SYSTEMS AND METHODS FOR AUTOMATED CONTENT GENERATION

• US 20110282649A1
• Filed: 05/13/2010
• Published: 11/17/2011
• Est. Priority Date: 05/13/2010
• Status: Active Grant

• Current Assignee: Expedia Inc. (Expedia Group, Inc.)
• Original Assignee: Expedia Inc. (Expedia Group, Inc.)
• Inventors: Bradley, Patrick, Hsu, Donny, Waksberg, Rene
• Granted Patent: US 8,457,948 B2
• Time in Patent Office: Days
• US Class Current: 704/8
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
• CPC Class Codes: G06F 40/186 Templates

Abstract

A content generation service is described that generates content for electronic documents in different languages based upon templates. The templates may include paragraph templates composed of sentence types including sentence templates. The sentence templates may further include variables having corresponding attributes. Each of the paragraph templates, sentence templates, and attributes may be hierarchically organized. The content generation service may obtain data describing an item of interest, such as a travel item. The obtained data may further specify a document language, section and paragraph for which content is to be generated. Content is generated for variables in hierarchical order, with higher ranked paragraphs considered first. Within the highest ranked paragraph, a sentence type is selected and the variables within the highest ranked sentence template of the sentence type are considered. Sentence templates which contain attributes matched by the data obtained for the item of interest are added to the generated document.

Claims

1. A computer-implemented method of electronically generating a document describing a property in different languages, the method comprising:

under control of one or more configured computer systems;

obtaining one or more paragraph templates for a paragraph describing the property, the paragraph templates comprising one or sentence types including one or more sentence templates, wherein each sentence template comprises one or more variables having associated attributes, and wherein each of the paragraph templates, sentence templates, and attributes are respectively organized hierarchically;

obtaining first data, wherein the first data comprises one or more attributes corresponding to at least one of the variable attributes of the sentence templates;

obtaining second data, the second data specifying the language of the template;

identifying the highest ranked paragraph template for the paragraph describing the property;

selecting a sentence type of the identified paragraph template;

identifying the highest ranked sentence template of the selected sentence type; and

if each of the attributes of the variables of the identified sentence template are identified within the attributes of the first data;

generating a document including the highest ranked sentence template by adding the identified attributes of the first data to the identified highest ranked sentence template in place of the variables of the identified highest ranked sentence template.

2. The computer-implemented method of claim 1, wherein obtaining one or more paragraph templates for a paragraph describing the property comprises:

identifying a language specified within the obtained second data; and

retrieving a paragraph template for the property which is written in the identified language.

3. The computer-implemented method of claim 1, wherein the obtained first data comprises one or more of a property name, property amenities, a property rating, a property location, and points of interest associated with the property.

4. The computer-implemented method of claim 1, wherein the generated document does not include unsatisfied sentence templates, wherein an unsatisfied sentence template has at least one variable attribute that has not been identified within the attributes of the first data.

5. The computer-implemented method of claim 4, wherein one or more selected sentence types are designated as being required.

6. The computer-implemented method of claim 5, wherein the generated document does not include paragraph templates comprising unsatisfied required sentence types, wherein each sentence template of an unsatisfied required sentence template has at least one variable attribute that has not been identified within the attributes of the first data.

7. A system for automatically generating content for an electronic document, the system comprising:

a data store that stores one or more templates for the electronic documents, wherein the templates comprise one or more paragraph templates for a document paragraph, the paragraph templates comprising one or more sentence types comprising one or more sentence templates, and the sentence templates comprising one or more variables having associated attributes, and wherein each of the paragraph templates, sentence templates, and attributes are respectively hierarchically organized; and

a content generation service in communication with the data store, the content generation service operative to;

obtain data regarding an item of interest to be described in the electronic document, the data comprising attributes corresponding to one or more of the variable attributes;

select the paragraph template which is to be employed for content generation from the data store;

identify the highest ranking sentence template of a selected sentence type whose variable attributes match the attributes of the obtained data; and

generate the electronic document including the identified sentence template, wherein attributes of the obtained data that match the attributes of the variables of the identified sentence template are added to the identified sentence template in place of the variables of the identified sentence template.

8. The system of claim 7, wherein the item of interest comprises at least one of flights, lodging properties, ground transportation, and cruises.

9. The system of claim 7, wherein data regarding the item of interest comprises one or more of a property name, property amenities, a property rating, a property location, and points of interest associated with the property.

10. The system of claim 7, wherein the hierarchy of the paragraph templates, sentence templates, and variable attributes is determined by an indicated rank within the data store.

11. The system of claim 7, wherein the attributes of the obtained data comprise at least one of the attributes themselves and corresponding attribute values.

12. The system of claim 11, wherein the variables of the identified sentence template include an indicator specifying whether the sentence template variables are replaced by the attribute or attribute value of the obtained data.

13. The system of claim 7, wherein selecting the paragraph template comprises:

obtaining additional data identifying the template language and document section; and

retrieving a paragraph template for the property which is written in the identified language and pertains to the identified section.

14. The system of claim 7, wherein selecting the paragraph template comprises selecting the highest ranked paragraph template for the document paragraph.

15. The system of claim 7, wherein the generated document does not include unsatisfied sentence templates, wherein an unsatisfied sentence template has at least one variable attribute that has not been identified within the attributes of the first data.

16. The system of claim 7, wherein one or more selected sentence types are designated as being required.

17. The system of claim 16, wherein the generated document does not include paragraph templates comprising unsatisfied required sentence types, wherein each sentence template of an unsatisfied required sentence template has at least one variable attribute that has not been identified within the attributes of the first data.

18. A computer-implemented method of electronically generating content for a document describing an item of interest, the method comprising:

under control of one or more configured computer systems;

receiving a request to generate content for the item of interest;

obtaining data regarding the item of interest, the data including one or more attributes describing the item of interest for use in content generation and one or more languages for content generation;

identifying a template based upon the language for content generation and the item of interest, wherein the template comprises one or more sentence types including one or more sentence templates, wherein the sentence templates include one or more variables having associated attributes, and wherein the sentence templates and attributes are, respectively, hierarchically organized;

identifying the highest ranked sentence template of a selected sentence type whose variable attributes match the attributes of the obtained data; and

generating a document, wherein document includes the identified highest ranked sentence template and wherein the variables of the identified highest ranked sentence template are replaced by the matching attributes of the obtained data.

19. The computer-implemented method of claim 18, wherein the item of interest comprises at least one of flights, lodging properties, ground transportation, and cruises.

20. The computer-implemented method of claim 18, wherein data regarding the item of interest comprises one or more of a property name, property amenities, a property rating, a property location, and points of interest associated with the property.

21. The computer-implemented method of claim 18, wherein the attributes of the obtained data comprise at least one of the attributes themselves and corresponding attribute values.

22. The computer-implemented method of claim 21, wherein the variables of the identified sentence template include an indicator specifying whether the sentence template variables are replaced by the attribute or attribute value of the obtained data.

23. The computer-implemented method of claim 18, wherein identifying the highest ranked sentence template comprises:

identifying a highest ranked paragraph template for a paragraph describing the item of interest, wherein the paragraph templates are hierarchically ranked; and

choosing the selected sentence type from the identified highest ranked paragraph template.

24. The computer-implemented method of claim 23, wherein the hierarchy of the paragraph templates, sentence templates, and variable attributes is determined from an indicated rank within a data store that maintains the respective paragraph templates, sentence templates, and variable attributes.

25. The computer-implemented method of claim 18, wherein the generated document does not include unsatisfied sentence templates, wherein an unsatisfied sentence template has at least one variable attribute that has not been identified within the attributes of the first data.

26. The computer-implemented method of claim 18, wherein one or more selected sentence types are designated as being required.

27. The computer-implemented method of claim 26, wherein the generated document does not include paragraph templates comprising unsatisfied required sentence types, wherein each sentence template of an unsatisfied required sentence template has at least one variable attribute that has not been identified within the attributes of the first data.

28. A computer-readable medium having instructions encoded thereon, wherein the instructions, when executed by a computing apparatus, cause the computing apparatus to:

control a template component operative to;

select a paragraph template for a paragraph describing an item of interest, wherein the paragraph template comprises one or more sentence types comprising one or more sentence templates, and wherein the sentence templates comprise one or more variables having associated attributes, and wherein each of the paragraph templates, sentence templates, and attributes are respectively hierarchically organized;

identify the highest ranking sentence template of a selected sentence type whose variable attributes match the attributes of the obtained data;

obtain data regarding the item of interest, the data comprising attributes corresponding to one or more attributes of the variables; and

generate an electronic document including the identified sentence template, wherein attributes of the obtained data that match the attributes of the variables of the identified sentence template are added to the identified sentence template in place of the variables of the identified sentence template.

29. The computer-readable medium of claim 28, wherein the item of interest comprises at least one of flights, lodging properties, ground transportation, and cruises.

30. The computer-readable medium of claim 28, wherein data regarding the item of interest comprises one or more of a property name, property amenities, a property rating, a property location, and points of interest associated with the property.

31. The computer-readable medium of claim 28, wherein the hierarchy of the paragraph templates, sentence templates, and variable attributes is determined by an indicated rank within a data store that maintains the respective paragraph templates, sentence template, and variable attributes.

32. The computer-readable medium of claim 28, wherein the attributes of the obtained data comprise at least one of the attributes themselves and corresponding attribute values.

33. The computer-readable medium of claim 32, wherein the variables of the identified sentence template include an indicator specifying whether the sentence template variables are replaced by an attribute or attribute value of the obtained data.

34. The computer-readable medium of claim 28, wherein selecting the paragraph template comprises:

obtaining additional data identifying the template language and document section; and

retrieving a paragraph template for the property which is written in the identified language and pertains to the identified section.

35. The computer-readable medium of claim 28, wherein selecting the paragraph template comprises selecting the highest ranked paragraph template of the paragraph.

36. The computer-readable medium of claim 28, wherein the generated document does not include unsatisfied sentence templates, wherein an unsatisfied sentence template has at least one variable attribute that has not been identified within the attributes of the first data.

37. The computer-readable medium of claim 28, wherein one or more selected sentence types are designated as being required.

38. The computer-readable medium of claim 37, wherein the generated document does not include paragraph templates comprising unsatisfied required sentence types, wherein each sentence template of an unsatisfied required sentence template has at least one variable attribute that has not been identified within the attributes of the first data.