# US 11,113,595 B2 · On-demand intelligent assistant > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,595 B2 - Document ID: US11113595B2 - Status: Granted - Kind: B2 - Application number: 15/984,682 - Filed: 2018-05-21 - Published: 2019-11-21 - Granted: 2021-09-07 - Earliest claimed: 2018-05-21 - Assignees: The Travelers Indemnify Company - Applicants: The Travelers Indemnity Company - Inventors: Eric Palumberi; David M. Fields; Erik A. Harrold - Web page: https://patentgrep.com/patent/US11113595B2 ## CPC - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G06V 40/172: {Classification, e.g. identification} - G10L 15/08: Speech classification or search - G06F 16/90332: {Natural language query formulation or dialogue systems} - G06F 40/35: Discourse or dialogue representation - G10L 2015/088: {Word spotting} - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract The present disclosure is directed to an on-demand intelligent assistant that obtains physical identifiers of a target individual using information received from sensors. The assistant determines an identity of the target individual using the physical identifiers. The assistant also caches the physical identifiers and the identity as baseline information of the target individual. The assistant further detects keywords used in communications of a user with the target individual. Moreover, the assistant determines that the user desires additional information of the target individual based on the keywords. Additionally, the assistant determines a query for the additional information using the baseline information and the keywords. Further, the assistant retrieves the additional information from a remote database using the query and provides the additional information to the user. ## Claims ### Claim 1 An on-demand intelligent data retrieval system, the system comprising: one or more sensors; an input/output interface device; a processor; and one or more computer-readable data storage devices storing program instructions that when executed by the processor, control the on-demand intelligent data retrieval system to perform operations comprising: obtaining one or more physical identifiers of a target individual using information received from the one or more sensors; determining an identity of the target individual using the one or more physical identifiers; caching the one or more physical identifiers of the target individual and the identity of the target individual in the one or more computer-readable data storage devices as baseline information of the target individual; detecting keywords used in communications of a user with the target individual using speech recognition; determining that the user desires additional information of the target individual based on the keywords; determining, based on one or more of a frequency and a distance of the keywords, a confidence score that the additional information desired by the user corresponds to a predetermined type of information; determining a query for the additional information of the target individual when the confidence score equals or exceeds a predetermined threshold, using the baseline information of the target individual and the keywords; retrieving the additional information of the target individual from a remote database system using the query; and providing, using the input/output interface device, the additional information of the target individual to the user. ### Claim 2 (depends on 1) The system of claim 1, wherein detecting the keywords used in communications of the user with the target individual comprises passively capturing the communications using the one or more sensors. ### Claim 3 (depends on 2) The system of claim 2, wherein determining the query for the additional information of the target individual comprises generating the query by passively obtaining parameters for the query from the user or the target individual. ### Claim 4 (depends on 3) The system of claim 3, wherein retrieving the additional information of the target individual comprises automatically providing the query to the remote database system. ### Claim 5 (depends on 1) The system of claim 1, wherein determining that the user desires additional information of the target individual comprises analyzing the keywords using natural language processing. ### Claim 6 (depends on 1) The system of claim 1, wherein the one or more physical identifiers comprise images or speech obtained from the target individual. ### Claim 7 (depends on 6) The system of claim 6, wherein obtaining the one or more physical identifiers comprises passively obtaining the images or the speech of the target individual. ### Claim 8 (depends on 1) The system of claim 1, wherein determining the identity of the target individual comprises determining the identity of the target individual using facial recognition or speech recognition. ### Claim 9 (depends on 1) The system of claim 1, wherein the operations further comprise obtaining user authorization to provide the additional information of the target individual. ### Claim 10 (depends on 9) The system of claim 9, wherein obtaining the user authorization occurs after retrieving the additional information of the target individual from a remote database system. ### Claim 11 (depends on 1) The system of claim 1, wherein: the one or more sensors comprise a camera and a microphone; the physical identifiers comprise image data obtained using the camera; the keywords comprise speech data obtained using the microphone; and the identity of the target individual comprises an alphanumeric code corresponding to information of the customer stored in the remote database system. ### Claim 12 A method for operating an intelligent assistant, the method comprising: obtaining one or more physical identifiers of a target individual using information received from one or more sensors; determining an identity of the target individual using the one or more physical identifiers; caching the one or more physical identifiers of the target individual and the identity of the target individual as baseline information of the target individual; detecting, using the one or more sensors and speech recognition, keywords used in communications of a user with the target individual; determining that the user desires additional information of the target individual based on the keywords; determining, based on one or more of a frequency and a distance of the keywords, a confidence score that the additional information desired by the user corresponds to a predetermined type of information; determining, when the confidence score equals or exceeds a predetermined threshold value, a query for the additional information of the target individual using the baseline information and the keywords; retrieving the additional information of the target individual from a remote database system using the query; and providing, using the input/output interface device, the additional information of the target individual to the user. ### Claim 13 (depends on 12) The method of claim 12, wherein detecting the keywords used in communications of the user with the target individual comprises passively capturing the communications using the one or more sensors. ### Claim 14 (depends on 13) The method of claim 13, wherein determining the query for the additional information of the target individual comprises generating the query by passively obtaining parameters for the query from the user or the target individual. ### Claim 15 (depends on 14) The method of claim 14, wherein retrieving the additional information of the target individual comprises automatically providing the query to the remote database system. ### Claim 16 (depends on 12) The method of claim 12, wherein determining that the user desires additional information of the target individual comprises analyzing the keywords using natural language processing. ### Claim 17 (depends on 12) The method stem of claim 12, wherein the one or more physical identifiers comprise images or speech obtained from the target individual. ### Claim 18 (depends on 17) The method of claim 17, wherein obtaining the one or more physical identifiers comprises passively obtaining the images or the speech of the target individual. ### Claim 19 (depends on 12) The method of claim 12, wherein determining the identity of the target individual comprises determining the identity of the target individual using facial recognition or speech recognition. ### Claim 20 (depends on 12) The method of claim 12, wherein: the one or more sensors comprise a camera and a microphone; the identity of the target individual comprises an alphanumeric code corresponding to information of the customer stored in the remote database system; obtaining the one or more physical identifiers of the target individual comprises obtaining images of the target individual using the camera; and detecting the keywords comprises obtaining speech of the user using the microphone.