System and method for single domain and multi-domain decision aid for product on the web

• US 9,588,580 B2
• Filed: 10/01/2012
• Issued: 03/07/2017
• Est. Priority Date: 09/30/2011
• Status: Active Grant

• Current Assignee: DeJoto Technologies, LLC
• Original Assignee: DeJoto Technologies, LLC
• Inventors: Hall, Debra J., Lombardo, Anthony G.
• Primary Examiner(s): Chang, Li-Wu
• Application Number:
  US13/632,811
• Publication Number:
  US 20140096035A1
• Time in Patent Office: 1,618 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 3/01 Input arrangements or combined input and output arrangements for interaction between user and computer G06F3/16 takes precedence
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A system and method for problem solving in multiple domains on the web is provided. Two facets of preference are applied regardless of domain: first, criteria selected by the user which indicates which elements relate to the user, and second, level of importance to the user. For each decision aid that the user saves to his/her member account, a series of methods applied thereto assist the user in making decisions through intelligent agent expertise, as well as through related eCommerce, social networking, guided content search and delivery of context-rich content. Relevancy of results is also calculated. Depending on characteristics inherent in a particular domain, one of two primary methods is employed. The Multi-Product method uses ontology and a neural network engine to reveal the subset of relevant results based on any combination of user inputs, implicitly and explicitly derived. The Single-Product method maps inputs to results using sub-category analysis of fit and then applies user-centric filters and discounting rules to return meaningful coaching and relevancy of results.

Claims

1. A system for aiding a user in making decisions with respect to products and services listed on the Internet comprising:

a. a remote access device configured to permit the user to input data and review results;

b. a server in communication with the remote access device and the Internet, said server programmed to;

i) capture user preferences input through the remote access device, the user preferences comprising level of importance designations for a plurality of criteria within a plurality of categories for a single-product domain, wherein each category is classified as a want or a need, the level of importance designations being selectable by the user to designate each of the criteria in a manner that provides binary certainty, the binary certainty having a first test being whether each of the criteria is not important or has importance, and having a second test applicable to any criteria that has importance being whether each of the criteria is less important or more important;

ii) calculate an overall stated importance for each category based on the level of importance designations for each of the criteria within the respective category;

iii) return a set of single-product domain results, via a neural network engine, in an order determined by performing steps comprising;

a) designating a degree-of-fit for a plurality of provider offerings of the single-product domain, the degree of fit being determined based on pre-determined but non-static fit percentage thresholds, and the degree of fit designation indicates whether each provider is most relevant, relevant, or less relevant;

b) devaluing the degree-of-fit for any provider offering for which the percentage calculation for a category classified as a need is below a pre-determined need percentage threshold and the overall stated importance designation indicates high importance, such that a provider offering designated a Most Relevant status prior to devaluation is demoted to the status of Relevant, and a provider that designated as a Relevant status prior to devaluation is demoted the status of Of Interest;

iv) return a set of multi-product domain results, via the neural network engine, in an order determined by performing steps comprising;

a) defining the criteria selected by the user under the first test of the binary certainty as being user-selected criteria;

b) mapping the user-selected criteria to a superset of products in an ontological schema of the system to produce a subset of potential relevant products, wherein the ontological schema is structured such that each criteria and each product are classified by a set of identifiers, and where there are instances of user-selected criteria having a set of identifiers that mathematically ensures a subset of the set of products is generated by the system;

v) display the returned sets of provider results for the single-product domain and the multi-product domain on the remote access device.

3. The system of claim 1, wherein the set of identifiers for each criteria selected by the user includes one intention, the intention being synonymous with one of the plurality of categories classified as a want or a need, and wherein the intention is a non-taxonomic construct within the ontology.

4. The system of claim 1, wherein:

the set of identifiers for each product comprises constructs that include at least one super class, at least one class, at least one subclass, at least one intention, at least one attribute, and at least one sub-attribute; and

the set of identifiers for each criteria selected by the user comprises constructs that include up to one super class, up to one class, up to one subclass, exactly one intention, exactly one attribute, and up to one sub-attribute.

5. The system of claim 1, wherein the ontological schema comprises a set of schematic relations (R) having constructs that are constant across domains such that a plurality of domains are satisfied by enforcing ontological mapping of criteria and products via a set of identifiers, and mapping requirements for each identifier, not by modifying the schematic relations (R) per domain (D).

6. The system of claim 5, wherein the constructs comprise:

(i) super class, (ii) class, which is sub-ordinate to super class, (iii) subclass, which is sub-ordinate to class, (iv) intention, which is synonymous with the plurality of categories classified as a want or a need, and which is a non-taxonomic construct, (v) attribute, and (vi) sub-attribute, which is sub-ordinate to attribute.

2. A method for aiding a user in making decisions with respect to products and services listed on the Internet comprising:

a. providing a remote access device configured to permit the user to input data and review results and a server in communication with the remote access device and the Internet;

b. capturing user preferences on the server, the user preferences being input through the remote access device, the user preferences comprising level of importance designations for a plurality of criteria within a plurality of categories for a single-product domain, wherein each category is classified as a want or a need, the level of importance designations being selectable by the user to designate each of the criteria in a manner that provides binary certainty, the binary certainty having a first test being whether each of the criteria is not important or has importance, and having a second test applicable to any criteria that has importance being whether each of the criteria is less important or more important;

c. calculating on the server an overall stated importance for each category based on the level of importance designations for each of the criteria within the respective category;

d. returning a set of single-product domain results, via a neural network engine, in an order determined by performing steps comprising;

i) designating a degree-of-fit for a plurality of provider offerings of the single-product domain, the degree of fit being determined based on pre-determined determined but non-static fit percentage thresholds, and the degree of fit designation indicates whether each provider is most relevant, relevant, or less relevant;

ii) devaluing the degree-of-fit for any provider offering for which the percentage calculation for a category classified as a need is below a pre-determined need percentage threshold and the overall stated importance designation indicates high importance, such that a provider offering designated a Most Relevant status prior to devaluation is demoted to the status of Relevant, and a provider that designated as a Relevant status prior to devaluation is demoted the status of Of Interest;

e. returning a set of multi-product domain results, via the neural network engine, in an order determined by performing steps comprising;

i) defining the criteria selected by the user under the first test of the binary certainty as being user-selected criteria;

ii) mapping the user-selected criteria to a superset of products in an ontological schema of the system to produce a subset of potential relevant products, wherein the ontological schema is structured such that each criteria and each product are classified by a set of identifiers, and where there are instances of user-selected criteria having a set of identifiers that mathematically ensures a subset of the set of products is generated by the system;

f. displaying the returned sets of provider results for the single-product domain and the multi-product domain on the remote access device.