System and method for field value recommendations based on confidence levels in analyzed dataset

Patent metadata

Field	Value
Publication number	US-11301766-B2
Application number	US-202017247764-A
Country	US
Kind code	B2
Filing date	Dec 22, 2020
Priority date	Sep 24, 2018
Publication date	Apr 12, 2022
Grant date	Apr 12, 2022

Abstract

A method of training a predictive model to predict a likely field value for one or more user selected fields within an application. The method comprises providing a user interface for user selection of the one or more user selected fields within the application; analyzing a pre-existing, user provided data set of objects; training, based on the analysis, the predictive model; determining, for each user selected field based on the analysis, a confidence function for the predictive model that identifies the percentage of cases predicted correctly at different applied confidence levels, the percentage of cases predicted incorrectly at different applied confidence levels, and the percentage of cases in which the prediction model could not provide a prediction at different applied confidence levels; and providing a user interface for user review of the confidence functions for user selection of confidence threshold levels to be used with the predictive model.

First claim

What is claimed is:

1. A system for providing a predicted field value for one or more user selected fields in a form generated by an application, the system comprising a controller configured to:
analyze an object received by the application to identify one or more fields of a form the application is configured to generate;
predict using a predictive model a likely field value for at least one of the one or more fields and a confidence level for at least one of the one or more likely field values, the confidence level having been derived from a confidence function for at least one of the one or more fields, wherein:
a user provided data set of objects has been analyzed for relationships between the one or more user selected fields and content in the objects in the data set, and
the predictive model has been trained using machine learning techniques to predict the confidence function and the likely field value for the one or more fields when the application receives a new object based on the relationships between the one or more user selected fields and the content in the objects in the data set; and

provide to the application the predicted field value for at least one predicted field and the predicted confidence level;
wherein the application displays the form in a user interface with the predicted field value for the at least one predicted field and the predicted confidence level for the at least one predicted field value.

2. The system of claim 1 , wherein the application provides user-selectable field value choices for the fields and wherein the user-selectable field value choices are selected via a picklist, lookup or checkbox.

3. The system of claim 1 , further configured to provide, for user selection via a first user interface, an option for the predictive model to identify a predicted field value as a best recommendation.

4. The system of claim 3 , wherein a confidence threshold level is used to determine the best recommendation, wherein predicted field values determined by the predictive model that have an associated confidence level that is below the confidence threshold level will not be recommended as a best recommendation and predicted field values determined by the predictive model that have an associated confidence level that is equal to or above the confidence threshold level will be recommended by the predictive model as a best recommendation via a visual indication.

5. The system of claim 3 , further configured to provide an option, for user selection via the first user interface, for the predictive model to automatically apply the best recommendation as a field value without user confirmation of the application of the best recommendation as a field value.

6. The system of claim 1 , further configured to recommend a confidence threshold level.

7. The system of claim 1 , further configured to provide an option, via a first user interface, to activate the predictive model for use with the application.

8. A method for providing a predicted field value for one or more user selected fields in a form generated by an application, the method comprising:
analyzing an object received by the application to identify one or more fields of a form the application is configured to generate;
predicting using a predictive model a likely field value for at least one of the one or more fields and a confidence level for at least one of the one or more likely field values, the confidence level having been derived from a confidence function for at least one of the one or more fields, wherein:
a user provided data set of objects has been analyzed for relationships between the one or more user selected fields and content in the objects in the data set, and
the predictive model has been trained using machine learning techniques to predict the confidence function and the likely field value for the one or more fields when the application receives a new object based on the relationships between the one or more user selected fields and the content in the objects in the data set;

providing to the application the predicted field value for at least one predicted field and the predicted confidence level; and
displaying, by the application, the form in a user interface with the predicted field value for the at least one predicted field and the predicted confidence level for the at least one predicted field value.

9. The method of claim 8 , further comprising providing, for user selection via a first user interface, an option for the predictive model to identify a predicted field value as a best recommendation.

10. The method of claim 9 , further comprising applying a confidence threshold level to determine the best recommendation, wherein predicted field values determined by the predictive model that have an associated confidence level that is below the confidence threshold level will not be recommended as a best recommendation and predicted field values determined by the predictive model that have an associated confidence level that is equal to or above the confidence threshold level will be recommended by the predictive model as a best recommendation via a visual indication.

11. The method of claim 9 , further comprising providing an option, for user selection via the first user interface, for the predictive model to automatically apply the best recommendation as a field value without user confirmation of the application of the best recommendation as a field value.

12. The method of claim 8 , further comprising automatically recommending a confidence threshold level.

13. The method of claim 8 , further comprising providing an option, via a first user interface, to activate the predictive model for use with the application.

14. The method of claim 8 , wherein the application provides user-selectable field value choices for the fields and wherein the user-selectable field value choices are selected via a picklist, lookup or checkbox.

15. Non-transitory computer readable media comprising programming instructions configurable to cause a processor to perform a method for providing a predicted field value for one or more user selected fields in a form generated by an application, the method comprising:
analyzing an object received by the application to identify one or more fields of a form the application is configured to generate;
predicting using a predictive model a likely field value for at least one of the one or more fields and a confidence level for at least one of the one or more likely field values, the confidence level having been derived from a confidence function for at least one of the one or more fields, wherein:
a user provided data set of objects has been analyzed for relationships between the one or more user selected fields and content in the objects in the data set, and
the predictive model has been trained using machine learning techniques to predict the confidence function and the likely field value for the one or more fields when the application receives a new object based on the relationships between the one or more user selected fields and the content in the objects in the data set; and

providing the predicted field value for at least one predicted field and a predicted confidence level derived from the confidence function for at least one predicted field value to the application for display, by the application, in a user interface when the form is displayed.

16. The non-transitory computer readable media of claim 15 , wherein the method further comprises providing, for user selection via a first user interface, an option for the predictive model to identify a predicted field value as

Assignees

• Salesforce Com Inc

Inventors

• Muramoto Kristen Noriko
• Chang Son Thanh
• Tussoit Clement Jacques Antoine
• Hoang Melissa
• Malla Chaitanya
• Kjellberg Orjan N
• Jimenez Carlos Enrique Mogollan
• Hu George

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F9/451 Primary

  Execution arrangements for user interfaces · CPC title

• G06N99/00

  Subject matter not provided for in other groups of this subclass · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• G06N5/048 Primary

  Fuzzy inferencing · CPC title