DESC:FIELD OF THE INVENTION
[001] The invention relates to an esports tournament.
[002] More particularly, the invention relates to an AI based management system and method for esport tournaments.

BACKGROUND OF THE INVENTION:
[003] Currently, in esports tournaments, the management is being done manually in the gaming space. A manual agent used to do mundane and repetitive tasks of organising esports tournaments, which is just a sequence of button clicks, reading text on the phone screens, and data entry of those texts.
[004] By the reference of US application no. US20200353363A1 by Christopher Bogart Slovak, Christopher Scott Andres, Thomas Patrick MCCLORY dated 2020-05-08, titled ”Artificial intelligence based video game state detection” discloses an artificial intelligence based video game state and game behaviour detection system and artificial intelligence based processes for detecting video game state and game behaviour are disclosed. The artificial intelligence based video game state and game behaviour detection system and the artificial intelligence based processes eliminate the restrictions and requirements of using third party provided means by collecting and process data directly from the game device, and then translating the game state into game data using a combination of machine learning and deep learning algorithms.
[005] By the reference of US application no. US20210129017A1 by NVIDIA CORPRATION dated 2019-10-31, titled ”Game event recognition” discloses a game-agnostic event detector that can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback.
[006] By the reference of KR application no. KR20200013514A by Nexon Korea Co., Ltd. dated 2018-07-30, titled ”Method, apparatus, and computer program for providing a function to replace the opponent user in a competition game” discloses a method for providing a function to replace a competition opponent user with AI, which comprises the following steps of: receiving a competition game matching request; connecting a first user account and a second user account; monitoring a game situation of the first user account; determining whether or not a withdrawal point of the first user account exceeds a threshold value; disconnecting the first user account and the second user account based on a determination result; and replacing a competition opponent user of the first user account with AI.
[007] By the reference of PCT application no. PCT/US2021/013973 by Nvidia Corporation dated 2021-01-19, titled ”Resoglution upscaling for event detection” discloses a game-agnostic event detector can be used to automatically identify game events. Game-specific configuration data can be used to specify types of pre-processing to be performed on media for a game session, as well as types of detectors to be used to detect events for the game. Event data for detected events can be written to an event log in a form that is both human- and process-readable. The event data can be used for various purposes, such as to generate highlight videos or provide player performance feedback. The event data may be determined based upon output from detectors such as optical character recognition (OCR) engines, and the regions may be upscaled and binarized before OCR processing.
[008] By the reference of US application no. US10825303B2 by Brett Dwain McDonald, Philip Z. Maymin dated 2019-06-13, titled ”System and method for using artificial intelligence to create live, mobile, betting system offering time-sensitive, curated and player-restricted bets on sub-outcomes of sports and esport events” discloses a system, process, and method that allows players to bet on sports or esports events from their mobile device in a way that is easy-to-understand, simple and fast-paced. Through the use of artificial intelligence, it allows the operator to offer bets only to certain registered members of the system rather than the public at-large thereby automating the balancing of their books through a dynamic offering. It also allows the operator to effectively and automatically generate more bets placed and automatically comply with taxation, laws and regulations of any jurisdiction in the world.
[009] By the reference of US application no. US11042784B2 by M37 Inc dated 2018-08-21, titled ”Machine learning system and method for determining or inferring user action and intent based on screen image analysis” discloses System(s) and method(s) that analyse image data associated with a computing screen operated by a user, and learns the image data (e.g., using pattern recognition, historical information analysis, user implicit and explicit training data, optical character recognition (OCR), video information, 360°/panoramic recordings, and so on) to concurrently glean information regarding multiple states of user interaction (e.g., analysing data associated with multiple applications open on a desktop, mobile phone or tablet). A machine learning model is trained on analysis of graphical image data associated with screen display to determine or infer user intent. An input component receives image data regarding a screen display associated with user interaction with a computing device. An analysis component employs the model to determine or infer user intent based on the image data analysis; and an action component provisions services to the user as a function of the determined or inferred user intent. In an implementation, a gaming component gamifies interaction with the user in connection with explicitly training the model.
[010] Therefore, there is a need for technology that can manage esports tournaments automatically in the gaming space.
[011] However, none of the above-discussed inventions provides such an AI based management system for esport tournaments having a vernacular OCR system and such method for esport tournaments.

OBJECTS OF THE INVENTION:
[012] The main object of the present invention is to provide an AI based management system for esport tournaments having OCR engine, Vernacular engine; OCR correction engine, candidate ranking engine and a method for esport tournaments.
[013] Another object of the present invention is to provide a system and method to create a custom room as per configuration as map and number of players.
[014] Another object of the present invention is to provide a system and method to perform OCR on the screen and extract room credentials.
[015] Another object of the present invention is to provide a system and method which has a spectator mode.
[016] Another object of the present invention is to provide a system and method to monitor the esport tournaments.
[017] Still another object of the present invention is to provide a system and method to provide a user wise rank.
[018] Yet another object of the present invention is to provide a system and method to automating the esport tournaments using an esport app.

SUMMARY OF THE INVENTION:
[019] According to one aspect of our invention, an AI based management system and method for esport tournaments comprising at least one specialised computer machine, comprising a data processor; a network interface, in API data communication with the data processor, for communication on a API data network; and a non-transient memory having at least one region for storing particular computer executable program code; a database containing applicable gambling laws, regulations; and at least one processor for executing the particular program code stored in the memory, wherein the particular program code is configured to at least perform the following operations of: at least one OCR ensemble engine; at least one automation module; at least one Winzo vernacular corpus; at least one OCR correction engine and at least one candidate ranking engine.
[020] In another aspect of the invention the computer system configured to offering an AI based management system for esport tournaments comprising at least one specialised computer machine, comprising a data processor; a network interface, in API data communication with the data processor, for communication on a API data network to execute the following steps: i) extract the tournament ID using API; ii) launching the app; iii) create custom rooms as per configuration; iv) room ID extraction; v) request registered players using API; vi) post room ID and password using API; vii) player identification process begins; viii) screenshot; ix) identify unregistered players and kickout; x) start game; xi) monitor game for fraudulent activities; xii) wait for result screen; xiii) screenshot; xiv) extract and post results using API.

BRIEF DESCRIPTION OF DRAWINGS:
[021] Reference will be made to embodiments of the invention, examples of which may be illustrated in accompanying figures. These figures are intended to be illustrative, not limiting. Although the invention is generally described in the context of these embodiments, it should be understood that it is not intended to limit the scope of the invention to these particular embodiments.
[022] Figure 1 illustrates a vernacular OCR system as per an embodiment herein.
[023] Figure 2 illustrates an AI based method for esport tournaments as per an embodiment herein.
[024] The referral numerals in the figures refer to: 101 - vernacular OCR system; 102 - OCR ensemble engine; 102A - English OCR; 102B - Gujarati OCR; 102C - Tamil OCR; 102D - Hindi OCR; 102E - Punjabi OCR; 102F - Telugu OCR; 102G - Bengali OCR; 102H - Kannada OCR; 102I - Marathi OCR; 103 - Automation module; 104 - winzo vernacular corpus; 104A - Names and directory data; 104B - chat data; 104C - Search data; 105 - OCR correction engine; 105A - Part of speech tagging model; 105B - Name correction model; 105C - Autocorrect model; 105D - REgex/n-gram based models; 105E - Sequential models using HMM, LSTM, BERT, Transformers; 105F - Autocompletion model; 106 - image; 107 - training data; 108 - output; 109 - candidate predictions; 110 - ranking engine; 111 - final prediction; 202 - a method of management for esport tournaments; 203 - extract the tournament ID using API; 204 - Launching the App.; 205 - Create custom room as per configuration; 206 - Room ID extraction; 207 - Request registered players using App.; 208 - Post room ID and password using API; 209 - Player identification process begin; 210 - Screenshot; 211 - Identity unregistered players and kickout; 212 - match time; 213 - start game; 214 - monitor game for fraudulent activities; 215 - wait for result screen; 216 - found; 217 - Screenshot; 218 - extract and post result using API; 219 - exit.

BRIEF DESCRIPTION OF INVENTION:
[025] The present invention will now be described hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. While the following description details the preferred embodiments of the present invention is not limited in its application to the details of construction and arrangement of the parts illustrated in the accompanying drawings. With reference to the figures, the enclosed description and drawings are merely illustrative of preferred embodiments and represent several different ways of configuring the present invention. Although specific components, materials, configurations and uses of the present invention are illustrated and set forth in this disclosure, it should be understood that a number of variations to the components and to the configuration of those components described herein and in the accompanying figures can be made without changing the scope and function of the invention set forth herein.
[026] The present invention is proposed as AI based management system and method for esport tournaments comprising at least one specialised computer machine, comprising a data processor; a network interface, in API data communication with the data processor, for communication on a API data network; and a non-transient memory having at least one region for storing particular computer executable program code; a database containing applicable gambling laws, regulations; and at least one processor for executing the particular program code stored in the memory, wherein the particular program code is configured to at least perform the following operations of: at least one OCR ensemble engine (102); at least one automation module (103); at least one Winzo vernacular corpus (104); at least one OCR correction engine (105) and at least one candidate ranking engine (110).
[027] The present invention as illustrated in Figure 1 provides one embodiment of the invention which includes a vernacular OCR system (101), which has an automation module (103), OCR ensemble engine (102), Winzp Vernacular corpus (104), OCR correction engine (105) and ranking engine (110).
[028] The present invention as illustrated in Figure 2 provides another embodiment of the invention which includes an AI based method for esport tournaments having computer system configured to offering an AI based management system for esport tournaments comprising at least one specialised computer machine, comprising a data processor; a network interface, in API data communication with the data processor, for communication on a API data network to execute the following steps: i) Extract the tournament ID using API; ii) launching the app; iii) create custom rooms as per configuration; iv) room ID extraction; v) request registered players using API; vi) Post room ID and password usingAPI; vii) Player identification process begins; viii) Screenshot; ix) Identify unregistered players and kickout; x) start game; xi) Monitor game for fraudulent activities; xii) Wait for result screen; xiii) Screenshot; xiv) Extract and post results using API.
[029] In another embodiment the invention provides an OCR engine in which the image is first passed into an OCR engine which is an ensemble of language specific OCR models which are pre trained on rich vernacular image data. The vernacular OCR models are still primitive in nature, the predictions of these components cannot be completely relied upon because of which post processing of data is required.
[030] In another embodiment, the invention provides Winzo Vernacular Corpus. Wherein Winzo has access to rich proprietary vernacular data which it has accumulated over the past few years through its 40 million+ user base distributed across 10 languages. These data are in multiple forms - name data, user’s directory data, chat data and search data. The invention system provides multiple points through which users can communicate with each other over chat and where users can search for various things within the platform (All this data has been used post receipt of terms and conditions of the user and we have not violated any privacy regulations).
[031] In another embodiment, we generated a corpus of structured data which we use for training multiple models which are used in OCR correction engine
[032] In another embodiment, the invention provide OCR correction engine, in which the prediction of the OCR is passed through a Vernacular OCR correction engine which is again built up of multiple components
[033] In another embodiment, all the following components have been trained on Winzo vernacular corpus comprising Parts of Speech tagging model, Sequence models, Auto correction model, Auto completion model, Regex/n-gram based models, Candidate ranking engine.
[034] In another embodiment, the invention provides parts of speech tagging models. Names are the toughest thing to predict especially in Vernacular space - because they are both inaccurate and it can’t be corrected by simple techniques like searching for the closest words in a language dictionary. The invention provides models which can infer parts of speech from text. Post tagging of parts of speech of prediction of OCR text, we will be able to infer parts of speech. In case we encounter a Noun, we pass that through our name correction model, It crawls over our directory and names data and corrects the OCR prediction if required.
[035] In another embodiment, the invention provides sequence models which have used sequence to sequence models to correct OCR predictions by observing the sequence of words. The system used Natural Language Processing techniques and architectures like HMM, BERT, LSTM, Transformers to correct the predictions if required.
[036] In another embodiment the invention provides an auto correction model. The system passes the prediction through autocorrect models which work similar to how autocorrect models in keyboards and “Did you mean” in Google work.
[037] In another embodiment, the invention provides an auto completion model, the invention passes the prediction through autocorrect models which work similar to how search works while typing.
[038] In another embodiment, the invention provides regex/n-gram based models. The system built regular expression based rules and n-gram basis techniques which helps in improving our OCR predictions.
[039] In another embodiment, the system combine results of all the above models basis the prediction from the OCR engine and generate a set of candidate predictions
[040] In another embodiment the invention provides a candidate ranking engine. The candidates generated by the OCR correction engine are then passed through a candidate ranking engine which ranks the candidates based on some rules and heuristics and a final prediction is generated.
[041] In another embodiment the invention provides a system and method to create a custom room as per configuration as map and number of players and extracts room credentials.
[042] In another embodiment the invention provides a system and method, which communicates the room credentials to the users who registered for that tournament.
[043] Another embodiment, the invention provides a system and method which has a spectator mode to keep track of people who keep on joining the room by performing OCR and checks if the name matches with any of the registered user ids; If a match is not found, kick the user out.
[044] Yet another embodiment, the invention provides a system and method to monitor the game and looks for any fraudulent behaviour through object and motion detection techniques, and distributes winnings and rankings to users.
[045] Still another embodiment, the invention provides a system and method to provide a user wise rank, once the tournament ends, the result declaration screen.
[046] The present disclosure described herein above has several technical advantages including, but not limited to,
? The invention automated set of tasks through an AI agent which can be seen as a Weak/Narrow AI automation where AI is expected to perform a very specific implementation of a limited part of mind (in this case - reading text through OCR technologies and performing an action basis the text)
? AI system runs by running an automation script which will be run on a device where the esports app is preinstalled.
[047] The disclosure has been described with reference to the accompanying embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein.
[048] The foregoing description of the specific embodiments so fully revealed 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 practised with modification within the scope of the embodiments as described herein

CLAIMS:

We Claim:

1. An AI based management system and method for esport tournaments comprising at least one specialised computer machine, comprising a data processor; a network interface, in API data communication with the data processor, for communication on a API data network; and a non-transient memory having at least one region for storing particular computer executable program code; a database containing applicable gambling laws, regulations; and at least one processor for executing the particular program code stored in the memory, wherein the particular program code is configured to at least perform the following operations of: at least one OCR ensemble engine (102); at least one automation module (103); at least one Winzo vernacular corpus (104); at least one OCR correction engine (105) and at least one candidate ranking engine (110).
2. The AI based management system and method for esport tournaments as claimed in claim 1, wherein OCR correction engine comprising a parts of speech tagging model (105A), a sequence model (105B), auto correction model (105C), auto completion model (105F), regex/n-gram based models (105D), Sequential models using HMM, LSTM, BERT, Transformers (105E).
3. The AI based management method for esport tournaments as claimed in claim 1, wherein a computer system configured to offering an AI based management system for esport tournaments comprising at least one specialised computer machine, comprising a data processor; a network interface, in API data communication with the data processor, for communication on a API data network to execute the following steps: i) extract the tournament ID using API; ii) launching the app; iii) create custom rooms as per configuration; iv) room ID extraction; v) request registered players using API; vi) post room ID and password using API; vii) player identification process begins; viii) screenshot; ix) identify unregistered players and kickout; x) start game; xi) monitor game for fraudulent activities; xii) wait for result screen; xiii) screenshot; xiv) extract and post results using API.
4. The AI based management method for esport tournaments as claimed in claim 1, wherein a non-transitory machine-useable storage medium embodying instructions which, when executed API by a machine, cause the machine to prompt a large number of users at a corresponding large number of user platforms to each submit for entry into a sports tournament; wherein said system creates a custom room as per configuration as map and number of players.
5. The AI based management method for esport tournaments as claimed in claim 1, wherein said system performs OCR on the screen and extracts room credentials.
6. The AI based management method for esport tournaments as claimed in claim 1, said system has a spectator mode.
7. The AI based management method for esport tournaments as claimed in claim 1, said system monitors the esport tournaments.
8. The AI based management method for esport tournaments as claimed in claim 1, said system provides a user wise rank.
9. The AI based management method for esport tournaments as claimed in claim 1, said system automating the esport tournaments using an esport app.
10. The AI based management method for esport tournaments as claimed in claim 1, a system having a spectator mode to keep track of people, who keep on joining the room by performing OCR and checks if the name matches with any of the registered user ids; If a match is not found, kick the user out.