DISPLAY SYSTEM, MACHINE LEARNING DEVICE, AND DISPLAY DEVICE

• US 20200133609A1
• Filed: 10/07/2019
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Fanuc Corporation
• Original Assignee: Fanuc Corporation
• Inventors: SUGIYAMA, Yuusuke
• Granted Patent: US 11,119,716 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/1423 controlling a plurality of local displays, e.g. CRT and flat panel display
• CPC Class Codes: G06F 3/147 using display panels
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence

Abstract

A display system includes a state acquisition section which acquires state data, a label acquisition section which acquires label data representing whether or not an operation performed when the state data is acquired is abnormal, a threshold calculation section which calculates, based on the state data and the label data, a threshold for determining whether or not an operation to be performed is likely to become abnormal, a display control section which controls display timing of a normal operation based on the threshold, and a display unit configured to display the normal operation according to the display timing.

Claims

1. A display system, comprising:

a state acquisition section which acquires state data including at least operation contents,

a label acquisition section which acquires label data representing whether or not an operation performed when the state data is acquired is abnormal,

a threshold calculation section which calculates, based on the state data and the label data, a threshold for determining whether or not an operation to be performed is likely to become abnormal,

a display control section which controls display timing of a normal operation based on the threshold, and

one or a plurality of display units configured to display the normal operation according to the display timing.

2. The display system according to claim 1, wherein the threshold is updated based on a learning model using the state data and the label data as teaching data.

3. The display system according to claim 1, wherein the state data further includes at least one of operator information, an operation time length, and an operation date and time.

4. The display system according to claim 2, wherein the learning model is shared between the plurality of display units.

5. The display system according to claim 1, wherein the display unit is constituted by augmented reality equipment.

6. The display system according to claim 1, wherein the display unit displays information for supporting an assembly operation.

7. The display system according to claim 1, wherein the state acquisition section, the label acquisition section, and the threshold calculation section are arranged in a local server or in a cloud server.

8. The display system according to claim 2, wherein the learning model is modeled for each operation and shared on a network.

9. A machine learning device, comprising:

a state acquisition section which acquires state data including at least operation contents,

a label acquisition section which acquires label data representing whether or not an operation performed when the state data is acquired is abnormal, and

a threshold calculation section which calculates, based on the state data and the label data, a threshold for determining whether or not an operation to be performed is likely to become abnormal, wherein

the threshold is updated based on a learning model using the state data and the label data as teaching data.

10. The machine learning device according to claim 9, wherein the learning model is modeled for each operation and shared on a network.

11. A display device, comprising:

a state acquisition section which acquires state data including at least operation contents,

a label acquisition section which acquires label data representing whether or not an operation performed when the state data is acquired is abnormal,

a threshold calculation section which calculates, based on the state data and the label data, a threshold for determining whether or not an operation to be performed is likely to become abnormal,

a display control section which controls display timing of a normal operation based on the threshold, and

a display unit configured to display the normal operation according to the display timing.