Patents by Inventor Mritunjay Kumar
Mritunjay Kumar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240070538Abstract: A system includes a memory and a processing device, operatively coupled to the memory, to perform operations including obtaining a set of base features associated with tabular data, selecting, from the set of base features, a set of relevant features using attention-based feature selection, wherein the set of relevant features is a subset of the set of base features, generating, from the set of relevant features using feature interaction, a set of interaction features, and generating a prediction using the set of interaction features.Type: ApplicationFiled: August 23, 2023Publication date: February 29, 2024Inventors: Mritunjay Kumar, Tejashri Kelhe, Nidhi Nika
-
Patent number: 11663677Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.Type: GrantFiled: May 26, 2021Date of Patent: May 30, 2023Assignee: Intuit Inc.Inventors: Saikat Mukherjee, Cem Unsal, William T. Laaser, Mritunjay Kumar, Anu Sreepathy, Per-Kristian Halvorsen
-
Patent number: 11521405Abstract: A method may include acquiring, from an initial document having a document type, initial document elements and initial attributes, deriving initial features for the initial document elements using the initial attributes, detecting initial form components using the initial features, clustering the initial form components into initial line objects of an initial structured representation by applying an unsupervised machine learning model to the geometric attributes of the initial document elements, acquiring, from a next document having the document type, next document elements and next attributes describing the next document elements, deriving next features for the next document elements using the next attributes, detecting next form components using the next features, determining that the initial form components and the next form components are different, clustering the next form components into next line objects of a next structured representation, and replacing the initial structured representation with theType: GrantFiled: April 29, 2021Date of Patent: December 6, 2022Assignee: Intuit Inc.Inventors: Anu Singh, Saikat Mukherjee, Mritunjay Kumar, Karpaga Ganesh Patchirajan
-
Patent number: 11295076Abstract: Generating a difference between a first and second plurality of lines of text in structured machine-readable format may include determining, by at least one processor, a line of the second plurality of lines that constitutes a best match for a line of the first plurality of lines. The line of the first plurality of lines and its respective best match may be associated with a similarity score. The at least one processor may compare the similarity score to a threshold value. In response to determining that the similarity score is greater than or equal to the threshold value, the at least one processor may compute, the textual difference between the line of the first plurality of lines and its best match. In response to computing the textual difference, the at least one processor may analyze the textual difference to identify a non-meaningful change.Type: GrantFiled: July 31, 2019Date of Patent: April 5, 2022Assignee: Intuit Inc.Inventors: Mritunjay Kumar, Saikat Mukherjee, Karpaga Ganesh Patchirajan, Anu Singh
-
Publication number: 20210362594Abstract: The present invention “car driver alcohol level and sleeping status detection and notification system using machine learning programming and IOT-based technology “is a vehicle driver sleepiness monitor, configured as a auto-contained Unit for dashboard unit. The invention is also providing for individual driver interrogation and notification response integrated with defined and fixed unit sensory inputs on vehicle condition and driver control action and translates these inputs into weighing factors to adjust a previous history and biological activity circadian rhythm reference Unit. The invention is also including an in turn to provide a vibration, water spray and audio-visual sleepiness warning alert and an automatic dialog system capable of keeping a drive awake while driving during a long trip or one that extends into the late evening.Type: ApplicationFiled: March 9, 2021Publication date: November 25, 2021Inventors: R. MADANA MOHANA, YUKTESH CHINTAMADAKA, CHANDIKA MOHAN BABU, K.S. NIRAJA, K. THIRUPAL REDDY, M. CHURCHILL DASS PRINCE, N T KISHORE KUMAR, VIANALA SUNITHA, Veerendra Chitrala, P. Kiranmai, Mritunjay Kumar Vishwakarma, Angajala Kishore Kumar, Raman Dugyala
-
Patent number: 11171928Abstract: In a method of Local Peer to Peer Direct Connection in NAT and overlay network. A request is received from a first peer at a relay gateway to establish a direct connection with a second peer. The first peer and the second peer are located behind a NAT firewall. An authentication request is relayed from the first peer at the relay gateway. The authentication request is forwarded from the relay gateway to the second peer. Upon performing authentication at the second peer, an authentication response is received at the relay gateway. The authentication response is received from the relay gateway at the first peer. An internal route propagation is performed from the second peer to the first peer via the relay gateway. A Local Peer to Peer Direct Connection is established between the first peer and the second peer for packet flow through the direct connection.Type: GrantFiled: December 6, 2018Date of Patent: November 9, 2021Assignee: COLORTOKENS, INC.Inventors: Deepak Kumar Mohanty, Ashish Trivedi, Ravi Voleti, Anoop Kapoor, Mritunjay Kumar, Suprio Pal
-
Publication number: 20210287302Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.Type: ApplicationFiled: May 26, 2021Publication date: September 16, 2021Applicant: Intuit Inc.Inventors: Saikat Mukherjee, Cem Unsal, William T. Laaser, Mritunjay Kumar, Anu Sreepathy, Per-Kristian Halvorsen
-
Publication number: 20210264146Abstract: A method may include acquiring, from an initial document having a document type, initial document elements and initial attributes, deriving initial features for the initial document elements using the initial attributes, detecting initial form components using the initial features, clustering the initial form components into initial line objects of an initial structured representation by applying an unsupervised machine learning model to the geometric attributes of the initial document elements, acquiring, from a next document having the document type, next document elements and next attributes describing the next document elements, deriving next features for the next document elements using the next attributes, detecting next form components using the next features, determining that the initial form components and the next form components are different, clustering the next form components into next line objects of a next structured representation, and replacing the initial structured representation with theType: ApplicationFiled: April 29, 2021Publication date: August 26, 2021Applicant: Intuit Inc.Inventors: Anu Singh, Saikat Mukherjee, Mritunjay Kumar, Karpaga Ganesh Patchirajan
-
Patent number: 11049190Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.Type: GrantFiled: December 20, 2016Date of Patent: June 29, 2021Assignee: Intuit Inc.Inventors: Saikat Mukherjee, Cem Unsal, William T. Laaser, Mritunjay Kumar, Anu Sreepathy, Per-Kristian Halvorsen
-
Patent number: 11048933Abstract: A method may include acquiring, from a document, document elements and attributes describing the document elements. One or more of the attributes may be geometric attributes describing a placement of the corresponding document element within the document. The method may further include deriving features for the document elements using the attributes, detecting form components using the features, clustering the form components into line objects of a structured representation by applying an unsupervised machine learning model to the geometric attributes of the document elements, and populating a compliance form using the structured representation.Type: GrantFiled: September 12, 2019Date of Patent: June 29, 2021Assignee: Intuit Inc.Inventors: Anu Singh, Saikat Mukherjee, Mritunjay Kumar, Karpaga Ganesh Patchirajan
-
Patent number: 10992635Abstract: A system and method for routing data packets between different overlay networks is disclosed. The method includes receiving a DNS lookup request for a resource from a first computing device coupled to a first overlay network. The first overlay network comprises a first edge application gateway. The method includes identifying a second computing device coupled to a second overlay network comprising the resource requested. The second overlay network comprises a second edge application gateway. The method further includes identifying a third overlay network. The data packets generated at, the first computing device is transferred to the first edge application gateway. The data packets are then transmitted from the first edge application gateway and the second edge application gateway over the third overlay network.Type: GrantFiled: October 17, 2018Date of Patent: April 27, 2021Assignee: COLORTOKENS, INC.Inventors: Anoop Singh Kapoor, Ashish Trivedi, Ravi Voleti, Deepak Mohanty, Mritunjay Kumar
-
Patent number: 10958580Abstract: A system and method for performing load balancing over an overlay network is disclosed. The load balancing is performed by a DNS load balancing module communicating to a plurality of computing devices communicatively coupled over the overlay network. The DNS load balancing module calculates and maintains a weighted value of each computing device among the plurality of computing device based on a plurality of parameters. The DNS load balancing module on receiving a DNS lookup request for a resource from a first computing device identifies a list of computing device among the plurality of computing device hosting the requested resource. The DNS load balancing module further performs load balancing by selecting a computing device among a list of computing devices for accessing the resource based on a weighted value calculated.Type: GrantFiled: October 17, 2018Date of Patent: March 23, 2021Assignee: COLORTOKENS, INC.Inventors: Anoop Singh Kapoor, Ashish Trivedi, Ravi Voleti, Deepak Mohanty, Mritunjay Kumar
-
Publication number: 20210034858Abstract: A method may include acquiring, from a document, document elements and attributes describing the document elements. One or more of the attributes may be geometric attributes describing a placement of the corresponding document element within the document. The method may further include deriving features for the document elements using the attributes, detecting form components using the features, clustering the form components into line objects of a structured representation by applying an unsupervised machine learning model to the geometric attributes of the document elements, and populating a compliance form using the structured representation.Type: ApplicationFiled: September 12, 2019Publication date: February 4, 2021Applicant: Intuit Inc.Inventors: Anu Singh, Saikat Mukherjee, Mritunjay Kumar, Karpaga Ganesh Patchirajan
-
Patent number: 10862804Abstract: A system and method for redirecting data packets communicated to a computing device over an overlay network is disclosed. The method includes monitoring resources installed on the computing device to identify the resources communicating over dedicated underlay IP address. The method further includes creating a rule based on the resources identified. The rule is transferred and stored on the computing device. On receiving a data packet, the rule is executed for redirecting the data packets from the overlay network to an underlay network and vice versa. The data packets are redirected by translating a destination IP address on a header of the data packet from an overlay IP address to an underlay IP address. The method thus redirects the data packets from the overlay network to the underlay network before reaching the resource, thereby preventing dropping of the data packet.Type: GrantFiled: October 9, 2018Date of Patent: December 8, 2020Assignee: COLOTOKENS INC.Inventors: Anoop Singh Kapoor, Ashish Trivedi, Ravi Voleti, Deepak Mohanty, Mritunjay Kumar
-
Publication number: 20200186496Abstract: In a method of Local Peer to Peer Direct Connection in NAT and overlay network. A request is received from a first peer at a relay gateway to establish a direct connection with a second peer. The first peer and the second peer are located behind a NAT firewall. An authentication request is relayed from the first peer at the relay gateway. The authentication request is forwarded from the relay gateway to the second peer. Upon performing authentication at the second peer, an authentication response is received at the relay gateway. The authentication response is received from the relay gateway at the first peer. An internal route propagation is performed from the second peer to the first peer via the relay gateway. A Local Peer to Peer Direct Connection is established between the first peer and the second peer for packet flow through the direct connection.Type: ApplicationFiled: December 6, 2018Publication date: June 11, 2020Inventors: Deepak Kumar MOHANTY, Ashish TRIVEDI, Ravi VOLETI, Anoop KAPOOR, Mritunjay KUMAR, Suprio PAL
-
Publication number: 20200127923Abstract: A system and method for performing load balancing over an overlay network is disclosed. The load balancing is performed by a DNS load balancing module communicating to a plurality of computing devices communicatively coupled over the overlay network. The DNS load balancing module calculates and maintains a weighted value of each computing device among the plurality of computing device based on a plurality of parameters. The DNS load balancing module on receiving a DNS lookup request for a resource from a first computing device identifies a list of computing device among the plurality of computing device hosting the requested resource. The DNS load balancing module further performs load balancing by selecting a computing device among a list of computing devices for accessing the resource based on a weighted value calculated.Type: ApplicationFiled: October 17, 2018Publication date: April 23, 2020Inventors: Anoop Singh KAPOOR, Ashish TRIVEDI, Ravi VOLETI, Deepak MOHANTY, Mritunjay KUMAR
-
Publication number: 20200127963Abstract: A system and method for routing data packets between different overlay networks is disclosed. The method includes receiving a DNS lookup request for a resource from a first computing device coupled to a first overlay network. The first overlay network comprises a first edge application gateway. The method includes identifying a second computing device coupled to a second overlay network comprising the resource requested. The second overlay network comprises a second edge application gateway. The method further includes identifying a third overlay network. The data packets generated at, the first computing device is transferred to the first edge application gateway. The data packets are then transmitted from the first edge application gateway and the second edge application gateway over the third overlay network.Type: ApplicationFiled: October 17, 2018Publication date: April 23, 2020Inventors: ANOOP SINGH KAPOOR, Ashish Trivedi, Ravi Voleti, Deepak Mohanty, Mritunjay Kumar
-
Publication number: 20200112510Abstract: A system and method for redirecting data packets communicated to a computing device over an overlay network is disclosed. The method includes monitoring resources installed on the computing device to identify the resources communicating over dedicated underlay IP address. The method further includes creating a rule based on the resources identified. The rule is transferred and stored on the computing device. On receiving a data packet, the rule is executed for redirecting the data packets from the overlay network to an underlay network and vice versa. The data packets are redirected by translating a destination IP address on a header of the data packet from an overlay IP address to an underlay IP address. The method thus redirects the data packets from the overlay network to the underlay network before reaching the resource, thereby preventing dropping of the data packet.Type: ApplicationFiled: October 9, 2018Publication date: April 9, 2020Inventors: Anoop Singh Kapoor, Ashish Trivedi, Ravi Voleti, Deepak Mohanty, Mritunjay Kumar
-
Publication number: 20180018676Abstract: A system generates structured compliance form data based on a compliance form having a plurality of data fields. The system includes multiple parsing modules each configured to generate respective parsed form data by analyzing compliance form data related to the compliance form with respective parsing processes. The system includes a combiner module configured to combine the various parsed formed data into combined parsed form data.Type: ApplicationFiled: December 20, 2016Publication date: January 18, 2018Applicant: Intuit Inc.Inventors: Saikat Mukherjee, Mritunjay Kumar, Anu Sreepathy, Per-Kristian Halvorsen
-
Publication number: 20180018741Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.Type: ApplicationFiled: December 20, 2016Publication date: January 18, 2018Applicant: Intuit Inc.Inventors: Saikat Mukherjee, Cem Unsal, William T. Laaser, Mritunjay Kumar, Anu Sreepathy, Per-Kristian Halvorsen