# US 10,769,419 B2 · Disruptor mitigation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,419 B2 - Document ID: US10769419B2 - Status: Granted - Kind: B2 - Application number: 16/133,432 - Filed: 2018-09-17 - Published: 2020-03-19 - Granted: 2020-09-08 - Earliest claimed: 2018-09-17 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Cesar Augusto Rodriguez Bravo; Gregory J. Boss; Bernadette Pierson; Jayashree Vaidyanathan - Web page: https://patentgrep.com/patent/US10769419B2 ## CPC - G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) - G06N 20/00: Machine learning - G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion} - G06V 40/70: Multimodal biometrics, e.g. combining information from different biometric modalities - H04L 41/40: using virtualisation of network functions or resources, e.g. SDN or NFV entities - H04L 41/5019: Ensuring fulfilment of SLA - H04L 43/0876: Network utilisation, e.g. volume of load or congestion level - H04L 43/20: the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV - H04L 51/04: Real-time or near real-time messaging, e.g. instant messaging [IM] - H04L 51/52: for supporting social networking services - H04L 67/04: specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability - H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) - H04L 67/12: specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks - H04L 67/52: specially adapted for the location of the user terminal - H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)} - H04L 67/566: Grouping or aggregating service requests, e.g. for unified processing - H04W 4/021: Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences - H04W 4/14: Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD] - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - H04L 51/222: using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area - H04W 4/21: for social networking applications - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - 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) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining one or more data feed that includes data of individuals within a crowd, wherein the crowd comprises a plurality of individuals gathered within an area; examining data of the one or more data feed to return behavior parameter values for respective individuals of the plurality of individuals; identifying, using values of the behavior parameter values, a disrupted group of a plurality of the individuals of the crowd, wherein the identifying is in dependence on a first one or more criterion being satisfied; detecting, using values of the behavior parameter values, a disruptor individual within the disrupted group, the detecting in dependence on a second one or more criterion being satisfied; and providing, by machine logic, one more disruptor mitigation output to mitigate disruptive behavior of the disruptor individual. ## Claims ### Claim 1 A method comprising: obtaining one or more data feed that includes data of individuals within a crowd, wherein the crowd comprises a plurality of individuals gathered within an area; examining data of the one or more data feed to return behavior parameter values for respective individuals of the plurality of individuals; identifying, using values of the behavior parameter values, a disrupted group of a plurality of the individuals of the crowd, wherein the identifying is in dependence on a first one or more criterion being satisfied; detecting, using values of the behavior parameter values, a disruptor individual within the disrupted group, the detecting in dependence on a second one or more criterion being satisfied; and providing, by machine logic, one more disruptor mitigation output to mitigate disruptive behavior of the disruptor individual, wherein the behavior parameter values for respective individuals of the crowd include sentiment parameter values, and wherein providing parameter values of the sentiment parameter values includes processing a video data stream provided by one or of more video camera for obtaining video image data representation of the crowd, wherein the processing the video data stream includes processing video data to return facial expression based sentiment parameter values for users within the crowd. ### Claim 2 A method comprising: obtaining one or more data feed that includes data of individuals within a crowd, wherein the crowd comprises a plurality of individuals gathered within an area; examining data of the one or more data feed to return behavior parameter values for respective individuals of the plurality of individuals; identifying, using values of the behavior parameter values, a disrupted group of a plurality of the individuals of the crowd, wherein the identifying is in dependence on a first one or more criterion being satisfied; detecting, using values of the behavior parameter values, a disruptor individual within the disrupted group, the detecting in dependence on a second one or more criterion being satisfied; and providing, by machine logic, one more disruptor mitigation output to mitigate disruptive behavior of the disruptor individual. ### Claim 3 (depends on 2) The method of claim 2, wherein the providing, by machine logic, one more disruptor mitigation output includes providing one or more output to send a text based message to a client computer device of the disruptor individual prompting redirection of activity of the disruptor individual. ### Claim 4 (depends on 2) The method of claim 2, wherein the providing, by machine logic, one more disruptor mitigation output includes providing one or more output to present a publicly observable message observable by individuals of the crowd prompting redirection of activity of the disruptor individual. ### Claim 5 (depends on 2) The method of claim 2, wherein the providing, by machine logic, one more disruptor mitigation output includes providing one or more output to send a text based message to a client computer device of a certain individual in proximity with the disruptor individual, the text based message instructing the certain individual in respect to interactions with the disruptor individual. ### Claim 6 (depends on 2) The method of claim 2, wherein the providing, by machine logic, one more disruptor mitigation output includes providing one or more output to send a text based message to a client computer device of the disruptor individual prompting redirection of activity of the disruptor individual, wherein the text based message is in dependence on historical data stored in a data repository specifying preferences of the disruptor individual, wherein the method includes performing video data processing to return an identifier for the disruptor individual, returning a preference for the disruptor individual using the identifier, and providing the text based message in dependence on the identifier. ### Claim 7 (depends on 2) The method of claim 2, wherein the providing, by machine logic, one more disruptor mitigation output includes providing one or more output to activate a physical barrier within the area to redirect traffic of the crowd within the area. ### Claim 8 (depends on 2) The method of claim 2, wherein the behavior parameter values for respective individuals of the crowd include sentiment parameter values, and wherein providing parameter values of the sentiment parameter values includes processing a video data stream provided by one or of more video camera for obtaining video image data representation of the crowd. ### Claim 9 (depends on 2) The method of claim 2, wherein the behavior parameter values for respective individuals of the crowd include sentiment parameter values, and wherein providing parameter values of the sentiment parameter values includes processing text based data provided by users of the crowd, text based data selected from the group consisting of social media postings and text based messages delivered by a messaging system. ### Claim 10 (depends on 2) The method of claim 2, wherein the behavior parameter values for respective individuals of the crowd include network utilization level parameter values, and wherein providing parameter values of the network utilization parameter values includes monitoring data uploads from and data downloads to client computer devices of individuals within the crowd. ### Claim 11 (depends on 2) The method of claim 2, wherein the behavior parameter values for respective individuals of the crowd include biometric variance parameter values, and wherein providing parameter values of the biometric variance parameter values includes processing biometric sensor outputs from integrated biometric sensors of wearable client computer devices being worn by users of the crowd. ### Claim 12 (depends on 2) The method of claim 2, wherein the first one or more criterion includes the criterion that a group aggregate sentiment parameter value associated to the group differs from a group aggregate sentiment parameter value associated to the crowd gathered in the area by more than a difference threshold value. ### Claim 13 (depends on 2) The method of claim 2, wherein the second one or more criterion includes the criterion that a sentiment value associated to the disruptor individual differs from an aggregate sentiment value associated to disrupted group by more than a difference threshold value. ### Claim 14 (depends on 2) The method of claim 2, wherein the first one or more criterion includes the criterion that a group aggregate behavior parameter value associated to the disrupted group differs from a group aggregate behavior parameter value associated to the crowd within the area by more than a difference threshold value, and wherein the second one or more criterion includes the criterion that a candidate disruptor individual among the disrupted group has exhibited a threshold exceeding behavior parameter value than has been exhibited by second candidate disruptor individual among the disrupted group. ### Claim 15 (depends on 2) The method of claim 2, wherein the identifying includes using moving window processing, wherein each window is a candidate disrupted region, and wherein the method includes calculating group aggregate sentiment values for each window and comparing the group aggregate sentiment values for each window to a group aggregate sentiment for the crowd within the area. ### Claim 16 (depends on 2) The method of claim 2, wherein the first one or more criterion includes the criterion that a group aggregate behavior parameter value associated to the disrupted group differs from a group aggregate behavior parameter value associated to the crowd within the area by more than a difference threshold value, and wherein the second one or more criterion includes the criterion that a candidate disruptor individual among the disrupted group has exhibited a threshold exceeding behavior parameter value for a longest time period among users with the disrupted group, wherein the providing, by machine logic, one more disruptor mitigation output includes providing one or more output to send a text based message to a client computer device of the disruptor individual prompting redirection of activity of the disruptor individual, wherein the text based message is in dependence on historical data stored in a data repository specifying preferences of the disruptor individual, wherein the method includes performing video data processing to return an identifier for the disruptor individual, returning a preference for the disruptor individual using the identifier, and providing the text based message in dependence on the identifier. ### Claim 17 (depends on 2) The method of claim 2, wherein the method includes deciding the one more disruptor mitigation output using a decision data structure that cognitively maps a methodology used for determination of one or more or the disrupted group or the disruptor individual to specified one or more action associated to the methodology, wherein the method includes using predictive model trained by machine learning for updating the decision data structure, wherein the method includes iteratively checking data of the one or more data feed to determine whether the one or more disruptor mitigation output has been successful and iteratively adjusting the one or more disruptor mitigation output in response to respective iterative determinations that the one or more disruptor mitigation output has not been successful. ### Claim 18 (depends on 2) The method of claim 2, wherein the one or more data feed includes a data feed from a data source selected from the group consisting of (a) client computer devices of the individuals of the crowd, (b) a video camera system oriented to capture video data representations of the crowd, (c) a social media system, and (d) a network resource that monitors network utilization levels of the individuals of the crowd. ### Claim 19 (depends on 2) The method of claim 2, wherein the one or more data feed includes a data feed from each of the following data sources: (a) client computer devices of the individuals of the crowd, (b) a video camera system oriented to capture video data representations of the crowd, (c) a social media system, and (d) a network resource that monitors network utilization levels of the individuals of the crowd. ### Claim 20 A system comprising: a memory; at least one processor in communication with the memory; and program instructions executable by one or more processor via the memory to perform a method comprising: obtaining one or more data feed that includes data of individuals within a crowd, wherein the crowd comprises a plurality of individuals gathered within an area; examining data of the one or more data feed to return behavior parameter values for respective individuals of the plurality of individuals; identifying, using values of the behavior parameter values, a disrupted group of a plurality of the individuals of the crowd, wherein the identifying is in dependence on a first one or more criterion being satisfied; detecting, using values of the behavior parameter values, a disruptor individual within the disrupted group, the detecting in dependence on a second one or more criterion being satisfied; and providing, by machine logic, one more disruptor mitigation output to mitigate disruptive behavior of the disruptor individual.