DYNAMIC LOADING OF CONTEXTUAL ONTOLOGIES FOR PREDICTIVE TOUCH SCREEN TYPING

• US 20160125071A1
• Filed: 10/30/2014
• Published: 05/05/2016
• Est. Priority Date: 10/30/2014
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Gabbai, Jonathan
• Granted Patent: US 9,880,714 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06F 3/04895 Guidance during keyboard input operation, e.g. prompting
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers

Abstract

A system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for generating a navigable user interface for the dynamic loading of contextual ontologies for predictive typing. In some embodiments, the method may include receiving an input from a client device, gathering context data corresponding to the input, and providing a predictive typing entry based on the context data and the received input, in a navigable user interface.

Claims

1. A method comprising:

receiving a typed input from a user during a communication session;

gathering context data corresponding to the input and the communication session;

retrieving a corresponding ontology, from a database of ontologies, based on the context data, wherein the ontologies comprise keywords for use in generating a predictive typing entry; and

providing the predictive typing entry based on the input, the context data and the corresponding ontology.

2. The method of claim 1, wherein the context data may include one or more parameters, including a user transaction history, a user query history, a content of a website, and a content of the communication session.

3. The method of claim 1, further comprising communicating the predictive typing entry as a text suggestion;

wherein the text suggestion may be a word, phrase, numerical quantity, price term, or combination thereof;

wherein the user may accept and reject the text suggestion for use; and

wherein the user may replace the text suggestion with a custom user input.

4. The method of claim 1, wherein the communication session includes a first time period and a second time period, and wherein the method further comprises:

receiving a first typed input from a user during the first period in a communication session;

gathering first context data corresponding to the first typed input and the first period in the communication session;

retrieving a first corresponding ontology, from the database of ontologies, based on the first context data;

providing the predictive typing entry based on the first typed input, the first context data and the first corresponding ontology;

receiving a second typed input from the user during the second time period in the communication session;

gathering second context data corresponding to the second typed input and the second period in the communication session;

retrieving a second corresponding ontology, from the database of ontologies, based on the second context data; and

providing the predictive typing entry based on the second typed input, the second context data and the second corresponding ontology.

5. The method of claim 1, further comprising the user saving the corresponding ontology locally;

and

recalling the corresponding ontology automatically.

6. The method of claim 1, further comprising regularly creating a new ontology, based on the context data and the user input;

storing the new ontology are stored in the database of ontologies; and

updating the new ontology with a subsequent related user input, wherein the subsequent related user input corresponds with the context data and the user input.

7. The method of claim 1, wherein two or more ontology may be streamed to the user, wherein the two or more ontology includes a baseline ontology and a category specific ontology;

wherein the most frequently used keywords of the corresponding ontology are streamed to the user first;

wherein the two or more corresponding ontology are used to generate the predictive typing suggestion; and

wherein the predictive typing suggestion may be generated while the two or more corresponding ontology are only partially loaded,

8. The method of claim 1, wherein the corresponding ontology may be comprised of two or more ontology components;

wherein the corresponding ontology and the two or more ontology components are dynamically loaded starting with a broadest ontology component, and providing additional narrower ontology components based on the context data and the input.

9. The method of claim 1, further comprising:

assigning a rank to the corresponding ontology based on a frequency of use, a conversion rate, a usage behavior, and an accuracy of the text suggestions;

wherein the frequency of use is the total number of times the corresponding ontology is used by the user, as compared with other ontologies in the database of ontologies;

wherein a higher conversion rate corresponds to a higher overall rank within the database of ontologies;

wherein the usage behavior is based on the keywords used from the corresponding ontology; and

wherein the accuracy of the predictive typing suggestion is calculated as the ratio of predictive typing suggestions rejected by the user against predictive typing suggestions accepted by the user; and

pre-caching the corresponding ontology with the highest assigned rank with the user.

10. The method of claim 2, further comprising pre-caching the corresponding ontology based on a previous context data associated with a previous communication session, the user transaction history, and the user query history.

12. The system of claim 10, wherein the corresponding ontology may comprise two or more ontology components;

wherein the ontology module is further configured to dynamically retrieve the corresponding ontology and the two or more ontology components, starting with a broadest ontology component, and providing additional narrow ontology components based on the context data and the received input.

13. The system of claim 10, wherein the communications module is further configured to receive a user input to accept the text suggestion;

and

receive a user input to reject the text suggestion.

14. The system of claim 10, wherein the ontology module is further configured to assign a rank to the corresponding ontology;

wherein the rank is based on a frequency of use, a conversion rate, a usage behavior, and an accuracy of the text suggestions;

wherein the frequency of use is the total number of times the corresponding ontology is used by the user, as compared with other ontologies in the database of ontologies;

wherein a higher conversion rate corresponds to a higher overall rank within the database of ontologies;

wherein the usage behavior is based on the keywords used from the corresponding ontology; and

wherein the accuracy of the predictive typing suggestion is calculated as the ratio of predictive typing suggestions rejected by the user against predictive typing suggestions accepted by the user.

15. The system of claim 10, wherein the ontology module is further configured to pre-cache the corresponding ontology.

11. A system to dynamically load contextual ontologies comprising:

a communications module, configured to receive an input from a user during a communication session;

a context data module, configured to gather context data corresponding to the received input from the user and the communication session;

an ontology database comprising ontologies;

an ontology module, configured to retrieve a corresponding ontology from the ontology database based on the context data;

a predictive typing entry module, configured to generate a predictive typing entry based on the context data, the received input, and the corresponding ontology, wherein the predictive typing entry generated by the predictive typing entry module is a text suggestion; and

a presentation module, configured to present the predictive typing entry to the user.

16. A machine-readable storage medium storing instructions that, when executed by a processor, causes the processor to perform a method to dynamically load contextual ontologies, the method comprising:

receiving an input from a user during a communication session;

gathering context data corresponding to the input and the communication session;

retrieving a corresponding ontology from an ontology database based on the context data; and

generating a predictive typing entry based on the input, the context data and the corresponding ontology.

17. The machine-readable storage medium of claim 16, wherein the corresponding ontology may comprise two or more ontology components;

wherein the method to dynamically load contextual ontologies further comprises;

dynamically retrieving the corresponding ontology and the two or more ontology components, starting with a broadest ontology component, and providing additional narrow ontology components based on the context data and the input.

18. The machine-readable storage medium of claim 16, wherein the predictive typing entry is a text suggestion which may be accepted or rejected by the user.

19. The machine-readable storage medium of claim 16, wherein the method to dynamically load contextual ontologies further comprises:

pre-caching the corresponding ontology.

20. The machine-readable storage medium of claim 16, wherein the method to dynamically load contextual ontologies further comprises:

assigning a rank to the corresponding ontology.