# US 2020/0401466 A1 · Facilitation of real time conversations based on topic determination > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401466 A1 - Document ID: US20200401466A1 - Status: Published application - Kind: A1 - Application number: 16/446,980 - Filed: 2019-06-20 - Published: 2020-12-24 - Earliest claimed: 2019-06-20 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Keith Gregory FROST; Stephen Arthur BOXWELL; Stanley John VERNIER; Kyle Matthew BRAKE - Web page: https://patentgrep.com/patent/US20200401466A1 ## CPC - G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications} - G06F 40/30: Semantic analysis - G06F 40/279: Recognition of textual entities - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit - G10L 15/1822: {Parsing for meaning understanding} - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - H04L 65/1066: Session management - H04L 65/403: Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Methods, systems and computer program products for facilitating real time conversations based on topic determination are provided. Aspects include receiving one or more user topic profiles. Aspects also include receiving an audio recording of a conversation obtained from one or more audio sensors. Aspects also include converting the audio recording of the conversation to text. Aspects also include determining a topic of the conversation by applying a topic model to the text. Aspects also include determining one or more potentially interested users based on the topic of the conversation and the one or more user topic profiles. Aspects also include notifying the one or more potentially interested users that the conversation is occurring. ## Claims ### Claim 1 A computer-implemented method comprising: receiving one or more user topic profiles; receiving an audio recording of a conversation obtained from one or more audio sensors; converting the audio recording of the conversation to text; determining, by applying a topic model to the text, a topic of the conversation; determining, based on the topic of the conversation and the one or more user topic profiles, one or more potentially interested users; and notifying the one or more potentially interested users that the conversation is occurring. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein notifying a user of the one or more potentially interested users that the conversation is occurring comprises: causing an audio output device associated with the user to play a sound indicative of the topic of the conversation; and providing the user with an option of listening to the conversation live via the audio output device associated with the user. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein notifying a user of the one or more potentially interested users that the conversation is occurring comprises: causing an audio output device associated with the user to play a portion of the audio recording; and providing the user with an option of listening to the conversation live via the audio output device associated with the user. ### Claim 4 (depends on 3) The computer-implemented method of claim 3 further comprising: responsive to receiving a user-input opt-in signal from a device associated with the user, electronically joining the user to the conversation. ### Claim 5 (depends on 4) The computer-implemented method of claim 4, wherein the audio output device comprises noise-reducing headphones. ### Claim 6 (depends on 1) The computer-implemented method of claim 1 further comprising: applying a change-point algorithm to determine a new topic of conversation; determining, based on the new topic of the conversation and the one or more user topic profiles, a new set of one or more potentially interested users; and notifying the new set of one or more potentially interested users that the conversation is occurring. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the one or more audio sensors comprises one or more microphones positioned within an office environment. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the one or more audio sensors comprise microphones associated with a persistent video conferencing application operating at multiple locations. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein determining the topic of conversation by applying a topic model to the text comprises: generating one or more subject scores, wherein each subject score is associated with a subject of conversation; determining that a given subject score of the one or more subject scores exceeds a predetermined threshold; and selecting a subject of conversation associated with the given subject score as the topic of conversation. ### Claim 10 (depends on 9) The computer-implemented method of claim 9, wherein each user topic profile of the one or more user topic profiles comprises one or more subjects of interest and determining one or more potentially interested users comprises: determining a subset of the one or more user topic profiles that comprises user topic profiles comprising a subject of interest that matches the topic of conversation; and designating one or more users associated with the subset of the one or more user topic profiles as being the one or more potentially interested users. ### Claim 11 A system comprising: a processor communicatively coupled to a memory, the processor configured to: receive one or more user topic profiles; receive an audio recording of a conversation obtained from one or more audio sensors; convert the audio recording of the conversation to text; determine, by applying a topic model to the text, a topic of the conversation; determine, based on the topic of the conversation and the one or more user topic profiles, one or more potentially interested users; and notify the one or more potentially interested users that the conversation is occurring. ### Claim 12 (depends on 11) The system of claim 11, wherein notifying a user of the one or more potentially interested users that the conversation is occurring comprises: causing an audio output device associated with the user to play a sound indicative of the topic of the conversation; and providing the user with an option of listening to the conversation live via the audio output device associated with the user. ### Claim 13 (depends on 11) The system of claim 11, wherein notifying a user of the one or more potentially interested users that the conversation is occurring comprises: causing an audio output device associated with the user to play a portion of the audio recording; and providing the user with an option of listening to the conversation live via the audio output device associated with the user. ### Claim 14 (depends on 13) The system of claim 13, wherein the processor is further configured to: responsive to receiving a user-input opt-in signal from a device associated with the user, electronically join the user to the conversation. ### Claim 15 (depends on 14) The system of claim 14, wherein the audio output device comprises noise-reducing headphones. ### Claim 16 (depends on 11) The system of claim 11, wherein the one or more audio sensors comprises one or more microphones positioned within an office environment. ### Claim 17 A computer program product comprising a computer readable storage medium having program instructions embodied therewith the program instructions executable by a computer processor to cause the computer processor to perform a method comprising: receiving one or more user topic profiles; receiving an audio recording of a conversation obtained from one or more audio sensors; converting the audio recording of the conversation to text; determining, by applying a topic model to the text, a topic of the conversation; determining, based on the topic of the conversation and the one or more user topic profiles, one or more potentially interested users; and notifying the one or more potentially interested users that the conversation is occurring. ### Claim 18 (depends on 17) The computer program product of claim 17, wherein notifying a user of the one or more potentially interested users that the conversation is occurring comprises: causing an audio output device associated with the user to play a sound indicative of the topic of the conversation; and providing the user with an option of listening to the conversation live via the audio output device associated with the user. ### Claim 19 (depends on 17) The computer program product of claim 17, wherein notifying a user of the one or more potentially interested users that the conversation is occurring comprises: causing an audio output device associated with the user to play a portion of the audio recording; and providing the user with an option of listening to the conversation live via the audio output device associated with the user. ### Claim 20 (depends on 19) The computer program product of claim 19, wherein the method further comprises: responsive to receiving a user-input opt-in signal from a device associated with the user, electronically joining the user to the conversation.