AU2021100901A4 - Artificial intelligence (ai) based online censoring engine system for social media platforms - Google Patents

Artificial intelligence (ai) based online censoring engine system for social media platforms Download PDF

Info

Publication number
AU2021100901A4
AU2021100901A4 AU2021100901A AU2021100901A AU2021100901A4 AU 2021100901 A4 AU2021100901 A4 AU 2021100901A4 AU 2021100901 A AU2021100901 A AU 2021100901A AU 2021100901 A AU2021100901 A AU 2021100901A AU 2021100901 A4 AU2021100901 A4 AU 2021100901A4
Authority
AU
Australia
Prior art keywords
input
module
user
processing
censoring
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.)
Ceased
Application number
AU2021100901A
Inventor
Ashima Aggarwal
Archana Sar
Sanjay Srivastava
Tanya Thankachan
Kamal Upreti
Binu Kuriakose Vargis
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aggarwal Ashima Ms
Sar Archana Dr
Thankachan Tanya Ms
Original Assignee
Aggarwal Ashima Ms
Sar Archana Dr
Thankachan Tanya Ms
Vargis Binu Kuriakose Mr
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aggarwal Ashima Ms, Sar Archana Dr, Thankachan Tanya Ms, Vargis Binu Kuriakose Mr filed Critical Aggarwal Ashima Ms
Priority to AU2021100901A priority Critical patent/AU2021100901A4/en
Application granted granted Critical
Publication of AU2021100901A4 publication Critical patent/AU2021100901A4/en
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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
    • G06F9/453—Help systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Artificial Intelligence (AREA)
  • Primary Health Care (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Information Transfer Between Computers (AREA)
  • Machine Translation (AREA)

Abstract

ARTIFICIAL INTELLIGENCE (AI) BASED ONLINE CENSORING ENGINESYSTEM FOR SOCIAL MEDIA PLATFORMS An Artificial Intelligence (AI) based online censoring engine system for social 5 media platforms is disclosed. A user interface module (102) is provided wherein a user securely logsand receives user inputs information in the form of text, audio and video input (106). The input (106) is translated to a standard language format when uploaded in other than the international standard format. The audio input (106) in the form of speech is converted into atext format by a translation module 10 (112) in the pre-processing module (108) and transmitted to the processing language module (110) for standard format. The input (106) is blocked when objectionable and uploaded to a public interface when approved. A chat bot interface (118) is provided for interacting with the user for objectionable input and receive queries from the user related to the input (106). 15 (FIG. 1 will be the reference figure) - 13 - rage 1 01 102 USER INTERFACE10 1106 INPUT MODULE 106 TEXT INPUT AUDIO INPUT VIDEO INPUT 112 PRE-10 PROCESSING 110 MODULE 1 12 PROCESSING FRAMING AND 114 LANGUAGE y RNLTNFEATURE MODULE EXTRACTION 116 Al MACHINE16 LEARNING MODULE 118 CHAT BOT INTERFACE ........... .......................... FIG. 1 block diagram of components and modules of an Artificial Intelligence(AI) based online censoring engine system 1

Description

rage 1 01
102 USER INTERFACE10
1106 INPUT MODULE 106
TEXT INPUT AUDIO INPUT VIDEO INPUT
PRE-10 PROCESSING 112 110 MODULE 1 12
PROCESSING FRAMING AND 114 LANGUAGE y RNLTNFEATURE MODULE EXTRACTION
116
Al MACHINE16 LEARNING
MODULE 118
CHAT BOT INTERFACE ........... ..........................
FIG. 1 block diagram of components and modules of an Artificial Intelligence(AI) based online censoring engine system
ARTIFICIAL INTELLIGENCE (AI) BASED ONLINE CENSORING ENGINE SYSTEM FOR SOCIAL MEDIA PLATFORMS TECHNICAL FIELD
[0001] The present disclosure relates to a field of computer and communication engineering and in particular to the artificial intelligence (Al) based online censoring engine system for social media platform.
BACKGROUND
[0002] The time of technology where people communicate, inspire and transform their behaviour through different modes such as social media platforms, which consists of so-called mobile applications like twitter, YouTube, Facebook and the like. These platforms devise algorithms to determine what their user's limited attention span will focus on, and side-tracking public responsibility. Billions of people are now sending electronic messages daily to each other in various electronic forms, formats, media and languages spoken and written in hundreds of different human languages. These messages are generally fashioned by the senders to conveysome underlying thought, information, or feeling that will fit into some context mutually understood or understandable by those involved. But, poetry, intentional deception, and psychotic m o t iv e s behind particular messages can render the underlying thoughts, information, or feelings hard to decipher. That is even in spite of the use of good grammar and correct spellings in the messages.
[0003] Translations in which the underlying thoughts, information, or feelings do not survive the translation or transcription are of little value and sometimes the misunderstandings can be costly, dangerous, or harmful. Real-time failures of human or machine readers to correctly perceive the underlying thoughts, information, or feelings in messages they read are similarly treacherous. Humans pretty naturally use their perceptions of their environment and people contacts to reduce the confusion of ambiguities always present in words, sentences, paragraphs, missives, thoughts, information, and feelings. Conventional machine readers have always taken each word at face value and operate blind as to why that word was chosen and not another. The results can be funny or bizarre at times. For humans, a word like "wine" can have qualia of taste, smell, color, age, proximity, temperature, availability, and cost. So, a message sentence including the word "wine" can be immediately classified as to which qualiais afoot by hints or outright flags and arrows pointing to the taste, smell, color, age, proximity, temperature, availability, and cost. A conventional machine reader will just dumbly log in the word "wine" and move on to other instances of the same word without requiring any adherence to a theme.
[0004] For example, United Patent no. US20190213498A1 addressed an artificial intelligence (AI) system comprises a computer network server connected to receive and analyse thousands of simultaneous voice and text messages which are written by humans. The otherwise important words can be recognized and assembled together. Each such word is contributed to agenerator that can spawn the word into its possible contexts, themes. Several such spreads can be used as templates on the others to find petals that exhibit a convergence of meaning. Once the context of a whole missive has been predicted, each paragraph is can be broken down into sub-contexts that are appropriate. However precise filtering of internet content is almost impossible, but there are variety of methods used to do this, including requiring discriminatory ISP (Internet service provider) licenses, filtering based on keywords, rerouting packets destined for a specific IP address to ablacklist, website blocking of a list of IP addresses and hardware and software manipulation.Filtering mechanisms may result into over blocking. The limitations and needs of the existing technology especially in social media communication platforms where a user can access and upload the content and transmit to public interface without filtering and censoring the content, is overcome by the technical advancements of the claimed invention.
OBJECTS OF THE INVENTION
[0005] It is an object of the present disclosure, which provides a method for censoring online data.
[0006] It is an object of the present disclosure which provides a method fact check online social media content.
[0007] It is an object of the present disclosure which provides a method uses Al.
SUMMARY
[00081 The present invention relates to a system of an Artificial Intelligence based framework for censoring online data (text, speech/audio, image and video) while it is getting uploaded. Thepresent system blocks the objectionable contents and will also give the reason for the same tothe user via Chabot. In an embodiment of the invention an Artificial Intelligence (AI) based online censoring engine system for social media platforms is disclosed. The system comprising: a user interfacemodule, wherein a user securely logs into the user interface module, wherein the user interface module includes smart gadgets, cellular devices, and the like; the user interface module comprises an input module, wherein the user inputs information on the input module,wherein the input module is in the form of text, audio and video; the input is transferred to apre-processing module, wherein the pre-processing model includes a processing language module in which the input text is translated to a standard language format when uploaded another than the international standard format, wherein the audio input in the form of speech is converted into a text format in the pre-processing module and transmitted to the processing language module for standard format; the pre-processing module transmits the input to a machine learning (ML) model based on the artificial intelligence (AI) engine for filtering andcensoring the input for objections as per the government norms, wherein the input is blockedwhen objectionable and uploaded to a public interface when approved; and a chat bot for interacting with the user for objectionable input and receive queries from the user related to the input, wherein the user interacts with the chat bot through a series of reasons and appealsagainst the input being objected and blocked.
[0009] In an aspect of the present invention, the input video after passing through the pre-processing module is transmitted to: a framing module, wherein the input video is classified according to the category of the content of the video with respect to the allocation of the public interface or social media platform; and a feature extraction module, wherein the input video after being framed in a particular classification is compressed and resized, thereby reducing the amount of data to be displayed on the public interface without removing the content of the input video.
[0010] In yet another aspect of the present invention, the system comprises: a social platform interface, wherein the user appeals against the input being temporarily blocked by the machine learning(ML) model based on Al engine.
[0011] In yet another aspect of the present invention, the artificial intelligence (AI) engine censors the input content of text, audio and video for a particular age group.
[0012] In yet another aspect of the present invention, a method Artificial Intelligence (AI) based online censoring engine for social media platforms. The method comprising steps: receiving an input from a user to a user interface module, wherein the user securely logs into the user interface module, wherein the user interface module includes smart electronic multimedia gadgets, wherein the user interface module comprises an input module, wherein the user inputs information on the input module, wherein the input module is in the form of text, audioand video; transmitting the input to a pre-processing module, wherein the pre processing model includes a processing language module; converting the input to a standard language format, when uploaded in other than the international standard format, wherein the audio input in the form of speech is converted into a text format in the pre-processing module and istransmitted to the processing language module for standard format; transmitting the input from the pre-processing module to a machine learning (ML) model based on the artificial intelligence (AI) engine for filtering and censoring the input for objections as per the government norms; blocking temporarily the input, when objectionable and uploading to a public interface, when approved; and interacting with the user through a chat bot for objectionable input and receive queries from the user related to the input, wherein the user interacts with the chat bot through a series of reasons and appeals against the input being objected and blocked.
BRIEF DESCRIPTION OF THE DRAWINGS
[0013] FIG. 1 illustrates a block diagram of components and modules of an Artificial Intelligence(AI)based online censoring engine system.
[0014] FIG. 2 illustrates a flow diagram of operation in the censoring system.
[0015] FIG. 3 illustrates a block diagram of the operations involved in the censoring system.
DETAILED DESCRIPTION
[0016] In an embodiment of the present disclosure, FIG. 1 illustrates a block diagram of components and modules of an Artificial Intelligence(AI)based online censoring engine system. The Artificial Intelligence (AI)based online censoring engine system for social media platforms. A user interface module (102) is provided wherein a user securely logs into the user interface module. The user interface module includes smart gadgets, cellular devices, and the like used today. The user interfacemodule (102) comprises an input module (104). The user inputs information on the input module and the input module (104) is in the form of text, audio and video input (106). The input (106) is transferred to a pre-processing module (108) and the pre-processing module (108) includes a processing language module (110) in which the input text (106) is translatedto a standard language format when uploaded in other than the international standard format. The international standard format can be termed as English or any other language internationally recognized. The audio input (106) in the form of speech is converted into a text format by a translation module (112) in the pre-processing module (108) and transmitted to the processing language module (110) for standard format.
[00171 In an aspect, the pre-processing module (108) transmits the input to a machine learning (ML) model (116)based on the artificial intelligence (AI) engine for filtering and censoring the input (106) forobjections as per the government norms. The input (106) is blocked when objectionable and uploaded to a public interface when approved. A chat bot interface (118) is provided for interacting with the user for objectionable input and receive queries from the user related to the input (106). The user interacts with the chat bot (118) through a series of reasons andappeals against the input being objected and blocked.
[0018] In yet another aspect of the present invention, the input (106) in the form of video after passing through the pre-processing module is transmitted to a framing module (114), wherein the input video is classified according to the category of the content of the video with respect to the allocation of the public interface or social media platform. The classification is generally based on age categories, education, entertainment and history. The input video (106) is also processed to a feature extraction module (114) wherein the input video after being framed in a particular classification is compressed and resized, thereby reducing the amount of data to be displayed on the public interface without removing the content of the input video.
[0019] In yet another aspect of the present invention, the social platform interface is also provided wherein the user appeals against the input being temporarily blocked by the machine learning (ML) model based on Al engine. A number of experts answer the user on the content being objectionable and temporarily blocked by the machine learning (ML) module. The artificial intelligence (AI) engine censors the input content of text, audio and video for a particular age group.
[0020] In yet another aspect of the present invention, FIG. 2 illustrates a flow diagram of operation in the censoring system. The method Artificial Intelligence (AI)based online censoring engine for social media platforms, the method comprising steps: the first step (210) states receiving an input from a user to a user interface module, wherein the user securely logs into the user interface module, wherein the user interface module includes smart electronic multimedia gadgets, wherein the user interface module comprises an input module, wherein the user inputs information on the input module, wherein the input module is in the form of text, audio and video; the second step(220) states transmitting the input to a pre processing module, wherein the pre-processing model includes a processing language module; the third step (230) states converting the input to a standard language format, when uploaded in other than the international standard format, wherein the audio input in the form of speech is converted into a text format in the pre- processing module and is transmitted to the processing language module for standard format;the fourth step (240) involves transmitting the input from the pre processing module to a machine learning (ML) model based on the artificial intelligence (AI) engine for filtering and censoring the input for objections as per the government norms; the fifth step (250) involvesblocking temporarily the input, when objectionable and uploading to a public interface, whenapproved; and the final step (260) involves interacting with the user through a chat bot for objectionable input and receive queries from the user related to the input, wherein the user interacts with the chat bot through a series of reasons and appeals against the input being objected and blocked.
[0021] In yet another aspect of the present invention, FIG. 3 illustrates a block diagram of the operations involved in the censoring system. When the user is trying to upload any data on the social media platform it undergoes relevantpre processing. The text data after pre- processing go through a natural language processing(NLP) block which converts the data into English if the uploaded data is in some other language. NLP block also extracts features which with trained machine learning (ML) modeldecides if the text is objectionable. If the user is uploading a speech data, it is converted into text and further processing will be done like text data. Video data uploaded by the user undergoes framing before applying to the feature extraction block followed by the trained ML model. The Chat-bot interacts with the user prompting him/her if the data is objectionable with the reasons for the same. The user may pass related query to the Chabot.Through a series of interactions with a user, the system may take final decision of blocking the data as the case persists. The user may further appeal against this decision which is registered by the system as a pending decision, temporarily blocking the data. The pending decisions is resolved by the experts appointed by a social media platform owner.
[0022] In yet another aspect of the present invention, the method comprises transmitting the input video after passing through the pre-processing module (108) a framing module (114).
[0023] In yet another aspect of the present invention, the method comprises classifying the input video (106) accordingto the category of the content of the video with respect to the allocation of the public interfaceor social media platform.
[0024] In yet another aspect of the present invention, the method comprises compressing and resizing the input video afterbeing framed in a particular classification, thereby reducing the amount of data to be displayed on the public interface without removing the content of the input video.

Claims (9)

We Claim:
1. An Artificial Intelligence (AI) based online censoring engine system for social mediaplatforms, the system comprising:
a user interface module (102), wherein a user securely logs into the user interface module, wherein the user interface module includes smart gadgets, cellular devices, and the like;
a user interface module (102) comprises an input module (104), wherein the user inputs information on the input module (104), wherein the input module is in the form of text,audio and video (106);
an input (106) is transferred to a pre-processing module (108), wherein the pre- processing model (108) includes a processing language module (110) in which the input text (106) is translated to a standard language format when uploaded in other than the international standard format, wherein the audio input (106) in the form of speech is converted into a text format by a translation module (112) in the pre-processing module (108) and transmitted to the processing language module (110) for standard format;
a pre-processing module (108) transmits the input to a machine learning (ML) module (116) based on the artificial intelligence (AI) engine for filtering and censoring the input (106) for objections as per the government norms, wherein the input (106) is blocked when objectionable and uploaded to a public interface when approved; and
a chat bot interface (118) for interacting with the user for objectionable input andreceive queries from the user related to the input, wherein the user interacts with the chat bot (118) through a series of reasons and appeals against the input being objected and blocked.
2. The system as claimed in claim 1, wherein the input video after passing through the pre-processing module (108) is transmitted to:
a framing module (114), wherein the input video (106) is classified according to the categoryof the content of the video with respect to the allocation of the public interface or social media platform; and
3. The system as claimed in claim 1, wherein said system comprises a feature extractionmodule (114), wherein the input video after being framed in a particular classificationis compressed and resized, thereby reducing the amount of data to be displayed on thepublic interface without removing the content of the input video. 4. The system as claimed in claim 1, wherein the system comprises:
a social platform interface, wherein the user appeals against the input beingtemporarily blocked by the machine learning (ML) model based on Al engine.
5. The system as claimed in claim 1, wherein the artificial intelligence (AI) enginecensors the input content of text, audio and video for a particular age group.
6. A method Artificial Intelligence (AI)based online censoring engine for social media platforms, the method comprising steps:
receiving an input from a user to a user interface module, wherein the user securely logs into the user interface module, wherein the user interface module includes smart electronic multimedia gadgets, wherein the user interface module comprises an input module,wherein the user inputs information on the input module, wherein the input module is in theform of text, audio and video;
Transmitting the input to a pre-processing module, wherein the pre processing modelincludes a processing language module; converting the input to a standard language format, when uploaded in other than the international standard format, wherein the audio input in the form of speech is converted intoa text format in the pre-processing module and is transmitted to the processing language module for standard format; blocking temporarily the input, when objectionable and uploading to a public interface, when approved; and interacting with the user through a chat bot for objectionable input and receive queriesfrom the user related to the input, wherein the user interacts with the chat bot through a seriesof reasons and appeals against the input being objected and blocked.
7. The method as claimed in claim 6, wherein said method comprises transmitting the input video after passing through the pre-processing module (108) a framing module(114); classifying the input video (106) according to the category or the content of the videowith respect to the allocation of the public interface or social media platform.
8. The method as claimed in claim 6, wherein said method comprises compressing andresizing the input video after being framed in a particular classification, thereby reducing the amount of data to be displayed on the public interface without removingthe content of the input video.
9. The method as claimed in claim 6, wherein said method comprises temporarily blocking, on a social platform interface, user appeals against the input by machine learning (ML) model based on Al engine.
Total no. of sheets: 3 16 Feb 2021 Page 1 of 3
102 USER INTERFACE LOGIN MODULE
104
INPUT MODULE 2021100901
106
TEXT INPUT AUDIO INPUT VIDEO INPUT
108 PRE‐ PROCESSING 110 MODULE 112
PROCESSING FRAMING AND 114 TRANSLATION LANGUAGE FEATURE MODULE MODULE EXTRACTION MODULES
116 AI MACHINE LEARNING (ML) MODULE 118
CHAT BOT INTERFACE
FIG. 1 block diagram of components and modules of an Artificial Intelligence (AI) based online censoring engine system
Total no. of sheets: 3 16 Feb 2021 Page 2 of 3
RECEIVING AN INPUT FROM A USER TO A USER INTERFACE MODULE, 210 WHEREIN THE USER SECURELY LOGS INTO THE USER INTERFACE MODULE 220 TRANSMITTING THE INPUT TO A PRE‐PROCESSING MODULE, 2021100901
WHEREIN THE PRE‐PROCESSING MODEL INCLUDES A PROCESSING LANGUAGE MODULE
230 CONVERTING THE INPUT TO A STANDARD LANGUAGE FORMAT, WHEN UPLOADED IN OTHER THAN THE INTERNATIONAL STANDARD FORMAT
240 TRANSMITTING THE INPUT FROM THE PRE‐PROCESSING MODULE TO A MACHINE LEARNING (ML) MODEL BASED ON THE ARTIFICIAL INTELLIGENCE (AI) ENGINE FOR FILTERING AND CENSORING THE INPUT FOR OBJECTIONS AS PER THE GOVERNMENT NORMS 260 BLOCKING TEMPORARILY THE INPUT, WHEN OBJECTIONABLE AND UPLOADING TO A PUBLIC INTERFACE, WHEN APPROVED
INTERACTING WITH THE USER THROUGH A CHAT BOT FOR 270 OBJECTIONABLE INPUT AND RECEIVE QUERIES FROM THE USER RELATED TO THE INPUT, WHEREIN THE USER INTERACTS WITH THE CHAT BOT THROUGH A SERIES OF REASONS AND APPEALS AGAINST THE INPUT BEING OBJECTED AND BLOCKED
FIG. 2 flow diagram of operation in the censoring system
Total no. of sheets: 3 16 Feb 2021 2021100901 Page 3 of 3
FIG. 3 block diagram of the operations involved in the censoring system
AU2021100901A 2021-02-16 2021-02-16 Artificial intelligence (ai) based online censoring engine system for social media platforms Ceased AU2021100901A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2021100901A AU2021100901A4 (en) 2021-02-16 2021-02-16 Artificial intelligence (ai) based online censoring engine system for social media platforms

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2021100901A AU2021100901A4 (en) 2021-02-16 2021-02-16 Artificial intelligence (ai) based online censoring engine system for social media platforms

Publications (1)

Publication Number Publication Date
AU2021100901A4 true AU2021100901A4 (en) 2021-04-29

Family

ID=75625720

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2021100901A Ceased AU2021100901A4 (en) 2021-02-16 2021-02-16 Artificial intelligence (ai) based online censoring engine system for social media platforms

Country Status (1)

Country Link
AU (1) AU2021100901A4 (en)

Similar Documents

Publication Publication Date Title
US11663403B2 (en) System and method for detecting undesirable and potentially harmful online behavior
US10089299B2 (en) Multi-media context language processing
US9514741B2 (en) Data shredding for speech recognition acoustic model training under data retention restrictions
KR20220150859A (en) System, Apparatus and Method For Processing Natural Language, and Computer Readable Recording Medium
US12223121B2 (en) Artificial intelligence-based system and method for dynamically predicting and suggesting emojis for messages
WO2019229768A1 (en) A bot engine for automatic dynamic intent computation
CN113239668B (en) Keyword intelligent extraction method and device, computer equipment and storage medium
CN116913278B (en) Voice processing method, device, equipment and storage medium
US20240320441A1 (en) Natural Language Processing Dialog Methods and Systems for Virtual Scenes
CN115545039A (en) Multi-modal rumor detection method and system
CN111832318A (en) Single sentence natural language processing method and device, computer equipment and readable storage medium
CN118070811B (en) Information interaction method, device, equipment and medium based on natural language understanding
CN113449081A (en) Text feature extraction method and device, computer equipment and storage medium
CN110472548A (en) A kind of video continuous sign language recognition method and system based on syntactic category device
CN107545505A (en) Insure recognition methods and the system of finance product information
WO2023142590A1 (en) Sign language video generation method and apparatus, computer device, and storage medium
AU2021100901A4 (en) Artificial intelligence (ai) based online censoring engine system for social media platforms
AU2020104298A4 (en) Censoring online social media platform content through artificial intelligence based framework
CN113380225A (en) Language model training method, speech recognition method and related device
CN116644765A (en) Speech translation method, speech translation device, electronic device, and storage medium
US12204864B2 (en) Dynamic semantic role classification
CN119513237A (en) Prompt word generation method, prompt word-based dialogue method and related device
CN116543798A (en) Emotion recognition method and device based on multiple classifiers, electronic equipment and medium
CN116701604A (en) Question and answer corpus construction method and device, question and answer method, equipment and medium
JP2012064073A (en) Automatic conversation control system and automatic conversation control method

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)
MK22 Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry