Abstract: An Artificial Intelligence (AI)-based data processing system employs a trained AI model for extracting features of products from various product classes and building a product ontology from the features. The product ontology is used to respond to user queries with product recommendations and customizations. Training data for the generation of the AI model for feature extraction is initially accessed and verified to determine of the training data meets a data density requirement. If the training data does not meet the data density requirement, data from one of a historic source or external sources is added to the training data. One of the plurality of AI models is selected for training based on the degree of overlap and the inter-class distance between the datasets of the various product classes within the training data.

Abstract: Data from multiple sources may be gathered continuously to perform reconciliation operations. The data items in a first data set may be matched with those in the second data set using a data matching technique. Based on the matching, a confidence score indicative of an extent of match between the data items in the data sets may be generated. Based on the confidence score and predefined thresholds, it may be ascertained if the data items are reconciled. The non-reconciled items in at least one of the first data set and the second data set may be classified in a classification category, based on an artificial intelligence based technique, the classification category being indicative of an explanation of a non-reconciled data item being non-reconcilable. When the data item is not reconciled and classified, the data item is identified as an open item for further analysis.

Abstract: An Artificial Intelligence (AI)-based data processing system employs a trained AI model for extracting features of products from various product classes and building a product ontology from the features. The product ontology is used to respond to user queries with product recommendations and customizations. Training data for the generation of the AI model for feature extraction is initially accessed and verified to determine of the training data meets a data density requirement. If the training data does not meet the data density requirement, data from one of a historic source or external sources is added to the training data. One of the plurality of AI models is selected for training based on the degree of overlap and the inter-class distance between the datasets of the various product classes within the training data.

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: Data from multiple sources may be gathered continuously to perform reconciliation operations. The data items in a first data set may be matched with those in the second data set using a data matching technique. Based on the matching, a confidence score indicative of an extent of match between the data items in the data sets may be generated. Based on the confidence score and predefined thresholds, it may be ascertained if the data items are reconciled. The non-reconciled items in at least one of the first data set and the second data set may be classified in a classification category, based on an artificial intelligence based technique, the classification category being indicative of an explanation of a non-reconciled data item being non-reconcilable. When the data item is not reconciled and classified, the data item is identified as an open item for further analysis.

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: Systems and methods for generating one or more actions are disclosed. The system retrieves data associated with patients from data sources. The data is analyzed to classify the patients into different categories. The system generates a set of profiles for the patients based on the data. A plurality of clusters is also generated based on the classification of the patients and the set of profiles. The system generates trend model based on the plurality of clusters. The trend comprises trend of plurality of diseases and rate of recovery of the plurality of diseases based on existing procedures and medications applied. Based on the trend model, the system generates scores corresponding to the plurality of clusters. Further, the clusters are ranked based on their scores. Finally, the system generates one or more actions (i.e., clinical actions) which include new procedure and a new medication based on the ranking of the clusters.

Abstract: This disclosure relates to systems and methods for improved knowledge mining. In one embodiment, a method is disclosed, which comprises filtering aggregated data encoded according to multiple data formats, using a combination of sliding-window and boundary-based filtration techniques. Machine learning and natural language processing are applied to the filtered data to generate a business ontology. Also, using a prediction analysis, one or more recommended classification techniques are automatically identified. The filtered data is clustered into an automatically determined number of categories based on the automatically recommended one or more classification techniques. The one or more classification techniques may utilize iterative feedback between a supervised learning technique and an unsupervised learning technique.

Abstract: This technology relates to method and optimization systems for optimizing storage of multi-dimensional data in data storage. The method comprises analyzing a plurality of queries received over period of time from one or more client machines. Then, a query pattern is determined from plurality of queries. Based on query pattern dimensionality of data is identified for determining data storage strategy. The dimensionality is characterized into 11 dimensions comprising 4 standard level dimensions and 7 higher level dimensions. A highest dimension out of 7 higher dimensions is parallel data storage dimension. Based on storage strategy, at least one of data and columns of a table is segmented in data storage. Next, data is stored in remote data storage when data is an element of last higher level dimension. Then, higher level dimensions are fragmented into one or more smaller level dimensions when data is element greater than 11 dimensions.

Abstract: Apparatuses, methods, and non-transitory computer readable medium that provide recommendations include determining personality traits of a sender and a recipient by applying a five-factor model to a plurality of datasets. Further, the method comprises associating a personality-product score with each of a plurality of products based on the personality traits and performing a need analysis on the user data to determine desired products from amongst the plurality of products. Further, the method comprises determining a multidimensional collaborative matrix by aggregating the personality traits, the personality-product score, the desired products, and product psychographic portfolio. Further, the method comprises determining an affinity score for at least one of the sender and the recipient towards each of the plurality of products based on the multidimensional collaborative matrix and recommending at least one product from amongst the plurality of products to the sender based on the affinity score.

Abstract: This disclosure relates to systems and methods for improved knowledge mining. In one embodiment, a method is disclosed, which comprises filtering aggregated data encoded according to multiple data formats, using a combination of sliding-window and boundary-based filtration techniques. Machine learning and natural language processing are applied to the filtered data to generate a business ontology. Also, using a prediction analysis, one or more recommended classification techniques are automatically identified. The filtered data is clustered into an automatically determined number of categories based on the automatically recommended one or more classification techniques. The one or more classification techniques may utilize iterative feedback between a supervised learning technique and an unsupervised learning technique.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for identifying a personality of a human subject based on correlations between personality traits obtained from the subject's physical features, which may include a movement pattern of the subject, such as the subject's gait. Embodiments in accordance with the present disclosure are further capable of providing a recommendation to the subject for a product or service based on the identified personality of the subject.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for human personality prediction by analyzing information collected from different sources such as social media, call detail record (CDR), email etc. using DISC (dominance, inducement, submission, and compliance) profiling and Big Five personality techniques (openness, conscientiousness, extraversion, agreeableness, and neuroticism). Embodiments in accordance with the present disclosure are further capable of using a self-learning model which learns from user response to the prediction.

Abstract: The present disclosure relates to a method and a device for determining potential risk of an insurance claim on an insuree by an insurer. In one embodiment, a plurality of insurance claims and data associated with the insurance claims is received and classified into segments. Upon classifying into segments, risk associated with each segment is determined based on which financial impact is predicted. On predicting the financial impact, the probability of availing an insurance policy by a potential insuree is also predicted. By profiling the customers, segments favorable for customers is determined. Further, prediction and forecast of high risk prone customer segments provides better understanding of risk prone customers and enables the companies to take necessary action on the risk prone customers. Further, the method enables automatic calculation of debts associated with the risk prone customers and provides better understanding of policies prone to risk based on debt calculation.

Abstract: Embodiments of the present disclosure disclose a method for optimizing processing of insurance claims. The method comprises one or more steps performed by an insurance data processing apparatus. The method comprises examining completeness of information in an insurance application form to avail insurance claims for an insured patient. Then, the information contained in the insurance application form is segmented into at least one of medical data and behavioural data of the insured patient. Next, one or more diseases from the medical data into a medical group and behavioural parameters from the behavioural data are classified into a behavioural group. The classification is performed using predefined one or more ontologies comprising medical ontologies and behavioural ontologies. Then, a relevancy of the insurance claims associated to the insured patient is verified based on the classification of the one or more diseases and the behavioural parameters.

Abstract: Apparatuses, methods, and non-transitory computer readable medium that provide recommendations include determining personality traits of a sender and a recipient by applying a five-factor model to a plurality of datasets. Further, the method comprises associating a personality-product score with each of a plurality of products based on the personality traits and performing a need analysis on the user data to determine desired products from amongst the plurality of products. Further, the method comprises determining a multidimensional collaborative matrix by aggregating the personality traits, the personality-product score, the desired products, and product psychographic portfolio. Further, the method comprises determining an affinity score for at least one of the sender and the recipient towards each of the plurality of products based on the multidimensional collaborative matrix and recommending at least one product from amongst the plurality of products to the sender based on the affinity score.

Abstract: This technology relates to method and optimization systems for optimizing storage of multi-dimensional data in data storage. The method comprises analyzing a plurality of queries received over period of time from one or more client machines. Then, a query pattern is determined from plurality of queries. Based on query pattern dimensionality of data is identified for determining data storage strategy. The dimensionality is characterized into 11 dimensions comprising 4 standard level dimensions and 7 higher level dimensions. A highest dimension out of 7 higher dimensions is parallel data storage dimension. Based on storage strategy, at least one of data and columns of a table is segmented in data storage. Next, data is stored in remote data storage when data is an element of last higher level dimension. Then, higher level dimensions are fragmented into one or more smaller level dimensions when data is element greater than 11 dimensions.

Abstract: This technology relates to devices, methods, and non-transitory computer-readable media for predicting affinity of a user towards a product based on personality elasticity of products. The personality elasticity of products means elasticity of affinity towards product with personality profile. The value of elasticity of a product with respect to a personality trait is higher if a difference in personality trait is significant in causing a variation in the affinity towards the product. Further, this technology provides improved product recommendations by correlating personality elasticity of products with big five personality trait model by retrieving user information (like psychographic and demographic details) from different sources. Higher weightage is attributed to more significant personality traits.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for human personality prediction by analyzing information collected from different sources such as social media, call detail record (CDR), email etc. using DISC (dominance, inducement, submission, and compliance) profiling and Big Five personality techniques (openness, conscientiousness, extraversion, agreeableness, and neuroticism). Embodiments in accordance with the present disclosure are further capable of using a self-learning model which learns from user response to the prediction.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for identifying a personality of a human subject based on correlations between personality traits obtained from the subject's physical features, which may include a movement pattern of the subject, such as the subject's gait. Embodiments in accordance with the present disclosure are further capable of providing a recommendation to the subject for a product or service based on the identified personality of the subject.