Interactive artificial intelligence

• US 6,446,056 B1
• Filed: 09/10/1999
• Issued: 09/03/2002
• Est. Priority Date: 09/10/1999
• Status: Expired due to Fees

• Current Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation)
• Original Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation)
• Inventors: Sadakuni, Naoki
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US09/394,369
• Time in Patent Office: 1,089 Days
• Field of Search: 345/157, 345/473, 345/734, 434/267, 704/1, 705/1, 707/1, 707/2, 706/14
• US Class Current: 706/14
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

Behavior of a device is modified based on the device'"'"'s experience. The device includes: (i) a sensing unit for sensing signals; (ii) a concern-generating unit programmed to generate concern-parameters; (iii) an actuating unit for actuating the device; and (iv) a memory storing a spreadsheet composed of multiple sets of data, each set corresponding to an event defined by signals received by the device, variations in its concern-parameters, and behavior of the device. When the device has variations in its concerns in a situation, the device extracts from the memory an event, if any, to best compensate for the variations to select behavior in the situation. The selected behavior may be adjusted by variations in its emotions. The behavior of the device is regulated by variations in its concerns, and the device can modify or improve its behavior based on the stored information obtained in the past.

Claims

1. A method for adjusting behavior of a device based on the device'"'"'s experience, said device comprising:

(i) a sensing unit for sensing signals;

(ii) a concern-generating unit programmed to generate concern-parameters;

(iii) an actuating unit for actuating the device; and

(iv) a memory storing a spreadsheet composed of multiple sets of data, each set corresponding to a discrete event which the device experienced, said event being defined by signals received by the device, variations in its concern-parameters, and behavior of the device,

said method comprising the steps of;

(a) sensing signals receivable by the device;

said device having concern-parameters (C_i) (i=entry number or time) which vary from predetermined standards (SC);

(b) selecting and extracting from the memory an experienced event, if any, to best compensate for the variations in its concern-parameters; and

(c) actuating the device based on the extracted information, and then computing variations in its concern-parameters (Δ

C_i), thereby updating the spreadsheet.

2. The method according to claim 1, wherein the device further comprises an emotion-generating unit programmed to generate emotion-parameters, and wherein, in step (a), the device has variations in its emotion-parameters, and in step (c), behavior of the device extracted from the memory is modified by the variations in its emotion-parameters under predetermined rules.

4. The method according to claim 1, wherein, in step (b), if no data on the event is extracted from the memory, the device behaves under predetermined rules.

6. The method according to claim 1, wherein the input-output relationship of the concern-generating unit is predetermined, said concern-generating unit receiving pre-selected sensed signals and outputting the concern-parameters.

7. The method according to claim 1, wherein the input-output relationship of the emotion-generating unit is predetermined, said emotion-generating unit receiving pre-selected sensed signals and the output of the concern-generating unit, and outputting the emotion-parameters.

8. The method according to claim 1, wherein the input-output relationship of the actuating unit is predetermined, said actuating unit receiving pre-selected sensed signals and the information from the memory, and actuating the device.

9. The method according to claim 1, further comprising a working memory which temporarily pools and stores information from the sensing unit, the concern-generating unit, and the first-mentioned memory until the device completes its action, and which outputs information to the concern-generating unit, the actuating unit, and the first-mentioned memory.

10. The method according to claim 1, wherein the updated memory stores variations in its concern-parameters (Δ

C′

_i) linked with the event, wherein Δ

C′

_i=α

Δ

C_i+(1−

Δ

) Δ

C′

<sub>i−

1</sub>(0<

α

<

1), wherein Δ

C′

<sub>i−

1</sub> is the previous data saved under the index of the event.

11. The method according to claim 1, wherein the concern-generating unit comprises a plurality (p) of concern modules, each differently programmed to generate and output the concern-parameter (C(n)_i) (n=1−

p), and, in step (b), the best compensating event is selected if the relevancy calculated based on the difference between the initial variation (SC(n)−

C(n)_i) and the recorded variation (Δ

C′

(n)<sub>i−

1</sub>) in each concern-parameter is higher than a pre-selected score, wherein the relevancy is defined by Σ

((SC(n)−

C(n)_i)−

Δ

C′

(n)<sub>i−

1</sub>)²(n=1−

p).

3. A method for adjusting behavior of a device based on the device'"'"'s experience, said device comprising:

(i) a sensing unit for sensing signals;

(ii) a concern-generating unit programmed to generate concern-parameters;

(iii) an actuating unit for actuating the device; and

(iv) a memory storing a spreadsheet composed of multiple sets of data, each set corresponding to an event defined by signals received by the device, variations in its concern-parameters, and behavior of the device,

said method comprising the steps of;

(a) sensing signals receivable by the device;

said device having concern-parameters (C_i) (i=entry number or time) which vary from predetermined standards (SC);

(b) extracting from the memory an event, if any, to best compensate for the variations in its concern-parameters; and

(c) actuating the device based on the extracted information, and then computing variations in its concern-parameters (Δ

C_i), thereby updating the memory,

wherein the updated memory stores variations in its concern-parameters (Δ

C′

_i) linked with the event, wherein Δ

C′

_i=α

Δ

C_i+(1−

α

) Δ

C′

<sub>i−

1</sub>(0<

α

<

1), wherein Δ

C′

<sub>i−

1</sub> is the previous data saved under the index of the event.

5. A method for adjusting behavior of a device based on the device'"'"'s experience, said device comprising:

(i) a sensing unit for sensing signals;

(ii) a concern-generating unit programmed to generate concern-parameters;

(iii) an actuating unit for actuating the device; and

(iv) a memory storing a spreadsheet composed of multiple sets of data, each set corresponding to an event defined by signals received by the device, variations in its concern-parameters, and behavior of the device,

said method comprising the steps of;

(a) sensing signals receivable by the device;

said device having concern-parameters (C_i) (i=entry number or time) which vary from predetermined standards (SC);

(b) extracting from the memory an event, if any, to best compensate for the variations in its concern-parameters; and

(c) actuating the device based on the extracted information, and then computing variations in its concern-parameters (Δ

C_i), thereby updating the memory,

wherein the concern-generating unit comprises a plurality (p) of concern modules, each differently programmed to generate and output the concern-parameter (C(n)_i) (n=1−

p), and, in step (b), the best compensating event is selected if the relevancy calculated based on the difference between the initial variation (SC(n)−

C(n)_i) and the recorded variation (Δ

C′

(n)<sub>i−

1</sub>) in each concern-parameter is higher than a pre-selected score, wherein the relevancy is defined by Σ

((SC(n)−

(n)_i)−

Δ

C′

(n)<sub>i−

1</sub>)²(n1−

p).