Tekion, Inc.

Satyavrat Mudgil

Anant Sitaram

Ved Surtani

Fahad Tasleem

Justin Hou

Akshat Gupta

A system and a method are disclosed for receiving, via a user interface, user input of a first parameter and a second parameter. The system identifies aggregations corresponding to the parameters, the aggregations updated based on input from respective sets of machines, the aggregations being siloed with respect to one another. The system transmits a first query to the first aggregation corresponding to the first parameter, and receives a first response to the first query comprising first data, and transmits a second query to the second aggregation corresponding to the second parameter, and receives a second response to the second query comprising second data. The system integrates the first data and the second data into integrated data, and provides for display, via the user interface, a representation of the integrated data.

Enabling real-time integration of up-to-date siloed data

Embodiments relate to a document parser module that can receive a document template from a producing entity, parse the template, and generate a mapping between the template and identifiers of the transaction entity. Using the mapping and parsed information, a document generator module may generate a document that includes the required identifier data and meets the submission standards of the producing entity. A configuration file may be saved so that a document can be generated and submitted every reporting period with little or no additional modification by the transaction entity.

Document parser and generator

A system and a method are disclosed for receiving, from a source of a plurality of candidate sources, a payload comprising content and metadata. The system selects a destination to which to route the payload based on the source and the content, and generates an entry at the destination based on the content. The system inputs the metadata into a classification engine, and receives, as output from the classification engine, one or more classifications for the payload. The system applies a metadata tag to the entry, the metadata tag indicating the one or more classifications. The system receives a search request from a client device specifying at least one of the one or more classifications, and, in response to receiving the search request, provides the entry to the client device based on a matching classification.

Metadata tag auto-application to posted entries

A document management system manages documents of an entity. The document management system monitors for entries in a document that are suspicious. Entries in the document are classified by the document management system as a 'suspicious entry' or a “non-suspicious entry.” In one embodiment, a suspicious entry is indicative of potentially suspicious activity at the entity.

Identifying suspicious entries in a document management system

A system and a method are disclosed for receiving, by a server, based on input by a user, a request to lock a set of data. Responsively, the server modifies the set of data to be locked, and determines whether an amount of bandwidth required to index the locked data exceeds a threshold. Responsive to determining that the amount of bandwidth exceeds the threshold, the server instructs a secondary server to allocate bandwidth to index a first portion of the locked data. The server indexes a second portion of the locked data in parallel with the secondary server indexing the first portion of the locked data, and generates an index by collating the indexed first and second portions of the locked data. The server receives a search request for a portion of the locked data, and retrieves the portion of the locked data based on referencing the index.

Selective offloading of bandwidth to enable large-scale data indexing

A system and a method are disclosed for receiving an entry, the entry comprising first content and a metadata tag corresponding to a classification, the first content populated by a first source. A rules engine determines that the first content comprises a data field associated with at least one of a plurality of reconciliation policies. Responsive to determining that the first content comprises a data field associated with at least one of the plurality of reconciliation policies, the rules engine selects a reconciliation policy based on the metadata tag. The rules engine retrieves, from a second source, second content associated with the data field, inputs the first content and the second content into a model, the model selected based on the reconciliation policy, the model generating an output, and performs a remediation action based on the output.

Data reconciliation and inconsistency determination for posted entries

A document management system manages documents of an entity. The document management system monitors for entries in a document that are suspicious. Entries in the document are classified by the document management system as a 'suspicious entry' or a 'non-suspicious entry.' In one embodiment, a suspicious entry is indicative of potentially suspicious activity at the entity.

A system and a method are disclosed herein for machine-learned detection of outliers within entity functions. An entity management system uses machine learning to cluster data characterizing functions performed by entities, and determines one or more data clusters that are outliers. The system receives entity function data indicating a metric and a type, and provides the received data into a supervised machine learning model. The model is trained to apply a label to the entity function data, where the label indicates a classification of the data into a cluster (e.g., an outlier cluster). This outlier detection may inform the system's generation of a function monitor to guide rectifying action that addresses the detected outliers. The system may receive user input affirming or rejection the classification of the data into a particular cluster. The system may leverage the user input to retrain the supervised machine learning model.

Machine-learned entity function management

A system and a method are disclosed herein for machine-learned detection of outliers within payload requests. An entity management system uses machine learning to cluster data characterizing requests from entities to route payloads, and determines one or more data clusters that are outliers. The system receives a request to route a payload to a destination, and applies a supervised machine learning model to size and type information indicated by the payload. The supervised machine learning model applies a label to the payload data (e.g., indicating that the payload routing request is an outlier). This outlier detection may drive a validation process to address detected outliers. The system may receive an indication to perform a validation function and transmit the payload to a validation destination. The system may leverage payload data and feedback received from an entity to optimize machine learning techniques to the entity.

Machine-learned validation framework

A document management system manages documents of an enterprise. The documents are managed in a secure manner such that access to entries included in the documents may be restricted according to a security policy associated with the documents. The document management system may secure documents such that entries are still provided to users that request the documents, but sensitive data included in the entries is masked according to the security policies for the documents.

Growing community of inventors

Bengaluru, India

Satyavrat Mudgil