Cognitive event predictor

• US 10,524,711 B2
• Filed: 06/09/2014
• Issued: 01/07/2020
• 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., Malkin, Peter K., Pickover, Clifford A.
• Primary Examiner(s): Henson, Devin B
• Assistant Examiner(s): Nguyen, H. Q.
• Application Number:
  US14/299,698
• Publication Number:
  US 20150351680A1
• Time in Patent Office: 2,038 Days
• 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 comprising:

storing a first specific set of sensor readings from a first sensor that describe a physiological state of a user in a first circular buffer, wherein the first circular buffer is reserved for storing sensor readings from the first sensor;

storing a second specific set of sensor readings from a second sensor that describe a speech pattern of the user in a second circular buffer, wherein the second circular buffer is reserved for storing sensor readings from the second sensor;

storing a third specific set of sensor readings from a third sensor that describe an environment of the user in a third circular buffer, wherein the third circular buffer is reserved for storing sensor readings from the third sensor, wherein the first sensor, the second sensor, and the third sensor are components of a wearable device, and wherein the first, second, and third specific set of sensor readings are received during a first time period;

in response to the first sensor generating the first specific set of sensor readings, the second sensor generating the second specific set of sensor readings, and the third sensor generating the third specific set of sensor readings, prompting, by one or more processors, the user to input at least a first “

push”

signal on a pre-programmed key on the wearable device, wherein the first “

push”

signal includes a signal representing a current cognitive state of the user as identified by the user;

receiving, by a hardware receiver, the first “

push”

signal from the user of the wearable device, wherein the first “

push”

signal is transmitted by the user in response to the user subjectively experiencing the current cognitive state;

receiving a fourth specific set of sensor readings from the first sensor, wherein the fourth specific set of sensor readings are received at a second time period that is subsequent to the first time period;

receiving a fifth specific set of sensor readings from the second sensor, wherein the fifth specific set of sensor readings are received at the second time period;

receiving a sixth specific set of sensor readings from the third sensor, wherein the sixth specific set of sensor readings are received at the second time period;

comparing, by the one or more processors, the first, second, and third specific set of sensor readings to their respective fourth, fifth, and sixth specific set of sensor readings;

determining, by the one or more processors, that the first, second, and third specific set of sensor readings match their respective fourth, fifth, and sixth specific set of sensor readings;

in response to determining that the first, second, and third specific set of sensor readings match their respective fourth, fifth, and sixth specific set of sensor readings, predicting, by the one or more processors, that the user will re-experience the current cognitive state of the user at a future time, wherein the future time will occur after sensor readings from the first time period and the second time period are compared, wherein predicting that the user will re-experience the current cognitive state of the user at the future time is performed by;

storing the first specific set of sensor readings from the first sensor in an accumulation data matrix, wherein the first set of sensor readings are identified by the at least first “

push”

signal from the user of the wearable device;

storing the second specific set of sensor readings from the second sensor in the accumulation data matrix, wherein the second set of sensor readings are identified by a second “

push”

signal from the user of the wearable device that occurs after the first “

push”

signal;

storing the third specific set of sensor readings from the third sensor in the accumulation data matrix, wherein the third set of sensor readings are identified by a third “

push”

signal from the user of the wearable device that occurs after the second “

push”

signal, wherein the first specific set of sensor readings, the second specific set of sensor readings, and the third specific set of sensor readings are respectively moved from the first circular buffer, the second circular buffer, and the third circular buffer to the accumulation data matrix;

averaging corresponding blocks from the first, second, and third sensor readings in the accumulation data matrix to create averaged blocks;

storing the averaged blocks from the first, second, and third sensor readings in a push average matrix;

comparing the push average matrix to the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings;

determining, by the one or more processors, that the push average matrix matches the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings within a predefined range; and

in response to determining that the push average matrix matches the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings within a predefined range, predicting, by the one or more processors, that the user will re-experience the current cognitive state of the user at the future time; and

in response to the one or more processors predicting that the user will re-experience the current cognitive state at the future time, transmitting to a smart phone, by a signal transmitter, a cognitive state signal that indicates the prediction that the user will re-experience the current cognitive state at the future time.

2. The method of claim 1, wherein the cognitive state signal is accessible only by the user.

3. The method of claim 1, further comprising:

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

4. A Cognitive Event Predictor (CEP) wearable device, wherein the CEP wearable device comprises a non-transitory computer readable storage medium having program code embodied therewith, and one or more processors for reading and executing the program code to perform a method comprising:

storing a first specific set of sensor readings from a first sensor that describe a physiological state of a user in a first circular buffer, wherein the first circular buffer is reserved for storing sensor readings from the first sensor;

storing a second specific set of sensor readings from a second sensor that describe a speech pattern of the user in a second circular buffer, wherein the second circular buffer is reserved for storing sensor readings from the second sensor;

storing a third specific set of sensor readings from a third sensor that describe an environment of the user in a third circular buffer, wherein the third circular buffer is reserved for storing sensor readings from the third sensor, wherein the first sensor, the second sensor, and the third sensor are components of a wearable device, and wherein the first, second, and third specific set of sensor readings are received during a first time period;

in response to the first sensor generating the first specific set of sensor readings, the second sensor generating the second specific set of sensor readings, and the third sensor generating the third specific set of sensor readings, prompting, by one or more processors, the user to input at least a first “

push”

signal on a pre-programmed key on the wearable device, wherein the first “

push”

signal includes a signal representing a current cognitive state of the user as identified by the user;

receiving, by a hardware receiver, the first “

push”

signal from the user of the wearable device, wherein the first “

push”

signal is transmitted by the user in response to the user subjectively experiencing the current cognitive state;

receiving a fourth specific set of sensor readings from the first sensor, wherein the fourth specific set of sensor readings are received at a second time period that is subsequent to the first time period;

receiving a fifth specific set of sensor readings from the second sensor, wherein the fifth specific set of sensor readings are received at the second time period;

receiving a sixth specific set of sensor readings from the third sensor, wherein the sixth specific set of sensor readings are received at the second time period;

comparing, by the one or more processors, the first, second, and third specific set of sensor readings to their respective fourth, fifth, and sixth specific set of sensor readings;

determining, by the one or more processors, that the first, second, and third specific set of sensor readings match their respective fourth, fifth, and sixth specific set of sensor readings;

in response to determining that the first, second, and third specific set of sensor readings match their respective fourth, fifth, and sixth specific set of sensor readings, predicting, by the one or more processors, that the user will re-experience the current cognitive state of the user at a future time, wherein the future time will occur after sensor readings from the first time period and the second time period are compared, wherein predicting that the user will re-experience the current cognitive state of the user at the future time is performed by;

storing the first specific set of sensor readings from the first sensor in an accumulation data matrix, wherein the first set of sensor readings are identified by the at least first “

push”

signal from the user of the wearable device;

storing the second specific set of sensor readings from the second sensor in the accumulation data matrix, wherein the second set of sensor readings are identified by a second “

push”

signal from the user of the wearable device that occurs after the first “

push”

signal;

storing the third specific set of sensor readings from the third sensor in the accumulation data matrix, wherein the third set of sensor readings are identified by a third “

push”

signal from the user of the wearable device that occurs after the second “

push”

signal, wherein the first specific set of sensor readings, the second specific set of sensor readings, and the third specific set of sensor readings are respectively moved from the first circular buffer, the second circular buffer, and the third circular buffer to the accumulation data matrix;

averaging corresponding blocks from the first, second, and third sensor readings in the accumulation data matrix to create averaged blocks;

storing the averaged blocks from the first, second, and third sensor readings in a push average matrix;

comparing the push average matrix to the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings;

determining, by the one or more processors, that the push average matrix matches the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings within a predefined range; and

in response to determining that the push average matrix matches the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings within a predefined range, predicting, by the one or more processors, that the user will re-experience the current cognitive state of the user at the future time; and

in response to the one or more processors predicting that the user will re-experience the current cognitive state at the future time, transmitting to a smart phone, by a signal transmitter, a cognitive state signal that indicates the prediction that the user will re-experience the current cognitive state at the future time.

5. A 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:

storing a first specific set of sensor readings from a first sensor that describe a physiological state of a user in a first circular buffer, wherein the first circular buffer is reserved for storing sensor readings from the first sensor;

storing a second specific set of sensor readings from a second sensor that describe a speech pattern of the user in a second circular buffer, wherein the second circular buffer is reserved for storing sensor readings from the second sensor;

storing a third specific set of sensor readings from a third sensor that describe an environment of the user in a third circular buffer, wherein the third circular buffer is reserved for storing sensor readings from the third sensor, wherein the first sensor, the second sensor, and the third sensor are components of a wearable device, and wherein the first, second, and third specific set of sensor readings are received during a first time period;

in response to the first sensor generating the first specific set of sensor readings, the second sensor generating the second specific set of sensor readings, and the third sensor generating the third specific set of sensor readings, prompting, by one or more processors, the user to input at least a first “

push”

signal on a pre-programmed key on the wearable device, wherein the first “

push”

signal includes a signal representing a current cognitive state of the user as identified by the user;

receiving, by a hardware receiver, the first “

push”

signal from the user of the wearable device, wherein the first “

push”

signal is transmitted by the user in response to the user subjectively experiencing the current cognitive state;

receiving a fourth specific set of sensor readings from the first sensor, wherein the fourth specific set of sensor readings are received at a second time period that is subsequent to the first time period;

receiving a fifth specific set of sensor readings from the second sensor, wherein the fifth specific set of sensor readings are received at the second time period;

receiving a sixth specific set of sensor readings from the third sensor, wherein the sixth specific set of sensor readings are received at the second time period;

comparing, by the one or more processors, the first, second, and third specific set of sensor readings to their respective fourth, fifth, and sixth specific set of sensor readings;

determining, by the one or more processors, that the first, second, and third specific set of sensor readings match their respective fourth, fifth, and sixth specific set of sensor readings;

in response to determining that the first, second, and third specific set of sensor readings match their respective fourth, fifth, and sixth specific set of sensor readings, predicting, by the one or more processors, that the user will re-experience the current cognitive state of the user at a future time, wherein the future time will occur after sensor readings from the first time period and the second time period are compared, wherein predicting that the user will re-experience the current cognitive state of the user at the future time is performed by;

storing the first specific set of sensor readings from the first sensor in an accumulation data matrix, wherein the first set of sensor readings are identified by the at least first “

push”

signal from the user of the wearable device;

storing the second specific set of sensor readings from the second sensor in the accumulation data matrix, wherein the second set of sensor readings are identified by a second “

push”

signal from the user of the wearable device that occurs after the first “

push”

signal;

storing the third specific set of sensor readings from the third sensor in the accumulation data matrix, wherein the third set of sensor readings are identified by a third “

push”

signal from the user of the wearable device that occurs after the second “

push”

signal, wherein the first specific set of sensor readings, the second specific set of sensor readings, and the third specific set of sensor readings are respectively moved from the first circular buffer, the second circular buffer, and the third circular buffer to the accumulation data matrix;

averaging corresponding blocks from the first, second, and third sensor readings in the accumulation data matrix to create averaged blocks;

storing the averaged blocks from the first, second, and third sensor readings in a push average matrix;

comparing the push average matrix to the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings;

determining, by the one or more processors, that the push average matrix matches the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings within a predefined range; and

in response to determining that the push average matrix matches the fourth specific set of sensor readings, the fifth specific set of sensor readings, and the sixth specific set of sensor readings within a predefined range, predicting, by the one or more processors, that the user will re-experience the current cognitive state of the user at the future time; and

in response to the one or more processors predicting that the user will re-experience the current cognitive state at the future time, transmitting to a smart phone, by a signal transmitter, a cognitive state signal that indicates the prediction that the user will re-experience the current cognitive state at the future time.

6. The computer program product of claim 5, wherein the first sensor and the second sensor detect a walking gait of the user.

7. The computer program product of claim 5, wherein the method further comprises:

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