Abstract: The present invention provides a method and a system for an on-device intent detection using streaming pipe inter-process communication. The method (100) and system (300) disclosed herein involves an on-device intent detection (ODI), that enables applications to recognize user interests which are essentially keywords as they type using an AI model or algorithm. These keywords are communicated to a partner application, installed on the user's device without using any Application Programming Interface (API) or server, thereby effectively improving performance. The user's list of keywords is saved in an AI model and sending the keywords to the partner application employing Android Interface Definition Language (AIDL) interface for inter-process communication (IPC).

Abstract: A system and a method for converting text in one of a plurality of input languages into a text in a second language using phonetic based transliteration are disclosed. The method includes receiving (802) an input text in a first script from a user; phonetically mapping (804) each character of the input text with a second script corresponding to the second language; validating (806) permutations of mapping of each input character with each character of second script and transliterating (808) input text in first script into an output text in second script. A transliteration engine (106) is configured to transliterate input text of first language into the output text of second language. The transliteration engine (106) includes a data reception module (108), a data transformation module (110), a training module (112), an inference module (114), and a database (116).

Abstract: A method for testing and analyzing privacy of a mobile application is disclosed. The method includes displaying (203)/(502) a list of mobile devices connected to a privacy testing system; enabling (202) a user to select a target mobile application for carrying out a privacy analysis and testing; checking (204)/(504) if an android debug bridge (ADB) command line tool is enabled on the mobile device; employing (215)/(508) an SSL unpinning process if the mobile application is embedded with SSL pinning; scanning (225)/(510) one or more encryptions and one or more obfuscations used by the target mobile application; monitoring (220)/(514) one or more file access requests generated by the target mobile application and generating (230)/(516) an analysis testing report of the target mobile application.

Abstract: A system (100) and method (800) for an AI keyboard (104) that includes an AI clipboard suggestion interface (114) that receives input from a clipboard of a computing device (102). An AI suggestion bar (112) receives input from typed text in the AI suggestion bar (112) of the computing device (102). The AI keyboard (104) generates an artificial intelligence suggestion by processing an action button prompt through an AI chat server (110) that has been trained with data representative of a user's topic and a user's profile. The AI keyboard (104) provides the processed response, or the predicted content via the network, in a typing box of the AI keyboard (104). The processed response or the predicted content is integrated into the user current conversation session without moving out from a current application interface.

Abstract: Disclosed is a user device (102). The user device (102) includes a plurality of imaging sensors (118). The plurality of imaging sensors (118) is configured to capture a plurality of images of a scene and a processing unit (110) configured to implement a Deep Neural Network (DNN) model. The DNN model is configured to encode and aggregate, by way of a plurality of encoders and blocks where input and output is added, respectively, of the DNN model, information associated with the plurality of images in latent space and generate, by way of a decoder of the DNN model, a map of three-dimensional information based on the encoded information corresponding to each image of the plurality of images such that the map illustrates distances between one or more objects in the scene and the plurality of imaging sensors (118).

Abstract: A system and a method for generating a frontal-facing view of the user includes an electronic device, an application module, and a trained machine-learning model. The trained machine-learning model is communicatively coupled with the electronic device and the application module, and enables the application module to perform certain operational steps for generating the frontal-facing view of the user. The trained machine-learning model is configured to automatically identify, through an encoder module, at least one learning style from at least one feature map. The trained machine-learning model is further configured automatically to generate, through a face-frontalization module, the frontal facing view of the user.

Abstract: A method for converting speech in one of a plurality of input languages into text using machine transliteration and transfer learning is disclosed. The method includes a training stage. The training stage includes receiving a training set of a plurality of audio files and an input text corresponding to the audio input in any input language using the speech recognition engine; transliterating the training set to transform the input text into transliterated text that includes characters of a base language and training acoustic model with the plurality of audio files and corresponding transliterated text using transfer learning. The method further includes an inference stage. The inference stage includes performing decoding on output of the trained acoustic model to generate text includes characters of the base language at inference and transliterating the generated text to output text includes characters in input language using reverse transliteration.

Abstract: The present invention provides a method and a system for character-to-character modeling for word suggestion and auto correction. The method is based on character-to-character modeling. The method involves data preparation using edit distance and hash table for encoder. The edit distance is employed for suitable candidate creation for touch input and thereafter, hash table is employed for removing invalid candidates. Furthermore, encoder-decoder model is used to encode valid candidates for touch input and then decode into word suggestions for completions. In addition, the present invention provides word suggestions from decoder, further optimized into more probable candidates using a language model with a scoring and ranking algorithm.

Abstract: The present invention provides systems and methods for dynamic word prediction and suggestion. The method includes an AI engine configured to render a touch-enabled keyboard interface on a display unit of the electronic device, identify a plurality of elements of an input message of a user on a messaging application and transform the input message into an array of a specific numbers based on the plurality of elements. The method further includes converting the array into a 2D matrix of embeddings by the AI engine, wherein the embeddings include semantic information of the input message to identify a context of the input message and converting the matrix into an output array with a changed dimension. The AI engine is further configured to convert the output array into probabilities of one or more words corresponding to the input message of the user on the messaging application.

Abstract: A system including an artificial intelligence (AI) engine and an AI-based method are provided for dynamically predicting and suggesting emojis on a quick access emoji interface. The AI engine detects an input message in an input field on a graphical user interface of a user application. The AI engine processes the input message to identify elements, for example, character elements, image elements, patterns, etc., of the input message. The AI engine analyzes and determines a context and factors, for example, emoji positions, one or more languages, intent, user and global preferences, etc., associated with the input message for each element of the input message. The AI engine dynamically generates predictions of emojis based on the context and one or more factors in real time. The AI engine renders one or more grouped sets of emojis on the emoji interface based on the dynamically generated predictions.

Abstract: A system for generating a contextualized text using a character-based convolutional neural network architecture (CNN) is disclosed. The system includes a memory, a character-based CNN engine having executable modules and a processor configured to execute the character-based CNN engine and the executable modules for generating contextualized text using a character-based convolutional neural network architecture (CNN).

Abstract: The present invention provides a method and a system for an on-device intent detection using streaming pipe inter-process communication. The method (100) and system (300) disclosed herein involves an on-device intent detection (ODI), that enables applications to recognize user interests which are essentially keywords as they type using an AI model or algorithm. These keywords are communicated to a partner application, installed on the user's device without using any Application Programming Interface (API) or server, thereby effectively improving performance. The user's list of keywords is saved in an AI model and sending the keywords to the partner application employing Android Interface Definition Language (AIDL) interface for inter-process communication (IPC).

Abstract: An integrated payment system (IPS) and a method are provided for managing payment transactions within an input interface. A payment system is integrated within a keyboard, independent of a messenger application. The IPS renders a payment interface element (PIE) on the keyboard. In response to a user input action on the PIE, the IPS automatically detects a recipient for a payment transaction during an interaction between a sender and the recipient, through the messenger application. The IPS automatically determines an identifier of the detected recipient and account information linked to the detected identifier for executing a payment transaction between the sender and the recipient. The IPS generates and renders transaction information within the keyboard for convenient user access.

Abstract: An actionable content generation system (ACGS) and a method for generating and rendering intent-based actionable content in real time are provided. The ACGS, integrated within an input interface, for example, a keyboard, detects and simultaneously analyzes one or more messages being entered by a user in an input field of a user application using the input interface in real time. The ACGS generates tokens from the message(s) and determines intent with a confidence element from the tokens in real time based on a stored mapping and a confidence computation. The ACGS generates actionable content based on the intent using campaign data. The ACGS renders at least one element containing the actionable content on a graphical user interface and/or the input interface for interaction by the user and performance of one or more recommended actions.

Abstract: The present invention provides systems and methods for dynamic word prediction and suggestion. The method includes an AI engine configured to render a touch-enabled keyboard interface on a display unit of the electronic device, identify a plurality of elements of an input message of a user on a messaging application and transform the input message into an array of a specific numbers based on the plurality of elements. The method further includes converting the array into a 2D matrix of embeddings by the AI engine, wherein the embeddings include semantic information of the input message to identify a context of the input message and converting the matrix into an output array with a changed dimension. The AI engine is further configured to convert the output array into probabilities of one or more words corresponding to the input message of the user on the messaging application.

Abstract: A method for testing and analyzing privacy of a mobile application is disclosed. The method includes displaying (203)/ (502) a list of mobile devices connected to a privacy testing system; enabling (202) a user to select a target mobile application for carrying out a privacy analysis and testing; checking (204)/ (504) if an android debug bridge (ADB) command line tool is enabled on the mobile device; employing (215)/ (508) an SSL unpinning process if the mobile application is embedded with SSL pinning; scanning (225)/ (510) one or more encryptions and one or more obfuscations used by the target mobile application; monitoring (220)/ (514) one or more file access requests generated by the target mobile application and generating (230)/ (516) an analysis testing report of the target mobile application.

Abstract: A system including an avatar generation engine (AGE) (607) and a method for automatically generating an avatar with pronounced features are provided. The AGE (607) extracts a primary image of a primary component, for example, a face component, and a secondary image of a secondary component, for example, a hair component, from an input image of a target object. The AGE (607) normalizes and processes the primary image for extracting a feature image corresponding to a feature indicating a distinct characteristic of the target object. The AGE (607) processes the extracted feature image for graphically pronouncing the features. The AGE (607) generates a primary canvas including a predicted tone of the primary component. The AGE (607) generates an avatar with pronounced features by merging a primary graphical image generated by merging the primary canvas with the graphically pronounced features, with a secondary graphical image of the secondary component.

Abstract: A method for converting speech in one of a plurality of input languages into text using machine transliteration and transfer learning is disclosed. The method includes a training stage. The training stage includes receiving a training set of a plurality of audio files and an input text corresponding to the audio input in any input language using the speech recognition engine; transliterating the training set to transform the input text into transliterated text that includes characters of a base language and training acoustic model with the plurality of audio files and corresponding transliterated text using transfer learning. The method further includes an inference stage. The inference stage includes performing decoding on output of the trained acoustic model to generate text includes characters of the base language at inference and transliterating the generated text to output text includes characters in input language using reverse transliteration.

Abstract: A system including a direct message sending engine (DMSE) and a method for directly sending messages with minimal user input are provided. When a user invokes an input interface proximal to an input message field (IMF) of a user application, the DMSE renders a list of preconfigured messages on the input interface. When the user performs a selection action on at least one of the preconfigured messages on the input interface, the DMSE receives the selection action and in response, the DMSE transforms properties of the IMF, commits the preconfigured message(s) to the IMF, and simultaneously and directly sends the preconfigured message(s) to a recipient device. On committing the preconfigured message(s) to the IMF, the DMSE simultaneously executes a programmatic simulation of an action key press, thereby directly sending the preconfigured message(s) to the recipient device free of a manual user input.

Abstract: A system and a method for converting text in one of a plurality of input languages into a text in a second language using phonetic based transliteration are disclosed. The method includes receiving (802) an input text in a first script from a user; phonetically mapping (804) each character of the input text with a second script corresponding to the second language; validating (806) permutations of mapping of each input character with each character of second script and transliterating (808) input text in first script into an output text in second script. A transliteration engine (106) is configured to transliterate input text of first language into the output text of second language. The transliteration engine (106) includes a data reception module (108), a data transformation module (110), a training module (112), an inference module (114), and a database (116).