초록 ▼

An input device (12) receives a natural language or conversational statement in the form of a character string (1). A processor (14) performs a natural language analysis (2) to convert the input natural language into a command language instruction for a computer program. A morphological analysis (3)

An input device (12) receives a natural language or conversational statement in the form of a character string (1). A processor (14) performs a natural language analysis (2) to convert the input natural language into a command language instruction for a computer program. A morphological analysis (3) compares words of the input character string with contents of a dictionary (10) to convert the input words into preselected words indicated by the dictionary which are output as another character string. In a semantic or syntax analysis (4; FIG. 9), one of the inputted and another character strings are analyzed to generate a corresponding chained functions structure (FIGS. 2, 3). From knowledge (FIG. 5, 7) described by the plurality of chained function structures and from rules stored in knowledge memory (11), a new character string is generated. If the new character string is in command language, the command is executed (7). If the new character string is not in command language, it is reanalyzed (8, 9) to generate yet another character string. In this manner, instructions can be input by a user in any of a multiplicity of national languages in conversational format and converted into appropriate command instructions for an executed computer program.

대표청구항 ▼

A method of processing a natural language into a command language in a system comprising a character input means, a processor and a storage device storing a dictionary and a knowledge data base including a plurality of predefined meaning structure changing rules and a plurality of predefined chained

A method of processing a natural language into a command language in a system comprising a character input means, a processor and a storage device storing a dictionary and a knowledge data base including a plurality of predefined meaning structure changing rules and a plurality of predefined chained functions structures defining expressions representative of the natural language and the command language, the method comprising: (a) a step of inputting a character string having a natural language form representing a request for a computer operation through said input means, and storing said character string in a stack; (b) a step performed with said processor of parsing the inputted character string into character sub-strings in accordance with said dictionary by comparing portions of the inputted character string with definitions stored in said dictionary; (c) a step of with the processor, analyzing syntax of each of said character sub-strings by searching the knowledge data base to select corresponding chained functions structures representative of the character sub-strings; (d) a step performed with said processor of retrieving knowledge stored in the knowledge data base in accordance with the corresponding chained functions structures selected by the analyzing syntax step (c), the retrieved knowledge defining concepts and structure of knowledge data elements representative of each syntax analyzed sub-string; (e) a step of with said processor, character string analyzing at least one of said syntax analyzed sub-strings by searching the retrieved knowledge described by the corresponding chained functions structures including the knowledge data elements from the corresponding chained functions structures, by matching at least one of the knowledge data elements with at least one of equivalent knowledge data elements of other chained functions structures in the knowledge data base; (f) a step of with said processor, generating an intermediate meaning structure representing each of said character string analyzed sub-strings from step (e) by combining the corresponding chained functions structures and the knowledge data elements from other chained functions structures matched in accordance with the character string analyzing step (e); and (g) a step of with said processor, generating at least one of a new character string in the natural language, an intermediate representation for obtaining a command language, and the command language which is equivalent to said syntax analyzed sub-string on the basis of said generated intermediate meaning structure, said new character string being stored in said stack, and said intermediate representation being stored in said knowledge database, and when the command language is generated, executing the command language, and when the command language is not generated, selecting a different one of said character strings from the stack and recursively repeating the processing until all of the character strings in said stack have each been subject to the generating step (g).