# US 2021/0241137 A1 · Systems and methods for using machine learning to generate precision predictions of readiness > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241137 A1 - Document ID: US20210241137A1 - Status: Published application - Kind: A1 - Application number: 16/781,582 - 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/US20210241137A1 ## CPC - G06N 5/04: Inference or reasoning models - G06N 3/0499: Feedforward networks - G06N 3/09: Supervised learning - G06N 3/092: Reinforcement learning - G06N 20/00: Machine learning - 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 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance - 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 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - 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 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - 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 - 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 generate precision predictions of readiness. In some implementations, a database is accessed to obtain status data that indicates activities or attributes of a subject. A set of feature scores is derived from the status data for the subject, the set of feature scores including values indicative of attributes or activities of the subject. The set of feature scores to one or more models that have been configured to predict readiness of subjects to satisfy one or more readiness criteria. The one or models can be models configured using machine learning training. Based on processing performed using the one or more machine learning models and the set of feature scores, a prediction regarding the subject's ability to achieve readiness to satisfy the one or more readiness criteria is generated. ## Claims ### Claim 1 A method performed by one or more computers, the method comprising: training, by the one or more computers, one or more machine learning models based on collected data indicating (i) activities performed by multiple subjects over time and (ii) performance results for a particular activity that the multiple subjects achieved, the one or more machine learning models being trained to be able to predict readiness of subjects to perform the particular activity and achieve a predetermined performance result for the particular activity based at least in part on prior activities performed by the subjects; accessing, by the one or more computers, a database to obtain status data that indicates activities performed by a subject, the status data comprising data provided from by an electronic device to the one or more computers over a communication network; deriving, by the one or more computers, a set of feature scores from the status data for the subject, the set of feature scores including values indicative of activities performed by the subject; providing, by the one or more computers, the set of feature scores to the one or more machine learning models that have been trained to predict readiness of subjects to perform the particular activity and achieve the predetermined performance result for the particular activity; generating, by the one or more computers and based on processing performed using the one or more machine learning models and the set of feature scores, a prediction indicating at least one of (i) a predicted time that the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result or (ii) whether the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result; and based on the prediction, providing, by the one or more computers, output data that is configured to perform at least one of altering a user interface of a device or altering interaction of a device with the subject. ### Claim at position 2 2-3. (canceled) ### Claim 4 (depends on 1) The method of claim 1, wherein the one or more machine learning models comprise at least one of a neural network, a support vector machine, a classifier, a regression model, a reinforcement learning model, a clustering model, a decision tree, a random forest model, a genetic algorithm, a Bayesian model, or a Gaussian mixture model. ### Claim 5 (canceled) ### 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 indicating a sequence of activities that includes activities performed by the subject at different times; and wherein the set of feature scores derived from the status data comprises values indicating the sequence of activities performed by the subject at the different times. ### Claim 7 (canceled) ### Claim 8 (depends on 1) The method of claim 1, 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, wherein the subject is an individual, and wherein receiving status data comprises receiving at least one of heart rate data for the subject, oxygen saturation data for the subject, data indicating an exercise distance for the subject, data indicating an exercise intensity for the subject, or data indicating a duration of an exercise for the subject. ### Claim 10 (depends on 1) The method of claim 1, wherein generating the prediction comprises generating output indicating a predicted time that the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result. ### Claim 11 (depends on 1) The method of claim 1, wherein generating the prediction comprises generating output indicating whether the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result. ### Claim 12 (depends on 11) The method of claim 11, wherein generating the output indicating whether the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result comprises: generating output indicating whether the subject will acquire an ability to perform the particular activity at the performance level within one or more constraints that comprise a limit on at least one of: a time to achieve readiness; resources available to the subject; or a training plan for the subject. ### Claim 13 (canceled) ### Claim 14 (depends on 1) The method of claim 1, comprising: generating the collected data by tracking (i) activities of each of the multiple subjects over a period of time and (ii) changes in levels of capability of the multiple subjects to perform the particular activity over the period of time. ### Claim 15 (depends on 1) The method of claim 1, wherein the subject is a group of individual subjects; wherein receiving status data comprises receiving activity data indicating activities of individual subjects in the group; and wherein the method further comprises: generating, based on the activity data, a readiness score for each of the individual subjects in the group, the readiness scores indicating predictions of respective capabilities of the individual subjects in the group; and generating a group readiness measure that indicates a predicted ability of the group of individual subjects to collectively satisfy one or more group readiness criteria. ### Claim 16 (depends on 15) The method of claim 15, wherein providing output comprises providing, based on the group readiness measure, output indicating (i) a predicted time that the group will achieve readiness to satisfy the one or more group readiness criteria or (ii) a likelihood or prediction whether the group will achieve readiness to satisfy the one or more group readiness criteria given one or more constraints. ### Claim 17 (depends on 15) The method of claim 15, further comprising: receiving additional activity data indicating activities of the subjects in the group; generating, based on the additional activity data, a new readiness score for each of the subjects in the group; generating a new group readiness measure; and providing, based on the new group readiness measure, new output data indicating (i) a new predicted time that the group will achieve readiness to satisfy the one or more group readiness criteria or (ii) a new likelihood or prediction whether the group will achieve readiness to satisfy the one or more group readiness criteria given one or more constraints. ### Claim 18 (depends on 15) The method of claim 15, comprising: determining that the group readiness measure does not satisfy a threshold; and in response to determining that the group readiness measure does not satisfy the threshold, performing at least one of: removing from the group one or more subjects determined to have individual readiness scores that are less than an average of individual readiness scores for subjects in the group; or adding to the group one or more subjects having individual readiness scores that are greater than an average of individual readiness scores for subjects in the group. ### 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 machine learning models based on collected data indicating (i) activities performed by each of multiple subjects over time and (ii) performance results for a particular activity that the multiple subjects achieved, the one or more machine learning models being trained to be able to predict readiness of subjects to perform the particular activity and achieve a predetermined performance result for the particular activity based at least in part on prior activities performed by the subjects; accessing, by the one or more computers, a database to obtain status data that indicates activities performed by a subject, the status data comprising data provided from by an electronic device to the one or more computers over a communication network; deriving, by the one or more computers, a set of feature scores from the status data for the subject, the set of feature scores including values indicative of activities performed by the subject; providing, by the one or more computers, the set of feature scores to the one or more machine learning models that have been trained to predict readiness of subjects to perform the particular activity and achieve the predetermined performance result for the particular activity; generating, by the one or more computers and based on processing performed using the one or more machine learning models and the set of feature scores, a prediction indicating at least one of (i) a predicted time that the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result or (ii) whether the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result; and based on the prediction, providing, by the one or more computers, output data that is configured to perform at least one of altering a user interface of a device or altering interaction of a device with the subject. ### Claim 20 One or more non-transitory computer-readable media storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform operations comprising: training, by the one or more computers, one or more machine learning models based on collected data indicating (i) activities performed by each of multiple subjects over time and (ii) performance results for a particular activity that the multiple subjects achieved, the one or more machine learning models being trained to be able to predict readiness of subjects to perform the particular activity and achieve a predetermined performance result for the particular activity based at least in part on prior activities performed by the subjects; accessing, by the one or more computers, a database to obtain status data that indicates activities performed by a subject, the status data comprising data provided from by an electronic device to the one or more computers over a communication network; deriving, by the one or more computers, a set of feature scores from the status data for the subject, the set of feature scores including values indicative of activities performed by the subject; providing, by the one or more computers, the set of feature scores to the one or more machine learning models that have been trained to predict readiness of subjects to perform the particular activity and achieve the predetermined performance result for the particular activity; generating, by the one or more computers and based on processing performed using the one or more machine learning models and the set of feature scores, a prediction indicating at least one of (i) a predicted time that the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result or (ii) whether the subject will acquire an ability to perform the particular activity and achieve the predetermined performance result; and based on the prediction, providing, by the one or more computers, output data that is configured to perform at least one of altering a user interface of a device or altering interaction of a device with the subject. ### Claim 21 (depends on 1) The method of claim 1, wherein providing the output data comprises providing a recommendation, determined based on the prediction, of an action to improve or accelerate acquisition of an ability of the subject to perform the particular activity and achieve the predetermined performance result. ### Claim 22 (depends on 1) The method of claim 1, wherein providing the output data comprises providing an indication, for each of one or more candidate actions, that quantifies a predicted change in readiness of the subject, relative to a level of readiness indicated by the prediction, that would be achieved if the candidate action is performed for the subject. ### Claim 23 (depends on 1) The method of claim 1, wherein the status data indicates planned future training exercises for the subject to perform; wherein the set of feature scores includes values indicating the planned future training exercises for the subject to perform; and wherein the prediction is based on the one or more machine learning models processing feature values indicating (i) past training exercises performed by the user, and (ii) the planned future training exercises for the user. ### Claim 24 (depends on 1) The method of claim 1, wherein the collected data includes attributes of the multiple subjects, and wherein the training includes training the one or more machine learning models to learn relationships among different attributes of the subjects and different levels of effectiveness of an activity in improving performance of subjects that have the respective attributes; wherein accessing the database comprises accessing data indicating attributes of the subject; wherein the set of feature scores includes values indicative of attributes of the subject; wherein the prediction is generated based on processing, using the one or more machine learning models, both the values indicating activities of the subject and the values indicating the attributes of the subject. ### Claim 25 (depends on 1) The method of claim 1, wherein the set of feature scores includes time series data indicating a sequence of activities that the subject performed at different times. ### Claim 26 (depends on 1) The method of claim 1, wherein achieving the performance result includes performance of the particular activity that satisfies a predetermined threshold for at least one of speed, latency, accuracy, precision, consistency, efficiency, reliability, scalability, capacity, throughput, volume, or intensity. ### Claim 27 (depends on 1) The method of claim 1, wherein achieving the performance result involves completing a task or performing the particular activity with at least a predetermined level of proficiency.