Intelligent performance-based product recommendation system

• US 7,809,601 B2
• Filed: 10/17/2001
• Issued: 10/05/2010
• Est. Priority Date: 10/18/2000
• Status: Active Grant

• Current Assignee: Johnson & Johnson Consumer Inc. (Johnson & Johnson)
• Original Assignee: Johnson & Johnson Consumer Companies Incorporated (Johnson & Johnson)
• Inventors: Bloom, Jeffrey Adam, Shaya, Steven A., Singarayar, John Anthony, Matheson, Neal, Kollias, Nikiforos
• Primary Examiner(s): THEIN, MARIA TERESA T
• Application Number:
  US09/981,516
• Publication Number:
  US 20020161664A1
• Time in Patent Office: 3,275 Days
• Field of Search: 700/233, 705/10, 705/26, 705/27, 705/28, 705/29, 705/7, 705/8, 705/9, 707/5
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0641 Shopping interfaces

Abstract

Systems and methods of utilizing communications networks and multivariate analysis to predict or recommend optimal products from a predefined population of commercially available products are disclosed. The recommendations are based on intelligence contained in processing elements and subjective and/or objective product information received from consumers or input to the systems as part of their initial setup. The output of the systems comprise sets of products that they predict the consumer will prefer and/or perform well for the problem or concern identified by the consumer. The performance and preference predictions are a function of consumer problems and product responsiveness patterns. Objective product information is generally obtained with diagnostic instruments. Data measured with the diagnostic instruments may be communicated to the data processing portions of the invention via the Internet. The outputs of the data processing portion of the system may be presented to consumers via the Internet as well.

Claims

1. A method of formulating individualized product recommendations, comprising:

receiving a first set of data from a consumer regarding a target substrate that includes a requirement to be addressed by a product; and

generating a set of individualized product recommendations for the consumer from a plurality of products within a product category with an assistance of one or more computing devices, the generating comprising;

feeding the first set of data as inputs into an intelligent performance-based product recommendation engine;

classifying the consumer, based on the inputs, in a population of consumers who previously used a product in the product category in connection with a substantially similar substrate and who are substantially similar to the consumer;

determining, based on the inputs and the classification of the consumer, a likelihood that the products in the product category will address the requirement with a predefined level of success when used in connection with the target substrate; and

selecting a set of products from the product category having a predefined likelihood of successfully addressing the requirement, the selected set of products comprising the set of individualized product recommendations.

2. The method of claim 1 wherein the receiving a first set of data step comprises receiving a concern about the substrate.

3. The method of claim 2 further comprising receiving a severity of the concern.

4. The method of claim 2 further comprising receiving an importance of the concern.

5. The method of claim 1 further comprising receiving a second set of data from the consumer, the second set of data comprising historical product data, and wherein the first and second sets of data comprise the inputs into the product recommendation engine.

6. The method of claim 5 wherein the receiving the second set of historical product data step comprises receiving performance data for products used by the consumer in the past.

7. The method of claim 5 wherein the receiving the second set of historical product data step comprises receiving preference data for products used by the consumer in the past.

8. The method of claim 1 further comprising receiving a third set of data from the consumer, the third set of data comprising personal profile information about the consumer, and wherein the first and third sets of data comprise the inputs into the product recommendation engine.

9. The method of claim 1 wherein the classifying and determining steps comprise operating on the inputs with a neural network.

10. The method of claim 1 wherein the classifying and determining steps comprise operating on the inputs with a collaborative filter.

11. The method of claim 1 wherein the classifying and determining steps comprise operating on the inputs with a content-based filter.

12. The method of claim 1 wherein the classifying and determining steps comprise operating on the inputs with a cascaded content-based filter and collaborative filter.

13. The method of claim 1 wherein the set of individualized product recommendations comprises a first list of products and a scored predicted performance utility for each listed product.

14. The method of claim 1 wherein the set of individualized product recommendations comprises a first list of top-N products and a scored predicted performance utility for each listed product.

15. The method of claim 1 wherein the set of individualized product recommendations comprises a first list of products and a scored predicted preference utility for each listed product.

16. The method of claim 1 wherein the set of individualized product recommendations comprises a first list of top-N products and a scored predicted product preference utility for each listed product.

17. The method of claim 1 wherein the set of individualized product recommendations comprises a first list of products and a purchase price for each listed product.

18. The method of claim 1 further comprising generating ancillary information from the product recommendation engine inputs.

19. The method of claim 18 wherein the ancillary information comprises information regarding effects of at least one of the products.

20. The method of claim 18 wherein the ancillary information comprises information regarding the condition of the target substrate relative to a designated population of consumers.

21. The method of claim 1 further comprising:

communicating the set of individualized product recommendations to the consumer.

22. The method of claim 21 wherein the communicating step comprises generating and delivering a web page containing the recommendations to the consumer.

23. The method of claim 1 further comprising:

receiving feedback from the consumer regarding use of a product in connection with the target substrate.

24. The method of claim 23 wherein the receiving feedback step comprises receiving feedback from the consumer regarding use of a previously recommended product.

25. The method of claim 23 wherein the receiving feedback step comprises receiving preference data regarding the product.

26. The method of claim 23 wherein the receiving feedback comprises receiving performance data regarding the product.

27. The method of claim 23 further comprising:

re-training the product recommendation engine based on the feedback.

28. The method of claim 1 wherein the receiving a first set of data from a consumer step comprises receiving a first set of data about the consumer'"'"'s skin, and the generating a set of individualized product recommendations for the consumer step comprises generating a set of individualized product recommendations from a plurality of skin-care products.

29. The method of claim 1 further comprising receiving a payment from the consumer.

30. A computer-readable medium having a program with computer-executable instructions for performing steps comprising:

receiving a first set of data from a consumer regarding a target substrate that includes a requirement to be addressed by a product; and

generating a set of individualized product recommendations for the consumer from a plurality of products within a product category by;

feeding the first set of data as inputs into an intelligent performance-based product recommendation engine;

classifying the consumer, based on the inputs, in a population of consumers who are substantially similar to the consumer and who previously used a product in the product category in connection with a substantially similar substrate;

determining, based on the inputs and the classification of the consumer, a likelihood that the products in the product category will address the requirement with a predefined level of success when used in connection with the target substrate; and

selecting a set of products from the product category having a predefined likelihood of successfully addressing the requirement, the selected set of products comprising the set of individualized product recommendations.