Patents by Inventor Srinivas Vinnakota
Srinivas Vinnakota 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: 20240143616Abstract: An application embedded within a cloud application may load a data object which accesses information from a database to generate visualizations of data. When the data object is transported from a development system to a production system, the database may not have table entries and views as expected and loading the data object might fail. In such cases, the datasource may be created from metadata. A first metadata call is sent to the database using the application metadata and an indication that a datasource was not found is received from the database. Query metadata is extracted from the application metadata of the data object and a datasource creation call is sent to the database using the extracted query metadata, thereby initiating creation of a datasource artifact in the database. Then, query results are obtained based on the datasource artifact and query results are provided in the cloud application.Type: ApplicationFiled: October 27, 2022Publication date: May 2, 2024Inventors: Vignesh Sankaran, Srinivas Vinnakota, Arpitha A Shetty, Sohandeep Das
-
Patent number: 11972755Abstract: Techniques for noise data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with noise text to generate an augmented training set of utterances; and training the intent classifier using the augmented training set of utterances. The augmenting includes: obtaining the noise text from a list of words, a text corpus, a publication, a dictionary, or any combination thereof irrelevant of original text within the utterances of the training set of utterances, and incorporating the noise text within the utterances relative to the original text in the utterances of the training set of utterances at a predefined augmentation ratio to generate augmented utterances.Type: GrantFiled: November 23, 2022Date of Patent: April 30, 2024Assignee: Oracle International CorporationInventors: Elias Luqman Jalaluddin, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Yu-Heng Hong, Balakota Srinivas Vinnakota
-
Publication number: 20240126795Abstract: Techniques are disclosed herein for integrating document question answering in an artificial intelligence-based platform, such as a chatbot system. The techniques include receiving a query from a user, rewriting the query to include one or more specific descriptors, computing an embedding vector for the rewritten query, retrieving one or more textual passages from a document store utilizing the embedding vector for the rewritten query, determining one or more answers to the rewritten query within the one or more textual passages, and returning the one or more answers.Type: ApplicationFiled: October 13, 2023Publication date: April 18, 2024Applicant: Oracle International CorporationInventors: Xu Zhong, Thanh Long Duong, Mark Edward Johnson, Charles Woodrow Dickstein, King-Hwa Lee, Xin Xu, Srinivasa Phani Kumar Gadde, Vishal Vishnoi, Christopher Kennewick, Balakota Srinivas Vinnakota, Raefer Christopher Gabriel
-
Patent number: 11922123Abstract: Techniques for automatically switching between chatbot skills in the same domain. In one particular aspect, a method is provided that includes receiving an utterance from a user within a chatbot session, where a current skill context is a first skill and a current group context is a first group, inputting the utterance into a candidate skills model for the first group, obtaining, using the candidate skills model, a ranking of skills within the first group, determining, based on the ranking of skills, a second skill is a highest ranked skill, changing the current skill context of the chatbot session to the second skill, inputting the utterance into a candidate flows model for the second skill, obtaining, using the candidate flows model, a ranking of intents within the second skill that match the utterance, and determining, based on the ranking of intents, an intent that is a highest ranked intent.Type: GrantFiled: September 30, 2021Date of Patent: March 5, 2024Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Vishal Vishnoi, Xin Xu, Elias Luqman Jalaluddin, Srinivasa Phani Kumar Gadde, Crystal C. Pan, Mark Edward Johnson, Thanh Long Duong, Balakota Srinivas Vinnakota, Manish Parekh
-
Publication number: 20230376696Abstract: The present disclosure relates to techniques for identifying out-of-domain utterances.Type: ApplicationFiled: August 2, 2023Publication date: November 23, 2023Applicant: Oracle International CorporationInventors: Thanh Long Duong, Mark Edward Johnson, Vishal Vishnoi, Crystal C. Pan, Vladislav Blinov, Cong Duy Vu Hoang, Elias Luqman Jalaluddin, Duy Vu, Balakota Srinivas Vinnakota
-
Patent number: 11809445Abstract: A method for accessing data stored in a database may include receiving a query to generate, based on blended data, a visualization. The blended data may include a first set of data from a first data source and a second set of data from a second data source. The query may also include a payload. The method may also include accessing the first set of data by injecting, into the payload, the first permission, and transmitting, to the first data source, the payload including the first permission. The method may also include accessing the second set of data by injecting, into the payload, the second permission, and transmitting, to the second data source, the payload including the first permission, the first set of data, and the second permission. The method may also include causing, using the blended data, presentation of the visualization. Related systems and articles of manufacture are provided.Type: GrantFiled: August 31, 2021Date of Patent: November 7, 2023Assignee: SAP SEInventors: Arpitha A Shetty, Veekshitha, Srinivas Vinnakota, Amrita Prabhakaran, Vijaya Pramilamma Bovilla, Priyanka Kommanapalli
-
Patent number: 11763092Abstract: The present disclosure relates to techniques for identifying out-of-domain utterances.Type: GrantFiled: March 30, 2021Date of Patent: September 19, 2023Assignee: Oracle International CorporationInventors: Thanh Long Duong, Mark Edward Johnson, Vishal Vishnoi, Crystal C. Pan, Vladislav Blinov, Cong Duy Vu Hoang, Elias Luqman Jalaluddin, Duy Vu, Balakota Srinivas Vinnakota
-
Publication number: 20230186161Abstract: Techniques are disclosed herein for synthesizing synthetic training data to facilitate training a natural language to logical form model. In one aspect, training data can be synthesized from original under a framework based on templates and a synchronous context-free grammar. In one aspect, training data can be synthesized under a framework based on a probabilistic context-free grammar and a translator. In one aspect, training data can be synthesized under a framework based on tree-to-string translation. In one aspect, the synthetic training data can be combined with original training data in order to train a machine learning model to translate an utterance to a logical form.Type: ApplicationFiled: December 13, 2022Publication date: June 15, 2023Applicant: Oracle International CorporationInventors: Philip Arthur, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Balakota Srinivas Vinnakota, Cong Duy Vu Hoang, Steve Wai-Chun Siu, Nitika Mathur, Gioacchino Tangari, Aashna Devang Kanuga
-
Publication number: 20230186025Abstract: Techniques for preprocessing data assets to be used in a natural language to logical form model based on scalable search and content-based schema linking. In one particular aspect, a method includes accessing an utterance, classifying named entities within the utterance into predefined classes, searching value lists within the database schema using tokens from the utterance to identify and output value matches including: (i) any value within the value lists that matches a token from the utterance and (ii) any attribute associated with a matching value, generating a data structure by organizing and storing: (i) each of the named entities and an assigned class for each of the named entities, (ii) each of the value matches and the token matching each of the value matches, and (iii) the utterance, in a predefined format for the data structure, and outputting the data structure.Type: ApplicationFiled: December 13, 2022Publication date: June 15, 2023Applicant: Oracle International CorporationInventors: Jae Min John, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Balakota Srinivas Vinnakota, Shivashankar Subramanian, Cong Duy Vu Hoang, Yakupitiyage Don Thanuja Samodhye Dharmasiri, Nitika Mathur, Aashna Devang Kanuga, Philip Arthur, Gioacchino Tangari, Steve Wai-Chun Siu
-
Publication number: 20230186026Abstract: Techniques are disclosed herein for synthesizing synthetic training data to facilitate training a natural language to logical form model. In one aspect, training data can be synthesized from original under a framework based on templates and a synchronous context-free grammar. In one aspect, training data can be synthesized under a framework based on a probabilistic context-free grammar and a translator. In one aspect, training data can be synthesized under a framework based on tree-to-string translation. In one aspect, the synthetic training data can be combined with original training data in order to train a machine learning model to translate an utterance to a logical form.Type: ApplicationFiled: December 13, 2022Publication date: June 15, 2023Applicant: Oracle International CorporationInventors: Philip Arthur, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Balakota Srinivas Vinnakota, Cong Duy Vu Hoang, Steve Wai-Chun Siu, Nitika Mathur, Gioacchino Tangari, Aashna Devang Kanuga
-
Publication number: 20230185799Abstract: Techniques are disclosed for training a model, using multi-task learning, to transform natural language to a logical form. In one particular aspect, a method includes accessing a first set of utterances that have non-follow-up utterances and a second set of utterances that have initial utterances and associated one or more follow-up utterances and training a model for translating an utterance to a logical form. The training is a joint training process that includes calculating a first loss for a first semantic parsing task based on one or more non-follow-up utterances from the first set of utterances, calculating a second loss for a second semantic parsing task based on one or more initial utterances and associated one or more follow-up utterances from the second set of utterances, combining the first and second losses to obtain a final loss, and updating model parameters of the model based on the final loss.Type: ApplicationFiled: December 13, 2022Publication date: June 15, 2023Applicant: Oracle International CorporationInventors: Cong Duy Vu Hoang, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Balakota Srinivas Vinnakota
-
Publication number: 20230185834Abstract: Techniques are disclosed herein for synthesizing synthetic training data to facilitate training a natural language to logical form model. In one aspect, training data can be synthesized from original under a framework based on templates and a synchronous context-free grammar. In one aspect, training data can be synthesized under a framework based on a probabilistic context-free grammar and a translator. In one aspect, training data can be synthesized under a framework based on tree-to-string translation. In one aspect, the synthetic training data can be combined with original training data in order to train a machine learning model to translate an utterance to a logical form.Type: ApplicationFiled: December 13, 2022Publication date: June 15, 2023Applicant: Oracle International CorporationInventors: Philip Arthur, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Srinivasa Phani Kumar Gadde, Balakota Srinivas Vinnakota, Cong Duy Vu Hoang, Steve Wai-Chun Siu, Nitika Mathur, Gioacchino Tangari, Aashna Devang Kanuga
-
Publication number: 20230169955Abstract: Techniques for noise data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with noise text to generate an augmented training set of utterances; and training the intent classifier using the augmented training set of utterances. The augmenting includes: obtaining the noise text from a list of words, a text corpus, a publication, a dictionary, or any combination thereof irrelevant of original text within the utterances of the training set of utterances, and incorporating the noise text within the utterances relative to the original text in the utterances of the training set of utterances at a predefined augmentation ratio to generate augmented utterances.Type: ApplicationFiled: November 23, 2022Publication date: June 1, 2023Applicant: Oracle International CorporationInventors: Elias Luqman Jalaluddin, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Yu-Heng Hong, Balakota Srinivas Vinnakota
-
Patent number: 11651768Abstract: Techniques for stop word data augmentation for training chatbot systems in natural language processing. In one particular aspect, a computer-implemented method includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with stop words to generate an augmented training set of out-of-domain utterances for an unresolved intent category corresponding to an unresolved intent; and training the intent classifier using the training set of utterances and the augmented training set of out-of-domain utterances. The augmenting includes: selecting one or more utterances from the training set of utterances, and for each selected utterance, preserving existing stop words within the utterance and replacing at least one non-stop word within the utterance with a stop word or stop word phrase selected from a list of stop words to generate an out-of-domain utterance.Type: GrantFiled: September 9, 2020Date of Patent: May 16, 2023Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Vishal Vishnoi, Mark Edward Johnson, Elias Luqman Jalaluddin, Balakota Srinivas Vinnakota, Thanh Long Duong, Gautam Singaraju
-
Publication number: 20230064676Abstract: A method for accessing data stored in a database may include receiving a query to generate, based on blended data, a visualization. The blended data may include a first set of data from a first data source and a second set of data from a second data source. The query may also include a payload. The method may also include accessing the first set of data by injecting, into the payload, the first permission, and transmitting, to the first data source, the payload including the first permission. The method may also include accessing the second set of data by injecting, into the payload, the second permission, and transmitting, to the second data source, the payload including the first permission, the first set of data, and the second permission. The method may also include causing, using the blended data, presentation of the visualization. Related systems and articles of manufacture are provided.Type: ApplicationFiled: August 31, 2021Publication date: March 2, 2023Inventors: Arpitha A Shetty, Veekshitha, Srinivas Vinnakota, Amrita Prabhakaran, Vijaya Pramilamma Bovilla, Priyanka Kommanapalli
-
Patent number: 11570183Abstract: A distribution network communicates content to tenant groups in a secure manner. An engine of the distribution network receives content created utilizing an application having different customers and partners. The engine also receives: a first identifier indicating a customer of the application with which a tenant is associated, and a second identifier indicating a partner of the application with which the tenant is associated. The engine references a stored database table to correlate the first identifier and the second identifier. Based upon the first identifier and the second identifier, the engine evaluates whether the tenant is to be provided access to the content. The engine may provide the tenant with the content according to an access right determined from the first identifier and the second identifier. Certain embodiments may find particular use disseminating content to new tenants of a customer, based upon prior distribution to other tenants of that customer.Type: GrantFiled: June 8, 2020Date of Patent: January 31, 2023Assignee: SAP SEInventors: Harikrishnan Mangayil, Abhishek Nagendra, Yash Bagadia, Subhadeep Khan, Jayant Sable, Srinivas Vinnakota, Sukesh Kaul
-
Patent number: 11538457Abstract: Techniques for noise data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with noise text to generate an augmented training set of utterances; and training the intent classifier using the augmented training set of utterances. The augmenting includes: obtaining the noise text from a list of words, a text corpus, a publication, a dictionary, or any combination thereof irrelevant of original text within the utterances of the training set of utterances, and incorporating the noise text within the utterances relative to the original text in the utterances of the training set of utterances at a predefined augmentation ratio to generate augmented utterances.Type: GrantFiled: September 9, 2020Date of Patent: December 27, 2022Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Elias Luqman Jalaluddin, Vishal Vishnoi, Mark Edward Johnson, Thanh Long Duong, Yu-Heng Hong, Balakota Srinivas Vinnakota
-
Patent number: 11475875Abstract: In one aspect, a computerized method useful for implementing a language neutral virtual assistant including the step of providing a language detector. The language detector comprises one or more trained language classifiers. With language detector identifying a language of an incoming message from a user to an artificially intelligent (AI) personal assistant. The method includes the step of receiving an incoming message to the AI personal assistant. The method includes the step of normalizing the incoming message, wherein the normalizing the incoming message comprises a set of spelling corrections and a set of grammar corrections. The method includes the step of translating the incoming message to a specified language with a specified encoding process and a specified decoding process. The method includes the step of providing an AI personal assistant engine that comprise an artificial intelligence which conducts a conversation via auditory or textual methods.Type: GrantFiled: October 27, 2019Date of Patent: October 18, 2022Inventors: Sriram Chakravarthy, Madhav Vodnala, Balakota Srinivas Vinnakota, Ram Menon
-
Publication number: 20220100961Abstract: Techniques for automatically switching between chatbot skills in the same domain. In one particular aspect, a method is provided that includes receiving an utterance from a user within a chatbot session, where a current skill context is a first skill and a current group context is a first group, inputting the utterance into a candidate skills model for the first group, obtaining, using the candidate skills model, a ranking of skills within the first group, determining, based on the ranking of skills, a second skill is a highest ranked skill, changing the current skill context of the chatbot session to the second skill, inputting the utterance into a candidate flows model for the second skill, obtaining, using the candidate flows model, a ranking of intents within the second skill that match the utterance, and determining, based on the ranking of intents, an intent that is a highest ranked intent.Type: ApplicationFiled: September 30, 2021Publication date: March 31, 2022Applicant: Oracle International CorporationInventors: Vishal Vishnoi, Xin Xu, Elias Luqman Jalaluddin, Srinivasa Phani Kumar Gadde, Crystal C. Pan, Mark Edward Johnson, Thanh Long Duong, Balakota Srinivas Vinnakota, Manish Parekh
-
Patent number: 11226943Abstract: A distribution network may efficiently communicate items/item details in a private manner, with different access rights tailored to various tenants residing within a same or different customer landscape. A first input comprising a flat file with items/item details, is received. A second input comprising permissions entries for per-user, per-item direct access rights (e.g., view, read, write, delete) is also received. The first and second inputs are recursively processed to find nearest ancestors having the direct access rights, with a hash maintained including the nearest ancestors. An effective permitted structure (e.g., tree comprising root and leaf nodes) is generated by recursively adding descendant items having inherited access rights, to the nearest ancestors. Ultimately, descendant item(s) are privately distributed to a user with an access right according to the effective permitted structure. Embodiments may be particularly suited to the private distribution of analytics content (e.g.Type: GrantFiled: May 5, 2020Date of Patent: January 18, 2022Assignee: SAP SEInventors: Harikrishnan Mangayil, Srinivas Vinnakota, Abhishek Nagendra, Sukesh Kaul, Subhadeep Khan, Yash Bagadia