# US 10,318,876 B2 · Mood detection with intelligence agents > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,318,876 B2 - Document ID: US10318876B2 - Status: Granted - Kind: B2 - Application number: 15/604,908 - Filed: 2017-05-25 - Published: 2018-11-29 - Granted: 2019-06-11 - Earliest claimed: 2017-05-25 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Aaron K. Baughman; Diwesh Pandey; John P. Perrino; Todd R. Whitman - Web page: https://patentgrep.com/patent/US10318876B2 ## CPC - G06N 5/043: Distributed expert systems; Blackboards - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Embodiments of the present invention provide systems and methods for increasing the quality of interactions between two or more entities. These entities are either individuals (e.g., human beings using a computer device) or artificial intelligence (AI) agents. The interactions between all of the entities within a computing environment are mapped and analyzed. Based on the mapped interactions, a relationship model is generated in order to run multiple applications within a computing environment. ## Claims ### Claim 1 A method comprising: observing, by one or more processors, interactions between a plurality of individuals and a plurality of artificial intelligence (AI) agents; creating, by one or more processors, a cognitive profile for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents using social media data, observation protocols, and biometric data for the plurality of individuals and special testing data for the plurality of AI agents, wherein the observation protocols comprise monitoring conversation tone and facial expressions during a respective interaction, and wherein the special testing data comprises sensor data, text data, and speech recognition data obtained during a respective interaction; mapping, by one or more processors, a set of interactions to each cognitive profile for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents based on the observed interactions between the plurality of individuals and the plurality of artificial intelligence (AI) agents; and generating, by one or more processors, an action operation for each respective individual and AI agent based on the cognitive profile for the respective individual and respective AI agent to ameliorate respective interactions between the plurality of individuals and plurality of AI agents. ### Claim 2 (depends on 1) The method of claim 1, wherein mapping the set of interactions, comprises: utilizing, by one or more processors, data objects to represent each of the plurality of individuals and a plurality of artificial intelligence (AI) agents; and utilizing, by one or more processors, data links to represent connections between two data objects. ### Claim 3 (depends on 2) The method of claim 2, further comprising: analyzing, by one or more processors, the mapped set of interactions to gauge a level of positive sentiment and a level of negative sentiment of each interaction within the mapped set of interactions. ### Claim 4 (depends on 3) The method of claim 3, further comprising: creating, by one or more processors, a plurality of relationship models based on the analyzed mapped set of interactions, wherein each relationship model is associated with a single interaction within the analyzed mapped set of interactions. ### Claim 5 (depends on 4) The method of claim 4, further comprising: utilizing, by one or more processors, the plurality of relationship models to implement solutions for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents based on the created cognitive profile and the mapped set of interactions for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents. ### Claim 6 A computer program product comprising: a computer readable storage medium and program instructions stored on the computer readable storage medium, the program instructions comprising: program instructions to observe interactions between a plurality of individuals and a plurality of artificial intelligence (AI) agents; program instructions to create a cognitive profile for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents using social media data, observation protocols, and biometric data for the plurality of individuals and special testing data for the plurality of AI agents, wherein the observation protocols comprise monitoring conversation tone and facial expressions during a respective interaction, and wherein the special testing data comprises sensor data, text data, and speech recognition data obtained during a respective interaction; program instructions to map a set of interactions to each cognitive profile for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents based on the observed interactions between the plurality of individuals and the plurality of artificial intelligence (AI) agents; and program instructions to generate an action operation for each respective individual and AI agent based on the cognitive profile for the respective individual and respective AI agent to ameliorate respective interactions between the plurality of individuals and plurality of AI agents. ### Claim 7 (depends on 6) The computer program product of claim 6, wherein the program instructions to map the set of interactions, comprise: program instructions to utilize data objects to represent each of the plurality of individuals and a plurality of artificial intelligence (AI) agents; and program instructions to utilize data links to represent connections between two data objects. ### Claim 8 (depends on 7) The computer program product of claim 7, further comprising: program instructions to analyze the mapped set of interactions to gauge a level of positive sentiments and negative sentiments of each interaction within the mapped set of interactions. ### Claim 9 (depends on 8) The computer program product of claim 8, further comprising: program instructions to create a plurality of relationship models based on the analyzed mapped set of interactions, wherein each relationship model corresponds to a single interaction within the analyzed mapped set of interactions. ### Claim 10 (depends on 9) The computer program product of claim 9, further comprising: program instructions to utilize the plurality of relationship models to implement solutions for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents based on the created cognitive profile and the mapped set of interactions for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents. ### Claim 11 A computer system comprising: one or more computer processors; one or more computer readable storage media; program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising: program instructions to observe interactions between a plurality of individuals and a plurality of artificial intelligence (AI) agents; program instructions to create a cognitive profile for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents using social media data, observation protocols, and biometric data for the plurality of individuals and special testing data for the plurality of AI agents, wherein the observation protocols comprise monitoring conversation tone and facial expressions during a respective interaction, and wherein the special testing data comprises sensor data, text data, and speech recognition data obtained during a respective interaction; program instructions to map a set of interactions to each cognitive profile for each respective individual of the plurality of individuals and each respective AI agent of the plurality of AI agents based on the observed interactions between the plurality of individuals and the plurality of artificial intelligence (AI) agents; and program instructions to generate an action operation for each respective individual and AI agent based on the cognitive profile for the respective individual and respective AI agent to ameliorate respective interactions between the plurality of individuals and plurality of AI agents. ### Claim 12 (depends on 11) The computer system of claim 11, wherein program instructions to output map the set of interactions, comprise: program instructions to utilize data objects to represent the plurality of individuals and a plurality of artificial intelligence (AI) agents; and program instructions to utilize data links to represent connections between two data objects. ### Claim 13 (depends on 12) The computer system of claim 12, further comprising: program instructions to analyze the mapped set of interactions to gauge a level of positive sentiments and negative sentiments of each interaction within the mapped set of interactions. ### Claim 14 (depends on 13) The computer system of claim 13, further comprising: program instructions to create a plurality of relationship models based on the analyzed mapped set of interactions, wherein each relationship model corresponds to a single interaction within the analyzed mapped set of interactions.