US5319740A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Expert system building method and system
Assignee: Hitachi Ltd
•
Filing: 1991-03-04
•
Granted: 1994-06-07
•
Expires: 2011-03-04
Abstract
Abstract An expert system building method wherein, in an expert system which executes an inference process according to a decision tree, at least one data unit or any combination of such data units of data forming an input/output information is made. Next, a data input/output method is specified on the basis of relationship between the at least one data unit and the input/output information. Thus, data possibly needed can be stored simultaneously. The expert system can execute an inference process according to the decision tree having the expert's knowledge described as they are with no relation to the data input, and the data can be simultaneously entered in units which are easy to understand by an end user with no relation to the process of the decision tree.
Inventors
- 👤 Hiroshi Yamada
- 👤 Kenichi Nakarai
- 👤 Katsuyuki Yoshino
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-28 17:26
CPC Classifications
G; G06; G06N; G06N5/00; G06N5/04
Claims Analysis
Total Claims: 13
Claim 1
Independent Claim
139 words
In an expert system having storing means, and means for operating a program having at least a decision tree comprising a plurality of nodes, a node deciding method comprising: a step of reading a group of data from said storing means, said group of data being in common to at least one of said nodes, and having input/output method information of the data of said group, and the data of said group including a plurality of data units which includes a plurality of data names, and said reading of a group of data being based upon a data name and a value of a data unit in said group of data; and a step of selecting a next node on said decision tree, on the basis of at least one data unit in at least one group of data.
Claim 2
Dependent Claim
139 words
In an expert system having storing means, and means for operating a program having at least a decision tree comprising a plurality of nodes, a node deciding method comprising: a step of reading a group of data from said storing means, said group of data being in common to at least one of said nodes, and having input/output method information of the data of said group, and the data of said group including a plurality of data units which includes a plurality of data names, and said reading of a group of data being based upon a data name and a value of a data unit in said group of data; and a step of selecting a next node on said decision tree, on the basis of at least one data unit in at least one group of data.
Claim 3
Dependent Claim
39 words
A node deciding method according to claim 1, further comprising: a step of writing said value of the data unit, in the course of operating said program, if the storing means has no corresponding value of the data unit.
Claim 4
Dependent Claim
28 words
A node deciding method according to claim 2, wherein an image displayed on a screen at a time of data input is specified as said input/output method information.
Claim 5
Dependent Claim
30 words
A node deciding method according to claim 3, wherein the image has a background image and an image having an input column for data to indicate parts of the image.
Claim 6
Dependent Claim
20 words
A node deciding method according to claim 2, wherein the data input/output method information specifies a medium for said writing.
Claim 7
Dependent Claim
25 words
A node deciding method according to claim 2, wherein the selection made by said selecting step is based upon said value of the data unit.
Claim 8
Dependent Claim
46 words
A node deciding method according to claim 2, wherein the decision made by said selecting step is based upon a total score of scores for each data unit used, each of said scores being made in terms of the value of each of the data units.
Claim 9
Dependent Claim
43 words
A node deciding method according to claim 1, further comprising: a step of storing a position in the program using one of the data units of the plurality if in the course of operating the program, the position has not been stored yet.
Claim 10
Dependent Claim
49 words
A node deciding method according to claim 8, wherein when an entered data unit of the plurality is corrected, a position corresponding to the corrected entered data unit, in said decision tree is passed to said program if the position corresponding to the corrected entered data unit is stored.
Claim 11
Dependent Claim
45 words
A node deciding method according to claim 1, wherein at least either of input or output is executed with use of a predetermined input/output method for default, if no data input/output method information is specified in the group of data read in said reading step.
Claim 12
Dependent Claim
27 words
A node deciding method according to claim 1 wherein said group of data in said step of reading is in common to a plurality of said nodes.
Claim 13
Dependent Claim
22 words
A node deciding method according to claim 1, further comprising: a step of displaying information with respect to the selected next node.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-06-06 | 1997-12-06 | 1998-06-07 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-06-06 | 2001-12-06 | 2002-06-07 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-06-06 | 2005-12-06 | 2006-06-07 | $7700.00 | Window Closed / Lapsed |