Order entry apparatus for automatic estimation and its method

• US 5,307,260 A
• Filed: 11/29/1990
• Issued: 04/26/1994
• Est. Priority Date: 11/29/1989
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Matoba, Hideaki, Inaba, Hidetoshi, Watanabe, Masahiro, Matsuzaki, Kichie, Onari, Hisashi
• Primary Examiner(s): Hayas, Gail O.
• Assistant Examiner(s): Brutman, Laura
• Application Number:
  US07/619,618
• Time in Patent Office: 1,244 Days
• Field of Search: 364/401, 364/403, 364/468, 364/474.24, 364/225, 364/917, 364/918, 395/21, 395/22, 395/24, 395/904, 395/924
• US Class Current: 703/2
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 10/0875 Itemisation or classification of parts, supplies or services, e.g. bill of materials

Abstract

Order entry apparatus for automatic estimation a transformation model comprising a pattern composed of a plurality of parameters representing custom product specifications, production line conditions and factors for composing the estimates for production cost and completion date. The parameters of this transformation model are specified by learning, leading to estimation for the requested product specifications, in broad consideration of conditions such as those of the production line. The use of a neural network model as this pattern transformation model makes pattern transformation more flexible and pattern learning more efficient. Estimation accuracy is also increased by entering values of predicted charges in production line conditions such as loads or stock obtained from resource requirements planning, process design, capacity requirements planning, etc.

Claims

1. An order entry apparatus for automatic estimation regarding a specified product, said order entry apparatus comprising:

user input means for entering requested product specifications for said specified product;

memory means for storing parameters of said requested product specifications for inputting to at least a pattern transformation model;

wherein said pattern transformation model comprises data processing cells and weighted parameters interconnecting said data processing cells;

patternizing means for generating a pattern to input to said pattern transformation model, based upon said entered requested product specifications; and

estimating means including said pattern transformation model for deriving an estimate item including a date of production completion for said specified product based upon said generated pattern input to said transformation model.

2. An order entry apparatus as set forth in claim 1, further comprising learning means for determining values of said weighted parameters interconnecting said data processing cells.

3. An order entry apparatus as set forth in claim 2, further comprising control means for changing the value of said estimated item based upon an altered product specifications, when said requested product specifications are altered.

4. An order entry apparatus as set forth in claim 1, wherein said pattern input to said pattern transformation model includes data regarding conditions for supplying said product.

5. An order entry apparatus as set forth in claim 4, wherein said data regarding said conditions for supplying said product include data regarding production line conditions producing said product, and said estimate item further includes an estimated price for said product.

6. An order entry apparatus as set forth in claim 4, wherein said data regarding said conditions for supplying said product include data concerning predicted changes in said production line conditions, said data obtained in accordance with resource requirements planning, process design, data regarding past production orders and/or capacity requirements planning.

7. A CAD apparatus comprising:

an input apparatus for entry of product design data for a specified product;

memory means for storing parameter values of the entered product design data for inputting to a pattern transformation model;

wherein said pattern transformation model comprises data processing cells and weighted parameters interconnecting said data processing cells;

means for learning said weighted parameter for determining values of indexes relating to productivity of said specified product as close as desired values;

patternizing means for generating a pattern for inputting to said pattern transformation model based upon said entered product design data; and

means for determining said indexes relating to the productivity of said specified product based upon said weighted parameters being determined by the learning means.

8. A method of automatic estimation for orders, said method comprising the steps of:

determining product specifications for a specified product;

storing in a memory, parameters of the determined product specifications for a pattern transformation model;

wherein said pattern transformation model comprises data processing cells and weighted parameters interconnecting said data processing cells;

generating a pattern to patternize to said pattern transformation model base upon said determined product specifications; and

determining values of estimate items for said specified product based upon the pattern generated in said generating step, input to said pattern transformation model by use of said input generated pattern.

9. An estimation method as set forth in claim 8, further comprising a learning step of learning values of said weighted parameters.

10. An estimation method as set forth in claim 8, wherein said pattern to patternize to said pattern transformation model includes data regarding conditions for supplying said product.

11. An estimation method asset forth in claim 10, wherein said data regarding conditions for supplying said product include data regarding production line conditions for producing said specified product, and said estimate items for include price and/or date of production completion for said specified product.

12. A method of CAD processing comprising the steps of:

entering product design data for a specified product;

storing in a memory device, parameter values of the entered product design data for inputting to a pattern transformation model;

wherein said pattern transformation model comprises data processing cells nd weighted parameters interconnecting said data processing cells;

learning said weighted parameters for determining values of indexes relating to productivity of said specified product as close as desired values;

generating a pattern for inputting to said pattern transformation model based upon said entered product design data; and

determining said indexes based upon said weighted parameters determined in the learning step.

13. A CAD processing method as set forth in claim 12, wherein said the determined indexes include production costs.