# US 2024/0005643 A1 · Information processing apparatus, information processing method, computer program, imaging device, vehicle device, and medical robot device

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

- Number: US 2024/0005643 A1
- Document ID: US20240005643A1
- Status: Published application
- Kind: A1
- Application number: 18/255,170
- Filed: 2021-10-14
- Published: 2024-01-04
- Earliest claimed: 2020-12-09
- Assignees: Sony Group Corporation
- Applicants: Sony Group Corporation
- Inventors: KENJI SUZUKI
- Web page: https://patentgrep.com/patent/US20240005643A1

## CPC

- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- A61B 34/32: operating autonomously
- G06N 20/00: Machine learning
- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G16H 40/60: for the operation of medical equipment or devices
- A61B 90/361: {Image-producing devices, e.g. surgical cameras}
- A61B 2034/2048: {using an accelerometer or inertia sensor}
- A61B 2034/2059: {Mechanical position encoders}
- A61B 2034/2065: {Tracking using image or pattern recognition}
- B60W 30/00: Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W 60/00: Drive control systems specially adapted for autonomous road vehicles
- B60W 2420/403: Image sensing, e.g. optical camera
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- 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
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT

## Abstract

Provided is an information processing apparatus for artificially increasing data of a minority attribute to generate learning data for making fair determination on each piece of input data. An information processing apparatus includes: a data holding unit configured to hold first learning data to be used for learning a machine learning model; an acquisition unit configured to acquire information regarding bias of the learning data; a data generation unit configured to generate second learning data by using data included in the learning data on the basis of the information regarding bias; and a learning unit configured to learn the machine learning model by using the first learning data and the second learning data.

## Claims

### Claim 1

An information processing apparatus comprising:
a data holding unit configured to hold first learning data to be used for learning of a machine learning model;
an acquisition unit configured to acquire information regarding bias of the learning data;
a data generation unit configured to generate second learning data by using data included in the learning data on a basis of the information regarding bias; and
a learning unit configured to learn the machine learning model by using the first learning data and the second learning data.

### Claim 2 (depends on 1)

The information processing apparatus according to claim 1, wherein
the acquisition unit acquires information indicating a minority attribute in the first learning data, and
from data of the minority attribute included in the first learning data, the data generation unit generates second learning data of a same attribute.

### Claim 3 (depends on 1)

The information processing apparatus according to claim 1, wherein
from data of the minority attribute included in the learning data, the data generation unit generates Adversarial Example to be second learning data.

### Claim 4 (depends on 3)

The information processing apparatus according to claim 3, wherein
the data generation unit generates Adversarial Example on a basis of Fast Gradient Sign Method.

### Claim 5 (depends on 1)

The information processing apparatus according to claim 1, wherein
the data generation unit generates second learning data by superimposing noise on data included in the learning data.

### Claim 6

An information processing method comprising:
a step of inputting first learning data to be used for learning of a machine learning model;
a step of acquiring information regarding bias of the learning data;
a step of generating second learning data by using data included in the learning data on a basis of the information regarding bias; and
a step of learning the machine learning model by using the first learning data and the second learning data.

### Claim 7

A computer program described in a computer-readable format to cause a computer to function as:
a data holding unit configured to hold first learning data to be used for learning of a machine learning model;
an acquisition unit configured to acquire information regarding bias of the learning data;
a data generation unit configured to generate second learning data by using data included in the learning data on a basis of the information regarding bias; and
a learning unit configured to learn the machine learning model by using the first learning data and the second learning data.

### Claim 8

An imaging device comprising:
an imaging unit configured to capture an image; and
a recognition unit configured to recognize the captured image by using a machine learning model, wherein
on a basis of information regarding bias of learning data for learning the machine learning model, the imaging device generates learning data by using data included in the learning data, and learns the machine learning model by using the generated learning data.

### Claim 9 (depends on 8)

The imaging device according to claim 8, wherein
learning data is generated by using data of an image that is to be minority in the learning data in accordance with a field to which the imaging device is applied, and the machine learning model is learned by using the generated learning data.

### Claim 10

A vehicle device comprising:
an imaging device including
an imaging unit configured to capture an image around a vehicle, and
a recognition unit configured to recognize the captured image by using a machine learning model, wherein
on a basis of information regarding bias of learning data for learning the machine learning model, the imaging device generates learning data by using data included in the learning data, and learns the machine learning model by using the generated learning data.

### Claim 11

A medical robot device comprising:
an imaging device including
an imaging unit configured to capture an image around a surgical site, and
a recognition unit configured to recognize the captured image by using a machine learning model, wherein
on a basis of information regarding bias of learning data for learning the machine learning model, the imaging device generates learning data by using data included in the learning data, and learns the machine learning model by using the generated learning data.
