Measuring cognitive load

• US 9,737,255 B2
• Filed: 09/29/2009
• Issued: 08/22/2017
• Est. Priority Date: 09/30/2008
• Status: Active Grant

• Current Assignee: National ICT Australia Limited
• Original Assignee: National ICT Australia Limited
• Inventors: Chen, Fang, Khawaja, Muhammad Asif, Choi, Eric
• Primary Examiner(s): EGLOFF, PETER RICHARD
• Application Number:
  US13/120,902
• Publication Number:
  US 20110207099A1
• Time in Patent Office: 2,884 Days
• Field of Search: 434227, 434236, 434323
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/4803 Speech analysis specially adapted for diagnostic purposes
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

This invention concerns measuring cognitive load. A word based input is produced by a person while performing a task (100). Predetermined grammatical features of the word based input are identified (104). Then, the identified grammatical features are weighted and combined to provide a measure indicating the person'"'"'s cognitive load (106). The use of grammatical features represents a divergence from the known methods of providing a measure of a person'"'"'s cognitive load. It is an advantage of the invention that by concentrating on the grammatical features it is able to provide an objective, non-intrusive measure of the person'"'"'s cognitive load. Aspects the invention include a method, a computer system and software that are used to perform the method.

Claims

1. A computer-implemented method for changing an output of a user interface of a computer system based on determination of a person'"'"'s cognitive load, the method comprising the steps of:

(a) receiving, from an input device, word based input produced by a person while performing a task;

(b) identifying automatically, using a processor, predetermined syntactical, morphological and semantic features of the word based input;

(c) weighting and combining, using a processor, the identified syntactical, morphological and semantic features to provide a measure of the person'"'"'s cognitive load;

(d) determining the person'"'"'s cognitive load, using a processor, in real-time or substantially real-time based on the measure of the person'"'"'s cognitive load;

(e) determining an output strategy of the user interface of the computer system, based on the determined cognitive load of the person; and

(f) changing the output of the user interface of the computer system to alleviate or increase the person'"'"'s cognitive load based on the determined output strategy while the person is performing the task, or after the task has been performed, wherein changing the output of the user interface of the computer system includes any one or more of;

(i) minimizing one or more applications displayed to the person;

(ii) showing only the displayed output for one application;

or

(iii) customizing the user interface to manage the flow of information.

2. The computer-implemented method of claim 1, further comprising the step of classifying the task.

3. The computer-implemented method of claim 2, wherein the predetermined syntactical, morphological and semantic features of step (b) are particular features relevant to that task classification.

4. The computer-implemented method of claim 1, wherein the predetermined syntactical, morphological and semantic features of step (b) include any one or more of:

identification of the number and types of nouns, pronouns, pronouns, propositions, and verbs;

identification of number and types of grammatical errors made;

identification of the number and types of a particular syntax or grammatical structures;

identification of the number and types of particular words and/or phrases at specific sentence and/or paragraph positions;

identification of the number of shorter or longer (i.e. six letters) words and/or sentences;

identification of semantics, meanings and interpretation of the words and/or sentences.

5. The computer-implemented method of claim 1, wherein the word based input is produced from speech of the person when performing the task.

6. The computer-implemented method of claim 2, further comprising classifying the task based on predetermined task and/or person profiles.

7. The computer-implemented method of claim 1, wherein the word based input of step (a) is text input that is typed by the person when performing the task.

8. The computer-implemented method of claim 6, wherein step (c) is based on the task and/or person profiles.

9. The computer-implemented method of claim 1 further comprising the step of receiving physiological input about the person and/or environmental data about the environment of the person while performing the task.

10. The computer-implemented method of claim 1, wherein the output strategy includes any one or more of:

(a) modulating pace, content, and format of the output;

(b) determining resources needed by the person to complete the task effectively and efficiently; and

(c) verifying for appropriateness the next task or system output or response.

13. Software instructions stored on a non-transitory machine-readable medium which when executed by a processor in a computer that can interface with a person, cause the processor to perform the method of changing an output of a user interface of a computer system based on determination of a person'"'"'s cognitive load according to claim 1.

11. A computer system to change an output of a user interface of the computer system based on determination of a person'"'"'s cognitive load while performing a task comprising:

a receiver to receive from an input device word based input produced by a person while performing the task; and

a classifier to identify automatically, using a processor, predetermined syntactical, morphological and semantic features of the word based input; and

a combiner to weight and combine the identified syntactical, morphological and semantic features to provide a measure of the person'"'"'s cognitive load; and

a processor to determine the person'"'"'s cognitive load in real-time or substantially real-time, based on the measure of the person'"'"'s cognitive load, determine an output strategy of the user interface of the computer system, based on the determined cognitive load of the person, and change the output of the user interface of the computer system to alleviate or increase the person'"'"'s cognitive load based on the determined output strategy, while the person is performing the task, or after the task has been performed, wherein changing the output of the user interface of the computer system includes any one or more of;

(i) minimizing one or more applications displayed to the person;

(ii) showing only the displayed output for one application;

or

(iii) customizing the user interface to manage the flow of information.

12. A computer system according to claim 11, wherein the person interacts with the computer system to perform the task.