# US 11,029,918 B2 · Conversational virtual healthcare assistant

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,029,918 B2
- Document ID: US11029918B2
- Status: Granted
- Kind: B2
- Application number: 15/811,301
- Filed: 2017-11-13
- Published: 2018-03-08
- Granted: 2021-06-08
- Earliest claimed: 2012-09-07
- Assignees: Verint Americas Inc.
- Applicants: Verint Americas Inc.
- Inventors: Fred A. Brown; Mitchell G. Lawrence; Victor O'Brien Morrison
- Web page: https://patentgrep.com/patent/US11029918B2

## CPC

- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 3/04886: by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
- G10L 15/08: Speech classification or search
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06Q 10/10: Office automation; Time management
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 50/50: for simulation or modelling of medical disorders
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A conversation user interface enables a patient to better understand their healthcare by integrating diagnosis, treatment, medication management, and/or payment, through a system that uses a virtual assistant to engage in conversation with the patient. The conversation user interface conveys a visual representation of a conversation between the virtual assistant and the patient. An identity of the patient, including preferences and/or medical records, is maintained throughout interactions so that each aspect of this integrated system has access to the same information. The conversation user interface allows the patient to interact with the virtual assistant using natural language commands to receive information and complete a task related to his or her healthcare.

## Claims

### Claim 1

One or more non-transitory computer-readable media storing computer-executable instructions that, when executed on one or more processors, cause the one or more processors to perform acts comprising:
causing display of a conversation user interface in conjunction with a content from a healthcare entity;
receiving patient input from a patient while the patient consumes the content from the healthcare entity, the input comprising one of verbal input, keypad input, or touch input;
representing the patient input in the conversation user interface;
determining a context from the patient input;
determining a first response to the user input based at least in part on medical records of the patient and assumptions derived from the context of the patient input;
representing the first response in the conversation user interface as a first message from a virtual assistant;
displaying the assumptions derived from the context of the input in the conversational user input, wherein the assumptions are displayed separate from the first message;
receiving a modification to at least one of the displayed assumptions; and
in response to receiving the modification:
determining a second response to the patient input based at least in part on the medical records of the patient and the modified assumptions; and
refreshing the conversation GUI to replace the first message with a second message from the virtual assistant representing the second response.

### Claim 2 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the input is verbal input, and the verbal input is represented in the conversation user interface in a text format through a speech recognition engine.

### Claim 3 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the patient input is verbal input, and the determining the first response comprises a combination of interpreting the verbal input through speech recognition techniques and ascertaining a suitable response for the verbal input through natural language processing techniques.

### Claim 4 (depends on 3)

One or more non-transitory computer-readable media as recited in claim 3, wherein the assumptions used to determine the first response comprise first assumptions pertaining to speech recognition of the verbal input and second assumptions pertaining to natural language processing of the verbal input.

### Claim 5 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the patient input is verbal input, and the acts further comprise:
authenticating an identity of the patient through analysis of the voice patterns contained in the verbal input.

### Claim 6 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the context comprises past behavior of the patient and the assumptions are derived at least in part from the past behavior of the patient.

### Claim 7 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the context comprises a status of the patient as checked in or checked out of a healthcare facility.

### Claim 8 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the acts further comprise:
receiving a request from the patient to expose the assumptions used in determining the response; and
displaying the assumptions derived from the content of the input in the conversational user input-in response to the request.

### Claim 9 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the user input is verbal input, and the acts further comprise:
determining that the patient input includes a query that cannot be processed unambiguously;
in response to the determination, displaying a dialog representation indicating an ambiguity in the conversational user interface, wherein the dialog representation comprises a plurality of options;
receiving a selection of one of the options of the plurality of options;
in response to the selection, determining a second response to the patient input based at least in part on the medical records of the patient and the selected option; and
representing the second response in the conversation user interface as a second message from the virtual assistant.

### Claim 10 (depends on 1)

One or more non-transitory computer-readable media as recited in claim 1, wherein the user input is verbal input, and the acts further comprise:
when the patent input is verbal input, detecting that the patient is in pain based on one or more speech patterns of the patient input; and
determining the context from the patient input and the detection that the patient is in pain.

### Claim 11

A system comprising:
one or more processors; and
memory storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
causing display of a conversation user interface along with a visual representation of a virtual assistant, the virtual assistant being configured with a persona;
receiving patient input comprising at least one of verbal input, keypad input, or touch input;
representing the patient input in the conversation user interface;
determining a context from the patient input;
determining a first response to the patient input based at least in part on a medical record and an assumption derived from the context of the patient input;
representing the first response in the conversation user interface as a first message from the virtual assistant;
displaying the assumption derived from the context of the patient input in the conversational user input, wherein the assumptions are displayed separate from the first message;
receiving a modification to the displayed assumption; and
in response to receiving the modification:
determining a second response to the patient input based at least in part on the medical records of the patient and the modified assumption; and
refreshing the conversation GUI to replace the first message with a second message from the virtual assistant representing the second response.

### Claim 12 (depends on 11)

The system of claim 11, wherein the determining the first response to the patient input is based on at least one of medical research results, nutrition information, or insurance information.

### Claim 13 (depends on 11)

The system of claim 11, wherein the operations further comprise:
parsing the patient input to identify one or more concepts expressed therein; and
determining an intent of the patient input based at least in part on the one or more concepts and the context; and
wherein the determining the response to the patient input is based at least in part on the intent and the context.

### Claim 14 (depends on 13)

The system of claim 13, wherein the identifying the one or more concepts comprises identifying one or more keywords within the patient input and mapping the one or more keywords to the one or more concepts.

### Claim 15 (depends on 13)

The system of claim 13, wherein the determining of the intent comprises mapping the one or more concepts to one of multiple different intents associated with the one or more concepts based at least in part on the context.

### Claim 16

A method comprising:
causing, by a computing device, display of a conversation user interface along with a visual representation of a virtual assistant, the virtual assistant being configured with a persona;
receiving, by the computing device, patient input comprising at least one of verbal input, keypad input, or touch input;
representing, by the computing device, the patient input in the conversation user interface;
determining, by the computing device, a context from the patient input;
determining, by the computing device, a first response to the patient input based at least in part on a medical record of a patient and an assumption derived from the context of the patient input;
representing, by the computing device, the first response in the conversation user interface as a first message from the virtual assistant;
displaying, by the computing device, the assumption derived from the context of the patient input in the conversational user input, wherein the assumptions are displayed separate from the first message;
receiving, by the computing device, a modification to the displayed assumption; and
in response to receiving the modification:
determining, by the computing device, a second response to the patient input based at least in part on the medical records of the patient and the modified assumption; and
refreshing, by the computing device, the conversation GUI to replace the first message with a second message from the virtual assistant representing.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
determining an intent of the patient input based at least in part on one or more concepts and a first portion of the context; and
wherein the determining the first response to the patient input is based at least in part on the intent and a second portion of the context.

### Claim 18 (depends on 16)

The method of claim 16, wherein the context comprises:
whether or not the patient has checked in with a healthcare entity;
a status of a medical device used by the patient;
a level of insurance coverage available to the patient;
a prescription medication used by the patient;
a diagnosed condition of the patient;
a time of day at which the patient provides the patient input to the virtual assistant;
a date on which the patient provides the patient input to the virtual assistant;
an age of the patient;
a location of the patient; or
a device type of a device associated with the patient.

### Claim 19 (depends on 16)

The method of claim 16, further comprising:
causing an action on behalf of the patient, the action comprising at least one of:
scheduling a medical appointment on behalf of the patient;
initiating a prescription refill request on behalf of the patient;
accessing data from a medical device on behalf of the patient;
communicating with an insurance provider on behalf of the patient; or
altering a previously initiated action on behalf of the patient.

### Claim 20 (depends on 16)

The method of claim 16, further comprising:
learning over time that certain words of the patient input map to certain vocabulary terms or concepts.