COGNITIVE EVENT PREDICTOR

• US 20150351680A1
• Filed: 06/09/2014
• Published: 12/10/2015
• Est. Priority Date: 06/09/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: GORDON, MICHAEL S., KOZLOSKI, JAMES R., PICKOVER, CLIFFORD A., MALKIN, PETER K.
• Granted Patent: US 10,524,711 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 5/0004 characterised by the type of physiological signal transmitted
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/162 Testing reaction times
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/4803 Speech analysis specially adapted for diagnostic purposes
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

A method and/or computer program product identifies and/or predicts a cognitive state of a user. A buffer on a device is loaded with a predetermined set of sensor readings for a user. A hardware receiver receives a “push” signal from the device. The “push” signal is transmitted by the user in response to the user subjectively experiencing a user-defined cognitive state. The “push” signal causes readings from the buffer to be loaded as pushed sensor readings onto a data matrix. One or more processors analyze the pushed sensor readings to identify a sensor pattern of the pushed sensor readings. In response to detecting a subsequent set of sensor readings that match the sensor pattern of the pushed sensor readings, a signal transmitter transmits a cognitive state signal that indicates a prediction of a particular cognitive state of the user.

Claims

1. A method of predicting a cognitive state of a user, the method comprising:

loading a buffer with a specific set of sensor readings for a user, wherein the buffer is communicatively coupled to a sensor device;

receiving, by a hardware receiver, a “

push”

signal from the sensor device, wherein the “

push”

signal is transmitted by the user in response to the user subjectively experiencing a user-defined cognitive state, and wherein the “

push”

signal causes readings from the buffer to be loaded as pushed sensor readings onto a data matrix;

analyzing, by one or more processors, the pushed sensor readings to identify a sensor pattern of the pushed sensor readings; and

in response to one or more processors detecting a subsequent set of sensor readings that match the sensor pattern of the pushed sensor readings, transmitting, by a signal transmitter, a cognitive state signal that indicates a prediction of a particular cognitive state of the user.

2. The method of claim 1, further comprising:

loading the specific set of sensor readings onto continuous circular buffers, wherein each of the continuous circular buffers stores data from a different sensor in the sensor device.

3. The method of claim 2, further comprising:

predicting whether a particular cognitive state will occur, based on a probability formula;

4. The method of claim 2, further comprising:

predicting whether the particular cognitive state will occur based on a statistical analysis of the subsequent set of sensor readings compared to the pushed sensor readings, wherein a match within a predefined statistical range between the subsequent set of sensor readings and the pushed sensor readings leads to the prediction of the particular cognitive state of the user.

5. The method of claim 2, wherein the sensor readings are from a set of smart sensors, and wherein the method further comprises the smart sensors:

detecting a particular physical event;

quantifying a level of the particular physical event;

converting the level of the particular physical event into a digital value; and

transmitting the digital value to continuous circular buffers.

6. The method of claim 5, further comprising:

detecting, by a smart sensor, physiological states of the user.

7. The method of claim 5, further comprising:

detecting, by a smart sensor, musculoskeletal bodily acts of the user.

8. The method of claim 5, further comprising:

detecting, by a smart sensor, keywords spoken by the user.

9. The method of claim 5, further comprising:

detecting, by a smart sensor, a quality of a voice pattern from the user.

10. The method of claim 5, further comprising:

detecting, by a smart sensor, ambient environmental conditions around the user.

11. The method of claim 5, further comprising:

receiving, by one or more processors, data from a single linear buffer, wherein the single linear buffer contains data from the smart sensors that describe a single type of sensor reading;

converting, by one or more processors, the data from the single linear buffer into a matrix; and

comparing, by one or more processors, the matrix to a known matrix, wherein the known matrix contains data that was previously received from the smart sensors prior to the user experiencing the cognitive state.

12. The method of claim 1, wherein the sensor device is a wearable device.

13. A Cognitive Event Predictor (CEP) wearable device comprising:

a set of one or more sensors, wherein the one or more sensors are configured to detect, record, and quantify a physical event associated with a user;

a set of buffers for storing a first set of sensor readings from the one or more sensors;

a hardware storage device for storing the first set of sensor readings as a first matrix, wherein the first set of sensor readings are stored as the first matrix in response to the user subjectively experiencing a user-defined cognitive state;

a hardware comparator for comparing the first matrix with a second matrix derived from a second set of sensor readings, wherein the second set of sensor readings are received after the first set of sensor readings; and

a signal transmitter, wherein the signal transmitter transmits a signal indicating a prediction that the user-defined cognitive state will re-occur in the user in response to the user experiencing factors that caused the first and second set of sensor readings to be generated by the set of one or more sensors.

14. The CEP wearable device of claim 13, wherein the one or more sensors are physiological sensors.

15. The CEP wearable device of claim 13, wherein the one or more sensors measure musculoskeletal bodily acts of the user.

16. The CEP wearable device of claim 13, wherein the one or more sensors are speech-to-text converters and analyzers, wherein the speech-to-text converters and analyzers examine a speech of the user for predefined features.

17. The CEP wearable device of claim 13, wherein the one or more sensors are speech inflection analyzers.

18. A computer program product for predicting a cognitive state of a user, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code readable and executable by a processor to perform method comprising:

loading a buffer with a predetermined set of sensor readings for a user, wherein the buffer is communicatively coupled to a wearable device;

receiving a “

push”

signal from the wearable device, wherein the “

push”

signal is transmitted by the user in response to the user subjectively experiencing a user-defined cognitive state, and wherein the “

push”

signal causes readings from the buffer to be loaded as pushed sensor readings onto a data matrix;

analyzing the pushed sensor readings to identify a sensor pattern of the pushed sensor readings; and

in response to one or more processors detecting a subsequent set of sensor readings that match the sensor pattern of the pushed sensor readings, transmitting a cognitive state signal that indicates a prediction of a particular cognitive state of the user.

19. The computer program product of claim 18, wherein the method further comprises:

loading the predetermined set of sensor readings onto continuous circular buffers, wherein each of the continuous circular buffers stores data from a different sensor in the wearable device.

20. The computer program product of claim 19, wherein the method further comprises:

predicting whether a particular cognitive state will occur, based on a probability formula;