Speech And Textual Analysis Device And Corresponding Method

• US 20070282598A1
• Filed: 08/09/2005
• Published: 12/06/2007
• Est. Priority Date: 08/13/2004
• Status: Active Grant

• Current Assignee: Infocodex AG
• Original Assignee: Swiss Reinsurance Company
• Inventors: Cuypers, Frank, Waelti, Paul, Waelti, Christoph, Trugenberger, Carlo
• Granted Patent: US 8,428,935 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning

Abstract

A speech and textual analysis device and method for forming a search and/or classification catalog. The device is based on a linguistic database and includes a taxonomy table containing variable taxon nodes. The speech and textual analysis device includes a weighting module, a weighting parameter being additionally assigned to each stored taxon node to register recurrence frequency of terms in the linguistic and/or textual data that is to be classified and/or sorted. The speech and/or textual analysis device includes an integration module for determining a predefinable number of agglomerates based on the weighting parameters of the taxon nodes in the taxonomy table and at least one neuronal network module for classifying and/or sorting the speech and/or textual data based on the agglomerates in the taxonomy table.

Claims

1-26. -26. (canceled)

27. :

A language and text analysis apparatus for formation of a search and/or classification catalog, which apparatus includes at least one linguistic databank for association of linguistic terms with data records, in which case the language and text analysis apparatus can be used to classify and/or to sort language and/or text data corresponding to the data records, and in which the linguistic terms include at least keywords and/or search terms,

wherein;

the linguistic databank includes links between words and/or linked terms of similar meaning, in which case the links can be associated with synonym groups in a taxonomy table,

the language and/or text analysis apparatus includes a weighting module for weighting of table elements in the taxonomy table on the basis of frequency of occurrence of individual links in the linguistic databank,

the language and/or text analysis apparatus includes an integration module, in which case the integration module can be used to generate a multidimensional, weighted content matrix on the basis of agglomerates of elements in the taxonomy table,

the language and/or text analysis apparatus includes at least one neural network module for classification and/or sorting of the language and/or text data on the basis of a content matrix, in which case definable descriptors for the language and/or text analysis apparatus can be used to determine appropriate constraints for one or more subject groups.

28. :

The language and text analysis apparatus as claimed in claim 27, wherein the links in the linguistic databank can be defined over more than one language.

29. :

A language and text analysis apparatus for formation of a search and/or classification catalog, which apparatus includes at least one linguistic databank for association of linguistic terms with data records, in which case the language and text analysis apparatus can be used to classify and/or to sort language and/or text data corresponding to the data records, and in which the linguistic terms include at least keywords and/or search terms,

wherein;

the language and text analysis apparatus includes a taxonomy table with variable taxon nodes on the basis of the linguistic databank, in which case one or more data records can be associated with one taxon node in the taxonomy table, and in which case each data record includes a variable significance factor for weighting of terms on the basis of at least filling words and/or linking words and/or keywords,

the language and text analysis apparatus includes a weighting module, in which a weighting parameter for recording of frequencies of occurrence of terms within the language and/or text data to be sorted and/or to be classified is additionally stored associated with each taxon node,

the language and/or text analysis apparatus includes an integration module for determination of a predefinable number of agglomerates on the basis of the weighting parameters of the taxon nodes in the taxonomy table, with one agglomerate including at least one taxon node, and

the language and/or text analysis apparatus includes at least one neural network module for classification and/or for sorting of the language and/or text data on the basis of the agglomerates in the taxonomy table.

30. :

The language and text analysis apparatus as claimed in claim 29, wherein the neural network module includes at least one self-organizing Kohonen map.

31. :

The language and text analysis apparatus as claimed in claim 29, wherein the language and text analysis apparatus includes an entropy module for determination of an entropy parameter, which can be stored in a memory module, on the basis of distribution of a data record in the language and/or text data.

32. :

The language and text analysis apparatus as claimed in claim 29, wherein the linguistic databank includes multilingual data records.

33. :

The language and text analysis apparatus as claimed in claim 29, wherein the language and text analysis apparatus includes a hash table that is associated with the linguistic databank in which case a hash value can be used to identify linguistically linked data records in the hash table.

34. :

The language and text analysis apparatus as claimed in claim 29, wherein a language parameter can be used to associate the data records with a language and can be identified as a synonym in the taxonomy table.

35. :

The language and text analysis apparatus as claimed in claim 29, wherein the entropy parameter is given by;

Entropy_DR=In(freqsum_DR)−

Σ

F_DRIn(F_DR)/freqsum_DR.

36. :

The language and text analysis apparatus as claimed in claim 29, wherein the agglomerates can be associated with an n-dimensional content matrix in an n-dimensional content space.

37. :

The language and text analysis apparatus as claimed in claim 36, wherein n is equal to 100.

38. :

The language and text analysis apparatus as claimed in claim 29, wherein the language and text analysis apparatus includes descriptors by which constraints that correspond to definable descriptors can be determined for a subject group.

39. :

The language and text analysis apparatus as claimed in claim 29, wherein the databank includes a universal, subject-independent, linguistic databank, and the taxonomy table can be produced universally and independently of subject.

40. :

An automated language and text analysis method for formation of a search and/or classification catalog, with a linguistic databank being used to record data records and to classify and/or sort language and/or text data on the basis of the data records,

wherein;

the data records in the linguistic databank are stored associated with a taxon node in a taxonomy table, with each data record including a variable significance factor for weighting of terms based at least on filling words and/or linking words and/or keywords,

the language and/or text data is recorded on the basis of the taxonomy table, with frequency of individual data records in the language and/or text data being determined by a weighting module and being associated with a weighting parameter for the taxon node,

an integration module is used to determine a determinable number of agglomerates in the taxonomy table on the basis of the weighting parameters of one or more taxon nodes,

a neural network module is used to classify and/or sort the language and/or text data on the basis of the agglomerates in the taxonomy table.

41. :

The automated language and text analysis method as claimed in claim 40, wherein the neural network module includes at least one self-organizing Kohonen map.

42. :

The automated language and text analysis method as claimed in claim 40, wherein an entropy module is used to determine an entropy factor on the basis of distribution of a data record in the language and/or text data.

43. :

The automated language and text analysis method as claimed in claim 40, wherein the linguistic databank includes multilingual data records.

44. :

The automated language and text analysis method as claimed in claim 40, wherein a hash table is stored associated with the linguistic databank, with the hash table including an identification of linked data records by a hash value.

45. :

The automated language and text analysis method as claimed in claim 40, wherein the data records can be associated with a language and can be weighted synonymously in the taxonomy table by a language parameter.

46. :

The automated language and text analysis method as claimed in claim 40, wherein the entropy factor is given by the term

Entropy_DR=In(freqsum_DR)−

Σ

F_DRIn(F_DR)/freqsum_DR.

47. :

The automated language and text analysis method as claimed in claim 40, wherein the agglomerates form an n-dimensional content space.

48. :

The automated language and text analysis method as claimed in claim 47, wherein n is equal to 100.

49. :

The automated language and text analysis method as claimed in claim 40, wherein definable descriptors can be used to determine corresponding constraints for a subject group.

50. :

The language and text analysis method as claimed in claim 40, wherein the taxon nodes in the taxonomy table are produced on the basis of a universal, subject-independent, linguistic databank, with the databank including at least the universal, subject-independent, linguistic databank.

52. :

A computer program product which can be loaded in an internal memory of a digital computer and including software code sections by which the operations as claimed in claim 40 can be carried out when the product is run on a computer, in which case the neural networks can be generated with software and/or hardware.

51. :

A computer program product on a computer-readable medium with computer program code means contained therein to control one or more processors in a computer-based system for automated language and text analysis by formation of a search and/or classification catalog, with data records being recorded on the basis of a linguistic databank, and with language and/or text data being classified and/or sorted on the basis of the data records,

wherein;

the computer program product can be used to store the data records in the linguistic databank associated with a taxon node in a taxonomy table, with each data record including a variable significance factor for weighting of terms on the basis at least of filling words and/or linking words and/or keywords,

the computer program product can be used to record the language and/or text data on the basis of the taxonomy table, with frequency of individual data records in the language and/or text data determining a weighting parameter for the taxon nodes,

the computer program product can be used to determine a determinable number of agglomerates in the taxonomy table on the basis of the weighting parameter of one or more taxon nodes,

the computer program product can be used to generate a neural network, which can be used to classify and/or sort the language and/or text data on the basis of the agglomerates in the taxonomy table, the language, and/or text data.