# US 2021/0241139 A1 · Systems and methods for using machine learning to improve processes for achieving readiness

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

- Number: US 2021/0241139 A1
- Document ID: US20210241139A1
- Status: Published application
- Kind: A1
- Application number: 16/781,793
- Filed: 2020-02-04
- Published: 2021-08-05
- Earliest claimed: 2020-02-04
- Assignees: VigNet Incorporated
- Applicants: Vignet Incorporated
- Inventors: Praduman Jain; Dave Klein; Josh Schilling
- Web page: https://patentgrep.com/patent/US20210241139A1

## CPC

- G06N 5/04: Inference or reasoning models
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N 20/00: Machine learning
- G06Q 10/0639: Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 20/10: relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G16H 20/70: relating to mental therapies, e.g. psychological therapy or autogenous training
- G16H 40/63: for local operation
- G16H 40/67: for remote operation
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- A63B 24/00: Electric or electronic controls for exercising apparatus of preceding groups; {Controlling or monitoring of exercises, sportive games, training or athletic performances}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/126: Evolutionary algorithms, e.g. genetic algorithms or genetic programming
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- Y02A 90/10: Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A63B: APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT (apparatus for passive exercising, massage A61H)
- Y02A: TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE

## Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using machine learning to improve processes for achieving readiness. In some implementations, a database is accessed to obtain status data that indicates activities or attributes of a subject. One or more readiness scores indicating a level of capability of the subject to satisfy one or more readiness criteria are generated. Data is accessed indicating multiple candidate actions for improving capability of the subject to satisfy one or more readiness criteria. A subset of the candidate actions for the subject are selected based on the one or more readiness scores generated using the one or more models. Output is provided to cause one or more of the actions in the selected subset to be performed or cause an indication one or more of the actions in the selected subset to be presented on a user interface.

## Claims

### Claim 1

A method performed by one or more computers, the method comprising:
training, by the one or more computers, one or more models based on example data indicating patterns with which multiple subjects that have different attributes have acquired readiness to satisfy one or more readiness criteria, the one or more models being trained to predict a level of capability of a subject to satisfy the one or more readiness criteria based on input that indicates attributes of the subject, wherein the training uses the attributes of the subjects and the corresponding patterns of acquiring readiness indicated by the example data to customize readiness predictions according to attributes that are indicated by input to the one or more models;
accessing, by the one or more computers, a database to obtain status data that indicates attributes of a subject, the status data comprising data provided by an electronic device to the one or more computers over a communication network;
generating, by the one or more computers, a set of multiple readiness scores for the subject, each of the readiness scores in the set indicating a level of capability of the subject to satisfy the one or more readiness criteria at a different time, the set of multiple readiness scores being generated using the one or more models and indicating a trend of acquiring readiness for the subject;
accessing, by the one or more computers, data indicating multiple candidate actions for improving capability of the subject to satisfy one or more readiness criteria;
selecting, by the one or more computers, a subset of the candidate actions for the subject based on a comparison of (i) a trend of acquiring readiness by the subject that is indicated by the set of multiple readiness scores generated using the one or more models and (ii) trends observed for other subjects in acquiring readiness to satisfy the one or more readiness criteria; and
providing, by the one or more computers, output configured to perform at least one of (i) causing one or more of the actions in the selected subset to be performed by the one or more computers or another system or (ii) causing an indication of one or more of the actions in the selected subset to be presented on a user interface of the one or more computers or another system.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more models comprise one or more machine learning models.

### Claim 3 (depends on 1)

The method of claim 1, wherein the one or more readiness criteria comprise at least one of:
a physical state of the subject;
a functional state of the subject; or
a level of capability of the subject to perform a task.

### Claim 4 (depends on 1)

The method of claim 1, wherein the one or more models comprise at least one of a neural network, a support vector machine, a classifier, a regression model, a clustering model, a decision tree, a random forest model, a genetic algorithm, a Bayesian model, or a Gaussian mixture model.

### Claim 5 (depends on 1)

The method of claim 1, wherein the one or more models have been trained based on training data indicating (i) activities or attributes of other subjects and (ii) outcomes for the other subjects with respect to the readiness criteria,
wherein the training uses the respective progressions of readiness of the other subjects over time to configure the one or more models to predict readiness of subjects to satisfy one or more readiness criteria.

### Claim 6 (depends on 1)

The method of claim 1, wherein the database comprises data generated for the subject over a period of time, the status data comprising information about activities or attributes of the subject at multiple points in time; and
wherein the one or more readiness scores are generated using the one or more models by providing, to the one or more models, a set of feature scores, derived from the status data, that comprises measures of the activities or attributes of the subject at each of the multiple points in time.

### Claim 7

(canceled)

### Claim 8 (depends on 6)

The method of claim 6, wherein the set of feature scores is based on sensor data that is acquired by one or more sensors during one or more activities of the subject or that indicates one or more attributes of the subject.

### Claim 9 (depends on 1)

The method of claim 1, comprising:
determining (i) a plurality of training options for the subject and (ii) measures of how the respective training options are predicted to affect the readiness of the subject to satisfy the one or more readiness criteria;
wherein the selection is based at least in part on the measures.

### Claim 10 (depends on 1)

The method of claim 1, wherein accessing the data indicating the multiple candidate actions comprises accessing data indicating candidate actions comprising at least one of:
changing a frequency, number, or intensity of planned training activities for the subject;
changing an allocation of resources for the subject;
changing a type of training for the subject;
changing an assignment of an individual to assist the subject in achieving readiness; or
providing, for output by a client device, a notification indicating the level of capability of the subject to satisfy one or more readiness criteria that is indicated by the one or more readiness scores.

### Claim 11 (depends on 1)

The method of claim 1, wherein accessing the data indicating the multiple candidate actions comprises:
generating one or more candidate actions based on information indicating available resources for training the subject and at least one of:
information about the subject from the database;
data indicating actions taken to improve readiness of the subject; or
data indicating one or more planned future actions to improve readiness of the subject.

### Claim 12 (depends on 1)

The method of claim 1, wherein selecting the subset of the candidate actions comprises:
determining a score for each of the candidate actions, the scores being indicative of a predicted effect of the respective candidate actions on readiness of the subject to satisfy the one or more readiness criteria; and
selecting the subset based on the scores for the candidate actions.

### Claim 13 (depends on 12)

The method of claim 12, wherein the scores for the candidate actions are determined based on data indicating changes in attributes or capabilities of one or more other subjects after actions corresponding to the candidate actions are performed for the one or more other subjects.

### Claim 14 (depends on 12)

The method of claim 12, wherein the scores for the candidate actions are determined based on data indicating previous activities of the subject and changes in attributes or capabilities of the subject after the previous activities.

### Claim 15 (depends on 1)

The method of claim 1, wherein the scores for the candidate actions are determined based on (i) current attributes of the subject and (ii) planned or scheduled activities of the subject.

### Claim at position 16

16-18. (canceled)

### Claim 19

A system comprising:
one or more computers; and
one or more computer-readable media storing instructions that, when executed, cause the one or more computers to perform operations comprising:
training, by the one or more computers, one or more models based on example data indicating patterns with which multiple subjects that have different attributes have acquired readiness to satisfy one or more readiness criteria, the one or more models being trained to predict a level of capability of a subject to satisfy the one or more readiness criteria based on input that indicates attributes of the subject, wherein the training uses the attributes of the subjects and the corresponding patterns of acquiring readiness indicated by the example data to customize readiness predictions according to attributes that are indicated by input to the one or more models;
accessing, by the one or more computers, a database to obtain status data that indicates attributes of a subject, the status data comprising data provided by an electronic device to the one or more computers over a communication network;
generating, by the one or more computers, a set of multiple readiness scores for the subject, each of the readiness scores in the set indicating a level of capability of the subject to satisfy the one or more readiness criteria at a different time, the set of multiple readiness scores being generated using the one or more models and indicating a trend of acquiring readiness for the subject;
accessing, by the one or more computers, data indicating multiple candidate actions for improving capability of the subject to satisfy one or more readiness criteria;
selecting, by the one or more computers, a subset of the candidate actions for the subject based on a comparison of (i) a trend of acquiring readiness by the subject that is indicated by the set of multiple readiness scores generated using the one or more models and (ii) trends observed for other subjects in acquiring readiness to satisfy the one or more readiness criteria; and
providing, by the one or more computers, output configured to perform at least one of (i) causing one or more of the actions in the selected subset to be performed by the one or more computers or another system or (ii) causing an indication of one or more of the actions in the selected subset to be presented on a user interface of the one or more computers or another system.

### Claim 20

One or more non-transitory computer-readable media storing instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:
training, by the one or more computers, one or more models based on example data indicating patterns with which multiple subjects that have different attributes have acquired readiness to satisfy one or more readiness criteria, the one or more models being trained to predict a level of capability of a subject to satisfy the one or more readiness criteria based on input that indicates attributes of the subject, wherein the training uses the attributes of the subjects and the corresponding patterns of acquiring readiness indicated by the example data to customize readiness predictions according to attributes that are indicated by input to the one or more models;
accessing, by the one or more computers, a database to obtain status data that indicates attributes of a subject, the status data comprising data provided by an electronic device to the one or more computers over a communication network;
generating, by the one or more computers, a set of multiple readiness scores for the subject, each of the readiness scores in the set indicating a level of capability of the subject to satisfy the one or more readiness criteria at a different time, the set of multiple readiness scores being generated using the one or more models and indicating a trend of acquiring readiness for the subject;
accessing, by the one or more computers, data indicating multiple candidate actions for improving capability of the subject to satisfy one or more readiness criteria;
selecting, by the one or more computers, a subset of the candidate actions for the subject based on a comparison of (i) a trend of acquiring readiness by the subject that is indicated by the set of multiple readiness scores generated using the one or more models and (ii) trends observed for other subjects in acquiring readiness to satisfy the one or more readiness criteria; and
providing, by the one or more computers, output configured to perform at least one of (i) causing one or more of the actions in the selected subset to be performed by the one or more computers or another system or (ii) causing an indication of one or more of the actions in the selected subset to be presented on a user interface of the one or more computers or another system.

### Claim 21 (depends on 1)

The method of claim 1, wherein the readiness scores indicate predicted measures of current capability of the subject to perform a particular activity.

### Claim 22 (depends on 1)

The method of claim 1, wherein the readiness scores indicate predicted measures of future capability of the subject to perform a particular activity.

### Claim 23 (depends on 1)

The method of claim 1, comprising determining, based on the comparison, that a progression of acquiring readiness by the subject deviates from a reference progression of acquiring readiness that is based on data indicating a progression of readiness measures over time for multiple subjects that successfully acquired readiness;
wherein selecting the subset of the candidate actions for the subject comprises selecting a subset of the candidate actions that is predicted to improve the subject's progression of acquiring readiness toward the reference progression of acquiring readiness.

### Claim 24 (depends on 1)

The method of claim 1, comprising causing a device to display one or more scores indicative of a predicted change to the readiness of the subject to satisfy the one or more readiness criteria.

### Claim 25 (depends on 1)

The method of claim 1, comprising generating visualization data to illustrate a timeline or trend indicating a progression of readiness of the subject to satisfy the one or more readiness criteria if one or more of the selected actions are performed; and
providing the visualization data to cause a device to display a visualization based on the visualization data.

### Claim 26 (depends on 1)

The method of claim 1, comprising determining a composite reference trend representing a typical progression toward readiness, the composite reference trend being based on progressions toward readiness by multiple subjects that have successfully acquired readiness to achieve the one or more readiness criteria; and
determining that the trend indicated by the set of readiness scores for the subject deviates from the composite reference trend;
wherein selecting the subset of the candidate actions for the subject comprises, in response to determining that the trend indicated by the set of readiness scores for the subject deviates from the composite reference trend, selecting candidate actions to adjust the progression of readiness by the subject to align with the composite reference trend for subjects that have successfully acquired readiness to satisfy the one or more readiness criteria.

### Claim 27 (depends on 1)

The method of claim 1, wherein the training uses the example data to learn relationships between different attributes of subjects and different outcomes in acquiring readiness to satisfy the one or more readiness criteria, the training updating the one or more models based on the learned relationships.

### Claim 28 (depends on 1)

The method of claim 1, wherein the training updates the one or more models to generate predictions in which the presence of different attributes results in different levels of effect that training activities are predicted to have on acquiring readiness to satisfy the one or more readiness criteria.

### Claim 28 (depends on 1)

The method of claim 1, wherein the subset of the candidate actions is selected based on the attributes of the subject.

### Claim 29 (depends on 1)

The method of claim 1, wherein selecting the subset of candidate actions comprises evaluating a magnitude of predicted improvement to the readiness of the subject for the different candidate actions and filtering the set of candidate actions such that the subset includes candidate actions predicted to provide the subject at least a minimum level of predicted improvement in acquiring readiness to satisfy the one or more readiness criteria.
