# US 2023/0267133 A1 · Systems and methods for providing predictions to applications executing on a computing device

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

- Number: US 2023/0267133 A1
- Document ID: US20230267133A1
- Status: Published application
- Kind: A1
- Application number: 18/299,684
- Filed: 2023-04-12
- Published: 2023-08-24
- Earliest claimed: 2015-06-05
- Assignees: Apple Inc.
- Applicants: Apple Inc.
- Inventors: Joao Pedro LACERDA; Gaurav KAPOOR
- Web page: https://patentgrep.com/patent/US20230267133A1

## CPC

- G06F 16/285: {Clustering or classification}
- G06F 3/0481: based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F 9/453: {Help systems}
- G06F 16/90335: {Query processing}
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The embodiments set forth techniques for implementing various “prediction engines” that can be configured to provide different kinds of predictions within a mobile computing device. According to some embodiments, each prediction engine can assign itself as an “expert” on one or more “prediction categories” within the mobile computing device. When a software application issues a request for a prediction for a particular category, and two or more prediction engines respond with their respective prediction(s), a “prediction center” can be configured to receive and process the predictions prior to responding to the request. Processing the predictions can involve removing duplicate information that exists across the predictions, sorting the predictions in accordance with confidence levels advertised by the prediction engines, and the like. In this manner, the prediction center can distill multiple predictions down into an optimized prediction and provide the optimized prediction to the software application.

## Claims

### Claim 1

A method, comprising, by a software application executing on a computing device:
issuing, to a prediction center executing on the computing device, a request for a prediction associated with a prediction category;
receiving the prediction from the prediction center;
monitoring activity at the computing device to determine an accuracy of the prediction;
generating prediction center feedback based on the accuracy; and
providing the prediction center feedback to the prediction center, wherein the prediction center feedback is constructed for updating the prediction center to improve accuracy of subsequent predictions associated with the prediction category.

### Claim 2 (depends on 1)

The method of claim 1, wherein the prediction center provides predictions for a plurality of prediction categories, and the plurality of prediction categories includes the prediction category.

### Claim 3 (depends on 1)

The method of claim 1, wherein issuing the request causes the prediction center to:
identify, among a plurality of prediction engines, one or more prediction engines that are capable of providing predictions associated with the prediction category;
provide, to the one or more prediction engines, information associated with the request;
receive one or more predictions from the one or more prediction engines;
aggregate the one or more predictions to generate the prediction.

### Claim 4 (depends on 3)

The method of claim 3, wherein improving the accuracy of subsequent predictions associated with the prediction category comprises:
providing the prediction center feedback to at least one of the one or more prediction engines, wherein the one or more prediction engines update, based on the prediction center feedback, respective confidence levels that are advertised to the prediction center with regard to generating predictions for the prediction category.

### Claim 5 (depends on 1)

The method of claim 1, wherein:
the prediction indicates that a particular action will be taken by a user of the computing device, and
monitoring the activity at the computing device comprises determining whether the particular action was taken by the user.

### Claim 6 (depends on 1)

The method of claim 1, wherein the prediction is associated with a confidence level.

### Claim 7 (depends on 6)

The method of claim 6, wherein the confidence level affects a manner in which the prediction center aggregates the prediction with the at least one other prediction.

### Claim 8

A non-transitory computer readable storage medium configured to store instructions that, when executed by at least one processor included in a computing device, cause the computing device to carry out steps that include:
issuing, to a prediction center executing on the computing device, a request for a prediction associated with a prediction category;
receiving the prediction from the prediction center;
monitoring activity at the computing device to determine an accuracy of the prediction;
generating prediction center feedback based on the accuracy; and
providing the prediction center feedback to the prediction center, wherein the prediction center feedback is constructed for updating the prediction center to improve accuracy of subsequent predictions associated with the prediction category.

### Claim 9 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein the prediction center provides predictions for a plurality of prediction categories, and the plurality of prediction categories includes the prediction category.

### Claim 10 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein issuing the request causes the prediction center to:
identify, among a plurality of prediction engines, one or more prediction engines that are capable of providing predictions associated with the prediction category;
provide, to the one or more prediction engines, information associated with the request;
receive one or more predictions from the one or more prediction engines;
aggregate the one or more predictions to generate the prediction.

### Claim 11 (depends on 10)

The non-transitory computer readable storage medium of claim 10, wherein improving the accuracy of subsequent predictions associated with the prediction category comprises:
providing the prediction center feedback to at least one of the one or more prediction engines, wherein the one or more prediction engines update, based on the prediction center feedback, respective confidence levels that are advertised to the prediction center with regard to generating predictions for the prediction category.

### Claim 12 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein:
the prediction indicates that a particular action will be taken by a user of the computing device, and
monitoring the activity at the computing device comprises determining whether the particular action was taken by the user.

### Claim 13 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein the prediction is associated with a confidence level.

### Claim 14 (depends on 13)

The non-transitory computer readable storage medium of claim 13, wherein the confidence level affects a manner in which the prediction center aggregates the prediction with the at least one other prediction.

### Claim 15

A computing device comprising at least one processor configured to cause the computing device to carry out steps that include:
issuing, to a prediction center executing on the computing device, a request for a prediction associated with a prediction category;
receiving the prediction from the prediction center;
monitoring activity at the computing device to determine an accuracy of the prediction;
generating prediction center feedback based on the accuracy; and
providing the prediction center feedback to the prediction center, wherein the prediction center feedback is constructed for updating the prediction center to improve accuracy of subsequent predictions associated with the prediction category.

### Claim 16 (depends on 15)

The computing device of claim 15, wherein the prediction center provides predictions for a plurality of prediction categories, and the plurality of prediction categories includes the prediction category.

### Claim 17 (depends on 15)

The computing device of claim 15, wherein issuing the request causes the prediction center to:
identify, among a plurality of prediction engines, one or more prediction engines that are capable of providing predictions associated with the prediction category;
provide, to the one or more prediction engines, information associated with the request;
receive one or more predictions from the one or more prediction engines;
aggregate the one or more predictions to generate the prediction.

### Claim 18 (depends on 17)

The computing device of claim 17, wherein improving the accuracy of subsequent predictions associated with the prediction category comprises:
providing the prediction center feedback to at least one of the one or more prediction engines, wherein the one or more prediction engines update, based on the prediction center feedback, respective confidence levels that are advertised to the prediction center with regard to generating predictions for the prediction category.

### Claim 19 (depends on 15)

The computing device of claim 15, wherein:
the prediction indicates that a particular action will be taken by a user of the computing device, and
monitoring the activity at the computing device comprises determining whether the particular action was taken by the user.

### Claim 20 (depends on 15)

The computing device of claim 15, wherein the prediction is associated with a confidence level.
