# US 11,115,520 B2 · Signal discovery using artificial intelligence models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,115,520 B2 - Document ID: US11115520B2 - Status: Granted - Kind: B2 - Application number: 16/897,568 - Filed: 2020-06-10 - Published: 2021-04-22 - Granted: 2021-09-07 - Earliest claimed: 2019-10-18 - Assignees: Invoca, Inc. - Applicants: Invoca, Inc. - Inventors: Michael McCourt; Sean Storlie; Victor Borda; Michael Lawrence; Anoop Praturu - Web page: https://patentgrep.com/patent/US11115520B2 ## CPC - G06F 16/3329: Natural language query formulation - H04M 3/2218: {Call detail recording} - G06F 16/3334: {Selection or weighting of terms from queries, including natural language queries} - G06F 16/45: Clustering; Classification - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning} - G10L 15/197: Probabilistic grammars, e.g. word n-grams - H04M 3/2281: {Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls} - H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)} - H04M 2201/40: using speech recognition - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Systems and methods for improving call topic models are described herein. In an embodiment a server computer receives call transcript data comprising an electronic digital representation of a verbal transcription of a call between a first person of a first person type and a second person of a second person type. The server computer splits the call transcript data into first person type data comprising words spoken by the first person in the call and second person type data comprising words spoken by the second person type in the call. The server computer uses a stored topic model to determine a topic of the call, the topic model simultaneously modeling the first person type data as a function of a first probability distribution of words used by the first person type for one or more topics and the second person type data as a function of a second probability distribution of words used by the second person type for the one or more topics, both the first probability distribution of words and the second probability distribution of words being modeled as a function of a third probability distribution of words for the one or more topics. The server computer then stores a data record identifying the topic of the call and/or stores data identifying the topic of the call with the call transcripts. ## Claims ### Claim 1 A method comprising: receiving call transcript data comprising an electronic digital representation of a verbal transcription of a current call between a first person of a first person type and a second person of a second person type; splitting the call transcript data into first person type data comprising words spoken by the first person in the current call and second person type data comprising words spoken by the second person type in the current call; storing a topic model, the topic model simultaneously modeling the first person type data as a function of a first probability distribution of words used by the first person type, over a plurality of calls, for one or more topics discussed in the current call and the second person type data as a function of a second probability distribution of words used by the second person type over the plurality of calls, for the one or more topics discussed in the current call, both the first probability distribution of words used by the first person type for the one or more topics and the second probability distribution of words used by the second person type for the one or more topics being modeled as a function of a third probability distribution of words for the one or more topics, the third probability distribution of words representing an overall probability distribution of words for each topic of the one or more topics discussed in the current call; using the topic model, determining a topic of the call; storing the call transcript data with additional data indicating the topic of the call. ### Claim 2 (depends on 1) The method of claim 1, wherein the topic model additionally models the call transcript data as a function of a plurality of topics which are modeled as a function of a plurality distribution of topics. ### Claim 3 (depends on 2) The method of claim 2, wherein the plurality distribution of topics is modeled as a function of an inferred prior probability distribution which is modeled as a function of a flat prior distribution. ### Claim 4 (depends on 1) The method of claim 1, wherein determining the topic of the call using the topic model comprises inverting the topic model using a Bayesian Belief Network. ### Claim 5 (depends on 1) The method of claim 1, wherein the third probability distribution of words for each topic is modeled as a function of an inferred prior probability distribution which is modeled as a function of a flat prior distribution. ### Claim 6 (depends on 5) The method of claim 5, wherein the third probability distribution of words is modeled as a function of the inferred prior probability distribution using a Pitman-Yor Process and the inferred prior probability distribution is modeled as a function of the flat prior distribution using a Pitman-Yor Process. ### Claim 7 (depends on 1) The method of claim 1, wherein the first person type is a caller type and the second person type is an agent type. ### Claim 8 (depends on 1) The method of claim 1, further comprising providing, to a client computing device, topic information indicating, for each of a plurality of topics, a number or percentage of calls received for that topic over a particular period of time. ### Claim 9 A system comprising: one or more processors; a memory storing instructions which, when executed by the one or more processors, causes performance of: receiving call transcript data comprising an electronic digital representation of a verbal transcription of a current call between a first person of a first person type and a second person of a second person type; splitting the call transcript data into first person type data comprising words spoken by the first person in the current call and second person type data comprising words spoken by the second person type in the current call; storing a topic model, the topic model simultaneously modeling the first person type data as a function of a first probability distribution of words used by the first person type, over a plurality of calls, for one or more topics discussed in the current call and the second person type data as a function of a second probability distribution of words used by the second person type over a plurality of calls, for the one or more topics discussed in the current call, both the first probability distribution of words used by the first person type for the one or more topics and the second probability distribution of words used by the second person type for the one or more topics being modeled as a function of a third probability distribution of words for the one or more topics the third probability distribution of words representing an overall probability distribution of words for each topic of the one or more topics discussed in the current call; using the topic model, determining a topic of the call; storing the call transcript data with additional data indicating the topic of the call. ### Claim 10 (depends on 9) The system of claim 9, wherein the topic model additionally models the call transcript data as a function of a plurality of topics which are modeled as a function of a plurality distribution of topics. ### Claim 11 (depends on 10) The system of claim 10, wherein the plurality distribution of topics is modeled as a function of an inferred prior probability distribution which is modeled as a function of a flat prior distribution. ### Claim 12 (depends on 9) The system of claim 9, wherein determining the topic of the call using the topic model comprises inverting the topic model using a Bayesian Belief Network. ### Claim 13 (depends on 9) The system of claim 9, wherein the third probability distribution of words for each topic is modeled as a function of an inferred prior probability distribution which is modeled as a function of a flat prior distribution. ### Claim 14 (depends on 13) The system of claim 13, wherein the third probability distribution of words is modeled as a function of the inferred prior probability distribution using a Pitman-Yor Process and the inferred prior probability distribution is modeled as a function of the flat prior distribution using a Pitman-Yor Process. ### Claim 15 (depends on 9) The system of claim 9, wherein the first person type is a caller type and the second person type is an agent type. ### Claim 16 (depends on 9) The system of claim 9, further comprising providing, to a client computing device, topic information indicating, for each of a plurality of topics, a number or percentage of calls received for that topic over a particular period of time. ### Claim 17 A computer-implemented method comprising: receiving call transcript data comprising an electronic digital representation of a verbal transcription of a call between a first person of a first person type and a second person of a second person type; splitting the call transcript data into first person type data comprising words spoken by the first person in the call and second person type data comprising words spoken by the second person type in the call; storing a topic model, the topic model simultaneously modeling the first person type data as a function of a first probability distribution of words used by the first person type for one or more topics and the second person type data as a function of a second probability distribution of words used by the second person type for the one or more topics, both the first probability distribution of words and the second probability distribution of words being modeled as a function of a third probability distribution of words for the one or more topics, the third probability distribution of words for each topic being modeled as a function of an inferred prior probability distribution which is modeled as a function of a flat prior distribution, the third probability distribution of words being modeled as a function of the inferred prior probability distribution using a Pitman-Yor Process and the inferred prior probability distribution is modeled as a function of the flat prior distribution using the Pitman-Yor Process; using the topic model, determining a topic of the call; storing the call transcript data with additional data indicating the topic of the call. ### Claim 18 A system comprising: one or more processors; a memory storing instructions which, when executed by the one or more processors, causes performance of: receiving call transcript data comprising an electronic digital representation of a verbal transcription of a call between a first person of a first person type and a second person of a second person type; splitting the call transcript data into first person type data comprising words spoken by the first person in the call and second person type data comprising words spoken by the second person type in the call; storing a topic model, the topic model simultaneously modeling the first person type data as a function of a first probability distribution of words used by the first person type for one or more topics and the second person type data as a function of a second probability distribution of words used by the second person type for the one or more topics, both the first probability distribution of words and the second probability distribution of words being modeled as a function of a third probability distribution of words for the one or more topics, the third probability distribution of words for each topic being modeled as a function of an inferred prior probability distribution which is modeled as a function of a flat prior distribution, the third probability distribution of words being modeled as a function of the inferred prior probability distribution using a Pitman-Yor Process and the inferred prior probability distribution is modeled as a function of the flat prior distribution using the Pitman-Yor Process; using the topic model, determining a topic of the call; storing the call transcript data with additional data indicating the topic of the call.