# US 2020/0401886 A1 · Method and system for providing machine learning service

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

- Number: US 2020/0401886 A1
- Document ID: US20200401886A1
- Status: Published application
- Kind: A1
- Application number: 16/904,237
- Filed: 2020-06-17
- Published: 2020-12-24
- Earliest claimed: 2019-06-18
- Assignees: Moloco, Inc.
- Applicants: Moloco, Inc.
- Inventors: Jian Gong Deng; Ikkjin Ahn; Daeseob Lim; Bokyung Choi; Sechan Oh; William Kanaan
- Web page: https://patentgrep.com/patent/US20200401886A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06N 3/098: Distributed learning, e.g. federated learning
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 30/0241: Advertisements
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- 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

## Abstract

The present disclosure provides methods and systems for providing machine learning model service. The method may comprise: (a) generating, by a first computing system, a first output data using a first machine learning model, wherein the first machine learning model is trained on a first training dataset; (b) transmitting the first output data to a second computing system, wherein the first training dataset and the first machine learning model are inaccessible to the second computing system; (c) creating an input data by joining the first output data with a selected set of input features accessible to the second computing system; and (d) generating a second output data using a second machine learning model to process the input data.

## Claims

### Claim 1

A method for providing machine learning model service, the method comprising:
(a) generating, by a first computing system, a first output data using a first machine learning model, wherein the first machine learning model is trained on a first training dataset;
(b) transmitting the first output data to a second computing system, wherein the first training dataset and the first machine learning model are inaccessible to the second computing system;
(c) creating an input data by joining the first output data with a selected set of input features accessible to the second computing system; and
(d) generating a second output data using a second machine learning model to process the input data, wherein the second machine learning model and the selected set of input features are inaccessible to the first computing system.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first output data comprises a prediction value.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first output data is joined with the selected set of input features according to one or more common features.

### Claim 4 (depends on 3)

The method of claim 3, wherein the one or more common features include a common feature identifier.

### Claim 5 (depends on 1)

The method of claim 1, wherein the second machine learning model is trained using supervised learning and a labeled dataset for training the second machine learning model comprises data generated by the first machine learning model.

### Claim 6 (depends on 5)

The method of claim 5, wherein the first machine learning model is a convolutional neural network, and the data generate by the first machine learning comprises output of a top layer of the convolutional neural network.

### Claim 7 (depends on 1)

The method of claim 1, wherein the selected set of input features are determined by evaluating a performance of the second machine learning model.

### Claim 8 (depends on 7)

The method of claim 7, wherein a different set of input features are selected until a performance metric of the second machine learning model is better than a threshold.

### Claim 9 (depends on 1)

The method of claim 1, further comprising receiving a request by the first computing system for generating the first output data.

### Claim 10 (depends on 9)

The method of claim 9, wherein the request includes one or more common features related to a prediction service.

### Claim 11

A serialized machine learning system comprising:
(a) a first computing system configured to generate a first output data using a first machine learning model, wherein the first machine learning model is trained on a first training dataset;
(b) a second computing system configured to generate a second output data using a second machine learning model to process an input data; and
(c) an integration component configured to create the input data by joining the first output data with a selected set of input features accessible to the second computing system,
wherein the first training dataset and the first machine learning model are inaccessible to the second computing system and wherein the second machine learning model and the selected set of input features are inaccessible to the first computing system.

### Claim 12 (depends on 11)

The serialized machine learning system of claim 11, wherein the first output data comprises a prediction value.

### Claim 13 (depends on 11)

The serialized machine learning system of claim 11, wherein the first output data is joined with the selected set of input features according to one or more common features.

### Claim 14 (depends on 13)

The serialized machine learning system of claim 13, wherein the one or more common features include a common feature identifier.

### Claim 15 (depends on 11)

The serialized machine learning system of claim 11, wherein the second machine learning model is trained using supervised learning and a labeled dataset for training the second machine learning model comprises data generated by the first machine learning model.

### Claim 16 (depends on 15)

The serialized machine learning system of claim 15, wherein the first machine learning model is a convolutional neural network, and the data generate by the first machine learning comprises output of a top layer of the convolutional neural network.

### Claim 17 (depends on 11)

The serialized machine learning system of claim 11, wherein the selected set of input features are determined by evaluating a performance of the second machine learning model.

### Claim 18 (depends on 17)

The serialized machine learning system of claim 17, wherein a different set of input features are selected until a performance metric of the second machine learning model is better than a threshold.

### Claim 19 (depends on 11)

The serialized machine learning system of claim 11, wherein the first computing system is configured to further receive a request for generating the first output data.

### Claim 20 (depends on 19)

The serialized machine learning system of claim 19, wherein the request includes one or more common features related to a prediction service.