Method and system for providing domain-specific and dynamic type ahead suggestions for search query terms with a customer self-service system for a tax return preparation system

• US 10,733,677 B2
• Filed: 10/18/2016
• Issued: 08/04/2020
• Est. Priority Date: 10/18/2016
• Status: Active Grant

• Current Assignee: Intuit, Inc.
• Original Assignee: Intuit, Inc.
• Inventors: Podgorny, Igor A., Indyk, Benjamin, Goodyear, Todd Frey
• Primary Examiner(s): Lu, Kuen S
• Application Number:
  US15/296,297
• Publication Number:
  US 20180108093A1
• Time in Patent Office: 1,386 Days
• Field of Search: 707767
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 40/123 Tax preparation or submission

Abstract

Disclosed methods and systems provide domain-specific type ahead suggestions for search query terms with a customer self-service system for a tax return preparation system, according to one embodiment. Type ahead suggestions include suggestions for completing a single search query term and/or suggestions for completing a search query having multiple search query terms. The customer self-service system receives one or more search query terms in a search text box, searches for potential search queries that are likely to complete the one or more search query terms, and provides a selected one of the potential search queries in the search text box as a type ahead suggestion, adjacent to the received one or more search query terms, according to one embodiment. The customer self-service system selects one of the potential search queries based on the received search query terms, the user'"'"'s profile, and/or the user'"'"'s tax data, according to one embodiment.

Claims

1. A computing system implemented method for providing domain-specific and dynamic type ahead suggestions for search query terms with a customer self-service system for a tax return preparation system, comprising:

providing, with one or more computing systems, a customer self-service system associated with a tax return preparation system;

storing, with the customer self-service system, potential search query data representing a plurality of potential search queries, in memory allocated for use by the customer self-service system;

maintaining user tax data representing financial information and personal information for users of the tax return preparation system;

maintaining user profile data representing user profiles for users of the tax return preparation system;

providing search algorithm data representing a search algorithm that identifies some of the plurality of potential search queries that are topically relevant to one or more search query terms received from a user;

providing search text box data representing a search text box, to enable receipt of the one or more search query terms;

receiving the one or more search query terms in the search text box as a portion of a search query;

applying search query data representing the one or more search query terms to the search algorithm to select one of the plurality of potential search queries, at least partially based on a topic relevance between the one or more search query terms and the one of the plurality of potential search queries and at least partially based on one or more of the user profile data and the user tax data;

updating user experience display data to include the one of the plurality of potential search queries as a type ahead suggestion for completing a search query for the user, the user experience display data representing a user experience display that includes the search text box; and

transmitting the user experience display data to a user computing system, to render the type ahead suggestion adjacent to the one or more search query terms received from the user in the search text box, to assist a user in articulating the search query, to decrease a quantity of time consumed by the user in entering the search query, and to decrease a quantity of time consumed by the user in finding an answer to the search query.

2. The computing system implemented method of claim 1, further comprising:

receiving subsequent ones of the one or more search query terms in the search text box, wherein the type ahead suggestion is dynamically updated and displayed as each of the subsequent ones of the one or more search query terms are received.

3. The computing system implemented method of claim 1, wherein the customer self-service system is part of the tax return preparation system.

4. The computing system implemented method of claim 1, wherein receiving the one or more search query terms includes:

receiving the one or more search query terms with the tax return preparation system and receiving the one or more search query terms by the customer self-service system from the tax return preparation system.

5. The computing system implemented method of claim 1, further comprising:

determining topic relevance scores for each of the plurality of potential search queries, at least partially based on the one or more search query terms;

sorting the topic relevance scores; and

selecting the one of the plurality of potential search queries as the type ahead suggestion, at least partially based on the topic relevance scores.

6. The computing system implemented method of claim 1, wherein the search algorithm includes a probabilistic topic model.

7. The computing system implemented method of claim 6, wherein the probabilistic topic model determines a topic relevance between the one of the potential search queries and the one or more search query terms, by identifying topics that are associated with the one of the potential search queries and by identifying topics that are associated with the one or more search query terms.

8. The computing system implemented method of claim 6, wherein the probabilistic topic model includes one or more of a Latent Dirichlet Allocation algorithm, a Latent Semantic Indexing (“

LSI”

) algorithm, a query clustering algorithm, and a query de-duplication algorithm.

9. The computing system implemented method of claim 1, wherein the search algorithm includes a predictive model.

10. The computing system implemented method of claim 9, wherein the predictive model is trained using a training operation that is selected from a group of predictive model training operations, consisting of:

regression;

logistic regression;

decision trees;

artificial neural networks;

support vector machines;

linear regression;

nearest neighbor methods;

distance based methods;

naive Bayes;

linear discriminant analysis; and

k-nearest neighbor algorithm.

11. The computing system implemented method of claim 1, wherein the customer self-service system provides answers to the search query using customer self-service system content that is selected from a group of customer self-service system content, consisting of:

crowd-sourced customer support content;

service provider content;

definitions content, wherein the definitions content includes explanations of one or more acronyms and definitions of tax-specific terms;

suggested potential search queries; and

user tax data for the user.

12. A computing system implemented method for providing domain-specific and dynamic type ahead suggestions for search query terms with a customer self-service system for a tax return preparation system, comprising:

providing, with one or more computing systems, a customer self-service system associated with a tax return preparation system;

storing, with the customer self-service system, potential search query data representing a plurality of potential search queries, in memory allocated for use by the customer self-service system;

receiving one or more search query terms in a search text box from a user as a portion of a search query;

storing topic term probability scores for a plurality of terms for each of the plurality of potential search queries;

determining topic relevance scores for the plurality of potential search queries by using the one of more search query terms from the search text box;

sorting the topic relevance scores to rank the plurality of potential search queries on relevance to the one or more potential search queries;

selecting one of the plurality of potential search queries with a highest rank that is indicated by a highest one of the topic relevance scores;

updating user experience display data to include the one of the plurality of potential search queries as a type ahead suggestion for completing a search query for the user, the user experience display data representing a user experience display that includes the search text box; and

transmitting the user experience display data to a user computing system, to render the type ahead suggestion adjacent to the one or more search query terms received from the user in the search text box, to assist a user in articulating the search query, to decrease a quantity of time consumed by the user in entering the search query, and to decrease a quantity of time consumed by the user in finding an answer to the search query that is partially represented by the one or more search query terms.

13. The computing system implemented method of claim 12, further comprising:

maintaining user profile data representing user profiles for users of the tax return preparation system;

storing user profile characteristics probability scores for the plurality of potential search queries; and

determining topic relevance scores for the plurality of potential search queries, using user profile characteristics probability scores that match user profile characteristics of a user profile of the user.

14. The computing system implemented method of claim 12, further comprising:

maintaining user tax data representing financial information and personal information for users of the tax return preparation system;

storing user tax data characteristics probability scores for the plurality of potential search queries; and

determining topic relevance scores for the plurality of potential search queries, using user tax data characteristics probability scores that match user profile characteristics of a user profile of the user.

15. The computing system implemented method of claim 12, wherein determining topic relevance scores for the plurality of potential search queries by using the one of more search query terms from the search text box, includes applying the one or more search query terms to a Latent Dirichlet Allocation algorithm.

16. The computing system implemented method of claim 12, wherein the customer self-service system is part of the tax return preparation system.

17. The computing system implemented method of claim 12, wherein receiving the one or more search query terms includes:

receiving the one or more search query terms with the tax return preparation system and receiving the one or more search query terms by the customer self-service system from the tax return preparation system.

18. A system that provides domain-specific and dynamic type ahead suggestions for search query terms with a customer self-service system for a tax return preparation system, comprising:

one or more processors; and

memory having instructions which, if executed by the one or more processors, cause the one or more processors to perform a process for providing domain-specific and dynamic type ahead suggestions for search query terms with a customer self-service system for a tax return preparation system, the process comprising;

providing a customer self-service system associated with a tax return preparation system;

storing, with the customer self-service system, potential search query data representing a plurality of potential search queries, in memory allocated for use by the customer self-service system;

maintaining user tax data representing financial information and personal information for users of the tax return preparation system;

maintaining user profile data representing user profiles for users of the tax return preparation system;

providing search algorithm data representing a search algorithm that identifies some of the plurality of potential search queries that are topically relevant to one or more search query terms received from a user;

providing search text box data representing a search text box, to enable receipt of the one or more search query terms;

receiving the one or more search query terms in the search text box as a portion of a search query;

applying search query data representing the one or more search query terms to the search algorithm to select one of the plurality of potential search queries, at least partially based on a topic relevance between the one or more search query terms and the one of the plurality of potential search queries and at least partially based on one or more of the user profile data and the user tax data;

updating user experience display data to include the one of the plurality of potential search queries as a type ahead suggestion for completing a search query for the user, the user experience display data representing a user experience display that includes the search text box; and

transmitting the user experience display data to the user computing system, to render the type ahead suggestion adjacent to the one or more search query terms received from the user in the search text box, to assist a user in articulating the search query, to decrease a quantity of time consumed by the user in entering the search query, and to decrease a quantity of time consumed by the user in finding an answer to the search query.

19. The system of claim 18, further comprising:

determining topic relevance scores for each of the plurality of potential search queries, at least partially based on the one or more search query terms;

sorting the topic relevance scores; and

selecting the one of the plurality of potential search queries as the type ahead suggestion, at least partially based on the topic relevance scores.

20. The system of claim 18, wherein the search algorithm includes a probabilistic topic model.

21. The system of claim 20, wherein the probabilistic topic model determines a topic relevance between the one of the potential search queries and the one or more search query terms, by identifying topics that are associated with the one of the potential search queries and by identifying topics that are associated with the one or more search query terms.

22. The system of claim 20, wherein the probabilistic topic model includes one or more of a Latent Dirichlet Allocation algorithm, a Latent Semantic Indexing (“

LSI”

) algorithm, a query clustering algorithm, and a query de-duplication algorithm.

23. The system of claim 18, wherein the search algorithm includes a predictive model.