Document processing, template generation and concept library generation method and apparatus

• US 8,949,108 B2
• Filed: 05/31/2011
• Issued: 02/03/2015
• Est. Priority Date: 05/31/2010
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cao, Feng, Hu, Gang, Li, Jing, Li, Zhong, Ren, Yong Liang, Wang, Xiao Yuan
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US13/118,730
• Publication Number:
  US 20110295595A1
• Time in Patent Office: 1,344 Days
• Field of Search: 704/9
• US Class Current: 704/9
• CPC Class Codes: G06F 40/143 Markup, e.g. Standard Generalized Markup Language [SGML] or Document Type Definition [DTD]
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

The present invention relates to document processing method and apparatus which can edit a natural language and generate a machine-processable document; a template generating method and apparatus which can be used for document processing method and apparatus; a concept library generating method and apparatus which can be used for the document processing method and apparatus and the template generating method and apparatus. The present invention provided a possibility for semantic interaction of documents in different systems and enhances efficiency.

Claims

1. An electronic document processing method, comprising steps of:

acquiring an electronic template comprising a set of semantic items, wherein (i) candidate values of the set of semantic items and relations among a plurality of semantic items in the set of semantic items are associated with one or more electronic semantic codes, and (ii) the electronic template is associated with a natural language expression mode;

receiving an electronic input value for at least one semantic item in the set of semantic items, wherein the electronic input value comprises one or more constituent values;

generating a first electronic document comprising (i) a first set of electronic semantic codes corresponding to the electronic input value, (ii) the relations among the plurality of semantic items, and (iii) a second set of electronic semantic codes corresponding to the relations among the plurality of semantic items; and

generating, based on the electronic input value and based on the natural language electronic expression mode, a second electronic document comprising the electronic input value.

2. The method of claim 1, wherein receiving the electronic input value comprises:

displaying an electronic input interface of the set of semantic items; and

receiving the electronic input value via the electronic input interface.

3. The method of claim 2, wherein displaying the electronic input interface comprises:

identifying a core concept in the electronic template;

identifying an interrelation between one or more semantic items in the set of semantic items and the core concept;

acquiring a qualifier concept from an electronic concept library, wherein an interrelation between the qualifier concept and the core concept is identical to the interrelation between the one or more semantic items and the core concept; and

generating, based on the qualifier concept, the electronic input interface for inputting the electronic input value.

4. The method of claim 1, wherein receiving the electronic input value comprises receiving the electronic input value from an external apparatus.

5. The method of claim 1, wherein acquiring the electronic template comprises acquiring the electronic template from an external apparatus.

6. The method of claim 1, wherein acquiring the electronic template comprises constructing the electronic template according to a natural language pattern.

7. The method of claim 1, wherein acquiring the electronic template comprises replacing a variable sentence element in a natural language electronic document sample with a semantic item of the electronic template to form the electronic template.

8. The method of claim 1, wherein at least one portion of the electronic document is generated based on a clinical document architecture (CDA) standard.

9. The method of claim 1, wherein the electronic template is generated from a natural language electronic document sample by a method comprising steps of:

identifying, based on the natural language electronic document sample, a core concept and one or more sentence elements;

determining a relation between a current concept of the one or more sentence elements and the core concept;

searching in an electronic concept library for a qualifier concept, wherein a relation between the qualifier concept and the core concept is identical to the relation between the current concept and the core concept;

generating, based on searching the electronic concept library, the set of semantic items of the electronic template; and

generating, based on the qualifier concept, the candidate values of the set of semantic items.

10. The method of claim 9, wherein generating the set of semantic items comprises:

selecting, as a semantic item, an interested sentence element from among the sentence elements, wherein the interested sentence element corresponds to at least one qualifier concept determined based on searching the electronic concept library, and wherein the at least one qualifier concept has candidate value options identical to candidate value options of the interested sentence element; and

replacing one or more sentence elements other than the interested sentence elements with semantic items having no candidate value option.

11. The method of claim 1, wherein the electronic template is generated from a natural language electronic document sample, by a method comprising steps of:

displaying the natural language electronic document sample via an electronic display device;

selecting an interested sentence element in the natural language electronic document sample as a core concept and as a semantic item in the set of semantic items of the electronic template;

determining a relation between a current concept of one or more semantic items in the set of semantic items, and the core concept;

searching in a concept library for a qualifier concept, wherein a relation between the qualifier concept and the core concept identical to the relation between the current concept and the core concept; and

generating, based on the qualifier concept, candidate values of the one or more semantic items in the set of semantic items.

12. The method of claim 9, wherein generating the candidate values of the set of semantic items comprises selecting candidate values from among the qualifier concept and the current concept.

13. The method of claim 3, wherein generating an electronic concept library comprises:

determining, based on a natural language electronic document sample, the core concept and the qualifier concept;

determining a relation between the qualifier concept and the core concept; and

storing in association with one another;

(i) the core concept, (ii) the qualifier concept, (iii) the relation between the qualifier concept and the core concept, and (iv) semantic codes corresponding to (i)-(iii).

14. A document processing device, comprising:

means configured to acquire a template comprising a set of semantic items, wherein (i) candidate values of the set of semantic items and relations among a plurality of semantic items in the set of semantic items are associated with one or more semantic codes, and (ii) the template is associated with a natural language expression mode;

semantic item input means configured to receive an input value for at least one semantic item in the set of semantic items, wherein the input value comprises one or more constituent values;

machine-processable document generating means configured to generate a first document comprising (i) a first set of semantic codes corresponding to the input value, (ii) the relations among the plurality of semantic items, and (iii) a second set of semantic codes corresponding to the relations among the plurality of semantic items; and

natural language document generating means configured to generate, based on the input value and based on the natural language expression mode, a second document comprising the input value.

15. The device of claim 14, wherein the semantic item input means comprises:

means configured to display an input interface of the set of semantic items; and

means configured to receive the input value via the input interface.

16. The device of claim 15, wherein means for displaying the input interface comprises:

means configured to identify a core concept in the template;

means configured to identify an interrelation between one or more semantic items in the set of semantic items and the core concept;

means configured to acquire a qualifier concept from a concept library, wherein an interrelation between the qualifier concept and the core concept is identical to the interrelation between the one or more semantic items and the core concept; and

means configured to generate, based on the qualifier concept, the input interface for inputting the input value.

17. The device of claim 14, further comprising means for generating the template from a natural language document sample, said means comprising:

means configured to identify, based on the natural language document sample, a core concept and one or more sentence elements;

means configured to determine a relation between a current concept of the one or more sentence elements and the core concept;

means configured to search in an concept library for a qualifier concept, wherein a relation between the qualifier concept and the core concept is identical to the relation between the current concept and the core concept;

means configured to generate, based on searching the concept library, the set of semantic items of the template; and

means configured to generate, based on the qualifier concept, the candidate values of the set of semantic items.

18. The device of claim 14, further comprising means for generating the template from a natural language document sample, said means comprising:

means configured to display the natural language document sample via a display device;

means configured to select an interested sentence element in the natural language document sample as a core concept and as a semantic item in the set of semantic items of the template;

means configured to determine a relation between a current concept of one or more semantic items in the set of semantic items, and the core concept;

means configured to search in a concept library for a qualifier concept, wherein a relation between the qualifier concept and the core concept identical to the relation between the current concept and the core concept; and

means configured to generate, based on the qualifier concept, candidate values of the one or more semantic items in the set of semantic items.

19. The device of claim 16, wherein generating a concept library comprises:

means configured to determine, based on a natural language document sample, the core concept and the qualifier concept;

means configured to determine a relation between the qualifier concept and the core concept; and

means configured to store in association with one another;

(i) the core concept, (ii) the qualifier concept, (iii) the relation between the qualifier concept and the core concept, and (iv) semantic codes corresponding to (i)-(iii).

20. A non-transitory computer readable article of manufacture tangibly embodying computer readable instructions which when executed causes a computer to carry out a document processing method, comprising steps of:

acquiring an electronic template comprising a set of semantic items, wherein (i) candidate values of the set of semantic items and relations among a plurality of semantic items in the set of semantic items are associated with one or more electronic semantic codes, and (ii) the electronic template is associated with a natural language expression mode;

receiving an electronic input value for at least one semantic item in the set of semantic items, wherein the electronic input value comprises one or more constituent values;

generating a first electronic document comprising (i) a first set of electronic semantic codes corresponding to the electronic input value, (ii) the relations among the plurality of semantic items, and (iii) a second set of electronic semantic codes corresponding to the relations among the plurality of semantic items; and

generating, based on the electronic input value and based on the natural language electronic expression mode, a second electronic document comprising the electronic input value.