Abstract: A hybrid rule-based Artificial Intelligence (AI) document processing system processes a non-editable document with at least one invoice to accurately extract data from tables in the invoices. The non-editable document is preprocessed for conversion into a markup format and pages including the invoice are identified. The invoice is processed via a document process by parsing the pages in different directions to generate a first set of predictions and via a block process wherein logical information blocks from the invoice are processed to generate a second set of predictions. The missing entries from a selected table are identified by applying rules to the first set of predictions and the second set of predictions. Any discrepancy between the missing entry values between the first and second set of predictions are resolved and the resulting data is exported to downstream systems for further uses.

Abstract: An Artificial Intelligence (AI) based user intent analyzer system analyzes a received user query to determine an intent of the user query and enables execution of processes on a backend system based on the user intent. The user query is divided into a plurality of portions and the portions with extraneous information are discarded. The remaining portions are parsed with a plurality of parsers. The output from the plurality of parsers is processed for extraction of the entities, entity attributes, verbs, and verb arguments. The entities and verbs are further filtered using knowledge graphs and the remaining entities and verbs are mapped to sub-intents using intent mapping rules retrieved from the knowledge graphs. The sub-intents are mapped to the final intent using process rules associated with the process to be executed by the backend system in response to the user query.

Abstract: An Artificial Intelligence (AI) based user intent analyzer system analyzes a received user query to determine an intent of the user query and enables execution of processes on a backend system based on the user intent. The user query is divided into a plurality of portions and the portions with extraneous information are discarded. The remaining portions are parsed with a plurality of parsers. The output from the plurality of parsers is processed for extraction of the entities, entity attributes, verbs, and verb arguments. The entities and verbs are further filtered using knowledge graphs and the remaining entities and verbs are mapped to sub-intents using intent mapping rules retrieved from the knowledge graphs. The sub-intents are mapped to the final intent using process rules associated with the process to be executed by the backend system in response to the user query.

Abstract: A hybrid rule-based Artificial Intelligence (AI) document processing system processes a non-editable document with at least one invoice to accurately extract data from tables in the invoices. The non-editable document is preprocessed for conversion into a markup format and pages including the invoice are identified. The invoice is processed via a document process by parsing the pages in different directions to generate a first set of predictions and via a block process wherein logical information blocks from the invoice are processed to generate a second set of predictions. The missing entries from a selected table are identified by applying rules to the first set of predictions and the second set of predictions. Any discrepancy between the missing entry values between the first and second set of predictions are resolved and the resulting data is exported to downstream systems for further uses.

Abstract: Disclosed subject matter relates to virtual assistance that includes a method and system for automatically generating response to a user query without language constraints. A response generating system receives the user query from a computing device associated with an end user and determines whether the user query belongs to at least one domain to determine goal data and a problem category of the user query. Further, a problem node associated with the user query is detected from problem nodes by parsing a predefined knowledge graph based on the goal data and the problem category. Furthermore, questions are provided based on problem sub-nodes of the problem node to the computing device to receive a feedback. The response to the user query extracted from the one of the problem sub-nodes is displayed to the end user based on the feedback. The present disclosure is highly scalable, reusable and requires minimal human supervision.

Abstract: A centralized data reconciliation system processes at least two data streams transmitting data related to one of a plurality of processes and executes a data reconciliation procedure. Unmatched data records identified during the data reconciliation procedure are further categorized into categorized records based on various reason categories and irreconcilable records which could not be categorized into the reason categories. The irreconcilable records are flagged for user input. The user input is recorded to further train the data reconciliation system. The at least two data streams are initially converted into self-describing data streams from which the entities and entity attributes are extracted using the data models received from the data streams. The data records from the first and second self-describing data streams are mapped. The matched pairs and unmatched pairs are selected from the mappings based on respective confidence scores that are estimated in accordance with the rules of data reconciliation.

Abstract: A centralized data reconciliation system processes at least two data streams transmitting data related to one of a plurality of processes and executes a data reconciliation procedure. Unmatched data records identified during the data reconciliation procedure are further categorized into categorized records based on various reason categories and irreconcilable records which could not be categorized into the reason categories. The irreconcilable records are flagged for user input. The user input is recorded to further train the data reconciliation system. The at least two data streams are initially converted into self-describing data streams from which the entities and entity attributes are extracted using the data models received from the data streams. The data records from the first and second self-describing data streams are mapped. The matched pairs and unmatched pairs are selected from the mappings based on respective confidence scores that are estimated in accordance with the rules of data reconciliation.

Abstract: Disclosed herein is a method and system for dynamically generating multimedia content file. The method comprises receiving, by a multimedia content generator, description of an event from a user. The method comprises identifying one or more keywords from the description of the event. Further, the method comprises mapping the one or more identified keywords with one or more images, related to one or more objects, stored in a content database for generating one or more scenes related to the description. An initial-level multimedia content file is generated by composing the one or more scenes. Furthermore the method comprises receiving one or more inputs on the initial-level multimedia content file from the user. Finally, a final-level multimedia content file is generated based on the one or more inputs received on the initial-level multimedia content file.

Abstract: Disclosed subject matter relates to virtual assistance that includes a method and system for automatically generating response to a user query without language constraints. A response generating system receives the user query from a computing device associated with an end user and determines whether the user query belongs to at least one domain to determine goal data and a problem category of the user query. Further, a problem node associated with the user query is detected from problem nodes by parsing a predefined knowledge graph based on the goal data and the problem category. Furthermore, questions are provided based on problem sub-nodes of the problem node to the computing device to receive a feedback. The response to the user query extracted from the one of the problem sub-nodes is displayed to the end user based on the feedback. The present disclosure is highly scalable, reusable and requires minimal human supervision.

Abstract: Disclosed herein is a method and system for dynamically generating multimedia content file. The method comprises receiving, by a multimedia content generator, description of an event from a user. The method comprises identifying one or more keywords from the description of the event. Further, the method comprises mapping the one or more identified keywords with one or more images, related to one or more objects, stored in a content database for generating one or more scenes related to the description. An initial-level multimedia content file is generated by composing the one or more scenes. Furthermore the method comprises receiving one or more inputs on the initial-level multimedia content file from the user. Finally, a final-level multimedia content file is generated based on the one or more inputs received on the initial-level multimedia content file.

Abstract: The present disclosure relates to a method and system for automatic assessment of a candidate. The method comprises receiving one or more answers from the candidate to one or more questions provided to the candidate, wherein the one or more questions provided to the candidate are related to one or more domains of expertise of the candidate. One or more keywords and key phrases are extracted from the received answers. Also, relationship among the one or more keywords and key phrases are identified upon extracting the key words and key phrases from the answers. Further, a multi-level score is assigned to each of the one or more answers based on the one or more keywords, key phrases and the relationship among the keywords and key phrases. The candidate is assessed based on the multi-level score assigned to each of the one or more answers received from the candidate.