IP Library › Granted Patent US 9,747,276
Granted Patent B2
US 9,747,276 · App. 14/541,663 · Granted Aug 29, 2017

Predicting individual or crowd behavior based on graphical text analysis of point recordings of audible expressions

Inventors: Guillermo A. Cecchi (New York, NY); James R. Kozloski (New Fairfield, CT); Clifford A. Pickover (Yorktown Heights, NY); Irina Rish (Rye Brook, NY)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G06F17/2765G06Q50/265G10L15/26G10L21/10G10L25/63
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,747,276
App. No.
14/541,663
Granted
Aug 29, 2017
Kind
B2
Abstract

Embodiments relate to determining a crowd behavior. A method of determining a crowd behavior is provided. The method collects, at one or more recording points in a crowd of individuals, audible expressions that the individuals of the crowd make. The method generates a graph of the audible expressions as the audible expressions are collected from the individuals. The method determines a crowd behavior by performing a graphical text analysis on the graph. The method outputs an indication of the crowd behavior to trigger a crowd control measure.

Claims (46)

1. A computer program product, comprising:

a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions readable by a processing circuit to cause the processing circuit to perform a method of determining a crowd behavior, the method comprising:

collecting, at one or more recording points in a crowd of individuals, audible expressions that the individuals of the crowd make;

generating a graph of the audible expressions as the audible expressions are collected from the individuals, wherein the graph comprises nodes that represent tokens and edges that represent temporal precedence in the audible expressions;

determining a crowd behavior by performing a graphical text analysis on the graph; and

outputting an indication of the crowd behavior to trigger a crowd control measure, wherein the crowd behavior comprises a risk metric, and wherein the crowd control measure is triggered when the risk metric is above a threshold.

2. The computer program product of claim 1 ,

wherein the determining comprises:

performing the graphical text analysis on the graph to identify at least one of a cognitive stage of each individual, a cognitive state of a group of individuals of the crowd, and a cognitive state of the crowd as a whole; and

determining the crowd behavior based on the identified cognitive state.

3. The computer program product of claim 1 , wherein the crowd control measure is for deterring the crowd behavior if the crowd behavior is determined to be a risk.

4. The computer program product of claim 1 , wherein the crowd control measure is for assisting the crowd in minimizing a risk the crowd behavior has.

5. The computer program product of claim 1 , wherein the audible expressions of the individuals are collected as the individuals approach or pass by the recording points.

6. A computer program product, comprising:

a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions readable by a processing circuit to cause the processing circuit to perform a method of determining a crowd behavior, the method comprising:

collecting, at one or more recording points in a crowd of individuals, audible expressions that the individuals of the crowd make;

generating a graph of the audible expressions as the audible expressions are collected from the individuals, wherein the graph comprises nodes that represent tokens and edges that represent temporal precedence in the audible expressions;

determining a crowd behavior by performing a graphical text analysis on the graph;

outputting an indication of the crowd behavior to trigger a crowd control measure;

collecting audible expressions from phone calls that the individuals make; and

using the audible expressions collected from the phone calls to generate the graph.

7. The computer program product of claim 1 , wherein the method further comprises:

collecting text messages that the individuals send; and

using the text messages to generate the graph.

8. The computer program product of claim 1 , wherein the recording points comprise a screening checkpoint, wherein the method further comprises:

determining a behavior of an individual or a behavior a group of individuals of the crowd by performing the graphical text analysis on the graph; and

outputting an indication of the determined individual or group behavior to trigger a security measure.

9. A computer system for determining a crowd behavior, the system comprising:

a memory having computer readable instructions; and

a processor configured to execute the computer readable instructions, the instructions comprising:

collecting, at one or more recording points in a crowd of individuals, audible expressions that the individuals of the crowd make;

generating a graph of the audible expressions as the audible expressions are collected from the individuals, wherein the graph comprises nodes that represent tokens and edges that represent temporal precedence in the audible expressions;

determining a crowd behavior by performing a graphical text analysis on the graph; and

outputting an indication of the crowd behavior to trigger a crowd control measure, wherein the crowd behavior comprises a risk metric, and wherein the crowd control measure is triggered when the risk metric is above a threshold.

10. The computer system of claim 9 , wherein the determining comprises:

performing the graphical text analysis on the graph to identify at least one of a cognitive stage of each individual, a cognitive state of a group of individuals of the crowd, and a cognitive state of the crowd as a whole; and

determining the crowd behavior based on the identified cognitive state.

11. The computer system of claim 9 , wherein the method further comprises:

collecting audible expressions from phone calls that the individuals make; and

using the audible expressions collected from the phone calls to generate the graph.

12. The computer system of claim 9 , wherein the method further comprises:

collecting text messages that the individuals send; and

using the text messages to generate the graph.

13. The computer system of claim 9 , wherein the recording points comprise a screening checkpoint, wherein the method further comprises:

determining a behavior of an individual or a behavior a group of individuals of the crowd by performing the graphical text analysis on the graph; and

outputting the determined individual or group behavior to trigger a security measure.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 14, 2014
From: CECCHI, GUILLERMO A.; KOZLOSKI, JAMES R.; PICKOVER, CLIFFORD A.; RISH, IRINA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 034175/0042 →
Continuity (1)
Related Publication 20160140107A1 · May 19, 2016