Abstract: A machine learning based (ML-based) method and system for automatically extracting and correcting financial information from documents, is disclosed. Initially, the documents are obtained from data sources and pre-processed to generate the pre-processed data associated with contents within the document. The contents are classified as potential key-value pairs corresponding to the financial information based on the system prompts and extracted using the ML model. The potential key-value pairs are corrected to obtain the corrected key-value pairs based on custom prompts, using the ML model. The corrected key-value pairs corresponding to the financial information are provided as the output to the end users on user interfaces associated with an electronic device. This technique extracts financial information regardless of structure or alignment by learning to recognize any added or removed prefixes or suffixes, enabling the prefixes or suffixes to make corrections and generate accurate key-value pairs.

Abstract: A machine learning based (ML-based) method and system for automatically extracting and correcting financial information from documents, is disclosed. Initially, the documents are obtained from data sources and pre-processed to generate the pre-processed data associated with contents within the document. The contents are classified as potential key-value pairs corresponding to the financial information based on the system prompts and extracted using the ML model. The potential key-value pairs are corrected to obtain the corrected key-value pairs based on custom prompts, using the ML model. The corrected key-value pairs corresponding to the financial information are provided as the output to the end users on user interfaces associated with an electronic device. This technique extracts financial information regardless of structure or alignment by learning to recognize any added or removed prefixes or suffixes, enabling the prefixes or suffixes to make corrections and generate accurate key-value pairs.

Abstract: A machine learning based (ML-based) system and method for automatically generating regexes to identify references associated with financial documents, is disclosed. Initially, data associated with references are obtained from financial documents. The data are pre-processed to generate pre-processed contents. The pre-processed contents are grouped into clusters, based on similarity of pre-processed contents using a clustering machine learning model. The regexes are generated at a character level for each of the clusters, using a machine learning (ML) model. The regexes are normalized based on at least one of: common patterns in the regexes within each of the clusters and positions of characters in the references within the clusters using threshold values. The regexes obtained after normalizing, are provided as an output, to end users on user interfaces associated with electronic devices associated with the end users.

Abstract: A machine learning based (ML-based) computing method and system for automatically categorizing electronic documents in electronic mails, is disclosed. Initially, data associated with the electronic documents are obtained from databases. The data are pre-processed to generate pre-processed texts. The pre-processed texts associated with the electronic documents are analyzed to classify the pre-processed texts into one of a finance related content and a non-finance related content, using a ML model. The electronic documents are categorized as one of electronic financial documents when the pre-processed texts are classified as finance related content, and electronic non-financial documents when the pre-processed texts are classified as non-finance related content, using the ML model.

Abstract: A machine learning based (ML-based) computing method and system for extracting data associated with financial transactions from payment notes, is disclosed. Initially, the payment notes are received from databases. The data in the payment notes are identified based on knowledges and patterns, associated with the data in the payment notes, using a ML model. The identified data in the payment notes are classified based on at least one of: the knowledges and the patterns, using the ML model. The data are extracted from the payment notes upon classifying the data in the payment notes, using the ML model. The output of the data extracted from the payment notes, is provided to the users through user interfaces of electronic devices associated with the users.

Abstract: An optical cavity array includes a plurality of mirrors that form an optical cavity, a first lens system located within the optical cavity, and a second lens system located within the optical cavity. The first lens system has a first output facing a first mirror of the plurality of mirrors and a second output facing a second mirror of the plurality of mirrors. The second lens system has a second input facing the first input and a second output facing the second mirror. The first and second lens systems are configured such that the optical cavity supports longitudinal modes that are transversely non-degenerate, forming spatially separated waists that lie along a focal plane that is axially located between the first and second inputs. When the longitudinal modes are excited, the waists may be used as an array of optical dipole traps.

Abstract: A machine learning based computing method for determining payment information from electronic mails, is disclosed.

Abstract: A machine learning based computing method for automatic data mapping for electronic documents (e.g., remittance documents or documents including remittance information) is disclosed.

Abstract: A machine learning based computing method for determining unique identifiers associated with first users based on information associated with financial transactions, is disclosed.

Abstract: A system and method for or facilitating correction of data in documents is disclosed. The method includes receiving one or more documents from and scanning the received one or more documents by using a document processing system for obtaining one or more mis-captured data fields. The method further includes obtaining a historical correction data and determining one or more deltas based on the obtained historical correction data by using a trained data correction-based ML model. Further, the method includes parsing the determined one or more deltas into one or more datasets, generating one or more correct data fields corresponding to the one or more mis-captured data fields and automatically replacing the one or more mis-captured data fields with the generated one or more correct data fields based on one or more predefined rules.

Abstract: A system and method for or facilitating correction of data in documents is disclosed. The method includes receiving one or more documents from and scanning the received one or more documents by using a document processing system for obtaining one or more mis-captured data fields. The method further includes obtaining a historical correction data and determining one or more deltas based on the obtained historical correction data by using a trained data correction-based ML model. Further, the method includes parsing the determined one or more deltas into one or more datasets, generating one or more correct data fields corresponding to the one or more mis-captured data fields and automatically replacing the one or more mis-captured data fields with the generated one or more correct data fields based on one or more predefined rules.

Abstract: Techniques and structures to facilitate anomaly detection within a networking system, including receiving a plurality of performance metric messages at a database system, extracting a plurality of anomaly detection messages included in the performance metric messages, storing the plurality of anomaly detection messages in an in-memory database and executing a machine learning model to process the plurality of anomaly detection messages in the in-memory database to detect whether anomalous usage of the networking system has been detected.

Abstract: Methods and systems are described for creating and/or processing a definition for a dashboard with manually input code and user selections in a graphical user interface. In some implementations, user interface elements are displayed and selections from a user accepted. Responsive to the selections, definitions for one or more visualizations and datasources are automatically generated and displayed in a user interface element that accepts manually input customizations and code from the user. The resulting combination of code and definitions is stored as a definition for the dashboard, which when processed will transform data received from the at least one of the datasources, combine the transformed data with data from another of the datasources, and cause the display of a visualization based on the combined data.

Abstract: Methods and systems are described for creating and/or processing a definition for a dashboard with manually input code and user selections in a graphical user interface. In some implementations, user interface elements are displayed and selections from a user accepted. Responsive to the selections, definitions for one or more visualizations and datasources are automatically generated and displayed in a user interface element that accepts manually input customizations and code from the user. The resulting combination of code and definitions is stored as a definition for the dashboard, which when processed will transform data received from the at least one of the datasources, combine the transformed data with data from another of the datasources, and cause the display of a visualization based on the combined data.

Abstract: System and methods are described for a monitoring system to monitor operations of a distributed computing system and provide feedback to subscribers. The monitoring system includes a data collection engine to receive data items comprising events, metrics, or one or more configurations about a distributed computing system being monitored, and to store selected data items into a message queue. The monitoring system also includes a data processing engine to receive the selected data items from the queue, transform the selected data items into transformed data items based at least in part on one or more settings for a subscriber and the one or more configurations of the distributed computing system, and store the transformed data items into one or more of a database and a cache.

Abstract: Techniques and structures to facilitate anomaly detection within a networking system, including receiving a plurality of performance metric messages at a database system, extracting a plurality of anomaly detection messages included in the performance metric messages, storing the plurality of anomaly detection messages in an in-memory database and executing a machine learning model to process the plurality of anomaly detection messages in the in-memory database to detect whether anomalous usage of the networking system has been detected

Abstract: Matching knowledge providers with knowledge consumers. Information corresponding to knowledge providers and information corresponding to knowledge consumers is managed in a database. Messages from remote electronic devices corresponding to the knowledge providers and the knowledge consumers are received. Subsequent information corresponding to the knowledge providers and the knowledge consumers is gathered from a plurality of remote platforms. Knowledge power agents configured to operate through the plurality of interfaces match knowledge providers with knowledge consumers based, at least in part, on shared interests, location and availability. In response to a match between at least one knowledge provider and at least one knowledge consumer, communicating via at least one of the plurality of interfaces information about the match to at least one knowledge consumer and at least one knowledge provider for which the match has been made.