METHOD AND SYSTEM FOR PROVIDING REAL TIME SEARCH PREVIEW PERSONALIZATION IN DATA MANAGEMENT SYSTEMS

• US 20190018899A1
• Filed: 04/19/2018
• Published: 01/17/2019
• Est. Priority Date: 07/14/2017
• Status: Active Grant

• Current Assignee: Intuit, Inc.
• Original Assignee: Intuit, Inc.
• Inventors: Podgorny, Igor A., Indyk, Benjamin, Wei, Ling Feng
• Granted Patent: US 10,922,367 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A method and system provides personalized search results to users of a data management system. The method and system receives a search query from a user and generate initial search results including a plurality of assistance documents relevant to the query data. The method and system utilizes natural language analysis and machine learning processes to analyze the query data, user attributes data, and the assistance documents in order to generate personalized previews of the assistance documents for the user. The method and system output personalized search results to the user including the personalized previews of the assistance documents.

Claims

1. A computing system implemented method for providing personalized search results to users of a data management system, the method comprising:

providing data management interview content data to a user of the data management system as part of a data management interview;

receiving query data from the user corresponding to a request for assistance related to the data management system;

generating initial search results data indicating an assistance document likely to be relevant to the request based on the query data;

generating, for the assistance document, personalized assistance document preview data including a preview of the assistance document personalized for the user based on attributes of the user;

generating personalized search results data identifying the assistance document and including the personalized assistance document preview data; and

outputting the personalized search results data to the user.

2. The method of claim 1, further comprising generating query semantics data identifying semantic characteristics of the query data by analyzing the query data with a natural language processing model.

3. The method of claim 2, further comprising generating a portion of the personalized assistance document preview data based on the query semantics data.

4. The method of claim 3, wherein generating the portion of the personalized assistance document preview data includes incorporating a portion of the query data into the personalized assistance document preview data.

5. The method of claim 2, further comprising generating assistance document semantics data indicating semantic properties of the assistance document by analyzing the assistance document with the natural language processing model.

6. The method of claim 5, further comprising generating the personalized assistance document preview data by selecting portions of the assistance document for inclusion in the personalized assistance document preview based on the assistance document semantics data.

7. The method of claim 5, further comprising generating the personalized assistance document preview data by selecting portions of the assistance document for inclusion in the personalized assistance document preview that are semantically similar to the query data based on the assistance document semantics data and the query semantics data.

8. The method of claim 1, further comprising generating the personalized assistance document preview data by selecting an assistance document preview from a group of assistance document previews associated with the assistance document.

9. The method of claim 1, further comprising training a predictive model with a machine learning process, a predictive model to identify characteristics of a preview document that are likely to be relevant to users of the data management system based on attributes of the user.

10. The method of claim 9, further comprising:

generating relevant preview characteristics data for the user by analyzing the attributes of the user with the predictive model; and

generating the personalized assistance document preview data based on relevant preview characteristics data.

11. The method of claim 9, wherein the predictive model includes one or more of:

a Latent Dirichlet Allocation model;

a logistic regression model;

a random forest model;

a K nearest neighbors model;

a linear regression model;

a support vector machine model;

a linear discriminant analysis model; and

a naï

ve Bayes model.

12. The method of claim 1, wherein the data management system includes one or more of:

a tax return preparation system;

a bookkeeping system; and

a transaction monitoring system.

13. The method of claim 1, wherein the attributes of the user include one or more of:

demographics data;

clickstream data indicating how the user has navigated through services of the data management system;

data management data of the user maintained by the data management system.

14. The method of claim 1, wherein the user attributes data includes the query data.

15. The method of claim 1, wherein the initial search results data include a plurality of assistance documents.

16. The method of claim 15, further comprising generating, for each assistance document, personalized assistance document preview data including a preview of the assistance document based on attributes of the user, wherein the personalized search results data lists each assistance document and include the personalized assistance document preview data for each assistance document.

17. A computing system implemented method for providing personalized search results to users of a data management system, the method comprising:

providing data management interview content data to a user of the data management system as part of a data management interview;

receiving query data from the user corresponding to a request for assistance related to the data management system;

generating initial search results data indicating an assistance document likely to be relevant to the request based on the query data;

analyzing the query data with a natural language processing model;

analyzing the user attributes data related to the user with a predictive model;

generating, for the assistance document, personalized assistance document preview data including a preview of the assistance document personalized for the user based on analysis by the natural language processing model and the predictive model;

generating personalized search results data identifying the assistance document and including the personalized assistance document preview data; and

outputting the personalized search results data to the user.

18. The method of claim 17, further comprising including in the personalized assistance document preview data an indication that the assistance document includes an image or video if the assistance document includes an image or video and the predictive model indicates that the user likely has a preference for assistance documents that include images or videos.

19. The method of claim 17, further comprising identifying, with the natural language processing model, key terms to include in the personalized assistance document preview data.

20. The method of claim 19, further comprising:

generating the personalized assistance document preview data with the key terms positioned in an F shape.

21. The method of claim 19, further comprising generating the assistance document preview data with the key terms positioned according to a golden triangle configuration.

22. The method of claim 17, wherein the attributes data includes one or more of:

demographics data;

clickstream data indicating how the user has navigated through services of the data management system;

data management data of the user maintained by the data management system.

23. The method of claim 17, further comprising generating, with the predictive model, generates relevant preview characteristics data corresponding to characteristics of an assistance document preview likely to be relevant to the user based on how historical users of the data management system that are similar to the user have selected assistance documents from search results in the past.

24. A system for providing personalized search results to users of a data management system, the system comprising:

at least one processor; and

at least one memory coupled to the at least one processor, the at least one memory having stored therein instructions which, when executed by any set of the one or more processors, perform a process including providing data management interview content data to a user of the data management system as part of a data management interview;

receiving query data from the user corresponding to a request for assistance related to the data management system;

generating initial search results data indicating an assistance document likely to be relevant to the request based on the query data;

generating, for the assistance document, personalized assistance document preview data including a preview of the assistance document personalized for the user based on attributes of the user;

generating personalized search results data identifying the assistance document and including the personalized assistance document preview data; and

outputting the personalized search results data to the user.

25. The system of claim 24, wherein the personalized search results data includes a link to the assistance document.

26. The system of claim 25, wherein the personalized assistance document preview data includes terms not included in the assistance document.

27. The system of claim 24, wherein the personalized assistance document preview data includes a title of the assistance document.

28. The system of claim 24, wherein the personalized assistance document preview data includes an altered title of the assistance document.

29. The system of claim 24, wherein the initial search results data include a plurality of assistance documents.

30. The method of claim 29, further comprising generating, for each assistance document, personalized assistance document preview data including a preview of the assistance document based on attributes of the user, wherein the personalized search results data lists each assistance document and include the personalized assistance document preview data for each assistance document.