload module 31 and a time allocation module 32;
the data uploading module 31 is configured to collect display data of a user that needs to be in the meeting, and back up the display data; the method comprises the following steps:
determining data to be collected before the meeting begins: determining the type of data to be collected before the conference starts, wherein the data can comprise conference duration, conference agenda, participants, discussion topics, the sound, time, participation degree and the like of each participant on the discussion topics;
the data acquisition table is designed in advance: the data acquisition table is designed so that chapters are available when data is acquired.
The time allocation module 32 is configured to analyze the management rights allocated by the user according to the rights allocation module 22 in combination with the presentation data collected by the data uploading module 31, so as to obtain a user time management scheme. The method comprises the following steps:
analyzing the user performance in conjunction with the collected data: and analyzing the performances of the participants by using a corresponding analysis model in combination with the acquired conference data so as to judge the contribution and influence of each participant. Wherein the data analysis technology is emotion analysis technology.
The protocol was derived by data analysis: according to the result of data analysis, a time allocation management scheme is formulated for each participant, so that the advantages and contribution of each participant are fully exerted, and enough time can be reserved for each participant to speak and communicate.
The time distribution module 32 uses an emotion analysis algorithm to analyze the collected presentation data in combination with the performance of the corresponding user to determine the contribution and impact of each user, for which the user is assigned a corresponding time. The expression is as follows:
collecting presentation data such as PPT, presentation file and the like of a participant and presentation data such as speaking time, interaction times and the like through a conference collecting tool;
data preprocessing: preprocessing the acquired display data and performance data, including text preprocessing, feature extraction and the like, so as to apply an emotion analysis algorithm;
emotion analysis: and analyzing and processing through an emotion analysis algorithm according to the preprocessed data. The emotion analysis algorithm can adopt a model based on a neural network, and can identify emotion, theme and the like of the text through feedback information of a training set;
impact assessment: evaluating the contribution and influence of each participant by combining the emotion analysis result, and grading each participant by using evaluation indexes such as speaking time, interaction times and the like;
time allocation: the time each participant uses the presentation data is reassigned according to the participant's score. The specific allocation may be under the control of the meeting planner or moderator;
and (3) evaluation result display: and displaying the results of the emotion analysis algorithm and the participant time allocation results to the participant or the conference sponsor, and improving the planning and operation of the subsequent conference according to the feedback.
In the above procedure, the processing result of the emotion analysis algorithm can be expressed by the following formula:
；
wherein, the liquid crystal display device comprises a liquid crystal display device,score representing participant i, +.>、/>And->Weights for text, time and interaction, respectively, < ->、/>And->Functions of emotion analysis, time allocation and interaction index, respectively>Is time. According to actual conditions, the weights in the formula can be adjusted according to requirementsHeavy parameters and index functions to obtain the best results.
The conference recording unit 40 is used for collecting conference process data and analyzing and extracting the process data; and recording meeting contents in real time through a deep learning algorithm, analyzing and abstracting the meeting contents, and automatically generating abstracts of meeting summary and key information. The advantage can greatly improve the efficiency of conference recording and arrangement, lighten the manual burden and simultaneously ensure the accuracy and the integrity of conference information;
the conference recording unit 40 includes a file identifying module 41 and a data extracting module 42;
the file identification module 41 is used for recording conference process data according to real time and carrying out unified visual conversion on the conference process data; the method comprises the following steps:
conference information acquisition: collecting conference contents and converting voices into texts by using conference collecting tools such as intelligent sound boxes, voice recognition software and the like;
data preprocessing: preprocessing and cleaning the collected voice text, including converting the voice text into lower case letters, removing punctuation marks and the like;
the data extraction module 42 is used for analyzing and extracting the data converted by the file identification module 41, and classifying the data according to the type of the data.
The data extraction module 42 uses a deep learning algorithm to analyze the converted meeting process data, extract key information and generate meeting summary, expressed as follows:
and (3) abstract extraction: analyzing and abstracting a text by adopting a text abstracting technology in deep learning, such as a Textrank algorithm, filtering irrelevant information, and extracting key information and abstracts in conference contents;
meeting summary generation: based on the abstract extraction result, generating a meeting summary, and displaying the summary to a participant or a meeting sponsor for confirmation and modification;
real-time update and feedback: updating the latest conference content text and abstract extraction result into the conference summary in real time, and modifying and updating the conference summary according to feedback of a participant or a sponsor, wherein the automatic abstract is performed by using a text abstract technology based on deep learning, and the following formula can be adopted:
；
wherein, the liquid crystal display device comprises a liquid crystal display device,importance score representing i-th sentence in text abstract,/->Representing the weight coefficient from the ith sentence to the jth sentence,/for>Representing the connection coefficient from the jth sentence to the other sentence, < >>The damping coefficient is generally set to 0.85.
The encryption protection unit 50 is used for encrypting according to the analysis of the extracted data by the conference recording unit 40 and classifying according to the conference management authority of the user.
The encryption protection unit 50 includes an information encryption module 51 and a data display module 52;
the information encryption module 51 is configured to encrypt the classified data of the data extraction module 42 in combination with the user data classified by the user acquisition module 21; the method comprises the following steps:
encryption mode selection: selecting proper encryption modes, such as symmetric encryption, asymmetric encryption, hash encryption and the like, according to different data classifications and user grades;
encryption rule definition: an encryption rule and an encryption algorithm are formulated, and encryption modes, encryption parameters, key management, access control and the like are defined and standardized;
combining data and user ratings: combining the classified data with user authority data, dividing according to different authority data and encryption modes, and generating a corresponding encryption data set;
encryption operation: and performing program operation on the encrypted data set according to the encryption rule and the encryption algorithm to generate an encryption result. The following formula can be used for symmetric encryption:
；
wherein E (M) represents encryption processing of plaintext M, generation of ciphertext C, D (C) represents decryption processing of ciphertext C, generation of plaintext M, K represents a key, and oplus represents an exclusive OR operator.
The data presentation module 52 is configured to verify a user accessing the record, and present corresponding conference process data to the user according to the verification result. The method comprises the following steps:
user authentication: verifying the user identity according to the key provided by the user to ensure that the user is a legal user;
and (3) verifying data authority: according to the identity and authority of the user, verifying and authorizing the accessible data to ensure legal, safe and orderly data access;
data presentation: conference process data which shows that the user has permission to access, including speaking content of a speaker, speaking records of the participant, conference planning and arrangement and the like;
access record preservation: the access record and access time of the user are recorded for subsequent data analysis and processing.
The second object of the present invention is to provide a deep learning-based remote desktop conference method, including any one of the above deep learning-based remote desktop conference systems, comprising the steps of:
s1, compressing data transmission and enhancing the compressed data;
s2, collecting conference user data and distributing corresponding conference management authorities for users;
s3, collecting information which needs to be displayed in the conference by the user, and distributing time for the user by combining with conference management authority;
s4, collecting conference process data, and analyzing and extracting the process data;
s5, encrypting according to the analyzed and extracted data, and classifying according to the conference management authority of the user.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A remote desktop conference system based on deep learning, characterized in that: comprises a data transmission unit (10), a user verification unit (20), a conference management unit (30), a conference recording unit (40) and an encryption protection unit (50);
the data transmission unit (10) is used for compressing data transmission and enhancing compressed data;
the user verification unit (20) is used for collecting conference user data and distributing corresponding conference management authorities for users;
the conference management unit (30) is used for collecting information which is needed to be displayed in a conference by a user and distributing time for the user by combining with conference management authority;
the conference recording unit (40) is used for collecting conference process data and analyzing and extracting the process data;
the encryption protection unit (50) is used for encrypting according to the analysis and extraction data of the conference recording unit (40) and classifying according to the conference management authority of the user.
2. The deep learning based remote desktop conferencing system of claim 1, wherein: the data transmission unit (10) comprises a data compression module (11) and a video enhancement module (12);
the data compression module (11) is used for collecting the data type of the conference and establishing a network data transmission optimization data channel according to the data type;
the video enhancement module (12) is used for enhancing the conference picture by using a deep learning image processing algorithm according to the data type acquired by the data compression module (11).
3. The deep learning based remote desktop conferencing system of claim 1, wherein: the user authentication unit (20) comprises a user acquisition module (21) and a rights allocation module (22);
the user acquisition module (21) is used for acquiring the user data of the meeting, and classifying the user data according to the user grade;
the right distribution module (22) is used for distributing the management right corresponding to the meeting to the user according to the user data classified by the user acquisition module (21).
4. A deep learning based remote desktop conferencing system in accordance with claim 3, wherein: the conference management unit (30) comprises a data uploading module (31) and a time distribution module (32);
the data uploading module (31) is used for collecting the display data of the meeting required by the user and backing up the display data;
the time distribution module (32) is used for analyzing the management rights distributed by the user according to the rights distribution module (22) and the display data collected by the data uploading module (31), so as to obtain a user time management scheme.
5. The deep learning based remote desktop conferencing system of claim 4, wherein: the time distribution module (32) analyzes the collected presentation data by using an emotion analysis algorithm in combination with the performance of the corresponding user to judge the contribution and influence of each user, and the corresponding time is distributed to the user.
6. The deep learning based remote desktop conferencing system of claim 1, wherein: the conference recording unit (40) comprises a file identification module (41) and a data extraction module (42);
the file identification module (41) is used for recording conference process data according to real time and carrying out unified visual conversion on the conference process data;
the data extraction module (42) is used for analyzing and extracting according to the data converted by the file identification module (41) and classifying the data according to the extraction result.
7. The deep learning based remote desktop conferencing system of claim 6, wherein: the data extraction module (42) uses a deep learning algorithm to analyze the converted meeting process data, extract key information and generate meeting summary.
8. The deep learning based remote desktop conferencing system of claim 6, wherein: the encryption protection unit (50) comprises an information encryption module (51) and a data display module (52);
the information encryption module (51) is used for encrypting the classified data of the data extraction module (42) by combining the classified user data of the user acquisition module (21);
the data display module (52) is used for verifying the user accessing the record and displaying the corresponding conference process data according to the verification result.
9. A method for implementing a deep learning based remote desktop conference, comprising the deep learning based remote desktop conference system of any of claims 1-8, characterized by: the method comprises the following steps:
s1, compressing data transmission and enhancing the compressed data;
s2, collecting conference user data and distributing corresponding conference management authorities for users;
s3, collecting information which needs to be displayed in the conference by the user, and distributing time for the user by combining with conference management authority;
s4, collecting conference process data, and analyzing and extracting the process data;
s5, encrypting according to the analyzed and extracted data, and classifying according to the conference management authority of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926555.8A CN116647635B (en) | 2023-07-27 | 2023-07-27 | Remote desktop conference system and method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926555.8A CN116647635B (en) | 2023-07-27 | 2023-07-27 | Remote desktop conference system and method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116647635A true CN116647635A (en) | 2023-08-25 |
| CN116647635B CN116647635B (en) | 2023-11-28 |
Family
ID=87640429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310926555.8A Active CN116647635B (en) | 2023-07-27 | 2023-07-27 | Remote desktop conference system and method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116647635B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107623833A (en) * | 2016-07-13 | 2018-01-23 | 中兴通讯股份有限公司 | The control method of video conference, apparatus and system |
| CN108346034A (en) * | 2018-02-02 | 2018-07-31 | 深圳市鹰硕技术有限公司 | A kind of meeting intelligent management and system |
| CN109769143A (en) * | 2019-02-03 | 2019-05-17 | 广州视源电子科技股份有限公司 | Method of video image processing, device, video system, equipment and storage medium |
| CN112565777A (en) * | 2020-11-30 | 2021-03-26 | 通号智慧城市研究设计院有限公司 | Deep learning model-based video data transmission method, system, medium and device |
| CN113746822A (en) * | 2021-08-25 | 2021-12-03 | 安徽创变信息科技有限公司 | Teleconference management method and system |
| CN114268761A (en) * | 2021-12-22 | 2022-04-01 | 北京达佳互联信息技术有限公司 | Conference control method, conference control apparatus, electronic device, storage medium, and program product |
| CN114765676A (en) * | 2020-12-31 | 2022-07-19 | 上海闻越信息技术有限公司 | Video conference management method and system |
-
2023
- 2023-07-27 CN CN202310926555.8A patent/CN116647635B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107623833A (en) * | 2016-07-13 | 2018-01-23 | 中兴通讯股份有限公司 | The control method of video conference, apparatus and system |
| CN108346034A (en) * | 2018-02-02 | 2018-07-31 | 深圳市鹰硕技术有限公司 | A kind of meeting intelligent management and system |
| CN109769143A (en) * | 2019-02-03 | 2019-05-17 | 广州视源电子科技股份有限公司 | Method of video image processing, device, video system, equipment and storage medium |
| CN112565777A (en) * | 2020-11-30 | 2021-03-26 | 通号智慧城市研究设计院有限公司 | Deep learning model-based video data transmission method, system, medium and device |
| CN114765676A (en) * | 2020-12-31 | 2022-07-19 | 上海闻越信息技术有限公司 | Video conference management method and system |
| CN113746822A (en) * | 2021-08-25 | 2021-12-03 | 安徽创变信息科技有限公司 | Teleconference management method and system |
| CN114268761A (en) * | 2021-12-22 | 2022-04-01 | 北京达佳互联信息技术有限公司 | Conference control method, conference control apparatus, electronic device, storage medium, and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116647635B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107911646B (en) | Method and device for sharing conference and generating conference record | |
| CN105009599B (en) | The automatic mark of Wonderful time | |
| US11323407B2 (en) | Methods, systems, apparatuses, and devices for facilitating managing digital content captured using multiple content capturing devices | |
| US8791977B2 (en) | Method and system for presenting metadata during a videoconference | |
| CN112272828A (en) | Obfuscating information relating to Personally Identifiable Information (PII) | |
| US9275254B2 (en) | Augmented reality system for public and private seminars | |
| Gao et al. | Optimizing quality of experience for adaptive bitrate streaming via viewer interest inference | |
| CN106448297A (en) | Cloud audio-video remote interactive class system | |
| KR20150103264A (en) | Voice and/or facial recognition based service provision | |
| US20150156543A1 (en) | Video reaction processing | |
| CN108391062A (en) | Video creating method and system | |
| CN104394437A (en) | Live broadcasting method and system | |
| KR20190005015A (en) | Online Conference System | |
| Higgins Joyce | Independent voices of entrepreneurial news: Setting a new agenda in Latin America | |
| CN114727047A (en) | System and method for resolving overlapping speech in a communication session | |
| CN113703579A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN109862375B (en) | Cloud recording and broadcasting system | |
| CN116647635B (en) | Remote desktop conference system and method based on deep learning | |
| CN114902217A (en) | System for authenticating digital content | |
| CN111666552A (en) | Personal information management system | |
| US20210406806A1 (en) | Systems and methods for intelligent monitoring | |
| US11716364B2 (en) | Reducing bandwidth requirements of virtual collaboration sessions | |
| US11611600B1 (en) | Streaming data processing for hybrid online meetings | |
| KR102291113B1 (en) | Apparatus and method for producing conference record | |
| JP6913995B1 (en) | Information processing system, information processing method and program |
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 |