Abstract: Described herein is a method and model system to improve the quality of search recall in the social media communication posts that often contains the local language words written in Romanized English script. A Deep Learning Transformer based model architecture and algorithm improves the search recall for a given English query. The model is trained to find named entities from post and queries, and these entities are compared to find the matching score using a specially designed model that takes into account the post's recency and its cleanliness score. The cleanliness score is obtained from a trained LSTM based model. The input English query is expanded to a set of equivalent queries by including contextually nearest words. The number of nearest words can be controlled using a slider mechanism.

Abstract: Described herein is a method of context aware chat categorization for business decisions. A business category of the chat presented by the viewer/user on a platform is predicted and groups of chats having similar context and created and arranged in an ordered score indicative of importance. The categorization method includes applying LSTM's in parallel with shared embeddings on said user data, applying an LSTM technique to determine sentence similarity, applying the user's social connectivity in the form of Eigen-centrality of its connectivity on said platform, determining the customised loss function, grouping of chats in categories based on context, context based grouping of chats wherein context is obtained from chat description, and determining attention score based on textual representation of human emotions such as emojis, repetitive characters, and words for each group of chats in a category.

Abstract: A system and method for determining a relationship among data sets. The method includes selecting a first data set from a first table, and a second data set from a second table, forming an inclusion dependency pair of data based on the selected first data set and the selected second data set, determining a resultant of the inclusion dependency pair, and determining a primary key-foreign key relationship between the first data set and the second data set based on the determined resultant.

Abstract: A method and an inclusion dependency determination system (IDDS) for determining inclusion dependency between columns of tables in a target database to establish primary key (PK)-foreign key (FK) relationships among data in the columns with minimized disk input and output operations are provided. The IDDS determines dependency characteristic data (DCD) of each column and arranges the columns by applying one or more predefined rules to the columns based on a minimum value of the data of each column. The IDDS determines pairs of arranged columns that demonstrate a possibility of inclusion dependency based on the DCD and identifies a first column and a second column of each determined pair as a candidate PK and a candidate FK respectively. The IDDS determines inclusion dependency between the candidate PK and the candidate FK on comparing data of the candidate PK with the data of the candidate FK using dynamically determined search techniques.

Abstract: A system and method for determining a relationship among data sets. The method includes selecting a first data set from a first table, and a second data set from a second table, forming an inclusion dependency pair of data based on the selected first data set and the selected second data set, determining a resultant of the inclusion dependency pair, and determining a primary key-foreign key relationship between the first data set and the second data set based on the determined resultant.

Abstract: A method and a machine learning relationship determination system (MLRDS) for determining primary key-foreign key (PK-FK) relationships among data in tables of a target database through machine learning (ML) are provided. The MLRDS selects columns of the tables in the target database and identifies inclusion dependency (ID) pairs from the selected columns. The MLRDS receives training data and validation data from a source database, computes PK-FK features for the inclusion dependency pairs, the training data, and the validation data, and generates trained ML models and validated ML models using the PK-FK features. The MLRDS determines an optimum algorithm decision threshold for a selected machine learning classification algorithm (MLCA), using which the MLRDS determines a resultant on whether the inclusion dependency pair is a PK-FK pair or a non-PK-FK pair. The MLRDS performs majority voting on the resultant for multiple MLCAs to confirm the PK-FK relationships between the inclusion dependency pairs.

Abstract: A method and an inclusion dependency determination system (IDDS) for determining inclusion dependency between columns of tables in a target database to establish primary key (PK)-foreign key (FK) relationships among data in the columns with minimized disk input and output operations are provided. The IDDS determines dependency characteristic data (DCD) of each column and arranges the columns by applying one or more predefined rules to the columns based on a minimum value of the data of each column. The IDDS determines pairs of arranged columns that demonstrate a possibility of inclusion dependency based on the DCD and identifies a first column and a second column of each determined pair as a candidate PK and a candidate FK respectively. The IDDS determines inclusion dependency between the candidate PK and the candidate FK on comparing data of the candidate PK with the data of the candidate FK using dynamically determined search techniques.

Abstract: A method and a machine learning relationship determination system (MLRDS) for determining primary key-foreign key (PK-FK) relationships among data in tables of a target database through machine learning (ML) are provided. The MLRDS selects columns of the tables in the target database and identifies inclusion dependency (ID) pairs from the selected columns. The MLRDS receives training data and validation data from a source database, computes PK-FK features for the inclusion dependency pairs, the training data, and the validation data, and generates trained ML models and validated ML models using the PK-FK features. The MLRDS determines an optimum algorithm decision threshold for a selected machine learning classification algorithm (MLCA), using which the MLRDS determines a resultant on whether the inclusion dependency pair is a PK-FK pair or a non-PK-FK pair. The MLRDS performs majority voting on the resultant for multiple MLCAs to confirm the PK-FK relationships between the inclusion dependency pairs.

Abstract: A computer implemented method and system is provided for classifying a document. A classifier is trained using training documents. A list of first words is obtained from the training documents. A prior probability is determined for each class of multiple classes. Conditional probabilities are calculated for the first words for each class. Confidence thresholds are determined. Confidence grades are defined for the classes using the confidence thresholds. A list of second words is obtained from the document. Conditional probabilities for the list of second words are determined from the calculated conditional probabilities for the list of first words. A posterior probability is calculated for each of the classes and compared with the determined confidence thresholds. Each class is assigned to one of the defined confidence grades based on the comparison. The document is assigned to one of the classes based on the posterior probability and the assigned confidence grades.

Abstract: A computer implemented method and system is provided for classifying a document. A classifier is trained using training documents. A list of first words is obtained from the training documents. A prior probability is determined for each class of multiple classes. Conditional probabilities are calculated for the first words for each class. Confidence thresholds are determined. Confidence grades are defined for the classes using the confidence thresholds. A list of second words is obtained from the document. Conditional probabilities for the list of second words are determined from the calculated conditional probabilities for the list of first words. A posterior probability is calculated for each of the classes and compared with the determined confidence thresholds. Each class is assigned to one of the defined confidence grades based on the comparison. The document is assigned to one of the classes based on the posterior probability and the assigned confidence grades.

Abstract: Disclosed herein is a method of grouping similar supplier names together in a database. The syntactical errors in the supplier names are corrected. The supplier names are grouped after correcting the syntactical errors. The abbreviations in the supplier names are captured. The ordering, pronunciation and stemming errors in the supplier names are corrected. A matching algorithm that matches and compares two supplier names is applied that comprises the steps of grouping supplier names based on first set of characters in the supplier names and calculating a matching score between the two supplier using Levenshtein distance between the two supplier names, along with the supplier names' sound codes obtained from a modified metaphone algorithm, length of each word, position of matching and mismatching characters, and stem of words in the supplier names. The matching scores are compared with set thresholds in order to further group the supplier names into clusters.

Abstract: Disclosed herein is a computer implemented method and system for grouping spend items in a list of said spend items, and for detecting outliers. The spend items entered into the spend database are phonetically sorted and grouped into second level clusters by the spend data clustering engine. In the first level of clustering, first level clusters are created by matching the spend items using generated word tokens and sorted sound codes. The unique spend items, in the list generated after first level clustering, are further matched to create second level clusters. The first level clusters are updated based on the second level of clustering. In order to determine discrepancies in clustering and spend, statistically deviating outliers are detected in each second level cluster. This engine provides clustering at configurable levels of accuracy. The engine's specific combination of word token and sound code matching provides accurate results for spend items.

Abstract: Disclosed herein is a computer implemented method and system that progressively relaxes search terms provided by a user. Data of predefined types is stored in a database. The data is obtained by uniquely modifying data previously stored in the database, based on the predefined types. Search terms of predefined types are accepted from the user. The search terms are compared with the stored data to find exact matches, if length of the search terms exceeds a predefined value. On not finding exact matches, the accepted search terms are modified uniquely based on the predefined types to structure first alternative queries. The first alternative queries are compared with the stored data to find exact matches. On not finding exact matches, the first alternative queries are modified based on the predefined types to structure second alternative queries. The second alternative queries are compared with the stored data to find approximate matches.

Abstract: Disclosed herein is a computer implemented method and system that progressively relaxes search terms provided by a user. Data of predefined types is stored in a database. The data is obtained by uniquely modifying data previously stored in the database, based on the predefined types. Search terms of predefined types are accepted from the user. The search terms are compared with the stored data to find exact matches, if length of the search terms exceeds a predefined value. On not finding exact matches, the accepted search terms are modified uniquely based on the predefined types to structure first alternative queries. The first alternative queries are compared with the stored data to find exact matches. On not finding exact matches, the first alternative queries are modified based on the predefined types to structure second alternative queries. The second alternative queries are compared with the stored data to find approximate matches.

Abstract: Disclosed herein is a computer implemented method and system for grouping spend items in a list of said spend items, and for detecting outliers. The spend items entered into the spend database are phonetically sorted and grouped into second level clusters by the spend data clustering engine. In the first level of clustering, first level clusters are created by matching the spend items using generated word tokens and sorted sound codes. The unique spend items, in the list generated after first level clustering, are further matched to create second level clusters. The first level clusters are updated based on the second level of clustering. In order to determine discrepancies in clustering and spend, statistically deviating outliers are detected in each second level cluster. This engine provides clustering at configurable levels of accuracy. The engine's specific combination of word token and sound code matching provides accurate results for spend items.

Abstract: Disclosed herein is a method of grouping similar supplier names together in a database. The syntactical errors in the supplier names are corrected. The supplier names are grouped after correcting the syntactical errors. The abbreviations in the supplier names are captured. The ordering, pronunciation and stemming errors in the supplier names are corrected. A matching algorithm that matches and compares two supplier names is applied that comprises the steps of grouping supplier names based on first set of characters in the supplier names and calculating a matching score between the two supplier using Levenshtein distance between the two supplier names, along with the supplier names' sound codes obtained from a modified metaphone algorithm, length of each word, position of matching and mismatching characters, and stem of words in the supplier names. The matching scores are compared with set thresholds in order to further group the supplier names into clusters.