Automated customized web portal template generation systems and methods

• US 9,747,556 B2
• Filed: 08/20/2014
• Issued: 08/29/2017
• Est. Priority Date: 08/20/2014
• Status: Active Grant

• Current Assignee: Vertafore Incorporated
• Original Assignee: Vertafore Incorporated
• Inventors: Garrison, Sara, Sinyagin, Aleksey
• Primary Examiner(s): Misir, Dave
• Application Number:
  US14/464,576
• Publication Number:
  US 20160055132A1
• Time in Patent Office: 1,105 Days
• Field of Search: 706 12
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• 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 40/221 Parsing markup language streams streaming G06F40/149
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

An automated Web portal template generation method includes parsing, via a parser subsystem, a number of Webpages of a first Website from which a Web portal template to be customized is to be accessed. The method further includes producing an entity feature set for the first Website based on a result of the parsing and processing the entity feature set for the first Website via a classifier subsystem to produce a set of data that represents, for each of a plurality of entities, a respective probability of the entity belonging to a respective one of a plurality of classes. The method additionally includes performing, by a color matching subsystem, color matching on the set of data produced by the classifier subsystem to generate a number of proposed color combinations for a proposed customization of the Web portal template.

Claims

1. A method of operation in an automated Web portal generation system to generate sets of customizations of Web portal templates, the method comprising:

parsing, by at least one component of the automated Web portal generation system, a number of Webpages of a first Website, represented by a domain or Universal Resource Locator (URL), from which a Web portal template to be customized is to be accessed;

producing an entity feature set for the first Website based on a result of the parsing;

processing the entity feature set for the first Website via a classifier executed by at least one component of the automated Web portal generation system to produce a set of data that represents, for each of a plurality of entities, a respective probability of the entity belonging to a respective one of a plurality of classes;

performing color matching on the set of data produced via the classifier to generate a number of proposed color combinations for a proposed customization of the Web portal template, wherein performing color matching to generate a number of proposed color combinations includes identifying candidate background colors by evaluating contrast between colors of each pair of a plurality of pairs of colors in a device-independent color space;

ranking pairs of color combinations based at least in part on the probabilities from the processing via the classifier;

returning the ranking as a collection of results for user evaluation; and

identifying one of the proposed color combinations for a proposed customization of the Web portal template.

2. The method of claim 1 wherein processing the entity feature set for the first Website via a classifier includes executing a classification algorithm that identifies a set of color schema and probabilities of attained color matches.

3. The method of claim 1 wherein the automated Web portal generation system includes machine-learning circuitry, and processing the entity feature set for the first Website via a classifier executed by at least one component of the automated Web portal generation system includes processing the entity feature set for the first Website via the classifier executed by the machine-learning circuitry.

4. The method of claim 3 wherein processing the entity feature set to produce a set of data includes processing the entity feature set to produce data that represents, for each of a plurality of hypertext markup language (HTML) or cascade style sheet (CSS) entities a respective probability of the HTML or CSS entity belonging to a respective one of the plurality of classes.

5. The method of claim 4 wherein classes include a Web background class, a mobile background class, a major font class, a second font class, and a mobile font class.

6. The method of claim 4 wherein processing the entity feature set to produce a set of data includes processing the entity feature set to produce data that represents, for each of a plurality of colors a respective probability of the color belonging to a respective one of the plurality of classes.

7. The method of claim 1, further comprising:

crawling an n-level deep page tree of the first Website before parsing the number of Webpages of the first Website.

8. The method of claim 6, further comprising:

identifying potential areas of styling in the number of Webpages that comprise the first Website; and

extracting cascade style sheet (CSS) information from at least some of the identified potential areas of styling on which to perform the parsing.

9. The method of claim 1 wherein performing color matching to generate a number of proposed color combinations includes calculating a Euclidean distance between colors for each pair of the plurality of pairs of colors.

10. The method of claim 1 wherein performing color matching to generate a number of proposed color combinations includes calculating a Euclidean distance between colors for each pair of the plurality of pairs of colors in a device-independent color space.

11. The method of claim 1 wherein performing color matching to generate a number of proposed color combinations includes calculating distances between colors to identify contrast factors using weights.

12. The method of claim 1 wherein performing color matching on the set of data produced via the classifier includes performing color matching to generate a number of proposed colors suitable for both mobile and non-mobile displays.

13. The method of claim 1 wherein identifying candidate background colors includes at least one of:

i) favoring dark fonts on light backgrounds; and

ii) discriminating against bright colors accounting for recessiveness and dominance of colors, accounting for a complimentary alignment of colors per a color wheel representation.

14. The method of claim 1 wherein identifying candidate background colors includes accounting for visually active or passive positions of the corresponding entities.

15. The method of claim 1 wherein producing an entity feature set for the first Website based on the results of the parsing includes executing a statistical calculation algorithm to identify at least one of a dominant color, a neutral color, a supplemental color or a recessive color with characteristics, the characteristics including at least one of attraction, coverage, lighting, or html positioning.

16. The method of claim 1, further comprising:

autonomously applying the identified one of the proposed color combinations to the Web portal template to produce an instance of a customized Web portal.

17. The method of claim 16, further comprising:

subsequently, detecting a change in the first Website; and

autonomously propagating a revision based on the detected change to the Web portal template to produce an instance of a revised customized Web portal.

18. An automated Web portal generation system that generates sets of customizations of Web portal templates, the system comprising:

at least one processor;

at least one non-transitory storage media communicably coupled to the at least one processor, the non-transitory storage media storing at least one of data or processor-readable instruction sets that, when executed by the at least one processor, cause the at least one processor to function as an automated Web portal system that;

parses a number of Webpages of a first Website), represented by a domain or Universal Resource Locator (URL), from which a Web portal template to be customized is to be accessed;

produces an entity feature set for the first Website based on a result of the parsing;

processes the entity feature set for the first Website via a classifier to produce a set of data that represents, for each of a plurality of hypertext markup language (HTML) or cascade style sheet (CSS) entities, a respective probability of the entity belonging to a respective one of a plurality of classes;

performs color matching on the set of data produced via the classifier to generate a number of proposed color combinations for a proposed customization of the Web portal template, wherein the performance of color matching to generate a number of proposed color combinations includes identification of candidate background colors by evaluation of contrast between colors of each pair of a plurality of pairs of colors in a device-independent color space;

ranks pairs of color combinations based at least in part on the probabilities from the processing via the classifier;

returns the ranking as a collection of results for user evaluation; and

identifies one of the proposed color combinations for a proposed customization of the Web portal template.

19. The automated Web portal generation system of claim 18 wherein the processor-readable instruction sets that cause the at least one processor to process the entity feature set for the first Website via a classifier further cause the at least one processor to:

execute a classification algorithm that identifies a set of color schema and probabilities of attained color matches.

20. The automated Web portal generation system of claim 18 wherein the at least one processor further comprises machine-learning circuitry;

and

wherein the processor-readable instruction sets that cause the at least one processor to process the entity feature set for the first Website via a classifier further cause the at least one processor to process the entity feature set for the first Website via the classifier executed by the machine-learning circuitry.