System and method for expert system analysis using quiescent and parallel reasoning and set structured knowledge representation

• US 5,778,157 A
• Filed: 06/17/1996
• Issued: 07/07/1998
• Est. Priority Date: 06/17/1996
• Status: Expired due to Fees

• Current Assignee: YY Software Corporation
• Original Assignee: YY Software Corporation
• Inventors: Herrera, Peter J., Zimmerman, Charles E., Oatman, Robert K., Sanouillet, Remy D.
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): Shah, Sanjiv
• Application Number:
  US08/666,887
• Time in Patent Office: 750 Days
• Field of Search: 395/51, 395/54, 395/10, 395/50, 395/63, 395/81, 395/12, 395/11, 395/55, 707/5, 707/6, 704/9
• US Class Current: 706/46
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

An integrated system and method for providing a flexible expert system development and runtime environment with an integrated natural language processor and set-oriented knowledge base. The system and process include an input device, a spreading activation module, a reasoning module, a decision module, and a knowledge base. The system and method may also include a natural language processing module. The spreading activation module utilizes the knowledge base, which is set-oriented with named relationships between concepts to traverse the knowledge base efficiently. The reasoning module executes related, nested logic statements which manipulate the complex facts in the knowledge base. The decision module selects the value or values from a list which are most relevant at the moment the module is called. The knowledge base represents all data in a nested, set-oriented manner. The system and method, in turn, produce an output in response to the input or command into the system.

Claims

1. An expert system for generating an output representation in response to at least one input, comprising;

a knowledge base that stores a plurality of linguistic and domain specific facts and statements from which are derived a plurality of associated concepts, each fact having at least one possible value;

an input module for receiving a plurality of user inputs;

a spreading activation module, coupled to the knowledge base and the input module to receive each input, and that generates at least one chain of the concepts to relate each input by selectively and iteratively associating each input with a plurality of facts and statements and applying constraints to the concepts associated with facts;

a decision module, coupled to the knowledge base and the input module for determining a value of fact from a plurality of possible values for a fact;

a natural language processing module, coupled to the knowledge base and spreading activation module, for evaluating linguistic statements relative to facts within the knowledge base as the facts have been constrained by the spreading activation module;

a reasoning module, coupled to the knowledge base and the decision module, for automatically executing the statements to update the facts in the knowledge base in response to changes in the value of other facts in the knowledge base; and

an output module coupled to the spreading activation module to receive the chains of concepts, and coupled to the knowledge base, to select one or more of the chains of concepts related to each input, and to generate an output representation of each input by determining the value for facts associated with the selected chains of concepts.

2. A method for generating an output representation for controlling an output device from an input received in an expert system, comprising:

storing a plurality of facts and statements, each fact having at least one possible value;

iteratively receiving at an input module the input comprising a plurality of input symbols;

determining for each stored fact a plurality of related concepts;

associating the input symbols to the stored plurality of facts and statements to generate a chain of concepts related to the input symbols to create a minimum number of the related concepts for processing by a natural language processing module;

determining a value for each stored fact associated with a concept from among multiple alternative values, at least some facts having a change in value;

executing the logic statements associated with each stored fact;

that has had a change in the value of the fact, until no additional statements are executed in response to changes in the value of the fact, and

generating from the values of stored facts related to the input symbols an output representation for the input symbols.

3. A system for integrated natural language processing and expert system analysis, comprising:

an input module for receiving at least one input;

a knowledge base for storing a plurality of linguistic and domain specific facts and statements from which are derived a plurality of associated concepts, each fact having at least one possible value, and each statement having at least one logic statement;

a natural language processing module coupled to the input module to receive an input for processing and for generating the output and coupled to the knowledge base for evaluating the linguistic statements and facts;

a spreading activation module, coupled to receive the input and coupled to the knowledge base for generating a list of concepts and coupled to the natural language processor for inputting the list of concepts to the natural language processor; and

a reasoning module, coupled to the knowledge base and operable in parallel with one or more modules of the expert system, for automatically executing logic statements to update the values of facts in the knowledge base in response to changes in the values of other facts in the knowledge base and coupled to produce an output responsive to the input.

4. The system in claim 3, comprising a decision module, coupled to the knowledge base and the reasoning module, for determining the value for a fact from a plurality of possible values for a fact, wherein the reasoning module automatically continuously executes logic statements in response to the change in the value of facts by the decision module.

5. The system in claim 3, wherein the list of concepts are coupled to form a chain for input into the natural language processing module.