International Business Machines Corporation

Microsoft Technology Licensing, LLC

Sinch Germany Gmbh

Neeraj Ramkrishna Singh

Soma Shekar Naganna

Abhishek Seth

Geetha Sravanthi Pulipaty

Shettigar Parkala Srinivas

James Albert O'Neill, Jr

Martin Oberhofer

Mohammad Khatibi

Kausik Ghatak

Ganessh Kumar R P

Priyanka Goel

Swathi Karri

Scott Schumacher

Kalapriya Kannan

Berthold Reinwald

Hima Patel

Balaji Ganesan

Bhomik Pande

Devbrat Sharma

Prabhakaran Ramalingam

Muhammed Abdul Majeed Ameen

Alexandre Luz Xavier Da Costa

Mark Wang

Marut Gaonkar

Saud Alam

Ruolin Wu

One embodiment provides a computer implemented method, including: obtaining an information document corresponding to an entity, wherein the information document includes redacted information spans; identifying an entity type for each of the redacted information spans, wherein the entity type identifies a relationship between a redacted information span and at least one other entity within the information document; replacing the redacted information spans with replacement entities corresponding to the entity type of a given redacted information span, wherein the replacing is performed in view of a frequency distribution of actual information and wherein the replacing includes maintaining relationships of the redacted information spans; and controlling bias within the replacement entities, wherein the controlling includes detecting bias within the replacement entities.

Generation of training data from redacted information

A system for searching and/or linking corresponding electronic data records includes: choosing, for a target electronic data record, a group of candidate electronic data record(s) for comparison; selecting a first set of one or more attributes for comparison between the target record and the group of candidate record(s), and choosing a threshold for the comparisons. The system further includes comparing attribute(s) of the target electronic data record to attribute(s) of the group of candidate records; and scoring the comparison of the attribute(s) of the target electronic data record to the attribute(s) of the candidate records. The system further can include configuring a sieve to apply to electronic records, wherein the sieve has a second set of attribute(s) and a corresponding threshold for each of the second set of attribute(s), and applying the sieve to one or more electronic data records to identify records.

Dynamic electronic data record resolution in electronic data environments

One or more trained embedding generation artificial intelligence models are executed to generate a plurality of record attribute embeddings. The plurality of record attribute embeddings represents a plurality of attributes of data of a plurality of records. Grouping of the plurality of record attribute embeddings is performed. The grouping of a record attribute embedding includes grouping attribute values of the record attribute embedding into one or more groups of attribute values. The performing grouping provides a plurality of groups of attribute values for the plurality of record attribute embeddings. Selected records are compared to provide a set of matched records. The comparing, based on a group of attribute values, includes comparing records that include one or more attribute values grouped in the group of attribute values providing a subset of matched records of the set of matched records. The set of matched records is stored in an accessible computer location.

Records processing based on record attribute embeddings

An approach for accessing multi-attribute data records of a master data management system. The method comprises: enhancing the master data management system with one or more search engines for enabling data record access. A request of data may be received at the master data management system. A set of one or more of the multiple attributes, referenced in the received request, may be identified. A combination of one or more of the search engines of the master data management system, whose performances for searching values of at least part of the set of attributes fulfil a current selection rule may be selected. And, the request may be processed using the combination of search engines. At least part of the results of the processing may be provided, and the selection rule may be updated based on user operations on the provided results, the updated selection rule becoming the current selection rule.

Method for accessing data records of a master data management system

A method, a structure, and a computer system for mapping data fields. The exemplary embodiments may include, based on determining that a first data set and a second data set contain homogenous data, mapping at least one column of the first data set to at least one column of the second data set based on comparing at least one of relative column position and unique value sets. Based on determining that the first data set and the second data set contain heterogeneous data, the exemplary embodiments may include mapping the at least one column of the first data set to the at least one column of the second data set based on a difference between distribution signatures of unique value sets within each of the first data set and the second data set being less than a threshold.

Mapping of heterogeneous data as matching fields

A computer-implemented method increases the efficiency of matching records from two sources. The method includes identifying a first source and a second source wherein each of the sources include one or more records and each record includes one or more attributes. The method further includes determining, based on a corpus, the one or more attributes and generating, based on the attributes, a set of feature vectors which vectors represent the one or more attributes. The method includes comparing each record in the first source against each record in the second source. The method further includes generating, in response to the comparing, a link confidence. The method also includes linking, in response to the link confidence being above a linking threshold, the associated records. The method includes determining a first feature vector of the set of feature vectors used in the linking, and outputting a set of results.

Feature vector generation for probabalistic matching

Computer system for performing biometric matching in a way that balances accuracy level required in the biometric matching against computing resources (for example, processor cycles) that will be needed to match authentication requesters with profiles of authorized users. In some embodiments, this is achieved by controlling the number of clusters and/or the number of clusters to be searched pursuant to an authentication request.

Automatic configuration switching in biometric matching

Servers configured to perform automatic summarization of content in electronic messages are discloses herein. In one embodiment, upon receiving an email, an server determines whether the incoming email is a templated message. In response to determining that the incoming email is not a templated message, the server classifies one or more sentences in the email as a statement of decision, judgement, inference, or fact, cluster the classified statements into clusters, and select one or more of the clusters to automatically generate summaries of the incoming email. The server can then insert data representing the generated summaries into the email before transmitting the email to a destination via a computer network.

Automatic summarization of content in electronic messages

Methods, computer program products and/or systems are provided that perform the following operations: obtaining payload attribute fields; determining potential matching fields from the payload attribute fields; determining a matching function for each of the potential matching fields; determining an attribute score for each of the potential matching fields based on the matching function; obtaining a score list for a reference data set; determining a correlation of the attribute score for each of the potential matching fields with the reference data set score list; selecting new matching fields from the potential matching fields based at least in part on the correlation; determining an optimal weight for each of the selected new matching fields; selecting attribute fields for matching from the selected new matching fields based on a threshold rate for false positives and false negatives; and providing the attribute fields for matching and the associated optimal weight for the attribute fields.

Auto detection of matching fields in entity resolution systems

A method for receiving an additional dataset including a plurality of additional data records; determining a record type using classifiers and an internal domain knowledge corpus; dividing the plurality of additional data records into a plurality of indexing groups; assigning the given additional data record to a match set based on completeness and similarity of natures of attributes of the given additional data record; and assigning the given additional data record to and a comparison group based on completeness and similarity of natures of attributes of the given additional data record.

Automatic generation of a matching algorithm in master data management

A method is disclosed for a database system that includes a set of data blocks comprising records having attributes. The set of data blocks are instances of at least one block type. The block type is defined by a subset of one or more attributes of the attributes. An instance of the block type comprises records having one distinct group of values of the subset of attributes. The method includes detecting that a subset of one or more data blocks of the block type, of the set of data blocks, reached a first maximum number of records. The method includes determining an additional attribute of the attributes to define a new block type by the combination of the additional attribute and the subset of attributes that define the block type. The method includes creating one or more data blocks which are instances of the new block type.

Method for dynamic data blocking in a database system

Configuring a data management system by receiving user interaction data associated with search results associated with a first system configuration, identifying a usage pattern in the user interaction data using a first machine learning model, and altering the first system configuration according to the usage pattern.

Data management configuration tuning through link preference detection

An approach is provided for providing optimized identification of duplicate data in a networked computing environment. An aggregate feature vector is created that is specific to an attribute of the data (e.g., a field that holds specific informational content). The aggregate feature vector has a set of dimensions that each define a specific comparison function used to test for similarity between data entries in the attribute. Each dimension in the aggregate feature vector is assigned an effectiveness, and a cost is computed for each dimension. Based on these two, a subset of dimensions is selected to form an optimized feature vector. This optimized feature vector can then be used to analyze a dataset to find matching data.

Quality-performance optimized identification of duplicate data

Indexing and matching records in a data management system by defining entity indexing attributes associated with system records, receiving an incoming data entity, selecting a set of entity candidates according to the entity indexing attributes, matching the incoming entity to an entity candidate, generating an analysis of the entity candidate selection according to entity attribute effectiveness, and revising the entity indexing attributes according to the analysis.

Defining indexing fields for matching data entities

Candidate data record prioritization for match processing includes identifying candidate records for use in match processing to determine records that match to an incoming record. The candidates are grouped into buckets according to bucket roles, with each bucket correlating to a bucket role, and with each bucket role being defined by a unique record attribute set. The method obtains an effectiveness score for each of the bucket roles. The scores are measures of effectiveness of the bucket roles in identifying candidates that match to incoming data records. The method establishes an order of priority in which to process the candidates by prioritizing the buckets into an order based on the effectiveness scores for the bucket roles. The process then commences match processing to process the candidates in the established order of priority where the match processing processes candidates of a higher priority bucket before processing candidates of lower priority buckets.

Growing community of inventors

Bengaluru, India

Neeraj Ramkrishna Singh