Guided interaction with a query assistant software using brainwave data

Patent metadata

Field	Value
Publication number	US-11567574-B2
Application number	US-202017028179-A
Country	US
Kind code	B2
Filing date	Sep 22, 2020
Priority date	Sep 22, 2020
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

Systems and methods are configured to enable guided interaction with query assistant software using brainwave data. In various embodiments, a client device presents a query assistant user interface to a monitored end-user that describes a query associated with a plurality of response options and an intended physiological action for each response option. Accordingly, one or more user monitoring data objects associated with the monitored end-user are received that include user brainwave monitoring data objects. These user monitoring data objects are processed using one or more response designation machine learning models to generate response designators based on the user monitoring data objects that includes a physiological response designator describing a selected intended physiological action that is deemed to be related to the user monitoring data objects. Accordingly, a user response is then determined based on the response designators and the user interface may be updated based on the user response.

First claim

The invention claimed is:

1. A computer-implemented method for enabling guided interaction with a query assistant software using brainwave data, the computer-implemented method comprising:
providing, by one or more processors, a query assistant user interface to a client device for presentation to a monitored end-user, wherein the query assistant user interface displays a query associated with a plurality of response options;
subsequent to providing the query assistant user interface, receiving, by the one or more processors, one or more user monitoring data objects associated with the monitored end-user, wherein the one or more user monitoring data objects comprise (i) one or more user brainwave monitoring data objects, and (ii) one or more physical action data objects captured by one or more sensors;
generating, using the one or more user monitoring data objects and a plurality of response designation machine learning models, a plurality of predicted response designators, wherein: (i) each of the plurality of response designators comprises a physiological response designator for a corresponding one of the response designation machine learning models, and (ii) each physiological response designator indicates the predicted likelihood that an intended physiological action was performed by the monitored end-user, wherein the predicted likelihood is generated by the corresponding one of the response designation machine learning models;
determining a user response based at least in part on the plurality of response designators by:
(i) identifying one or more dependent nodes of a current node of a conversation decision tree data object, wherein each dependent node of the one or more dependent nodes is associated with a related set of candidate response designator values,
(ii) identifying a selected dependent node of the one or more dependent nodes whose related set of candidate response designator values has a highest degree of overlap relative to the plurality of response designators, and
(iii) determining the user response based at least in part on the selected dependent node; and

providing a subsequent query to the query assistant user interface, wherein (a) the subsequent query is based at least in part on the determined user response, and (b) is presented via the client device to the monitored end-user.

2. The computer-implemented method of claim 1 , wherein the plurality of intended physiological actions comprises an intended jaw movement action and an intended eye blinking action.

3. The computer-implemented method of claim 1 , wherein the one or more user monitoring data objects further comprise at least one of a user device monitoring data object, a visual monitoring data object, an audio monitoring data object, or a user personification data object.

4. The computer-implemented method of claim 1 , wherein the plurality of response designators further comprises at least one of an emotional intensity designator, an emotional sensitivity designator, a physiological response intensity designator, or a user personification designator.

5. The computer-implemented method of claim 1 , wherein causing the client device to update the query assistant user interface based at least in part on the user response comprises:
determining whether the selected dependent node is associated with an updated query having a plurality of updated response options; and
in response to determining that the selected dependent node is associated with the updated query, causing the client device to update the query assistant user interface to describe the updated query.

6. The computer-implemented method of claim 1 , wherein the plurality of response designation machine learning models comprises a sentiment detection machine learning model.

7. The computer-implemented method of claim 6 , wherein:
the sentiment detection machine learning model is a supervised machine learning model trained using ground-truth sentiment designation labels; and
the ground-truth sentiment designation labels are generated based at least in part on sentiment reporting data for the monitored end-user over a sentiment monitoring window.

8. The computer-implemented method of claim 1 , wherein the plurality of response designation machine learning models comprises an intensity detection machine learning model.

9. The computer-implemented method of claim 8 , wherein:
the intensity detection machine learning model is a supervised machine learning model trained using ground-truth intensity designation labels; and
the ground-truth intensity designation labels are generated based at least in part on intensity reporting data for the monitored end-user over an intensity monitoring window.

10. An apparatus for enabling guided interaction with a query assistant software using brainwave data, the apparatus comprising at least one processor and at least one memory including a computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to:
provide a query assistant user interface to a client device for presentation to a monitored end-user, wherein the query assistant user interface displays a query associated with a plurality of response options;
subsequent to providing the query assistant user interface, receive one or more user monitoring data objects associated with the monitored end-user, wherein the one or more user monitoring data objects comprise (i) one or more user brainwave monitoring data objects, and (ii) one or more physical action data objects captured by one or more sensors;
generate, using the one or more user monitoring data objects and a plurality of response designation machine learning models, a plurality of predicted response designators, wherein: (i) each of the plurality of response designators comprises a physiological response designator for a corresponding one of the response designation machine learning models, and (ii) each physiological response designator indicates the predicted likelihood that an intended physiological action was performed by the monitored end-user, wherein the predicted likelihood is generated by the corresponding one of the response designation machine learning models;
determine a user response based at least in part on the plurality of response designators by:
(i) identifying one or more dependent nodes of a current node of a conversation decision tree data object, wherein each dependent node of the one or more dependent nodes is associated with a related set of candidate response designator values,
(ii) identifying a selected dependent node of the one or more dependent nodes whose related set of candidate response designator values has a highest degree of overlap relative to the plurality of response designators, and
(iii) determining the user response based at least in part on the selected dependent node; and

provide a subsequent query to the query assistant user interface, wherein (a) the subsequent query is based at least in part on the determined user response, and (b) is presented via the client device to the monitored end-user.

11. The apparatus of claim 10 , wherein the one or more user monitoring data objects further comprise at least one of a user device monitoring data object, a visual monitoring data object, an audio monitoring data object, or a user personification data object.

12. The apparatus of claim 10 , wherein the plurality of response designators further comprises at least one of an emotional intensity designator, an emotional sensitivity designator, a physiological response intensity designator, or a user personification designator.

13. The apparatus o

Assignees

• Optum Tech Inc

Inventors

• Krishna Amit
• Dutta Rahul
• Hasija Love
• Kumar Atul

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/9032

  Query formulation · CPC title

• G06F3/015 Primary

  Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/09

  Supervised learning · CPC title