# US 2023/0419814 A1 · Display system, display device, and non-transitory computer-readable storage medium storing program

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

- Number: US 2023/0419814 A1
- Document ID: US20230419814A1
- Status: Published application
- Kind: A1
- Application number: 18/212,416
- Filed: 2023-06-21
- Published: 2023-12-28
- Earliest claimed: 2022-06-22
- Assignees: Seiko Epson Corporation
- Applicants: Seiko Epson Corporation
- Inventors: Hiroki NISHIOKA
- Web page: https://patentgrep.com/patent/US20230419814A1

## CPC

- G08B 21/24: Reminder alarms, e.g. anti-loss alarms
- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 10/82: using neural networks
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 40/23: {Recognition of whole body movements, e.g. for sport training}
- G06V 40/25: {Recognition of walking or running movements, e.g. gait recognition}
- G09G 3/002: {to project the image of a two-dimensional display, such as an array of light emitting or modulating elements or a CRT}
- G08B 5/36: using visible light sources
- G09G 2354/00: Aspects of interface with display user
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G09G: ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION (arrangements for transferring data between digital computers and displays G06F3/14; static indicating arrangements comprising an association of a number of separate sources or light control cells G09F9/00; static indicating arrangements comprising integral associations of a number of light sources H01J, H01K, H10H, H05B33/12; scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission, details thereof H04N1/00)

## Abstract

A display system is provided with a display device, a first imaging device, a storage device, and a processing device. The display device displays an image based on content information at a display position. The first imaging device images a human who is going to pass through the display position. The storage device stores a learned model obtained by performing machine learning on a correspondence relation between features of a behavior of the human, the content information to be used for the image, and a degree of risk of the human. The processing device obtains pre-passage behavior data representing a behavior of the human based on imaging result of the first imaging device, and determines the content information to be used for the image using the pre-passage behavior data and the learned model.

## Claims

### Claim 1

A display system comprising:
a display device configured to display an image based on content information at a display position;
a first imaging device;
a storage device configured to store a learned model obtained by performing machine learning on a correspondence relation between pre-passage behavior data representing features of a behavior of a human who is going to pass through the display position imaged by the first imaging device, the content information to be used for the image, and a degree of risk of the human who passed through the display position; and
a processing device which performs
obtaining first pre-passage behavior data representing features of a behavior of a first human who is going to pass through the display position based on an imaging result obtained by imaging the first human who is going to pass through the display position using the first imaging device, and
determining first content information to be used for a first image corresponding to the first pre-passage behavior data using the first pre-passage behavior data and the learned model.

### Claim 2 (depends on 1)

The display system according to claim 1, wherein
the correspondence relation includes a relation between the pre-passage behavior data, the content information, the degree of risk, and environmental data related to a surrounding environment of the display position, and
the processing device performs
obtaining first environmental data when the first human passes through the display position, and
determining the first content information using the first environmental data, the first pre-passage behavior data, and the learned model.

### Claim 3 (depends on 1)

The display system according to claim 1, wherein
the processing device performs determining at least one of the display position, display timing of the first image, and a display color or luminance of the first image using the first pre-passage behavior data and the learned model.

### Claim 4 (depends on 1)

The display system according to claim 1, further comprising:
a second imaging device, wherein
the processing device performs
obtaining first degree of risk based on first post-passage behavior data representing features of a behavior of the first human who passed through the display position based on an imaging result obtained by imaging the first human who passed through the display position using the second imaging device, and
relearning the learned model using the first degree of risk.

### Claim 5 (depends on 1)

The display system according to claim 1, wherein
the processing device makes the display device display the first image at the display position based on the first content information.

### Claim 6 (depends on 1)

The display system according to claim 1, wherein
the first content information to be used for the first image includes image data.

### Claim 7 (depends on 6)

The display system according to claim 6, further comprising:
a sound emitting device configured to emit a sound around the display position, wherein
the first content information to be used for the first image includes audio data, and
the processing device makes the sound emitting device emit a sound based on the first content information.

### Claim 8 (depends on 4)

The display system according to claim 4, wherein
the first degree of risk is represented by a difference between features set in advance to the human who passed through the display position and features represented by the first post-passage behavior data.

### Claim 9 (depends on 4)

The display system according to claim 4, wherein
the first pre-passage behavior data represents features of a behavior of the first human passing through a first region,
the first post-passage behavior data represents features of a behavior of the first human passing through a second region different from the first region, and
the display position is located between the first region and the second region.

### Claim 10 (depends on 2)

The display system according to claim 2, wherein
a surrounding environment of the display position is an environment related to a risk of the human in an area including the display position.

### Claim 11

A display device which displays an image comprising:
a storage device configured to store
a learned model obtained by performing machine learning on a correspondence relation between pre-passage behavior data representing features of a behavior of a human who is going to pass through a display position of the image,
content information to be used for displaying the image, and
a degree of risk of a human who passed through the display position; and
a processing device which performs
obtaining first pre-passage behavior data representing features of a behavior of a first human who is going to pass through the display position based on an imaging result obtained by imaging the first human who is going to pass through the display position, and
determining first content information to be used for a first image corresponding to the first pre-passage behavior data using the first pre-passage behavior data and the learned model.

### Claim 12

A non-transitory computer-readable storage medium storing a program configured to make a computer execute processing comprising:
obtaining first pre-passage behavior data representing features of a behavior of a first human who is going to pass through the display position based on an imaging result obtained by imaging the first human who is going to pass through the display position of a first image based on first content image; and
determining first content information to be used for the first image using a learned model obtained by performing machine learning on a correspondence relation between features of a behavior of a human who is going to pass through the display position, content information to be used for an image, and a degree of risk of the human who passed through the display position, and the first pre-passage behavior data.
