Patents by Inventor Gautam Singaraju
Gautam Singaraju 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).
-
Patent number: 11928430Abstract: Techniques are described to determine whether an input utterance is unrelated to a set of skill bots associated with a master bot. In some embodiments, a system described herein includes a training system and a master bot. The training system trains a classifier of the master bot. The training includes accessing training utterances associated with the skill bots and generating training feature vectors from the training utterances. The training further includes generating multiple set representations of the training feature vectors, where each set representation corresponds to a subset of the training feature vectors, and configuring the classifier with the set representations. The master bot accesses an input utterance and generates an input feature vector. The master bot uses the classifier to compare the input feature vector to the multiple set representations so as to determine whether the input feature falls outside and, thus, cannot be handled by the skill bots.Type: GrantFiled: September 10, 2020Date of Patent: March 12, 2024Assignee: Oracle International CorporationInventors: Crystal C. Pan, Gautam Singaraju, Vishal Vishnoi, Srinivasa Phani Kumar Gadde
-
Patent number: 11775572Abstract: Techniques for chatbots, and more particularly, to techniques for using a directed acyclic graph (DAG) based framework to build and train models. In one particular aspect, a computer implemented method is provided that includes generating, by a DAG based framework, a first model and a second model, executing the first model for a chatbot in run-time and second model for the chatbot in design-time, collecting attributes for intent classification associated with a set of utterances with the chatbot running the first model and the second model, evaluating, using one or more metrics, performance of the first model and the second model based on an analysis of the attributes for the intent classification, determining whether the performance of the second model is improved as compared to the performance of the first model, and executing the first model or the second model for the chatbot in run-time based on the performance determination.Type: GrantFiled: November 15, 2021Date of Patent: October 3, 2023Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Gautam Singaraju, Crystal Pan
-
Publication number: 20230252975Abstract: Techniques are described for invoking and switching between chatbots of a chatbot system. In some embodiments, the chatbot system is capable of routing an utterance received while a user is already interacting with a first chatbot in the chatbot system. For instance, the chatbot system may identify a second chatbot based on determining that (i) such an utterance is an invalid input to the first chatbot or (ii) that the first chatbot is attempting to route the utterance to a destination associated with the first chatbot. Identifying the second chatbot can involve computing, using a predictive model, separate confidence scores for the first chatbot and the second chatbot, and then determining that a confidence score for the second chatbot satisfies one or more confidence score thresholds. The utterance is then routed to the second chatbot based on the identifying of the second chatbot.Type: ApplicationFiled: April 19, 2023Publication date: August 10, 2023Applicant: Oracle International CorporationInventors: Vishal Vishnoi, Xin Xu, Srinivasa Phani Kumar Gadde, Fen Wang, Muruganantham Chinnananchi, Manish Parekh, Stephen Andrew McRitchie, Jae Min John, Crystal C. Pan, Gautam Singaraju, Saba Amsalu Teserra
-
Publication number: 20230206087Abstract: Techniques disclosed herein relate generally to constructing a customized knowledge graph. In one embodiment, entities and relations among entities are extracted from a user dataset based on certain rules to generate a seed graph. Large-scale knowledge graphs are then traversed using a finite state machine to identify candidate entities and/or relations to add to the seed graph. A priority function is used to select entities and/or relations from the candidate entities and/or relations. The selected entities and/or relations are then added to the seed graph to generate the customized knowledge graph.Type: ApplicationFiled: March 3, 2023Publication date: June 29, 2023Applicant: Oracle International CorporationInventors: Gautam Singaraju, Prithviraj Venkata Ammanabrolu
-
Patent number: 11657797Abstract: Techniques are described for invoking and switching between chatbots of a chatbot system. In some embodiments, the chatbot system is capable of routing an utterance received while a user is already interacting with a first chatbot in the chatbot system. For instance, the chatbot system may identify a second chatbot based on determining that (i) such an utterance is an invalid input to the first chatbot or (ii) that the first chatbot is attempting to route the utterance to a destination associated with the first chatbot. Identifying the second chatbot can involve computing, using a predictive model, separate confidence scores for the first chatbot and the second chatbot, and then determining that a confidence score for the second chatbot satisfies one or more confidence score thresholds. The utterance is then routed to the second chatbot based on the identifying of the second chatbot.Type: GrantFiled: April 23, 2020Date of Patent: May 23, 2023Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Vishal Vishnoi, Xin Xu, Srinivasa Phani Kumar Gadde, Fen Wang, Muruganantham Chinnananchi, Manish Parekh, Stephen Andrew McRitchie, Jae Min John, Crystal C. Pan, Gautam Singaraju, Saba Amsalu Teserra
-
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
-
Patent number: 11625620Abstract: Techniques disclosed herein relate generally to constructing a customized knowledge graph. In one embodiment, entities and relations among entities are extracted from a user dataset based on certain rules to generate a seed graph. Large-scale knowledge graphs are then traversed using a finite state machine to identify candidate entities and/or relations to add to the seed graph. A priority function is used to select entities and/or relations from the candidate entities and/or relations. The selected entities and/or relations are then added to the seed graph to generate the customized knowledge graph.Type: GrantFiled: August 15, 2019Date of Patent: April 11, 2023Assignee: Oracle International CorporationInventors: Gautam Singaraju, Prithviraj Venkata Ammanabrolu
-
Patent number: 11551135Abstract: Techniques disclosed herein relate to generating a hierarchical classification model that includes a plurality of classification models. The hierarchical classification model is configured to classify an input into a class in a plurality of classes and includes a tree structure. The tree structure includes leaf nodes and non-leaf nodes. Each non-leaf node has two child nodes associated with two respective sets of classes in the plurality of classes, where a difference between numbers of classes in the two sets of classes is zero or one. Each leaf node is associated with at least two but fewer than a first threshold number of classes. Each of the leaf nodes and non-leaf nodes is associated with a classification model in the plurality of classification models of the hierarchical classification model. The classification model associated with each respective node in the tree structure can be trained independently.Type: GrantFiled: September 28, 2018Date of Patent: January 10, 2023Assignee: Oracle International CorporationInventors: Gautam Singaraju, Jiarui Ding, Sangameswaran Viswanathan
-
Patent number: 11416777Abstract: Techniques herein relate to improving quality of classification models for differentiating different user intents by improving the quality of training samples used to train the classification models. Pairs of user intents that are difficult to differentiate by classification models trained using the given training samples are identified based upon distinguishability scores (e.g., F-scores). For each of the identified pairs of intents, pairs of training samples each including a training sample associated with a first intent and a training sample associated with a second intent in the pair of intents are ranked based upon a similarity score between the two training samples in each pair of training samples. A particular pair of training samples with a highest similarity score is selected and provided as output with a suggestion for modifying the particular pair of training samples.Type: GrantFiled: September 30, 2020Date of Patent: August 16, 2022Assignee: Oracle International CorporationInventors: Gautam Singaraju, Jiarui Ding, Vishal Vishnoi, Mark Joseph Sugg, Edward E. Wong
-
Publication number: 20220171938Abstract: Techniques for out-of-domain 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 a machine-learning model to identify one or more intents for one or more utterances, and augmenting the training set of utterances with out-of-domain (OOD) examples. The augmenting includes: generating a data set of OOD examples, filtering out OOD examples from the data set of OOD examples, determining a difficulty value for each OOD example remaining within the filtered data set of the OOD examples, and generating augmented batches of utterances comprising utterances from the training set of utterances and utterances from the filtered data set of the OOD based on the difficulty value for each OOD. Thereafter, the machine-learning model is trained using the augmented batches of utterances in accordance with a curriculum training protocol.Type: ApplicationFiled: October 28, 2021Publication date: June 2, 2022Applicant: Oracle International CorporationInventors: Elias Luqman Jalaluddin, Vishal Vishnoi, Thanh Long Duong, Mark Edward Johnson, Poorya Zaremoodi, Gautam Singaraju, Ying Xu, Vladislav Blinov, Yu-Heng Hong
-
Publication number: 20220171930Abstract: Techniques for keyword 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 a machine-learning model to identify one or more intents for one or more utterances, augmenting the training set of utterances with out-of-domain (OOD) examples. The augmenting includes: identifying keywords within utterances of the training set of utterances, generating a set of OOD examples with the identified keywords, filtering out OOD examples from the set of OOD examples that have a context substantially similar to context of the utterances of the training set of utterances, and incorporating the set of OOD examples without the filtered OOD examples into the training set of utterances to generate an augmented training set of utterances. Thereafter, the machine-learning model is trained using the augmented training set of utterances.Type: ApplicationFiled: October 28, 2021Publication date: June 2, 2022Applicant: Oracle International CorporationInventors: Elias Luqman Jalaluddin, Vishal Vishnoi, Thanh Long Duong, Mark Edward Johnson, Poorya Zaremoodi, Gautam Singaraju, Ying Xu, Vladislav Blinov
-
Publication number: 20220078140Abstract: Techniques for chatbots, and more particularly, to techniques for using a directed acyclic graph (DAG) based framework to build and train models. In one particular aspect, a computer implemented method is provided that includes generating, by a DAG based framework, a first model and a second model, executing the first model for a chatbot in run-time and second model for the chatbot in design-time, collecting attributes for intent classification associated with a set of utterances with the chatbot running the first model and the second model, evaluating, using one or more metrics, performance of the first model and the second model based on an analysis of the attributes for the intent classification, determining whether the performance of the second model is improved as compared to the performance of the first model, and executing the first model or the second model for the chatbot in run-time based on the performance determination.Type: ApplicationFiled: November 15, 2021Publication date: March 10, 2022Applicant: Oracle International CorporationInventors: Gautam Singaraju, Crystal Pan
-
Publication number: 20220058347Abstract: A chatbot system is configured to execute code to perform determining, by the chatbot system, a classification result for an utterance and one or more anchors each anchor of the one or more anchors corresponding to one or more anchor words of the utterance. For each anchor of the one or more anchors, one or more synthetic utterances are generated, and one or more classification results for the one or more synthetic utterances are determined. A report is generated by the chatbot system comprising a representation of a particular anchor of the one or more anchors, the particular anchor corresponding to a highest confidence value among the one or more anchors. The one or more synthetic utterances may be used to generate a new training dataset for training a machine-learning model. The training dataset may be refined according to a threshold confidence values to filter out datasets for training.Type: ApplicationFiled: August 20, 2021Publication date: February 24, 2022Applicant: Oracle International CorporationInventors: Gautam Singaraju, Vishal Vishnoi, Manish Parekh, Alexander Wang
-
Patent number: 11206229Abstract: Techniques for chatbots, and more particularly, to techniques for using a directed acyclic graph (DAG) based framework to build and train models. In one particular aspect, a computer implemented method is provided that includes generating, by a DAG based framework, a first model and a second model, executing the first model for a chatbot in run-time and second model for the chatbot in design-time, collecting attributes for intent classification associated with a set of utterances with the chatbot running the first model and the second model, evaluating, using one or more metrics, performance of the first model and the second model based on an analysis of the attributes for the intent classification, determining whether the performance of the second model is improved as compared to the performance of the first model, and executing the first model or the second model for the chatbot in run-time based on the performance determination.Type: GrantFiled: March 19, 2020Date of Patent: December 21, 2021Assignee: Oracle International CorporationInventors: Gautam Singaraju, Crystal Pan
-
Publication number: 20210082400Abstract: 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: ApplicationFiled: September 9, 2020Publication date: March 18, 2021Applicant: Oracle International CorporationInventors: Vishal Vishnoi, Mark Edward Johnson, Elias Luqman Jalaluddin, Balakota Srinivas Vinnakota, Thanh Long Duong, Gautam Singaraju
-
Publication number: 20210083994Abstract: Techniques are described to determine whether an input utterance is unrelated to a set of skill bots associated with a master bot. In some embodiments, a system described herein includes a training system and a master bot. The training system trains a classifier of the master bot. The training includes accessing training utterances associated with the skill bots and generating training feature vectors from the training utterances. The training further includes generating multiple set representations of the training feature vectors, where each set representation corresponds to a subset of the training feature vectors, and configuring the classifier with the set representations. The master bot accesses an input utterance and generates an input feature vector. The master bot uses the classifier to compare the input feature vector to the multiple set representations so as to determine whether the input feature falls outside and, thus, cannot be handled by the skill bots.Type: ApplicationFiled: September 10, 2020Publication date: March 18, 2021Applicant: Oracle International CorporationInventors: Crystal C. Pan, Gautam Singaraju, Vishal Vishnoi, Srinivasa Phani Kumar Gadde
-
Publication number: 20210012245Abstract: Techniques disclosed herein relate to improving quality of classification models for differentiating different user intents by improving the quality of training samples used to train the classification models. Pairs of user intents that are difficult to differentiate by classification models trained using the given training samples are identified based upon distinguishability scores (e.g., F-scores). For each of the identified pairs of intents, pairs of training samples each including a training sample associated with a first intent and a training sample associated with a second intent in the pair of intents are ranked based upon a similarity score between the two training samples in each pair of training samples. The identified pairs of intents and the pairs of training samples having the highest similarity scores may be presented to users through a user interface, along with user-selectable options or suggestions for improving the training samples.Type: ApplicationFiled: September 30, 2020Publication date: January 14, 2021Applicant: Oracle International CorporationInventors: Gautam Singaraju, Jiarui Ding, Vishal Vishnoi, Mark Joseph Sugg, Edward E. Wong
-
Patent number: 10824962Abstract: Techniques for improving quality of classification models for differentiating different user intents by improving the quality of training samples used to train the classification models are described. Pairs of user intents that are difficult to differentiate by classification models trained using the given training samples are identified based upon distinguishability scores (e.g., F-scores). For each of the identified pairs of intents, pairs of training samples each including a training sample associated with a first intent and a training sample associated with a second intent in the pair of intents are ranked based upon a similarity score between the two training samples in each pair of training samples. The identified pairs of intents and the pairs of training samples having the highest similarity scores may be presented to users through a user interface, along with user-selectable options or suggestions for improving the training samples.Type: GrantFiled: September 28, 2018Date of Patent: November 3, 2020Assignee: Oracle International CorporationInventors: Gautam Singaraju, Jiarui Ding, Vishal Vishnoi, Mark Joseph Sugg, Edward E. Wong
-
Publication number: 20200344185Abstract: Techniques for chatbots, and more particularly, to techniques for using a directed acyclic graph (DAG) based framework to build and train models. In one particular aspect, a computer implemented method is provided that includes generating, by a DAG based framework, a first model and a second model, executing the first model for a chatbot in run-time and second model for the chatbot in design-time, collecting attributes for intent classification associated with a set of utterances with the chatbot running the first model and the second model, evaluating, using one or more metrics, performance of the first model and the second model based on an analysis of the attributes for the intent classification, determining whether the performance of the second model is improved as compared to the performance of the first model, and executing the first model or the second model for the chatbot in run-time based on the performance determination.Type: ApplicationFiled: March 19, 2020Publication date: October 29, 2020Applicant: Oracle International CorporationInventors: Gautam Singaraju, Crystal Pan
-
Publication number: 20200342850Abstract: Techniques are described for invoking and switching between chatbots of a chatbot system. In some embodiments, the chatbot system is capable of routing an utterance received while a user is already interacting with a first chatbot in the chatbot system. For instance, the chatbot system may identify a second chatbot based on determining that (i) such an utterance is an invalid input to the first chatbot or (ii) that the first chatbot is attempting to route the utterance to a destination associated with the first chatbot. Identifying the second chatbot can involve computing, using a predictive model, separate confidence scores for the first chatbot and the second chatbot, and then determining that a confidence score for the second chatbot satisfies one or more confidence score thresholds. The utterance is then routed to the second chatbot based on the identifying of the second chatbot.Type: ApplicationFiled: April 23, 2020Publication date: October 29, 2020Applicant: Oracle International CorporationInventors: Vishal Vishnoi, Xin Xu, Srinivasa Phani Kumar Gadde, Fen Wang, Muruganantham Chinnananchi, Manish Parekh, Stephen Andrew McRitchie, Jae Min John, Crystal C. Pan, Gautam Singaraju, Saba Amsalu Teserra