EP0689147A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Natural language processing system and method
Assignee: Canon Inc
•
Filing: 1995-06-21
•
Granted: —
•
Expires: 2015-06-21
Abstract
Abstract A natural language processing method, by which a sequence of natural language information is analyzed so as to derive a concept represented by the information. In this method, the input natural language information is sequentially processed as word by word. At that time, the kind of a subsequent word is expected from a currently processed word by using knowledge concerning the word order of words in the natural language information. Thus the processing is performed by eliminating ambiguity in the information on the basis of such an expectation.
Inventors
- 👤 Aruna Rohra Suda
- 👤 Suresh Jeyachandran
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 15:06
CPC Classifications
G; G06; G06F; G06F40/00; G06F40/20; G06F40/253; G06F40/30
Claims Analysis
Total Claims: 45
Claim 1
Independent Claim
95 words
A natural language processing system comprising: input means for inputting information represented in a natural language; a knowledge base for storing linguistic knowledge and general knowledge; partition means for partitioning the information, which is inputted by said input means, into words; derivation means for referring to knowledge stored in said knowledge base and for deriving concepts respectively represented by the words obtained by said partition means; and integration means for relating the concepts of the words, which are derived by the derivation means, with one another by referring to knowledge stored in said knowledge base.
Claim 2
Dependent Claim
25 words
The natural language processing system according to claim 1 further comprises extraction means for extracting specific data from the concepts derived by said derivation means.
Claim 3
Dependent Claim
54 words
The natural language processing system according to claim 2, wherein the information represents the contents of a document of a specific domain, wherein said knowledge base has knowledge of the specific domain, and wherein said extraction means refers to the knowledge of the specific domain stored in said knowledge base and extracts specific data.
Claim 4
Dependent Claim
74 words
A natural language processing system comprising: input means for inputting information represented in a natural language; a knowledge base for storing therein linguistic knowledge and knowledge concerning a domain of information to be processed; expectation means for expecting a kind of information to be inputted from said input means, on the basis of the knowledge stored in said knowledge base; and processing means for processing information whose kind is expected by said expectation means.
Claim 5
Dependent Claim
34 words
The natural language processing system according to claim 4, wherein said expectation means has discrimination means for discriminating a kind of information which can be inputted, before information is inputted from said input means.
Claim 6
Dependent Claim
31 words
The natural language processing system according to claim 4, which further comprises preprocessing means for performing a preprocessing corresponding to the kind of information, which is expected by said expectation means.
Claim 7
Dependent Claim
30 words
The natural language processing system according to claim 6, wherein said preprocessing means prepares a knowledge structure corresponding to the kind of information, which is expected by said expectation means.
Claim 8
Dependent Claim
53 words
The natural language processing system according to claim 4, which further comprises: expectation information storing means for storing therein a result of a expectation made by said expectation means; and updating means for updating contents of information, which is stored in said expectation information storing means, on the basis of said knowledge base.
Claim 9
Dependent Claim
23 words
The natural language processing system according to claim 4, wherein said knowledge base has knowledge concerning a domain of information to be processed.
Claim 10
Dependent Claim
34 words
The natural language processing system according to claim 9, wherein said expectation means has discrimination means for discriminating a kind of information which can be inputted, before information is inputted from said input means.
Claim 11
Dependent Claim
31 words
The natural language processing system according to claim 9, which further comprises preprocessing means for performing a preprocessing corresponding to the kind of information, which is expected by said expectation means.
Claim 12
Dependent Claim
30 words
The natural language processing system according to claim 11, wherein the preprocessing means prepares a knowledge structure corresponding to the kind of information, which is expected by said expectation means.
Claim 13
Dependent Claim
51 words
The natural language processing system according to claim 9, which further comprises: expectation information storing means for storing therein a result of a expectation made by said expectation means; and updating means for updating contents of information stored in the expectation information storing means, on the basis of said knowledge base.
Claim 14
Dependent Claim
114 words
A natural language processing system comprising: input means for inputting information represented in a natural language; a knowledge base for storing therein knowledge concerning a domain of information to be processed, general knowledge and linguistic knowledge; expectation means for expecting a kind of information to be inputted by the input means, on the basis of the knowledge stored in said knowledge base; expectation information storing means for storing a result of an expectation made by said expectation means, as expectation information; and analysis means for analyzing information inputted from said input means by referring to the expectation information stored in the expectation information storing means and to the knowledge stored in the knowledge base.
Claim 15
Dependent Claim
50 words
The natural language processing system according to claim 14, wherein said expectation means expects a kind of information subsequent to current information on the basis of a result of an analysis of the current information, which is made by said analysis means, and the knowledge stored in said knowledge base.
Claim 16
Dependent Claim
42 words
The natural language processing system according to claim 15, which further comprises updating means for updating contents of information, which is stored in said expectation information storing means, on the basis of a result of an expectation made by said expectation means.
Claim 17
Dependent Claim
39 words
The natural processing system according to claim 14, which further comprises extraction means for extracting specific data from the information inputted from said input means, on the basis of a result of an analysis made by said analysis means.
Claim 18
Dependent Claim
54 words
The natural language processing system according to claim 17, wherein the information represents the contents of a document of a specific domain, wherein said knowledge base has knowledge of the specific domain, and wherein said extraction means refers to the knowledge of the specific domain stored in said knowledge base and extracts specific data.
Claim 19
Dependent Claim
40 words
The natural language processing system according to claim 14, wherein said input means inputs a set of sentences, wherein said analysis means processes a set of sentences as sentence by sentence and outputs concepts as a result of an analysis.
Claim 20
Dependent Claim
27 words
The natural language processing system according to claim 19, which further comprises identification means for identifying a beautification concept among the concepts outputted by the analysis means.
Claim 21
Dependent Claim
31 words
The natural language processing system according to claim 19, which further comprises connection means for connecting associated concepts with one another among a plurality of concepts outputted by the analysis means.
Claim 22
Dependent Claim
32 words
The natural language processing system according to claim 19, which further comprises separation means for separating concepts, which are unsuitably connected with one another, from among concepts outputted by the analysis means.
Claim 23
Dependent Claim
92 words
A natural language processing method comprising: the input step of inputting information in a natural language; the partition step of partitioning the information inputted in the input step; the derivation step of referring to knowledge stored in a knowledge base, which stores linguistic knowledge and general knowledge, and deriving concepts represented by the words obtained in the partition step; and the integration step of relating the concepts, which are derived respectively correspondingly to the words in the derivation step, with one another by referring to the knowledge stored in the knowledge base.
Claim 24
Dependent Claim
27 words
The natural language processing method according to claim 23, which further comprises the extraction step of extracting specific data from the concepts derived in the derivation step.
Claim 25
Dependent Claim
56 words
The natural language processing method according to claim 24, wherein the information represents the contents of a document of a specific domain, wherein the knowledge base has knowledge of the specific domain, and wherein in the extraction step specific data is extracted by referring to the knowledge of the specific domain stored in the knowledge base.
Claim 26
Dependent Claim
70 words
A natural language processing method comprising: the input step of inputting information in a natural language; the expectation step of expecting the kind of information inputted in the input step on the basis of knowledge stored in the knowledge base, which stores therein linguistic knowledge and knowledge concerning the field of information to be processed; and the step of processing the information whose kind is expected in the expectation step.
Claim 27
Dependent Claim
35 words
The natural language processing method according to claim 26, wherein the expectation step has the discrimination step of discriminating a kind of information, which can be inputted, before information is inputted in the input step.
Claim 28
Dependent Claim
32 words
The natural language processing method according to claim 26, which further comprises the preprocessing step of performing a preprocessing corresponding to the kind of information, which is expected in the expectation step.
Claim 29
Dependent Claim
32 words
The natural language processing method according to claim 28, wherein in the preprocessing step, a knowledge structure corresponding to the kind of information, which is expected in the expectation step, is prepared.
Claim 30
Dependent Claim
58 words
The natural language processing method according to claim 26, which further comprises: the expectation information storing step of storing a result of an expectation made in the expectation step, in an expectation information memory; and the updating step of updating contents of information, which is stored in the expectation information memory, on the basis of the knowledge base.
Claim 31
Dependent Claim
23 words
The natural language processing method according to claim 26, wherein the knowledge base has knowledge concerning a domain of information to be processed.
Claim 32
Dependent Claim
35 words
The natural language processing method according to claim 31, wherein the expectation step has the discrimination step of discriminating a kind of information, which can be inputted, before information is inputted in the input step.
Claim 33
Dependent Claim
32 words
The natural language processing method according to claim 31, which further comprises the preprocessing step of performing a preprocessing corresponding to the kind of information, which is expected in the expectation step.
Claim 34
Dependent Claim
32 words
The natural language processing method according to claim 33, wherein in the preprocessing step, a knowledge structure corresponding to the kind of information, which is expected in the expectation step, is prepared.
Claim 35
Dependent Claim
56 words
The natural language processing method according to claim 31, which further comprises: the expectation information storing step of storing a result of an expectation made in the expectation step, in an expectation information memory; and the updating step of updating contents of information stored in the expectation information memory, on the basis of the knowledge base.
Claim 36
Dependent Claim
118 words
A natural language processing method comprising: the input step of inputting information in a natural language; the expectation step of expecting the kind of information inputted in the input step on the basis of knowledge stored in the knowledge base, which stores therein knowledge concerning a domain of information to be processed, general knowledge and linguistic knowledge; the expectation information storing step of storing information, which represents a result of an expectation made in the expectation step, in an expectation information memory as expectation information; and the analysis step of analyzing the information inputted in the input step by referring to the expectation information stored in the expectation information memory and the knowledge stored in the knowledge base.
Claim 37
Dependent Claim
52 words
The natural language processing method according to claim 36, wherein in the expectation step, a kind of information subsequent to current information is expected on the basis of a result of an analysis of the current information, which is made in the analysis step, and the knowledge stored in the knowledge base.
Claim 38
Dependent Claim
42 words
The natural language processing system according to claim 37, which further comprises the updating step of updating contents of information, which is stored in the expectation information memory, on the basis of a result of an expectation made in the expectation step.
Claim 39
Dependent Claim
41 words
The natural processing method according to claim 36, which further comprises extraction step of extracting specific data from the information, which is inputted in the input step, on the basis of a result of an analysis made in the analysis step.
Claim 40
Dependent Claim
56 words
The natural processing method according to claim 39, wherein the information represents the contents of a document of a specific domain, wherein the knowledge base has knowledge of the specific domain, and wherein in the extraction step, the knowledge of the specific domain stored in the knowledge base is referred to and specific data is extracted.
Claim 41
Dependent Claim
45 words
The natural language processing system according to claim 36, wherein in the input step, a plurality of sentences are inputted, wherein in the analysis step, a set of sentences are processed as sentence by sentence and concepts are outputted as a result of an analysis.
Claim 42
Dependent Claim
28 words
The natural language processing system according to claim 41, which further comprises the identification step of identifying a beautification concept among the concepts outputted by the analysis means.
Claim 43
Dependent Claim
32 words
The natural language processing system according to claim 41, which further comprises the connection step of connecting associated concepts with one another among a plurality of concepts outputted in the analysis step.
Claim 44
Dependent Claim
33 words
The natural language processing system according to claim 41, which further comprises the separation step of separating concepts, which are unsuitably connected with one another, from among concepts outputted by the analysis means.
Claim 45
Independent Claim
14 words
A system or method having the features of any combination of the preceding claims.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.