DESC:FORM 2
The Patent Act 1970
(39 of 1970)
&
The Patent Rules, 2005

COMPLETE SPECIFICATION
(SEE SECTION 10 AND RULE 13)

TITLE OF THE INVENTION

“SYSTEM AND METHOD FACILITATING DATA CONVERSION”

APPLICANTS:
Name : Kartikey Pandey

Nationality : Indian

Address : E 161, Assetz Marq , Kannamangla , Seegehalli , Kadugodi , Bangalore , Karnataka , 560067

The following specification describes the invention and the manner in which it is to be performed.
FIELD OF INVENTION
[0001] The present disclosure relates to data conversion and more particularly to system and method providing conversion of voice data into text data.
BACKGROUND OF INVENTION
[0002] With advancement in technology, information sharing channels have also increased. Meetings and information exchange are not limited to just documents, but information these days is also exchanged and shared in verbal recordings and textual documentation.
[0003] Data conversion from one format to another has become very common and many systems are present that provide conversion of data in multiple formats. Though data conversion has become an easier process, however, the conversion happens over complete data for maintaining context of data so that there is no compromise with respect to meaning of data. Such converted data may be exact replication of data and may not provide any advantage in terms of memory savings or time savings.
[0004] Furthermore, such conversions may not save time as user again need to scroll through or read through the entire data in a converted format. There is no way the user may skip going through the data and save time to understand the context of the data. If data is in word format, the user is required to read entire data or if the data is in audio format, the user is required to listen to entire audio data for understanding the context and meaning of the data.
[0005] Though many systems are there for converting one format of data (information) into other format, however, such systems face challenges such as correct translation of voice to text or text to voice, meaningful data interpretation and conversion. Furthermore, such conversions may also lack grammatical and contextual accuracy.
OBJECT OF INVENTION
[0006] The principal object of the embodiments herein is to provide a system and method providing data conversion.
[0007] Another embodiment of the proposed invention is to provide generation of compressed data while maintaining context and information of the data.
[0008] Another embodiment of the proposed invention provides the system and method for converting voice data to text data and text data to voice data.
SUMMARY
[0009] Before the present method and system facilitating data, conversion is described, it is to be understood that this application is not limited to the particular system, and methodologies described, as there can be multiple possible embodiments that are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is to describe the particular versions or embodiments only and is not intended to limit the scope of the present application. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.
[0010] In one implementation, describes is a system facilitating data conversion. The system comprises of a processor, a memory coupled to the processor. The memory is configured to store a plurality of instructions to be executed by the processor and the processor is configured for receiving, through a reception means, an input data in first format, identifying, contextual information from the input data in the first format by using Artificial Intelligence (AI) techniques and filtering, by using a filtering engine, objected data from the input data in the first format. The processor is further configured for generating, a compressed data in second format according to the filtering and contextual information.
[0011] In one implementation, disclosed is a method facilitating data conversion. The method comprises of receiving, through a reception means, an input data in first format, identifying, through a processor, contextual information from the input data in the first format by using Artificial Intelligence (AI) techniques and filtering, by using a filtering engine coupled with the processor, objected data from the input data in the first format. The method further comprises generating, a compressed data in second format according to the filtering and contextual information.
[0012] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
BRIEF DESCRIPTION OF FIGURES
[0013] This invention is illustrated in the accompanying drawings, throughout which like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:
[0014] Figure 1 shows a network implementation of a system facilitating data conversion, in accordance with an embodiment as disclosed herein.
[0015] Figure 2 shows block diagram of the system facilitating data conversion, in accordance with an embodiment as disclosed herein.
[0016] Figure 3 shows additional details of the system facilitating data conversion, in accordance with an embodiment as disclosed herein.
[0017] Figure 4 shows flow diagram of method facilitating data conversion, in accordance with an embodiment as disclosed herein.
DETAILED DESCRIPTION OF INVENTION
[0018] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term “or” as used herein, refers to a non-exclusive or, unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[0019] Accordingly, the embodiments herein provide a system and method providing data conversion. The proposed system and method provide a python based Artificial Intelligence (AI) powered platform configured to use multiple python libraries to record and transcribe voice data and then convert voice data into text data. The voice data after conversion to text data is further used for generating Summary of converted data in a compressed format thereby saving memory and bandwidth during data transmission.
[0020] Referring now to Figure 1, a network implementation 1000 of a system 100 facilitating data conversion is disclosed. In one example, the system 100 may be connected with mobile devices (also referred as device 200) 200-1 through 200-N (collectively referred as 200) through a communication network 300.
[0021] It should be understood that the system 100 and the device (s) 200 correspond to computing devices. It may be understood that the system 100 may also be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, a network server, a cloud-based computing environment, or a smart phone and the like. It may be understood that the mobile devices 200 may correspond to a variety of a variety of portable computing devices, such as a laptop computer, a desktop computer, a notebook, a smart phone, a tablet, a phablet, and the like.
[0022] In one implementation, the communication network 300 may be a wireless network, a wired network, or a combination thereof. The communication network 300 can be implemented as one of the different types of networks, such as intranet, Local Area Network (LAN), Wireless Personal Area Network (WPAN), Wireless Local Area Network (WLAN), wide area network (WAN), the internet, and the like. The communication network 106 may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, MQ Telemetry Transport (MQTT), Extensible Messaging and Presence Protocol (XMPP), Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further, the communication network 600 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
[0023] In accordance with an embodiment, referring to Figure 2, illustrated is a block diagram of the system 100 facilitating data conversion. The system 100 includes at least one processor 102, a memory 104, a user interface 106. The system 100 further includes a communication unit 108.
[0024] The at least one processor 102 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the at least one processor 102 may be configured to fetch and execute computer-readable instructions stored in the memory 104.
[0025] The user interface 106 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, a command line interface, and the like. The user interface 106 may allow a user to interact with the system 100. Further, the user interface 106 may enable the system 100 to communicate with the mobile devices 200, and other computing devices, such as web servers and external data servers (not shown). The user interface 106 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. The user interface 106 may include one or more ports for connecting a number of devices to one another or to another server.
[0026] The memory 104, amongst other things, serves as a repository for storing data processed, received, and generated by one or more of modules (not shown in Figure). The memory 104 may include any computer-readable medium or computer program product known in the art including, for example, volatile memory, such as Static Random-Access Memory (SRAM) and Dynamic Random-Access Memory (DRAM), and/or non-volatile memory, such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable and Programmable ROM (EEPROM), flash memories, hard disks, optical disks, and magnetic tapes.
[0027] The memory 104 may include data generated as a result of the execution of one or more of the modules. The memory 104 is connected to a plurality of modules.
[0028] The system 100 also comprise database 110 that may include a repository for storing the input data and the compressed data, computed, received, and generated by the processor 102. Furthermore, the data 112 may include other data for storing data generated as a result of the execution of the AI technologies/methodologies executed by the processor 102.
[0029] The system 100 also comprise a communication unit 114 for enabling communication of the system 100 with other devices 200 and server (not shown in Figure 2) for exchanging or transmitting the compressed data. The communication unit 110 may comprise a wired or wireless communication unit and may be similarly implemented as discussed for the network 300 discussed above and hence description of the communication unit 114 is not repeated for the sake of brevity.
[0030] In accordance with an embodiment, details of the system 100 facilitating data conversion will now be discussed. The processor 102 is configured for receiving an input data in first format. The reception means comprises a microphone configured in the system, an external memory device such as pen drive, memory card, Compact Disc (CD) or other data storage device.
[0031] The first format comprises an audio data recorded in a WAV format, a text data, a video data.
[0032] The processor 102 is further configured for identifying contextual information from the input data in the first format by using Artificial Intelligence (AI) techniques. The contextual information comprises subject matter details of the input data, objective of the input data, or topic associated with the input data. The AI techniques use multiple python libraries comprising Gensim, PySimpleGUI
[0033] For example, the processor 102 uses AI techniques for identifying keywords on the input data and then identifies the contextual information.
[0034] Once the contextual information is identified, the processor 102 uses data filters or filtering engine for filtering objected data from the input data in the first format.
[0035] Based on the filtering, the processor 102 is configured for generating a compressed data in second format according to the filtering and contextual information.
[0036] The second format comprises a text format, an audio format, a presentation, a graphical illustration of the input data.
[0037] The processor 102 filters the data by removing noise data in a set of frequency (frequency may be set according to the requirements of converting the input data) from the input data in an audio format and the processor 102 then removes each of repetitive words, malicious words, extra punctuations, articles from the input data in the audio format. While filtering, the processor 102 retains meaning of the input data based on identification of the contextual information.
[0038] In an example, the processor 102 reads a conversation in an audio data received as the input data recorded in a WAV format as the first format. The objective of the system 100 is to summarize the input data in the second format while compressing the input data to save memory and bandwidth while transmitting the compressed data into the second format to one or more external device (later shown in Figure 3).
[0039] The processor 102 converts the audio data by using a Google Text to Speech library for creating the compressed data in the second format comprising a text file from the WAV format.
[0040] As part of conversion, the processor 102 organizes and punctuates the compressed data by using a Natural Language Processor as the processor 102 by using external databases comprising Wikipedia or google news articles.
[0041] The processor 102 also uses an open-source library known as Gensim to summarize the text and display the text to the user in multiple ways.
[0042] For example, in a recorded physics lecture over newton’s second law of motion, the processor 102 identifies the keywords such as physics, newton, second law, force etc. The processor 102 then matches the keywords from one or more python libraries and creates title of the lecture, body summarizing points of the lecture, and examples discussed during the lecture. The summary may be created in text file (.txt) which is lesser in size compared to the audio file or text file (when all input data is converted).
[0043] The compressed data is generated by converting the input data in the first format into the second data for generating the compressed data by using a google text to speech library. The compressed data is less in size compared to the input data and the compressed data provides a summary of the first data.
[0044] The summary comprises, minutes of meeting, notes of input data, relevant points according to the contextual information in a predefined format along with hyperlinks to additional sources providing details on the contextual information. The hyperlinks comprise web links routing towards websites authenticated by the system and the predefined format comprises a customized format for example, an excel sheet report, a summary in a word file with headings and sub-headings etc.
[0045] In another exemplary embodiment, the system 100 comprises an encoder (not shown in Figure) for encoding the compressed data by using changing crypts for generating encoded compressed data in form of binary files. The communication unit 114 is configured for broadcasting the encoded compressed data to external electronic devices.
[0046] In accordance with an embodiment, examples showing working of the proposed system 100 will now be discussed.
[0047] Referring to Figure 3, in one example, the input data in the audio format may be received by the system 102 through the microphone or recorder 302. The input data describes: “Cities and towns contribute over 70% of the greenhouse gases that are emitted in various parts of the world. Human activities such as manufacturing goods have significantly increased air pollution through the emission of greenhouse gases. This problem has been exacerbated by the fact that water bodies and vegetation in most cities have lost their capacity to absorb greenhouse gases. The environmental problems in urban areas have been on the rise due to the increased use of non-renewable sources of fuel for industrial production and transportation.
[0048] Affluence and consumerism have led to high demand for consumer products across the globe, thereby increasing environmental pressures. In the least developed countries, cities are characterized by uncontrolled development and rapid population growth. Consequently, the demand for housing and consumer goods has tremendously increased in these countries. Construction of new houses often leads to the destruction of the vegetation which is expected to absorb the greenhouse gases. These gases are responsible for the climate changes that have been witnessed in different parts of the world. For example, natural calamities such as floods and landslides regularly occur in most cities. Apart from air pollution, most urban areas are characterized by high noise levels. The main sources of noise in these areas include aircraft, industrial production, and construction activities. The effects of high noise levels on city residents include sleep disturbance, stress, loss of hearing, and increased anxiety. Energy consumption in urban areas is one of the major causes of heat islands. Heat islands occur due because the rate at which rural areas radiate heat into the atmosphere is at least twice as high as the rate in cities.
[0049] Thus, cities are warmer than rural areas because they are associated with high energy consumption and low heat radiation. The use of energy for purposes such as cooking, transportation, and generation of electricity in urban areas is much higher than in rural areas. For example, the per capita consumption of coal in Chinese cities is at least three times more than the consumption in rural areas. Heat islands usually trap atmospheric pollutants, thereby causing cloudiness and fog. It also causes high precipitation, thunderstorms, and hailstorms in cities. Empirical studies show that city residents are increasingly becoming vulnerable to disasters such as floods and landslides due to climate change. Urban development also causes water pollution. Waste management is normally a serious challenge in large cities, especially, in the least developed countries. In these cities, untreated solid wastes are often disposed of in dumpsites.
[0050] Eventually, these wastes contaminate groundwater sources. In some cases, industrial wastes are discharged directly into water bodies such as rivers and lakes. These pollutants normally contaminate water, thereby causing the death of aquatic animals such as fish. The use of water from the contaminated water bodies often causes diseases such as diarrhea in cities. Finally, urban development usually interferes with the course of rivers and streams. Real estate developers prefer to construct houses along the coastline or river banks. These areas are attractive to most real estate developers due to their scenic features. However, urban developments in these areas usually lead to the destruction of riparian vegetation and the alteration of stream channels. For example, the construction of a dam to supply water in an urban area can alter the hydrology of river destruction to physical habitats. The environmental effects of urbanization are expected to increase if remedial measures are not taken at the right time.”
[0051] The processor 102 first identifies the contextual information from the input data based on keywords (marked in bold in paragraphs of the above example) and maps with the python libraries. The processor 102 filters background noise of any vehicles, people’s chat etc. and also removes repeat words along with extra articles and punctuations. The filtering may be performed by using various Machine Learning models for classifying the contextual information as relevant from the input data. The ML models comprise regression, classification algorithms such as decision tree and other similar ML models. The ML models uses Support Vector Machine (SVM) algorithms for classifying the contextual information as relevant.
[0052] The compressed data in a summarised form towards the input data is shown below. The compressed data may be generated in a word file .txt extension 304.
[0053] “Cities and towns contribute over 70% of the greenhouse gases that are emitted in various parts of the world. This problem has been exacerbated by the fact that water bodies and vegetation in most cities have lost their capacity to absorb greenhouse gases. The environmental problems in urban areas have been on the rise due to the increased use of non-renewable sources of fuel for industrial production and transportation. Apart from air pollution, most urban areas are characterized by high noise levels. Heat islands occur because the rate at which rural areas radiate heat into the atmosphere is at least twice as high as the rate in cities. Urban development also causes water pollution. For example, the construction of a dam to supply water in an urban area can alter the hydrology of a river and destroy physical habitats.”
[0054] In above example, the processor 102 retains the meaning and context of the input data while generating a crisp summary. The processor 102 uses the AI and Machine Learning (ML) models here and identifies the most important statements in the input and creates a summary from the statements. The processor 102 understands the first line is about statement of purpose, so the processor 102 adds the first to the summary. The processor 102 then takes the most used and important words and identifies sentences using the important words and statements, to then create the summary. Now, every good summary must end in an example, so the processor 102 picks the most important example from the input data and adds the example to the summary to better help understand the summary of the compressed data.
[0055] In the above example, the processor 102 uses the Speech to Text conversion, then punctuator to create each sentence of the compresses data. The processor 102 removes the unnecessary word such as repeat words, repeat sentence, extra words, synonyms etc. and then uses the Neural Network Summarization followed by the punctuator again to create the summary with a conclusion.
[0056] Understanding the subject matter of the text is a complex process. The process of summarization through the processor 102 is split into 2 methods here. Under 1st method, if the AI understands and identifies the type or topic of text, the processor 102 summarizes in a certain different (as defined under the predefined way) way than just a normal summary.
[0057] If the input data is a meeting conversation in the audio/video format, the AI considers words relating to time and deadlines, and agenda important. If the audio or video is a text about science, the processor 102 considers definitions important, etc while generating the compressed data.
[0058] The AI uses the relevant words list and provides accurate hyperlinks to Articles and posts about the relevant topic in the summary. The Audio and Video are converted to text using Google's Speech to Text API. The processor 102 uses integrated thesaurus/ dictionary to identify Obscene, absurd or Abusive content and removes such malicious words. A word search configured in the processor 102 removes such malicious words from the text before summarization.
[0059] The compressed data 304 may then be encoded at the server 306 and may be transmitted or shared with the external device 308. The transmission is a secure transmission where compressed data in a binary format is shared with the external device 308.
[0060] In accordance with an embodiment, referring to Figure 4, flow diagram for a method 400 facilitating data conversion is shown. The method 400 may be executed through the system 100 as discussed above.
[0061] The order in which the method 400 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 400 or alternate methods. Additionally, individual blocks may be deleted from the method 400 without departing from the scope of the subject matter described herein.
[0062] At step 402, the method 400 receives the input data in first format. The input data is received through the microphone, the pen drive, the CD or other similar external means.
[0063] At step 404, the method 400 identifies the contextual information from the input data in the first format by using the Artificial Intelligence (AI) techniques. The contextual information may be identified through the processor 102.
[0064] At step 406, the method 400 filters the objected data from the input data in the first format. The input data may be filtered by using the filtering engine coupled with the processor 102.
[0065] At step 408, the method 400 generates the compressed data in second format according to the filtering and contextual information. The compressed data may be generated by the processor 102.
[0066] Details of the method 400 are similar to the details of the system 100 and hence are not repeated for the sake of brevity.
[0067] In another exemplary embodiment, the system 100 and the method 400 are provided with 3 functions for summarizing the text document, a pre-recorded meeting or recording and converting short speeches and monologues. For the graphic user interface 106, the system 100 uses an open-source library known as PySimpleGUI. The PySimpleGUI is based on Tkinter python library and displays all text on the Graphic user Interface 106.
[0068] Another application of the system 100 is for physically challenged people. For example, a blind student may speak out an answer and the answer may then be transcribed and generated in the compressed format as discussed above.
[0069] The proposed system 100 and the method 400 may also be used as assistant to teachers for creating class notes by communication channels such using audio, video, and presentations.
[0070] The proposed system 100 and the method 400 are configured for recording teacher’s Audio, video of what teacher is writing and presentation screen. Using the AI technologies in the proposed system 100 and the method 400, the system 100 may create a comprehensive Note of any lecture that may be further reviewed and updated by the teacher if needed, and may also be shared with the students through data transmission in the encoded form as discussed above.
[0071] Exemplary embodiments discussed above may provide certain advantages. Though not required to practice aspects of the disclosure, the advantages may include those provided by the following features.
[0072] Some embodiments of the method 400 and the system 1000 may create a compressed data by changing or converting the data from one format to another while retaining meaning and context of the input data.
[0001] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

,CLAIMS:I/WE CLAIM:
1. A system facilitating data conversion, the system comprising:
a processor;
a memory coupled to the processor, wherein the memory is configured to store a plurality of instructions to be executed by the processor, wherein the processor is configured for:
receiving, through a reception means, an input data in first format;
identifying, contextual information from the input data in the first format by using Artificial Intelligence (AI) techniques and Machine Learning (ML) models;
filtering, by using a filtering engine, objected data from the input data in the first format; and
generating, a compressed data in second format according to the filtering and contextual information.
2. The system as claimed in claim 1, wherein the first format comprises an audio data recorded in a WAV format, a text data, a video data, and wherein the reception means comprises a microphone, a recorder, a CD, or an external memory means.
3. The system as claimed in claim 1, wherein the contextual information comprises subject matter details of the input data, objective of the input data, or topic associated with the input data.
4. The system as claimed in claim 1, wherein the filtering comprises:
removing noise data in a set of frequency from the input data in an audio format, wherein the set of frequency is selected according to compressed data to be generated, wherein noise frequency comprises a frequency higher than 20,000 Hz or the frequency lower than 20Hz; and
removing, each of repetitive words, malicious words, extra punctuations, articles from the input data in the audio format.
5. The system as claimed in claim 1, wherein the generating comprises:
converting the input data in the first format into the second data for generating the compressed data by using a google text to speech library, wherein the compressed data is less in size compared to the input data, wherein the compressed data provides a summary of the first data, wherein the summary comprises, minutes of meeting, notes of input data, relevant points according to the contextual information in a predefined format along with hyperlinks to additional sources providing details on the contextual information, wherein the hyperlinks comprises web links routing towards websites authenticated by the system, wherein the predefined format comprises a customized format.
6. The system as claimed in claim 1, wherein the generating comprises:
reading a conversation in audio data recorded in a WAV format;
converting the audio data by using a Google Text to Speech library for creating the compressed data in the second format comprising a text file from the WAV format;
organizing and punctuating the compressed data by using a Natural Language Processor by using external databases comprising Wikipedia, or google news articles.
7. The system as claimed in claim 1, wherein second format comprises a text format, an audio format, a presentation, a graphical illustration of the input data.
8. The system as claimed in claim 1, wherein the AI techniques use multiple python libraries, wherein the multiple python libraries comprise Gensim, PySimpleGUI, and wherein the Machine Learning (ML) models comprise Support Vector Machine (SVM) model.
9. The system as claimed in claim 1, comprising:
an encoder for encoding the compressed data by using changing crypts for generating encoded compressed data in form of binary files;
a communication unit for broadcasting the encoded compressed data to external electronic devices.
10. A method facilitating data conversion, the method comprising:
receiving, through a reception means, an input data in first format;
identifying, through a processor, contextual information from the input data in the first format by using Artificial Intelligence (AI) techniques and Machine Learning (ML) models;
filtering, by using a filtering engine coupled with the processor, objected data from the input data in the first format; and
generating, a compressed data in second format according to the filtering and contextual information.
11. The method as claimed in claim 10, wherein the contextual information comprises subject matter details of the input data, objective of the input data, or topic associated with the input data.
12. The method as claimed in claim 10, wherein the filtering comprises:
removing noise data in a set of frequency from the input data in an audio format, wherein noise frequency comprises a frequency higher than 20,000 Hz or the frequency lower than 20Hz; and
removing, each of repetitive words, malicious words, extra punctuations, articles from the input data in the audio format.
13. The method as claimed in claim 10, wherein the generating comprises:
converting the input data in the first format into the second data for generating the compressed data by using a google text to speech library, wherein the compressed data is less in size compared to the input data, wherein the compressed data provides a summary of the first data, wherein the summary comprises, minutes of meeting, notes of input data, relevant points according to the contextual information in a predefined format along with hyperlinks to additional sources providing details on the contextual information, wherein the hyperlinks comprises web links routing towards websites authenticated by the system, wherein the predefined format comprises a customized format.
14. The method as claimed in claim 10, wherein the generating comprises:
reading a conversation in audio data recorded in a WAV format;
converting the audio data by using a Google Text to Speech library for creating the compressed data in the second format comprising a text file from the WAV format;
organizing and punctuating the compressed data by using a Natural Language Processor by using external databases comprising Wikipedia, or google news articles.
15. The method as claimed in claim 10, wherein second format comprises a text format, an audio format, a presentation, a graphical illustration of the input data.
16. The method as claimed in claim 10, wherein the AI techniques use multiple python libraries, wherein the multiple python libraries comprise Gensim, PySimpleGUI, and wherein the Machine Learning (ML) models comprise Support Vector Machine (SVM) model.
17. The method as claimed in claim 10, comprising:
encoding, through an encoder, the compressed data by using changing crypts for generating encoded compressed data in form of binary files; and
broadcasting, through a communication unit, the encoded compressed data to external electronic devices.