# US 10,770,072 B2 · Cognitive triggering of human interaction strategies to facilitate collaboration, productivity, and learning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,770,072 B2
- Document ID: US10770072B2
- Status: Granted
- Kind: B2
- Application number: 16/214,696
- Filed: 2018-12-10
- Published: 2020-06-11
- Granted: 2020-09-08
- Earliest claimed: 2018-12-10
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Vinícius Costa Villas Bôas Segura; Ana Fucs; Rodrigo Laiola Guimaraes; Julio Nogima
- Web page: https://patentgrep.com/patent/US10770072B2

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit
- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- H04L 12/1818: {Conference organisation arrangements, e.g. handling schedules, setting up parameters needed by nodes to attend a conference, booking network resources, notifying involved parties}
- H04L 12/1822: {Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission}
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G10L 13/00: Speech synthesis; Text to speech systems
- G10L 2015/088: {Word spotting}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Embodiments are directed to a computer-implemented method that includes receiving, at a triggering system, input data about an environment. Machine learning (ML) algorithms extract features from the input data and analyze relationships among and between the features to generate user-interaction-readiness model of person-A's readiness to participate in a human interaction with other persons in the environment. The ML algorithms to apply real-world data about person-A to the user-interaction-readiness model to generate a first classification output comprising data representing person-A's readiness to participate in a human interaction with other persons in the environment. Based at least in part on a determination that person-A and another person(s) in the environment are interaction candidates, the triggering system triggers the initiation of human interaction strategies configured to facilitate human interactions between person-A and the previously identified another person(s) in the environment.

## Claims

### Claim 1

A computer-implemented method of triggering a dialogue system to implement human interaction strategies configured to facilitate human interactions between and among selected persons in an environment, the computer-implemented method comprising:
receiving, at a triggering system, input data about the environment;
using machine learning (ML) algorithms of the triggering system to extract features from the input data;
using the ML algorithms of the triggering system to analyze relationships among and between the features extracted from the input data to generate a person-A user-interaction-readiness model for person-A in the environment, wherein the person-A user-interaction-readiness model comprises a model of person-A's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms to apply real-world data about person-A to the person-A user-interaction-readiness model to generate a first classification output comprising data representing person-A's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms of the triggering system to analyze relationships among and between the features extracted from the input data to generate a person-B user-interaction-readiness model for person-B in the environment, wherein the person-B user-interaction-readiness model comprises a model that indicates person-B's readiness to participate in a human interaction with another person in the environment;
using the ML algorithms to apply real-world data about person-B to the person-B user-interaction-readiness model to generate a second classification output comprising data representing person-B's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms of the triggering system to extract features from the input data, the first classification output, and the second classification output;
using the ML algorithms of the triggering system to analyze relationships among and between the features extracted from the input data, the first classification output, and the second classification output to generate a user-interaction-candidates group model for person-A and person-B in the environment, wherein the user-interaction-candidates group model comprises a model of person-A's and Person B's readiness to participate in a human interaction that includes person-A and person-B;
using the ML algorithms to apply real-world data about person-A and person-B to the user-interaction-candidates group model to generate a third classification output comprising data representing person-A's readiness to participate in a human interaction with person-B in the environment, as well as person-B's readiness to participate in a human interaction with person-A; and
based at least in part on the third classification output, triggering the dialogue system to initiate the implementation of human interaction strategies configured to facilitate human interactions between person-A and person-B in the environment.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1 further comprising monitoring implementation of the human interaction strategies.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2 further comprising storing human interaction effectiveness data representing an effectiveness of the implementation of the human interaction strategies.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3 further comprising accessing the human interaction effectiveness data and using the ML algorithms of the triggering system to extract features from the human interaction effectiveness data.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4 further comprising using the ML algorithms of the triggering system to analyze relationships among and between the features extracted from the human interaction effectiveness data, the input data, the first classification output, and the second classification output to train the user-interaction-candidates group model for person-A and person-B in the environment.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the input data comprise topics data comprising topics of potential interest to person-A and person-B.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1 further comprising:
using the ML algorithms of the triggering system to analyze relationships among and between the features extracted from the input data to generate a person-A cognitive trait model for person-A in the environment, wherein the person-A cognitive trait model comprises a model of person-A's cognitive traits;
using the ML algorithms to apply real-world data about person-A to the person-A cognitive trait model to generate a fourth classification output comprising data representing person-A's cognitive traits;
using the ML algorithms of the triggering system to analyze relationships among and between the features extracted from the input data to generate a person-B cognitive trait model for person-B in the environment, wherein the person-B cognitive trait model comprises a model of person-B's cognitive traits;
using the ML algorithms to apply real-world data about person-B to the person-B cognitive trait model to generate a fifth classification output comprising data representing person-B's cognitive traits;
using the ML algorithms of the triggering system to extract features from the fourth classification output and the fifth classification output; and
using the ML algorithms of the triggering system to analyze relationships among and between the features extracted from the input data, the first classification output, the second classification output, the fourth classification output, and the fifth classification output to generate the user-interaction-candidates group model for person-A and person-B in the environment, wherein the user-interaction-candidates group model comprises a model of person-A's and Person B's readiness to participate in a human interaction that includes person-A and person-B.

### Claim 8

A computer triggering system for triggering a dialogue system to implement human interaction strategies configured to facilitate human interactions between and among selected persons in an environment, the computer triggering system configure to perform operations comprising:
receiving input data about the environment;
using machine learning (ML) algorithms of the computer triggering system to extract features from the input data;
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-A user-interaction-readiness model for person-A in the environment, wherein the person-A user-interaction-readiness model comprises a model of person-A's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms to apply real-world data about person-A to the person-A user-interaction-readiness model to generate a first classification output comprising data representing person-A's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-B user-interaction-readiness model for person-B in the environment, wherein the person-B user-interaction-readiness model comprises a model that indicates person-B's readiness to participate in a human interaction with another person in the environment;
using the ML algorithms to apply real-world data about person-B to the person-B user-interaction-readiness model to generate a second classification output comprising data representing person-B's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms to extract features from the input data, the first classification output, and the second classification output;
using the ML algorithms to analyze relationships among and between the features extracted from the input data, the first classification output, and the second classification output to generate a user-interaction-candidates group model for person-A and person-B in the environment, wherein the user-interaction-candidates group model comprises a model of person-A's and Person B's readiness to participate in a human interaction that includes person-A and person-B;
using the ML algorithms to apply real-world data about person-A and person-B to the user-interaction-candidates group model to generate a third classification output comprising data representing person-A's readiness to participate in a human interaction with person-B in the environment, as well as person-B's readiness to participate in a human interaction with person-A; and
based at least in part on the third classification output, triggering the dialogue system to initiate the implementation of human interaction strategies configured to facilitate human interactions between person-A and person-B in the environment.

### Claim 9 (depends on 8)

The computer system of claim 8 further comprising monitoring implementation of the human interaction strategies.

### Claim 10 (depends on 9)

The computer system of claim 9 further comprising storing human interaction effectiveness data representing an effectiveness of the implementation of the human interaction strategies.

### Claim 11 (depends on 10)

The computer system of claim 10 further comprising accessing the human interaction effectiveness data and using the ML algorithms of the triggering system to extract features from the human interaction effectiveness data.

### Claim 12 (depends on 11)

The computer system of claim 11 further comprising using the ML algorithms to analyze relationships among and between the features extracted from the human interaction effectiveness data, the input data, the first classification output, and the second classification output to train the user-interaction-candidates group model for person-A and person-B in the environment.

### Claim 13 (depends on 8)

The computer system of claim 8, wherein the input data comprise topics data comprising topics of potential interest to person-A and person-B.

### Claim 14 (depends on 8)

The computer system of claim 8 further comprising:
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-A cognitive trait model for person-A in the environment, wherein the person-A cognitive trait model comprises a model of person-A's cognitive traits;
using the ML algorithms to apply real-world data about person-A to the person-A cognitive trait model to generate a fourth classification output comprising data representing person-A's cognitive traits;
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-B cognitive trait model for person-B in the environment, wherein the person-B cognitive trait model comprises a model of person-B's cognitive traits;
using the ML algorithms to apply real-world data about person-B to the person-B cognitive trait model to generate a fifth classification output comprising data representing person-B's cognitive traits;
using the ML algorithms to extract features from the fourth classification output and the fifth classification output; and
using the ML algorithms to analyze relationships among and between the features extracted from the input data, the first classification output, the second classification output, the fourth classification output, and the fifth classification output to generate the user-interaction-candidates group model for person-A and person-B in the environment, wherein the user-interaction-candidates group model comprises a model of person-A's and Person B's readiness to participate in a human interaction that includes person-A and person-B.

### Claim 15

A computer program product for triggering a dialogue system to implement human interaction strategies configured to facilitate human interactions between and among selected persons in an environment, the computer program product comprising a computer readable program stored on a computer readable storage medium, wherein the computer readable program, when executed on a processor, causes the processor to perform a method comprising:
receiving input data about the environment;
using machine learning (ML) algorithms of the processor to extract features from the input data;
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-A user-interaction-readiness model for person-A in the environment, wherein the person-A user-interaction-readiness model comprises a model of person-A's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms to apply real-world data about person-A to the person-A user-interaction-readiness model to generate a first classification output comprising data representing person-A's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-B user-interaction-readiness model for person-B in the environment, wherein the person-B user-interaction-readiness model comprises a model that indicates person-B's readiness to participate in a human interaction with another person in the environment;
using the ML algorithms to apply real-world data about person-B to the person-B user-interaction-readiness model to generate a second classification output comprising data representing person-B's readiness to participate in a human interaction with other persons in the environment;
using the ML algorithms to extract features from the input data, the first classification output, and the second classification output;
using the ML algorithms to analyze relationships among and between the features extracted from the input data, the first classification output, and the second classification output to generate a user-interaction-candidates group model for person-A and person-B in the environment, wherein the user-interaction-candidates group model comprises a model of person-A's and Person B's readiness to participate in a human interaction that includes person-A and person-B;
using the ML algorithms to apply real-world data about person-A and person-B to the user-interaction-candidates group model to generate a third classification output comprising data representing person-A's readiness to participate in a human interaction with person-B in the environment, as well as person-B's readiness to participate in a human interaction with person-A; and
based at least in part on the third classification output, triggering the dialogue system to initiate the implementation of human interaction strategies configured to facilitate human interactions between person-A and person-B in the environment.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein the method performed by the processor further comprises:
monitoring implementation of the human interaction strategies; and
storing human interaction effectiveness data representing an effectiveness of the implementation of the human interaction strategies.

### Claim 17 (depends on 16)

The computer program product of claim 16, wherein the method performed by the processor further comprises accessing the human interaction effectiveness data and using the ML algorithms of the triggering system to extract features from the human interaction effectiveness data.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the method performed by the processor further comprises using the ML algorithms to analyze relationships among and between the features extracted from the human interaction effectiveness data, the input data, the first classification output, and the second classification output to train the user-interaction-candidates group model for person-A and person-B in the environment.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein the input data comprise topics data comprising topics of potential interest to person-A and person-B.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein the method performed by the processor further comprises:
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-A cognitive trait model for person-A in the environment, wherein the person-A cognitive trait model comprises a model of person-A's cognitive traits;
using the ML algorithms to apply real-world data about person-A to the person-A cognitive trait model to generate a fourth classification output comprising data representing person-A's cognitive traits;
using the ML algorithms to analyze relationships among and between the features extracted from the input data to generate a person-B cognitive trait model for person-B in the environment, wherein the person-B cognitive trait model comprises a model of person-B's cognitive traits;
using the ML algorithms to apply real-world data about person-B to the person-B cognitive trait model to generate a fifth classification output comprising data representing person-B's cognitive traits;
using the ML algorithms to extract features from the fourth classification output and the fifth classification output; and
using the ML algorithms to analyze relationships among and between the features extracted from the input data, the first classification output, the second classification output, the fourth classification output, and the fifth classification output to generate the user-interaction-candidates group model for person-A and person-B in the environment, wherein the user-interaction-candidates group model comprises a model of person-A's and Person B's readiness to participate in a human interaction that includes person-A and person-B.