International Business Machines Corporation

Pratyush Kumar

Sampath Dechu

Mohit Jain

Vijay Ekambaram

Ramachandra Kota

Shivkumar Kalyanaraman

Ashok Pon Kumar Sree Prakash

Nitin Kumar Gupta

Sachindra Joshi

Pankaj Satyanarayan Dayama

Ajay Gupta

Senthil Kumar Kumarasamy Mani

Neelamadhav Gantayat

Samarth Bharadwaj

Vikas Chandan

Sukanya Randhawa

Anup Agarwal

Jeremy R Fox

Fang Lu

Kuntal Dey

Zachary A Silverstein

Clement Decrop

Amith Singhee

Ramasuri Narayanam

Karthik Sankaranarayanan

Yedendra Shrinivasan

Vikas V Joshi

Anamitra Roy Choudhury

Lohit K Namboodiri

Megha Nawhal

Anshul Bhavesh Shah

Gyanendra Sharma

The present invention may include a computing device that receives root data, where the root data comprises a plurality of datasets. The computing device determines a context of each dataset within the plurality of datasets. The computing device identifies one or more users based on monitoring behavior of the one or more users related to each dataset. The computing device appends metadata associated with each dataset within the plurality of datasets with the determined context and the one or more identified users and setts access restrictions to each dataset in the metadata based on the context and the one or more identified users.

Contextualization of organization data and handling storage quantification

One embodiment provides a method, including: utilizing at least one processor to execute computer code that performs the steps of: providing, on a display device, a communications window, wherein the communications window comprises a request for user input to start a conversation with an online assistant; receiving a user input identifying a request by the user to be completed by the online assistant; updating, based upon the request, the communications window, wherein the updated communications window comprises a summary of the conversation including prepopulated variable terms and allows user interaction to adjust the summary including adjustment of the prepopulated variable terms; and iteratively updating the communications windows based upon user input adjusting the summary. Other aspects are described and claimed.

Adaptive communications display window

Methods, systems, and computer program products for user-preference driven control of electrical and thermal output from a photonic energy device are provided herein. A system includes a solar photovoltaic module, and a fluid positioned on the solar photovoltaic module. The system also includes configurable reflective surfaces that collect and distribute direct solar and diffuse solar radiation across multiple portions of the fluid and/or portions of the solar photovoltaic module. Additionally, the reflective surfaces is physically connected to the solar photovoltaic module at an angle that is variable in relation to the surface of the solar photovoltaic module. Further, the system includes a controller that modulates an amount of thermal output and/or electrical power output generated by the solar photovoltaic module by transmitting a signal to adjust at least one variable pertaining to the fluid, and transmitting a signal to adjust at least one variable pertaining to the reflective surfaces.

User-preference driven control of electrical and thermal output from a photonic energy device

Methods, systems, and computer program products for exercise monitoring and coaching using audio devices are provided herein. A computer-implemented method includes processing a first set of one or more auditory prompts, wherein the first set of auditory prompts pertains to initiation of at least one activity with respect to a user; detecting, in connection with the first set of auditory prompts, one or more sets of movements being performed by the user, wherein said detecting comprises (i) emitting one or more acoustic waves towards the user and (ii) processing reflection of the one or more acoustic waves from the user; classifying, based on said detecting, the one or more sets of movements as one or more predefined exercises; and generating and outputting a second set of auditory prompts to the user, wherein the second set of auditory prompts pertains to the predefined exercises being performed by the user.

Exercise monitoring and coaching using audio devices

A blockchain configuration may be used to store a distributed ledger for information security and accessibility. One example method of operation may include determining a proof-of-work via a device and using a predefined set of nonce values when determining the proof-of-work, storing the proof-of-work on a blockchain, and broadcasting the proof-of-work as a broadcast message.

Proof-of-work for smart contracts on a blockchain

A method, computer system, and computer program product for a conversational system driven by a semantic network with a library of templated query operators are provided. The embodiment may include loading one or more operators for the conversational system to the library of templated query operators. The embodiment may also include receiving a query statement from a user. The embodiment may further include identifying an operator from the library to process the received query. The embodiment may also include identifying one or more input terms for the identified operator within the received query. The embodiment may further include generating one or more output terms based on processing the one or more identified input terms using the identified operator. The embodiment may also include generating a natural language response to the received query based on the one or more generated output terms.

Designing conversational systems driven by a semantic network with a library of templated query operators

Aspects of the present disclosure concern cognitive interview management. Audio data from an interviewer in an interview is received. The audio data is processed by converting the audio data into structured text. The structured text is then analyzed to identify questions in the structured text. The structured text data is also analyzed to determine at least one tonal dimension, at least one class dimension, and at least one difficulty dimension of the structured text. A feature vector is then generated having the determined dimensions. A reference feature vector is received having at least one reference tonal dimension, at least one reference class dimension, and at least one reference difficulty dimension. The generated feature vector and reference feature vector are then compared. A determination is made whether the comparison satisfies a match threshold, and in response to the comparison satisfying the match threshold, the interviewer is selected for a panel.

Feature vector profile generation for interviews

One embodiment provides a method, including: obtaining a plurality of chatlogs involving a conversational agent, wherein the plurality of chatlogs represent interactions between users and the conversational agent; identifying dialog states of the conversational agent, wherein each dialog state corresponds to a possible response by the conversational agent; generating a dialog tree including one or more dialog flows of the conversational agent, wherein a dialog flow represents an interaction that occurred between the conversational agent and a user; and providing a conversational reflow user interface for a conversational reflow system allowing execution of the conversational agent to mimic interactions between users and the conversational agent, wherein the conversational reflow system advances through dialog flows based upon input provided by a user at the conversational reflow user interface and the conversational reflow user interface displays output based upon the dialog states of the dialog tree.

Conversational agent dialog flow user interface

Methods, systems and computer program products for speech and gesture interaction of multiple users with devices using voice activated interfaces are provided herein. A computer-implemented method includes transmitting a pilot signal from a device comprising a voice activated interface, the pilot signal having a frequency, detecting motion of at least one user around the device, associating the detected motion with a gesture, and performing a function in response to the gesture. Detecting the motion includes receiving a reflected signal of the pilot signal caused by the motion of the at least one user, and detecting a shift in the reflected signal from the pilot signal, wherein detecting the shift comprises determining one or more differences between a waveform corresponding to the pilot signal and a waveform corresponding to the reflected signal.

Multiple user interaction with audio devices using speech and gestures

One embodiment provides a method, including: obtaining, at an information handling device, an image of a person; determining physical characteristics of the person by analyzing the image; receiving an image of at least one selected piece of jewelry, the selected jewelry having a given jewelry profile, wherein the jewelry profile describes features and construction of the selected piece of jewelry; overlaying the image of the at least one selected piece of jewelry onto an image of the person, wherein the overlaying comprises analyzing resizing the image of the at least one selected piece of jewelry to match the physical characteristics of the person, in view of the jewelry profile of the at least one selected piece of jewelry; and providing, on a display of the information handling device, an output image of the image of the person comprising the overlaid image of the at least one piece of jewelry.

Hybrid virtual and physical jewelry shopping experience

Methods, systems, and computer program products for systematic browsing of automated conversation exchange program knowledge bases are provided herein. A computer-implemented method includes generating one or more initial questions to be submitted to an automated conversation exchange program; generating one or more natural language variants of the initial questions; submitting the one or more natural language variants of the initial questions to the automated conversation exchange program; identifying one or more valid responses returned by the automated conversation exchange program in response to the submitted natural language variants of the initial questions; deriving one or more items of data from the identified valid responses; storing the derived items of data in an automated conversation exchange program knowledge base; and systematically browsing the automated conversation exchange program knowledge base in connection with one or more application tasks.

Systematic browsing of automated conversation exchange program knowledge bases

A blockchain configuration may be used to store a distributed ledger for an energy optimization procedure. One example method of operation may include measuring energy metrics associated with network devices operating on a network via meter devices, identifying potential changes to existing energy usage of the network based on the energy metrics, logging the energy metrics and the potential changes as part of a distributed ledger, and storing the distributed ledger in a blockchain block.

Autonomous peer-to-peer energy networks operating on a blockchain

Methods, systems, and computer program products for search engine optimization techniques are provided herein. A computer-implemented method includes cataloging functionalities of one or more automated conversation exchange programs via a set of hypertext markup language pages, wherein the automated conversation exchange programs comprise computer programs capable of carrying out conversational exchanges with a user; semantically interlinking the set of hypertext markup language pages by adding, to each of the pages, hyperlinks to one or more of the other pages based on semantic similarity of page content; facilitating discoverability, via search engines, of the hypertext markup language pages based on the semantic interlinking; and redirecting a user search visit to one of the discoverable hypertext markup language pages, via one of the search engines, to one of the automated conversation exchange programs, wherein redirecting the user search visit to the automated conversation exchange program comprises providing the automated conversation exchange program with context information pertaining to the user search via deep conversational links.

Search engine optimization techniques

One embodiment provides a method, including: utilizing at least one processor to execute computer code that performs the steps of: using an electronic device to engage in an interactive session between a user and a virtual assistant; receiving, at the electronic device, audio input from the user, wherein the audio input comprises a problem-solving query corresponding to a request by the user for assistance in solving a problem related to at least one object; parsing the audio input to identify at least one annotated video file corresponding to the at least one object and the problem-solving query; determining a state of the object and a location in the at least one annotated video file corresponding to the state of the object; and providing, to the user and based on the location in the at least one annotated video file, instructional output related to the problem-solving query.

Interactive voice based assistant for object assistance

One embodiment provides a method, including: receiving user voice input comprising a user command to perform an action; determining whether the user command comprises a high risk command or a low risk command; providing a first audible query and a second audible query, wherein the first audible query and the second audible query are related to a verification request for verifying that the user voice input is provided by a user and wherein an answer corresponding to one of the first audible query and the second audible query is stored in a system; receiving a first voice answer input responsive to the first audible query and a second voice answer input responsive to the second audible query; and performing, responsive to determining that at least one of the first voice answer input and the second voice answer input matches the answer stored in the system, the action.

Growing community of inventors

Chennai, India

Pratyush Kumar