Infosys Limited

Mphasis Limited

Infosys Technologies Limited

Cognizant Technology Solutions India Pvt. Ltd.

Harman Connected Services, Inc.

Jai Ganesh

Shrirang Prakash Sahasrabudhe

Shaurabh Bharti

Ajay Kolhatkar

Navin Kasa

Rajendrakumar Premnarayan Mishra

Udayaadithya Avadhanam

Nishtha Srivastava

Ashutosh Vyas

Divay Garg

Archisman Majumdar

Srinivas Padmanabhuni

Bharadwaj Raghuraman

Mayank Mathur

Karthik Rajendran

Hemanth Panyam

Satish Pandelenghat

Nachiket Kare

Vaishnavi Shiwankar

Somdev Goswami

Dodla Mounya

Aveek Choudhury

Ravi Sahu

Sahana H S

Aakash Tatoba Walavalkar

Adusumilli Sai Kiran

Kimber Lockhart

Vibhav Kamath

Damini Gupta

Rajdeep Sharma

Tarun Prakash Sharma

Bishwajeet Mondal

Faustina Selvadeepa

Ankit Mishra

Mukund Raj

Rohit Kumar Patel

Meer Ahmed

Neha Ranjeet Ghorpade

Priyesha Chetan Kapadia

Gopakumar Madhuragil Gopalakrishnan

Saurabh Singh

Seema Pandey

Vijaya Bhaskar Peddinti

Avadhanam Udayaadithya

Aravindhan Arunagiri

Niranjan Varadarajan Iyengar

Divya Choudhary

Pallavi Mokkarala

Disclosed herein are systems and methods for graph-based dynamic information retrieval and synthesis, particularly for enhancing the response generation of chatbot applications using large language models (LLMs). The methods involve receiving a user query, generating a query embedding, and accessing a knowledge graph comprising nodes representing documents with associated document embeddings. A set of documents is retrieved based on similarity scores, and a distance matrix is constructed to calculate shortest-path distances between nodes. Documents are clustered to identify a largest cluster from which content is retrieved to formulate a response. The disclosed embodiments improve upon retrieval augmented generation (RAG) by leveraging the hierarchical relationships of a knowledge graph and node interconnectedness to provide contextually coherent information and mitigate the inclusion of information from irrelevant or superficially related documents in LLM responses.

Systems and methods for graph-based dynamic information retrieval and synthesis

The present invention provides for a system and a method for improved representation of classical data on quantum systems. Input classical data is received and a feature set is created from the classical data. A functional transformation is performed on the created feature set to reduce high dimensional data associated with the feature set and a low dimensional feature space dataset is generated. A feature space transformation is performed on the low-dimensional feature space dataset to obtain a new feature space dataset with enhanced feature representation of the low-dimensional feature space dataset in a multi-dimensional space. The new feature space dataset results in optimal mapping of the input classical data into a quantum format. The new feature space dataset is sampled and batches of the sampled dataset are selected. The sampled dataset is mapped into an optimized quantum format for loading the sampled dataset into quantum states.

System and method for optimized processing of information on quantum systems

A system and a method for predicting errors and failure of an application and performing preventive maintenance measures is disclosed. The present invention provides for generating timestamped event logs and extracting data which includes application Id, service Id, user Id, host, error information, resource information, user request data and frequently used execution sequences of associated software components. Further, multiple user requests are modelled based on information extracted from the timestamped event logs and an execution sequence of associated software components is created based on data extracted from timestamped event logs. Further, an execution scheme is generated based on modelled user requests, execution sequence of associated applications and resource status. Yet further, propensity of failure of application is predicted based on the timestamped event logs, user requests, execution sequence of associated applications, resource status and execution scheme of the application by applying a holistic technique.

Adaptive system and a method for application error prediction and management

A method and system for automated creation of graphical user interface applications is provided. The invention provides for provisioning, management and scaling of hardware and software required for the graphical user interface applications by a single action on a command interface of a user terminal, based on a voice command provided by the user.

Method and system for automated creation of graphical user interfaces

A system and method for optimizing aggregation and analysis of data across multiple data sources of multiple enterprises is provided. Data extraction rules are generated by invoking an automatic rule generation rule. Automatic rule generation rule is invoked if a predefined set of rules is not applicable for extracting data. Further, data adaptation rules is generated if data extracted by applying data extraction rules and a predefined set of rules does not correspond to a predetermined output. The data adaptation rules is encapsulated in a feedback loop for transmitting to the data acquisition unit. Data optimization rules s generated based on data extraction rules and data adaptation rules. One or more metrics is generated based on data optimization rules. The metrics specify characteristics relevant to one or more enterprises.

System and method for optimizing aggregation and analysis of data across multiple data sources

System and method for computing critical data of multiple entities is provided. Elements, from a set of predetermined elements, are assigned to sentences of a first dataset associated with an entity of an industry type. Predetermined elements characterize reputation of entities of various industries. Features determined from sentences of first dataset are categorized into groups. Features of a new dataset of a different entity of said industry type are matched with grouped features and same groups are allotted thereto. Classification rules are applied on matched features. Elements are assigned to sentences of new dataset based on allotted groups, which elements are same as those assigned to first dataset. Reputation scores are generated for said entities by determining positive and negative sentiments from the first and new dataset. Steps of assigning elements and grouping are repeated for datasets associated with entities of different industry types for creating a taxonomy for them.

System and method for computing critical data of an entity using cognitive analysis of emergent data

This technology relates to a method, non-transitory computer readable medium, and influencer analyzing computing device for analyzing content associated with one or more influencers of at least one social network. This technique involves identifying key influencers of at least one social network with respect to a topic of interest. Thereafter, an overall topic cloud and an influencer topic cloud for each key influencer is created and analyzed. The overall topic cloud and an influencer topic cloud are compared to cross-verify if the identification of the key influencers is correct. After that, volume of social interaction of the key influencers with respect to the topic of interest are determined and visualized.

Systems and methods for analyzing social network content of a key influencer

Display screen with graphical user interface

A method and system for reporting web standard non-compliance of web pages is provided. The method includes receiving a local copy of the web page to be tested for web standard non-compliance. The method further includes determining a set of errors on the web page corresponding to a user specified accessibility guideline. Thereafter an HTML overlay report is generated based on the determined set of errors. Further, a set of controls is generated based on the user specified accessibility guideline, the local copy and the set of errors. Finally, one or more controls are selected from the set of controls and based on the one or more selected controls and the determined set of errors one or more images are associated with each HTML element non-conformant to the accessibility guideline on the web page.

Method and system for reporting web standard non-compliance of web pages

A system and method for monitoring and analyzing social network databases to determine actual key influencers is disclosed. Inputs are received from the user, which includes search keyword(s), time, date, language, area and country. Content corresponding to the user inputs is fetched from the social network databases. The fetched content is analyzed to identify a list of probable key influencers. Among the probable key influencers, actual key influencers are determined based on parameters associated with the probable key influencer. Reports may be generated based on the actual key influencers and the content they posted on the social network.

System and method for monitoring and analyzing social network databases

Tools and techniques are described for estimating web accessibility and remediation efforts. One or more web accessibility standards can be indicated to be included in the effort estimate. A user can indicate which individual guidelines are to be included in standard test effort estimates by selecting individual guidelines, sub-guidelines or priority or success criteria levels. Standard test effort estimates are calculated based on test factors associated with the indicated individual guidelines or sub-guidelines. A total test effort estimate is calculated based on the standard test effort estimates and one or more web page counts, and a web accessibility and remediation effort estimate is calculated based on the total test effort estimate. A framework implementing the effort estimation methods can comprise multiple spreadsheets for use within a spreadsheet application running on a computing device.

Estimation of web accessibility assessment and remediation efforts

Interoperability across two or more heterogeneous clinical medical error taxonomies can be improved by associating categories in various taxonomies with one or more categories in a master taxonomy. These associations can be expressed using a unique identifier, e.g., a number that identifies one or more categories in the master taxonomy. Various aspects of the associations and/or one or more master taxonomies can be modified by users of a system employing embodiments of the technologies described herein. Searches of clinical medical error records can also be aided using the technologies described herein.

Interoperability across heterogeneous taxonomies

A system and method for accessing the usability and accessibility of a website includes generating a checklist of accommodations corresponding to an accessibility metric of the website, selecting one or more profiles of the website, and selecting Web 2.0 features of the website. The method may further include investigating tradeoffs of accommodations of different sets of Web 2.0 features and determining one or more accommodations necessary for a particular group of users.

System and method for assessing the usability and accessibility of Web 2.0 features and functionalities of websites

A system and method for assessing and remedying accessibility of websites is provided. The method includes receiving a website address for assessment, an accessibility guideline and level of assessment to be performed from the user. The method further includes crawling the website for extracting information. The information comprises HTML tags used in designing a webpage. Thereafter, the website is scanned for checking conformance to one or more accessibility parameters. Finally, one or more assessment reports are provided to the user.

Method and system for assessing and remedying accessibility of websites

Growing community of inventors

Bengaluru, India

Jai Ganesh