# US 11,907,273 B2 · Augmenting user responses to queries > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,907,273 B2 - Document ID: US11907273B2 - Status: Granted - Kind: B2 - Application number: 17/351,316 - Filed: 2021-06-18 - Published: 2022-12-22 - Granted: 2024-02-20 - Earliest claimed: 2021-06-18 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Indervir Singh Banipal; Shikhar Kwatra; Nadiya Kochura; Sourav Mazumder - Web page: https://patentgrep.com/patent/US11907273B2 ## CPC - G06F 16/3329: Natural language query formulation - G16H 40/67: for remote operation - G06F 16/3344: {using natural language analysis} - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/047: Probabilistic or stochastic networks - G06N 3/0475: Generative networks - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 5/02: Knowledge representation; Symbolic representation - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G16H 30/40: for processing medical images, e.g. editing - G16H 40/63: for local operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/30: for calculating health indices; for individual health risk assessment - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Generating a query response by receiving data for a non-user utterance, determining a question answering (QA) system response to the non-user utterance, receiving data for a user utterance responsive to the non-user utterance, determining a confidence score for the user utterance, determining a deviation between the user utterance and the QA system response, and providing the QA system response according to a combination of the deviation and the confidence score. ## Claims ### Claim 1 A method for generating a query response, the method comprising: receiving, by one or more computer processors, data for an utterance; determining, by the one or more computer processors, a first vector representation for a question answering system response to the utterance; receiving, by the one or more computer processors, data for a user utterance responsive to the utterance; determining, by the one or more computer processors, a second vector representation and a confidence score for the user utterance; determining, by the one or more computer processors, a deviation between the first vector representation and the second vector representation; and providing, by the one or more computer processors, the question answering system response according to a communication context factor and a combination of the deviation and the confidence score. ### Claim 2 (depends on 1) The method according to claim 1, further comprising training, by the one or more computer processors, the question answering system by: receiving user biometric data; and building a knowledge graph incorporating the user biometric data. ### Claim 3 (depends on 1) The method according to claim 1, further comprising providing, by the one or more computer processors, the question answering system response to an originator of the utterance. ### Claim 4 (depends on 1) The method according to claim 1, wherein determining the confidence score includes consideration of an attribute selected from the group consisting of pause gap analysis, tonal analysis, facial expression analysis, personality trait analysis, and combinations thereof. ### Claim 5 (depends on 1) The method according to claim 1, further comprising providing, by the one or more computer processors, the question answering system response to the user according to a response sensitivity. ### Claim 6 (depends on 1) The method according to claim 1, further comprising providing, by the one or more computer processors, the question answering system response according to a user opt-in status. ### Claim 7 A computer program product for generating a query response, the computer program product comprising one or more computer readable storage devices and collectively stored program instructions on the one or more computer readable storage devices, the stored program instructions comprising: program instructions to receive data for an utterance; program instructions to determine a first vector representation for a question answering system response to the utterance; program instructions to receive data for a user utterance responsive to the utterance; program instructions to determine a second vector representation and a confidence score for the user utterance; program instructions to determine a deviation between the first vector representation and the second vector representation; and program instructions to provide the question answering system response according to a communication context factor and a combination of the deviation and the confidence score. ### Claim 8 (depends on 7) The computer program product according to claim 7, the stored program instructions further comprising program instructions to train the question answering system by: receiving user biometric data; and building a knowledge graph incorporating the user biometric data. ### Claim 9 (depends on 7) The computer program product according to claim 7, the stored program instructions further comprising program instructions to provide the question answering system response to an originator of the utterance. ### Claim 10 (depends on 7) The computer program product according to claim 7, wherein determining the confidence score includes consideration of an attribute selected from the group consisting of pause gap analysis, tonal analysis, facial expression analysis, personality trait analysis, and combinations thereof. ### Claim 11 (depends on 7) The computer program product according to claim 7, the stored program instructions further comprising program instructions to provide the question answering system response to the user according to a response sensitivity. ### Claim 12 (depends on 7) The computer program product according to claim 7, the stored program instructions further comprising program instructions to provide the question answering system response according to a user opt-in status. ### Claim 13 A computer system for generating a query response, the computer system comprising: one or more computer processors; one or more computer readable storage devices; and stored program instructions on the one or more computer readable storage devices for execution by the one or more computer processors, the stored program instructions comprising: program instructions to receive data for an utterance; program instructions to determine a first vector representation for a question answering system response to the utterance; program instructions to receive data for a user utterance responsive to the utterance; program instructions to determine a second vector representation and a confidence score for the user utterance; program instructions to determine a deviation between the first vector representation and the second vector representation; and program instructions to provide the question answering system response according to a communication context factor and a combination of the deviation and the confidence score. ### Claim 14 (depends on 13) The computer system according to claim 13, the stored program instructions further comprising program instructions to train the question answering system by: receiving user biometric data; and building a knowledge graph incorporating the user biometric data. ### Claim 15 (depends on 13) The computer system according to claim 13, the stored program instructions further comprising program instructions to provide the question answering system response to an originator of the utterance. ### Claim 16 (depends on 13) The computer system according to claim 13, wherein determining the confidence score includes consideration of an attribute selected from the group consisting of pause gap analysis, tonal analysis, facial expression analysis, personality trait analysis, and combinations thereof. ### Claim 17 (depends on 13) The computer system according to claim 13, the stored program instructions further comprising program instructions to provide the question answering system response to the user according to a response sensitivity. ### Claim 18 (depends on 13) The computer system according to claim 13, the stored program instructions further comprising program instructions to provide the question answering system response according to a user opt-in status.