US-12620471-B2 - Application tonality adjustment model

US12620471B2US 12620471 B2US12620471 B2US 12620471B2US-12620471-B2

Abstract

Methods, systems, and devices for adjusting a messaging tonality of messages delivered to a user are described. The system may acquire baseline physiological data measured from the user and generate one or more messages based on the baseline physiological data and in accordance with a first messaging tonality. The system may acquire additional physiological data from the user based on providing the one or more messages. In some cases, the system may perform an evaluation of the first messaging tonality by comparing the additional physiological data with the baseline physiological data and select a second messaging tonality from a plurality of messaging tonalities based on the evaluation of the first messaging tonality. The system may generate one or more additional messages to be provided to the user in accordance with the second messaging tonality based on selecting the second messaging tonality.

Inventors

Mats Kyyrö
Sofia Strömmer
Shishir Bhattarai
Kaisa Helena Tarvainen
Daria Kalmykova
Marko Uusitalo
Tarja Karjalainen
David Lee Hwang
Michael Johnson
Antonio Gusmao
Kathryn LaBeaume
Marcin Banaszynski
Josh Mobley
Kathryn Berry
Kelsey Radloff
Mari Pauliina Karsikas
Johanna Leena Kyllikki Still

Assignees

OURA HEALTH OY

Dates

Publication Date: 20260505
Application Date: 20230929

Claims (20)

1 . A system for adjusting a messaging tonality of messages delivered to a user, comprising: a wearable ring device configured to measure physiological data from a finger of the user, the wearable ring device comprising: one or more temperature sensors disposed at least partially within or beneath an inner curved surface of the wearable ring device and configured to acquire skin temperature data from the user through the inner curved surface; one or more light-emitting components configured to emit light into a tissue of the user through the inner curved surface of the wearable ring device; one or more light-receiving components configured to receive, through the inner curved surface, the light emitted by the one or more light-emitting components through the tissue of the user; one or more processors configured to process the physiological data associated with the user, the physiological data comprising the skin temperature data and heart rate data that is based at least in part on the light received by the one or more light-receiving components; and a wireless communications module configured to transmit the physiological data generated by the one or more processors; an application associated with the wearable ring device and executable by the wearable ring device, a user device communicatively coupled with the wearable ring device, or both; and one or more additional processors communicatively coupled with the wearable ring device, the application, or both, wherein the one or more additional processors are configured to: acquire baseline physiological data measured from the user via the wearable ring device; generate, using one or more large language models, one or more messages to be provided to the user via the application in response to the baseline physiological data and in accordance with a first messaging tonality; acquire additional physiological data from the user via the wearable ring device based at least in part on providing the one or more messages to the user in accordance with the first messaging tonality; perform an evaluation of the first messaging tonality by comparing the additional physiological data with the baseline physiological data; select a second messaging tonality from a plurality of messaging tonalities based at least in part on the evaluation of the first messaging tonality, wherein the second messaging tonality is associated with the one or more large language models; and generate, using the one or more large language models, one or more additional messages to be provided to the user via the application in accordance with the second messaging tonality based at least in part on selecting the second messaging tonality.
2 . The system of claim 1 , wherein the one or more additional processors are configured to: acquire second physiological data from the user via the wearable ring device based at least in part on providing the one or more messages to the user in accordance with the second messaging tonality; perform an evaluation of the second messaging tonality by comparing the second physiological data with the baseline physiological data, the additional physiological data, or both; select the second messaging tonality or a third messaging tonality from the plurality of messaging tonalities based at least in part on the evaluation of the second messaging tonality; and generate, using the one or more large language models, one or more additional messages to be provided to the user via the application in accordance with the second messaging tonality or the third messaging tonality based at least in part on the selecting.
3 . The system of claim 1 , wherein the one or more messages, the one or more additional messages, or both, are generated using the one or more large language models prior to acquiring the additional physiological data from the user, wherein the one or more additional processors are further configured to: retrieve the one or more messages that are to be provided to the user via the application from a database based at least in part on acquiring the baseline physiological data; and retrieve the one or more additional messages that are to be provided to the user via the application from the database based at least in part on acquiring the additional physiological data.
4 . The system of claim 1 , wherein the one or more additional processors are further configured to: receive a physiological data set from the user, one or more additional users, or both; determine that the physiological data set satisfies one or more thresholds; generate, using the one or more large language models, the one or more messages that are to be provided to the user in accordance with the first messaging tonality based at least in part on the baseline physiological data, the additional physiological data, or both, satisfying the one or more thresholds; and generate, using the one or more large language models, the one or more additional messages that are to be provided to the user in accordance with the second messaging tonality based at least in part on the baseline physiological data, the additional physiological data, or both, satisfying the one or more thresholds.
5 . The system of claim 1 , wherein the one or more additional processors are further configured to: input the baseline physiological data into one or more machine learning models; and input one or more evaluations of the baseline physiological data that are output from the one or more machine learning models into the one or more large language models, wherein generating the one or more messages is based at least in part on inputting the one or more evaluations into the one or more large language models.
6 . The system of claim 1 , wherein the one or more additional processors are configured to: identify a personality type of the user based at least in part on user interactions with the application; and select the first messaging tonality, the second messaging tonality, or both, based at least in part on identifying the personality type, wherein generating the one or more messages is based at least in part on selecting the first messaging tonality, and wherein generating the one or more additional messages is based at least in part on selecting the second messaging tonality.
7 . The system of claim 1 , wherein the one or more additional processors are configured to: determine that the additional physiological data satisfies one or more thresholds based at least in part on comparing the additional physiological data with the baseline physiological data, wherein the second messaging tonality is selected from the plurality of messaging tonalities based at least in part on determining the additional physiological data satisfies the one or more thresholds.
8 . The system of claim 1 , wherein the one or more additional processors are configured to: identify a trigger condition to transition from the first messaging tonality to the second messaging tonality based at least in part on acquiring the additional physiological data, wherein selecting the second messaging tonality is based at least in part on identifying the trigger condition.
9 . The system of claim 8 , wherein the one or more additional processors are configured to: receive a user input comprising an age of the user, a medical history of the user, one or more tags, a user interaction with the application, user feedback associated with the one or more messages generated in accordance with the first messaging tonality, one or more modifications to the first messaging tonality, or any combination thereof, wherein selecting the second messaging tonality is based at least in part on receiving the user input.
10 . The system of claim 1 , wherein the one or more additional processors are configured to: cause a graphical user interface (GUI) of the user device to display the one or more messages via the application in accordance with the first messaging tonality based at least in part on generating the one or more messages; and cause the GUI of the user device to display the one or more additional messages via the application in accordance with the second messaging tonality based at least in part on generating the one or more additional messages.
11 . The system of claim 1 , wherein the one or more additional processors are configured to: cause the user device to provide, via the application, a first audio output of the one or more messages in accordance with the first messaging tonality based at least in part on generating the one or more messages; and cause the user device to provide, via the application, a second audio output of the one or more additional messages in accordance with the second messaging tonality based at least in part on generating the one or more additional messages.
12 . The system of claim 1 , wherein the one or more additional processors are configured to: input the baseline physiological data into the one or more large language models based at least in part on receiving the baseline physiological data, wherein generating the one or more messages are based at least in part on inputting the baseline physiological data into the one or more large language models; and input the additional physiological data into the one or more large language models based at least in part on acquiring the additional physiological data, wherein generating the one or more additional messages are based at least in part on inputting the additional physiological data into the one or more large language models.
13 . The system of claim 1 , wherein the first messaging tonality is associated with a first set of characteristics, and wherein the second messaging tonality is associated with a second set of characteristics, wherein the first set of characteristics, the second set of characteristics, or both, comprise a word choice, a word arrangement, a punctuation, one or more graphical elements, a volume, a cadence, an inflection, or any combination thereof.
14 . The system of claim 1 , wherein the wearable ring device comprises a finger-worn device, a wrist-worn device, a head-worn device, a chest-worn device, or a combination thereof.
15 . The system of claim 1 , wherein the one or more additional processors are located within the wearable ring device, within the user device, with a server, or any combination thereof.
16 . The system of claim 1 , wherein the wearable ring device collects the baseline physiological data and the additional physiological data from the user based on arterial blood flow, capillary blood flow, arteriole blood flow, or a combination thereof.
17 . A system for adjusting a messaging tonality of messages delivered to a user, comprising: a wearable ring device configured to measure physiological data from a finger of the user, the wearable ring device comprising: one or more temperature sensors disposed at least partially within or beneath an inner curved surface of the wearable ring device and configured to acquire skin temperature data from the user through the inner curved surface; one or more light-emitting components configured to emit light into a tissue of the user through the inner curved surface of the wearable ring device; one or more light-receiving components configured to receive, through the inner curved surface, the light emitted by the one or more light-emitting components through the tissue of the user; one or more processors configured to process the physiological data associated with the user, the physiological data comprising the skin temperature data and heart rate data that is based at least in part on the light received by the one or more light-receiving components; and a wireless communications module configured to transmit the physiological data generated by the one or more processors; one or more memories storing processor-executable code; and one or more additional processors coupled with the one or more memories and individually or collectively operable to execute the code to: acquire baseline physiological data measured from the user via the wearable ring device; generate, using one or more large language models, one or more messages to be provided to the user via an application associated with the wearable ring device in response to the baseline physiological data and in accordance with a first messaging tonality; acquire additional physiological data from the user via the wearable ring device based at least in part on providing the one or more messages to the user in accordance with the first messaging tonality; perform an evaluation of the first messaging tonality by comparing the additional physiological data with the baseline physiological data; select a second messaging tonality from a plurality of messaging tonalities based at least in part on the evaluation of the first messaging tonality, wherein the second messaging tonality is associated with the one or more large language models; and generate, using the one or more large language models, one or more additional messages to be provided to the user via the application in accordance with the second messaging tonality based at least in part on selecting the second messaging tonality.
18 . The system of claim 17 , wherein the one or more additional processors are further configured to: acquire second physiological data from the user via the wearable ring device based at least in part on providing the one or more messages to the user in accordance with the second messaging tonality; perform an evaluation of the second messaging tonality by comparing the second physiological data with the baseline physiological data, the additional physiological data, or both; select the second messaging tonality or a third messaging tonality from the plurality of messaging tonalities based at least in part on the evaluation of the second messaging tonality; and generate, using the one or more large language models, one or more additional messages to be provided to the user via the application in accordance with the second messaging tonality or the third messaging tonality based at least in part on the selecting.
19 . A method for adjusting a messaging tonality of messages delivered to a user, comprising: acquiring baseline physiological data from the user via a wearable ring device configured to be worn on a finger of the user, the baseline physiological data comprising at least skin temperature data acquired through an inner curved surface of the wearable ring device via one or more temperature sensors, and heart rate data acquired via one or more light-emitting components and one or more light-receiving components of the wearable ring device; transmitting, using a wireless communications module of the wearable ring device, the baseline physiological data to a user device, a server, or both, comprising one or more processors; generating, using one or more large language models, one or more messages to be provided to the user via an application associated with the wearable ring device in response to the baseline physiological data and in accordance with a first messaging tonality; acquiring additional physiological data from the user via the wearable ring device based at least in part on providing the one or more messages to the user in accordance with the first messaging tonality; performing an evaluation of the first messaging tonality by comparing the additional physiological data with the baseline physiological data; selecting a second messaging tonality from a plurality of messaging tonalities based at least in part on the evaluation of the first messaging tonality, wherein the second messaging tonality is associated with the one or more large language models; and generating, using the one or more large language models, one or more additional messages to be provided to the user via the application in accordance with the second messaging tonality based at least in part on selecting the second messaging tonality.
20 . The method of claim 19 , further comprising: acquiring second physiological data from the user via the wearable ring device based at least in part on providing the one or more messages to the user in accordance with the second messaging tonality; performing an evaluation of the second messaging tonality by comparing the second physiological data with the baseline physiological data, the additional physiological data, or both; selecting the second messaging tonality or a third messaging tonality from the plurality of messaging tonalities based at least in part on the evaluation of the second messaging tonality; and generating, using the one or more large language models, one or more additional messages to be provided to the user via the application in accordance with the second messaging tonality or the third messaging tonality based at least in part on the selecting.

Description

FIELD OF TECHNOLOGY The following relates to wearable devices and data processing, including techniques for an application tonality adjustment model. BACKGROUND Some wearable devices may be configured to collect data from users including photoplethysmogram (PPG) data, heart rate data, and the like. Some wearable devices may be associated with an application on a user device that generates messages and/or insights for the user based on the acquired physiological data. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 illustrates an example of a system that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 2 illustrates an example of a system that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 3 shows an example of a system that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 4 shows an example of a system that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 5 shows an example of a graphical user interface (GUI) that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 6 shows a block diagram of an apparatus that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 7 shows a block diagram of a wearable application that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 8 shows a diagram of a system including a device that supports techniques for an application tonality adjustment model in accordance with aspects of the present disclosure. FIG. 9 shows a flowchart illustrating methods that support application tonality adjustment model in accordance with aspects of the present disclosure. DETAILED DESCRIPTION Some wearable devices may be configured to acquire physiological data from a user, including photoplethysmogram (PPG) data, temperature data, heart rate, heart rate variability (HRV) data, sleep data, respiratory data, blood pressure data, and the like. Acquired physiological data may be used to analyze behavioral and physiological characteristics associated with the user, such as movement, sleeping patterns, and the like. Many users have a desire for more insight regarding their physical health, including their activity patterns, sleep patterns, and overall physical well-being. In some cases, wearable devices may be associated with an application on a user device that generates messages and/or insights for the user based on the acquired physiological data. However, conventional techniques that provide messages and/or insights to the user may utilize a same tone and/or content of the message for every user. That is, any user that exhibits physiological data that satisfies certain thresholds or characteristics may receive a message that is delivered with the same messaging tonality (e.g., “an encouraging coach” tonality). The content of messages delivered within the application may vary based on each respective user's physiological data, but existing applications may not allow the messaging tonality to vary from user to user. That is, even for devices that collect a user's physiological data, typical devices and applications lack the ability to collect other physiological, behavioral, or contextual inputs from the user that can be combined with the measured data to more comprehensively understand the complete set of physiological contributors to a user's health. Moreover, existing applications do not allow the messaging tonality to vary from user to user. Due to the fact that different users may react differently to various messaging tonalities, the inability to tailor messaging tonalities to each respective user may result in a lack of engagement and may affect a user's ability and motivation to improve their overall health. Accordingly, aspects of the present disclosure are directed to techniques for adjusting the tonality of messages delivered to the user to determine which messaging tonality the user best responds to (e.g., which tonality results in an improved and/or maintained health outcome). For example, the system may generate, using one or more large language models (LLMs), one or more messages to be provided to the user via the application in accordance with a first messaging tonality and in response to baseline physiological data of the user. The system may acquire additional physiological data from the user via the wearable device after providing the one or more messages to the user in accordance with the first messaging tonality. In some cases, the system may perform an evaluation of the first messaging tonality by comparing the additional physiological data with the baseline physiological data