# US 2023/0273984 A1 · Information processing system and information processing method

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

- Number: US 2023/0273984 A1
- Document ID: US20230273984A1
- Status: Published application
- Kind: A1
- Application number: 18/068,170
- Filed: 2022-12-19
- Published: 2023-08-31
- Earliest claimed: 2022-02-25
- Assignees: Hitachi, Ltd.
- Applicants: Hitachi, Ltd.
- Inventors: Zisheng LI; Masahiro OGINO
- Web page: https://patentgrep.com/patent/US20230273984A1

## CPC

- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An information processing system includes: a processor that executes a program; and a storage device that stores the program, in which the storage device stores sensor data that is biological information of a user measured by a sensor and user data collected in association with the sensor data, and the processor acquires the sensor data, and imputes the sensor data using a causal relationship between the acquired sensor data and the user data.

## Claims

### Claim 1

An information processing system comprising:
a calculation device that executes a program; and a storage device that stores the program, wherein
the storage device stores user data that includes sensor data that is biological information of a user measured by a sensor device and data collected in association with the sensor data, and
the calculation device
acquires the sensor data, and
imputes the acquired sensor data using a causal relationship between items of the user data.

### Claim 2 (depends on 1)

The information processing system according to claim 1, wherein
the user data includes at least one of a user's behavior, emotion, biological information, and an intervention measure.

### Claim 3 (depends on 1)

The information processing system according to claim 1, wherein
the user data can be represented by a graph structure representing a causal relationship among items of the user data, and
the calculation device imputes the sensor data using a feature of the graph structure.

### Claim 4 (depends on 1)

The information processing system according to claim 1, wherein
the sensor data is represented by a numerical value.

### Claim 5 (depends on 1)

The information processing system according to claim 1, wherein
behavior and emotion data of the user is input by the user.

### Claim 6 (depends on 1)

The information processing system according to claim 1, wherein
the calculation device discriminates behavior and emotion data of the user from the sensor data.

### Claim 7 (depends on 1)

The information processing system according to claim 1, wherein
the calculation device determines a parameter of a model so as to minimize a training loss that is calculated from a data imputation loss in imputation of the sensor data, a confounder loss in adjustment of a data feature using a confounder representing a relationship among items of the user data, and a predicted loss in prediction of an intervention effect from the user data.

### Claim 8 (depends on 7)

The information processing system according to claim 7, wherein
the calculation device adjusts a confounder so as to minimize a loss of a confounder representing a relationship among items of the user data, and predicts an intervention effect.

### Claim 9

An information processing method for an information processing system to impute sensor data, wherein
the information processing system includes a computer that has a calculation device that executes predetermined processing and a storage device that is connected to the calculation device,
the storage device stores user data that includes sensor data that is biological information of a user measured by a sensor device and data collected in association with the sensor data, and
the information processing method includes
a procedure in which the calculation device acquires the sensor data, and
a procedure in which the calculation device imputes the acquired sensor data using a causal relationship between items of the user data.
