International Business Machines Corporation

[24]7.ai, Inc.

Nitin Singh

Pankaj Satyanarayan Dayama

Vinayaka D Pandit

Rishi Saket

Dhinakaran Vinayagamurthy

Shivkumar Kalyanaraman

Sukanya Randhawa

Santosh Ravi Kiran Penubothula

Padmanabha Venkatagiri Seshadri

Amith Singhee

Kedar Kulkarni

Abhishek Singh

Satyam Dwivedi

Prabuchandran Krithivasan Jayachandran

Kameshwaran Sampath

Rajagopala Udupa

Kavita Rai Dutta

One embodiment provides a method, including: receiving, from a user at a collaboration platform, a request to perform a computation; generating a workflow comprising a sequence of steps for performing the computation; identifying potential data sources comprising the type of data and able to assist in performing at least one of the sequence of steps of the workflow; selecting computation data sources that collaborate to perform the computation, wherein the selecting is performed dynamically and based upon characteristics of a network created by the collaboration platform and between the computation data sources; and facilitating performance of the computation by the computation data sources using data of the computation data sources, wherein during performance of the computation the computation data sources collaborate within the network to perform the workflow while maintaining individual privacy of the data of the computation data sources and providing proof verifying a trustworthiness of the computation.

Platform for dynamic collaborative computation with confidentiality and verifiability

One embodiment provides a method, including: receiving, at a service provider and from a user, a request for computation of a function, wherein the request includes a description of the function to be computed and requirements of the user; identifying, from data sources accessible to the service provider, a plurality of data sources to participate in the computation in view of the requirements and the description of the function, wherein each of the plurality of data sources includes data of a data owner and constraints on use of the data; identifying a multi-party computation protocol and parameters of the multi-party computation protocol for performing the computation; and running the computation of the function using the data of the plurality of data sources and in view of the requirements of the user and the constraints of the plurality of data sources.

Automation of multi-party computation as a service according to user regulations and requirements

An example operation may include one or more of generating, by an executing client, a blockchain transaction comprising an anonymous rating, a proof, a nullifier, and a root node value, receiving, by a smart contract, the blockchain transaction, the anonymous rating related to an authorizing client, verifying the proof with the root node value and the nullifier, verifying that the root node value is a current or a previous merkle tree root node value, adding the anonymous rating to a shared ledger, marking the nullifier as used, and storing the marked nullifier to the shared ledger.

Anonymous database rating update

An example operation may include one or more of receiving, from an executing client, a blockchain transaction comprising an anonymous rating related to an authorizing client, a merkle tree root node value, a proof, and a nullifier, and in response, executing, by a smart contract, a valid historical value assert call on a lookback key storing the merkle tree root node value, verifying, through a valid historical value assert call, that the merkle tree root node value is a current or previous value of the merkle tree root node value, verifying the proof with the merkle tree root node value and the nullifier, adding the anonymous rating to a shared ledger, marking the nullifier as used, and storing the marked nullifier to the shared ledger.

Anonymous rating structure for database

Methods, systems, and computer program products for verifying confidential machine learning models are provided herein. A computer-implemented method includes obtaining (i) a set of training data and (ii) a request, from a requestor, for a machine learning model, wherein the request is accompanied by at least a set of test data; obtaining a commitment from a provider in response to the request, the commitment comprising a special hash corresponding to parameters of a candidate machine learning model trained on the set of training data; revealing the set of test data to the requestor; obtaining, from the requestor, (i) a claim of performance of the candidate machine learning model for the test data and (ii) a proof of the performance of the candidate machine learning model; and verifying the claimed performance for the requestor based on (i) the special hash and (ii) the proof of the claimed performance.

Verifying confidential machine learning models

Methods, systems, and computer program products for anomaly and mode inference from time series data are provided herein. A computer-implemented method includes receiving time-series sensor data for each one of a group of devices; extracting a set of states for each device in the group from the time-series sensor data; constructing a state-transition graph for each of the devices, wherein each of the state-transition graphs comprises nodes corresponding to each state in the set and edges corresponding to a probability of transition between the extracted states over time; identifying, for each set, a given state as one of: a mode, a normal state and an anomalous state based on the state-transition graph; and detecting one or more anomalous devices in the group by computing similarities between different devices in the group, based at least in part on the determined state-transition graphs.

Anomaly and mode inference from time series data

An example operation may include one or more of receiving, by a document validation node, documents from a plurality of document owner nodes over a blockchain network, generating, by the document validation node, commitments for the documents on the blockchain network, deriving, by the document validation node, proofs to verify predicates of the documents, and generating, by the document validation node, a document relationship graph (DRG) based on the commitments and the predicates.

Document validation

An example operation may include one or more of storing a tree structure via a blockchain storage, the tree structure comprising anonymous behavior data of a plurality of blockchain participants stored in a plurality of nodes in a hierarchical structure, receiving a request to add new anonymous behavior data to the tree structure, the request comprising a zero-knowledge proof generated by a blockchain participant, identifying an active leaf on the tree structure which stores previously recorded anonymous behavior data of the blockchain participant associated with the request based on the zero-knowledge proof, generating a new active leaf for the blockchain participant based on the new anonymous behavior data and the previously recorded anonymous behavior, and storing the new active leaf as a leaf node on the tree structure in the blockchain storage.

Privacy-preserving anomalous behavior detection

One embodiment provides a method, including: obtaining historical information for equipment having at least one control, wherein the historical information indicates a setting for the at least one control during operation of the equipment and identifies operating performance of the equipment corresponding to the indicated setting; receiving a goal for the equipment, wherein the goal is related to a desired operating performance of the equipment; identifying, a plurality of sets of contiguous good reference segments, wherein a contiguous set of good reference segments comprises a plurality of operating time segments where the desired operating performance goal was achieved for a predetermined of time; identifying, a subset of sets comprising reference segments that are achievable from a current operating state of the equipment; selecting, a reference segment that is attainable based upon exogenous factors related to an operating environment of the equipment; and providing a recommendation to an operator of the equipment.

Identifying equipment operating control settings using historical information

An example operation may include one or more of receiving a content request to add a content to a blockchain storage structure implemented on a blockchain database, temporarily storing the content of the content request in a queue implemented via the blockchain database based on when the request is received, receiving a request to flush the queue which is invoked by chaincode, and in response to the flush request, removing the content from the queue and adding the content to the blockchain storage structure.

Conflict resolution for blockchain storage structure

A method and apparatus for providing multimodal interaction assistance to customers seeking assistance from agents of an enterprise is disclosed. The method includes augmenting an ongoing voice interaction between a caller and an automated agent with a speech synchronized web session. A session identifier and contextual information in relation to the speech synchronized web session are stored in a database. A display of an option to interact with a human agent is caused during the ongoing speech synchronized web session. In response to a selection of the option by the caller, a co-browsing of the speech synchronized web session by the caller and the human agent is facilitated. The co-browsing of the speech synchronized web session and the contextual information stored in relation to the speech synchronized web session enable the human agent to provide assistance to the caller.

Method and apparatus for providing multimodal interaction assistance to callers

One embodiment provides a method, including: determining a light profile of light falling onto a solar module, wherein the light profile identifies (i) a position of the light with respect to the solar module and (ii) the intensity of the light with respect to solar panels within the solar module; identifying at least one solar panel within the solar module having partial light coverage; and changing the light profile by shaping the reflection of the light onto the solar module created by a flexible curved reflector in proximity to the solar module, thereby increasing the amount of light falling onto said at least one solar panel within the solar module; the changing the light profile comprising modifying the geometry of the flexible curved reflector by activating at least one actuator to move at least a portion of the flexible curved reflector.

Dynamically controlled curved solar reflectors for flexible photovoltaic generation

Methods and systems for cost-effective precision solar farming with mobile photonic harvesters are provided herein. An example computer-implemented method includes automatically determining, for each of multiple solar photovoltaic modules within a system, the angle of captured solar radiation with respect to the surface of the solar photovoltaic module, wherein the system comprises (i) the multiple solar photovoltaic modules and (ii) multiple moveable reflective surfaces used in conjunction with at least some of the multiple solar photovoltaic modules; automatically detaching one or more of the reflective surfaces from one or more respective first positions within the system based on the determined angles of captured solar radiation; and automatically attaching the one or more detached reflective surfaces to one or more respective second positions within the system based on the determined angles of captured solar radiation, such that the amount of solar radiation captured by the solar photovoltaic module is increased.

Growing community of inventors

Bengaluru, India

Nitin Singh