International Business Machines Corporation

Jignesh K Karia

Mukundan Sundararajan

Pankaj Satyanarayan Dayama

Vishal Awal

Neha Shah

Shilpa Shetty

Jitan S Chandanani

Deepa Dubey

Arindam Dasgupta

Dayama Pankaj Satyanarayan

Sudip Dutta

Suman Das

Ravindranath Nemani

Rahul Hundet

Michael Edward Alexander

Steven Layne Canepa

Priti Srikrishnan

Radhika Sharma

Sandipan Sarkar

Dipayan Ghosh

Pankaj Verma

Debojyoti Das

A condition resolution system is provided for facilitating resolution of a condition for an entity. The system obtains an indication of a condition to be resolved for the entity, groups the entity with one or more other entities into a group of entities, and ascertains one or more options for resolving the condition using the condition to be resolved and option-related data associated with entities of the group of entities. The condition resolution system further evaluates the one or more options to select an option to resolve the condition for the entity, and determines a risk score for the selected option for resolving the condition. The risk score is based on one or more risk factors, and based on the risk score being acceptable, the system initiates an action based on the selected option to resolve the condition for the entity.

Condition resolution system

A system and method for deactivating telephone numbers are presented. The method includes, in response to a request to deactivate a telephone number, communicating a query to a blockchain for the telephone number, wherein a block on the blockchain identifies an organization that had sent a previous message to the telephone number. The method also includes determining, based on a response to the query, the organization and generating and activating a filter configured to stop a future message sent by the organization to the telephone number.

Telephone number deactivation process

In an approach, a processor receives a query relating to mobile number porting on a mobile network that includes a hierarchy including a mobile network operator and a mobile virtual network operator, the query requiring access to customer private data. A processor identifies a minimal number of participants in the mobile network with access to the customer private data. A customer provides a response to the query.

Securely responding to queries involving mobile virtual network operators on a mobile network

A method, computer system, and a computer program product for message directing are provided. A first computer receives a registration of members organized into a first closed group hierarchy. The first computer receives a notification of a sensed change of an element in an environment of the first closed group hierarchy. The first computer receives a first message from an external device. The first message relates to the changed element. The first computer selects a first member of the first closed group hierarchy for receipt of the first message. The selecting is based on message routing guidelines established for the first closed group hierarchy. In response to receiving the notification of the sensed change, the first computer transmits the first message to the selected first member of the first closed group hierarchy.

Routing preference based communication to a closed group hierarchy

Classifier accuracy is increased in machine learning applications by training a machine learning (ML) model including a classifier across classes by determining weighted input points for a contributing set to store the values for true positive and true negative predications. In a following step, input data is provided to the classifier of the machine learning model at runtime, and a classification output is determined from the classifier. For the classification output, values for input during runtime are compared with a sample of inputs stored for training the machine learning model to determine the distance in spread for the classification output. A class is determined from the classification output having a smallest distance and spread. The method can further determine if the class with the smallest distance and spread is a true positive or true negative by comparing the class with the smallest distance and spread with the classification output.

Machine learning classifying of data using decision boundaries

A method, system and apparatus for providing edge data correctness and correctness spread determination, including identifying an incorrectness bias in data received at an edge server of a network through a filter with filter rules, performing corrective measures to the data according to the incorrectness bias that is identified, and learning and automatically updating the filter rules of the filter based on an extent of the incorrectness bias of the data and spread of the incorrectness bias of the data to reduce latency in future data validation of the data.

Edge data correctness and correctness spread determination

Promotional offers are offered to telecom subscribers in roaming network areas by recording promotional preferences of subscribers for receiving promotional calls, forwarding subscriber information from a local network telecom service provider to a roaming network service provider, and measuring with the roaming network telecom service provider the subscribers that are present within a roaming network geography. The subscribers can then be ranked by their duration within the roaming network geography, and promotional pools can be generated for the subscribers within the roaming network based on their preferences. Promotional offers can then be matched to the subscribers in the promotional pools based using the ranking of subscribers and the promotional preferences.

Matching promotions to telecom user preferences using artificial intelligence

Message delivery in cellular roaming scenarios involves a user device activated with a home telecommunications service provider (TSP) that provides cellular service to the user device. The user device is located in a remote location and the user device is activated with a remote TSP providing roaming cellular service to the user device in a remote location on a cellular network of the remote TSP. A process includes, based on the user initiating a transaction with a remote application server that requires user authentication based on delivery of a transactional text message, receiving from the remote application server the transactional text message, encrypting the transactional text message to produce an encrypted transactional text message, and forwarding the encrypted transactional text message to the remote TSP for delivery as a short message service (SMS) text to the user device in the remote location via the cellular network of the remote TSP.

Message delivery in cellular roaming scenarios

A computer-implemented method for virtual agent conversation training is disclosed. The computer-implemented method includes determining a current state of a first stage of a conversation between a pair of virtual agents. The computer-implemented method further includes determining a pivot distance between the current state of the first stage of the conversation and a subsequent, second stage of the conversation. The computer-implemented method further includes responsive to determining that the pivot distance between the current state of the first stage of the conversation and the subsequent, second stage of the conversation is below a predetermined threshold, determining an angle of dislocation with respect to the pivot distance. The computer-implemented method further includes terminating the conversation based, at least in part, on determining that the angle of dislocation is above a predetermined threshold.

Method to improve digital agent conversations

Promotional offers are presented to users by tagging users of the services with the user preferences. Promotional offers are received from vendors. The vendors are classified as being in a home area or roaming areas for the services. The users are tracked through movement of a device for the user that is receiving the services to determine whether the user is in the home area or the roaming areas. Promotional offers from the vendors are matched to the user preferences according to the tagging of the users, wherein the promotional offers are from the home area of the home network or the roaming area of the roaming network.

Matching regional promotions to telecom user preferences using artificial intelligence

A learning model is created using a computer which includes receiving input from a user. The learning model includes comparing the input to the knowledge area in a knowledge database to assess a level of proficiency on topics within the knowledge area. The learning model includes determining topics of knowledge within the knowledge area where a user currently meets a proficiency threshold for one or more topics. A work topic is identified within the knowledge area where the user does not meet the proficiency threshold. Study material is presented to the user for the work topic of the knowledge area using an interactive mechanism. Feedback is received regarding the study material for the work topic from the interactive mechanism from the user. The learning model includes evaluating the feedback from the user to determine a score which indicates when the user meets a proficiency threshold for the work topic.

Computer enabled modeling for facilitating a user learning trajectory to a learning goal

A method, system, and computer program product for consent and content template mapping are provided. The method identifies a content type within a content template. A set of content categories is identified that is associated with the content type. One or more consent templates are identified as associated with one or more of the content type and the set of content categories. The content template is mapped to the one or more consent templates to generate a consent template graph. The method provides a multimedia message to a user based on a consent template associated with the user and the content template.

Consent to content template mapping

A method, system and computer program product for a heuristic determination of in-process damage class control to manage expected output product category. The heuristic technique determines the predicted damages and their ranges while keeping the initial expected defects, the respective classes and range of defect and mitigation. The method dynamically computes a damage mitigation range of operation while being within the overall constraints and completes the computation in smaller number of loops being run at the edge computers so that the manufacturing equipment can operate at a higher velocity for higher quality of the output. The method includes a step of reducing error of the co-efficient and damage counts. An Internet of Things (IoT) based robot is used to mitigate the damages in the manufacturing steps to ensure that the output class of the product remains what was expected at the start despite damages and mitigation measures.

Managing a manufacturing process based on heuristic determination of predicted damages

Origin information for promotional calls is provided by recording caller numbers for parties making the promotional calls; and receiving subscriber numbers for receiving the promotional calls. The subscribers numbers are stored in a database that also includes approved content for the promotional calls to be received by the subscriber. Caller numbers and approved content are matched for the subscriber with a call scrubber including a disturbed ledger. The distributed ledger recording a caller designation attached to the caller numbers indicative of a type for the promotional call. A promotional call is received by the subscriber. The caller identification for the subscriber indicates both the caller numbers and the caller designation that is indicative of the type for the promotional call.

Identifying caller details for promotional voice communication

A method, system, and computer program product for implementing mobile device roaming optimization is provided. The method includes receiving a selection for services associated with a first mobile device provider for activation during travel to a location associated with mobile device roaming attributes with respect to a mobile device of a user. A blockchain structure and a hash masking sensitive data of the user are generated. It is detected that the user and mobile device have traveled to the location and access to the blockchain structure is enabled. Roaming usage attributes of the mobile device are determined. Subsequently, operational functionality of the mobile device at the geographical location is enabled via roaming usage of a network of the second mobile device provider and second hash of consumption related information compliant with data residency is transmitted to the first mobile device provider to facilitate resolution of disputes across entities.

Growing community of inventors

Thane, India

Jignesh K Karia