Keypoint Technologies India Pvt. Ltd.

Sumit Goswami

Sunil Motaparti

Prima Dona Kurian

Sandeep Yelubolu

Manish Jha

Shailaja Gummadidala

Naveen Durga

The present invention provides various systems and methods to intelligently predict the user's intent and persona based on derived hyper-contextual information from user's computing device and device-server ranking system to serve at least one search advertisement or at least one search string relevant to user's intent and persona at the time of user entering input or even before user entering input in the search editor of a computing-device application or webpage in real-time using a recommendation engine. The present invention suggests providing the recommendation engine implemented on the computing device that may enable the user to automatically perform hyper-contextual discovery and intelligently predict user's intent and persona and in response provide at least one search advertisement or at least one search string relevant to user intent.

Contextual discovery

A contextual discovery application is presented. The contextual discovery application is adapted to be executed on a computing device, wherein the computing device is a client in a client-server environment and the contextual discovery application on execution enables a processing unit to receive a set of information from a data acquisition unit on the computing device and to process the set of information to identify a contextual information from the set of information, to receive one or more advertisements from a database related to the contextual information, and it renders the advertisement on a display unit of the computing device in a real-time. The data acquisition unit acquires the set of information from at least one application currently running or previously running on the computing device. Embodiments including a computing device and system and methods for facilitating contextual discovery are also presented.

The present invention relates to a computer-implemented method for inputting text into an electronic device (). A virtual keyboard () having a plurality of keys () is displayed on a display screen () and one or more characters are associated with each key. An input pattern is generated by a user and the key(s) () positioned on or proximal to the input pattern are identified. The keys () in the virtual keyboard () are allocated to pre-defined groups (A,B,C), such that each group comprises a plurality of said keys (). The input pattern is encoded in dependence on the pre-defined groups in which each of said one or more identified keys () are arranged. A candidate word or words is identified to be input into the electronic device () based on the encoded input pattern. The present invention also relates to computer-implemented methods for identifying candidate words based on the correlation between input and candidate string lengths; and/or upper/lower input length thresholds; and/or the identification of valid/invalid string combinations. The present invention also relates to a corresponding system, such as a computational apparatus ().

Input pattern detection over virtual keyboard for candidate word identification

The present invention relates to a computer-implemented method for inputting text into an electronic device (). The method includes selecting a first set of candidate words stored in a database. At least one of the first set of candidate words is then displayed on a screen () for selection by a user. The user generates a continuous input pattern () and the method identifies one or more candidate words disposed along or proximal to the continuous input pattern (). The one or more identified candidate words are then input into a text entry field (). The method includes refreshing the displayed candidate words when the continuous input pattern () traces a predefined refresh gesture or enters/exits a predefined region (). The present invention also relates to a computing device programmed to perform the method described herein.

Text input method using continuous trace across two or more clusters of candidate words to select two or more words to form a sequence, wherein the candidate words are arranged based on selection probabilities

In accordance with an example embodiment, a system and method for facilitating spotting of words and phrases is disclosed. The system includes a scanning module, a storage module, a computation module, a dictionary generation module and a transceiver module. The scanning module periodically scans a plurality of content sources to identify words and phrases being shared as spots in one or more online communities of remote users. The storage module is configured to store the spots along with information related to the spots. The computation module determines at least one popularity-based metric for each spot stored in the storage module. The dictionary generation module is configured to generate and periodically update a spotting dictionary comprising at least a listing of popular spots based on the at least one popularity-based metric associated with each spot. The transceiver module is configured to provision the spotting dictionary to one or more remote users.

Growing community of inventors

Hyderabad Telangana, India

Sumit Goswami