Input interpretation based upon a context

• US 10,572,591 B2
• Filed: 11/18/2016
• Issued: 02/25/2020
• Est. Priority Date: 11/18/2016
• Status: Active Grant

• Current Assignee: Lenovo PC International Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Inventors: Dubs, Justin Tyler, Kapinos, Robert James, VanBlon, Russell Speight, Ramirez Flores, Axel
• Primary Examiner(s): Sharma, Neeraj
• Application Number:
  US15/355,682
• Publication Number:
  US 20180143971A1
• Time in Patent Office: 1,194 Days
• Field of Search: None
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

One embodiment provides a method, including: receiving, at an information handling device, an indication to perform an action associated with an element in an application; adjusting, using a processor, a confidence score of the element based upon at least one input context; responsive to the confidence score being higher than a predetermined threshold, performing the action; and responsive to the confidence score being lower than the predetermined threshold, performing a second action. Other aspects are described and claimed.

Claims

1. A method, comprising:

receiving, at an information handling device, an indication to perform an action on a dataset comprising a textual communication within a communication application, wherein the action controls a delivery of the textual communication, wherein the receiving an indication comprises receiving input at an element in the communication application, wherein the element comprises a control feature of the communication application and wherein the action corresponds to the control feature;

adjusting, using a processor, a confidence score of the action corresponding to the element based upon at least one input context, wherein the confidence score indicates a confidence that the action is to be performed by the communication application;

responsive to the confidence score being higher than a predetermined threshold, performing the action on the dataset, wherein the predetermined threshold is correlated to the communication application, wherein the predetermined threshold of the element is dynamically determined based upon the location of the element in the application; and

responsive to the confidence score being lower than the predetermined threshold, performing a second action with respect to the dataset, wherein the second action comprises rejecting the action unless additional user input is received to perform the action and suggesting a corrective action to the dataset.

2. The method of claim 1, wherein the action is at least one action selected from the group consisting of send, close, search, and delete.

3. The method of claim 1, wherein the element is a control feature selected from the group consisting of a send button, an exit button, a search button, and a delete button.

4. The method of claim 1, wherein the at least one context comprises at least one of an application type, an input type, an input location, and dataset grammar.

5. The method of claim 4, wherein the application type comprises at least one of a text message, an email, and a social media post.

6. The method of claim 5, wherein the predetermined threshold of the element is adjusted based on the application type.

7. The method of claim 1, wherein the confidence score of the element is decreased based upon the distance between a center of the input location and a center of the element.

8. The method of claim 4, wherein the confidence score of the element is decreased based upon the presence of grammatical errors.

9. The method of claim 1, wherein the second action comprises at least one action selected from the group consisting of rejecting the action, providing a notification to a user that the action was rejected, querying the user whether the action should be performed, and providing a suggestion to a user.

10. An information handling device, comprising:

a processor;

a memory device that stores instructions executable by the processor to;

receive an indication to perform an action on a dataset comprising a textual communication within a communication application, wherein the action controls a delivery of the textual communication, wherein the receiving an indication comprises receiving input at an element in the communication application, wherein the element comprises a control feature of the communication application and wherein the action corresponds to the control feature;

adjust a confidence score of the action corresponding to the element based upon at least one input context, wherein the confidence score indicates a confidence that the action is to be performed by the communication application;

responsive to the confidence score being higher than a predetermined threshold, perform the action on the dataset, wherein the predetermined threshold is correlated to the communication application, wherein the predetermined threshold of the element is dynamically determined based upon the location of the element in the application; and

responsive to the confidence score being lower than the predetermined threshold, perform a second action with respect to the dataset, wherein the second action comprises rejecting the action unless additional user input is received to perform the action and suggesting a corrective action to the dataset.

11. The information handling device of claim 10, wherein the action is at least one action selected from the group consisting of send, close, search, and delete.

12. The information handling device of claim 10, wherein the element is a control feature selected from the group consisting of a send button, an exit button, a search button, and a delete button.

13. The information handling device of claim 10, wherein the at least one context comprises at least one of an application type, an input type, an input location, and dataset grammar.

14. The information handling device of claim 13, wherein the application type comprises at least one of a text message, an email, and a social media post.

15. The information handling device of claim 14, wherein the predetermined threshold of the element is adjusted based on the application type.

16. The information handling device of claim 10, wherein the confidence score of the element is decreased based upon the distance between a center of the input location and a center of the element.

17. The information handling device of claim 13, wherein the confidence score of the element is decreased based upon the presence of grammatical errors.

18. A product, comprising:

a non-signal storage device that stores code, the code being executable by a processor and comprising;

code that receives an indication to perform an action on a dataset comprising a textual communication within a communication application, wherein the action controls a delivery of the textual communication, wherein the receiving an indication comprises receiving input at an element in the communication application, wherein the element comprises a control feature of the communication application and wherein the action corresponds to the control feature;

code that adjusts a confidence score of the action corresponding to the element based upon at least one input context, wherein the confidence score indicates a confidence that the action is to be performed by the communication application;

responsive to the confidence score being higher than a predetermined threshold, code that performs the action on the dataset, wherein the predetermined threshold is correlated to the communication application, wherein the predetermined threshold of the element is dynamically determined based upon the location of the element in the application; and

responsive to the confidence score being lower than the predetermined threshold, code that performs a second action with respect to the dataset, wherein the second action comprises rejecting the action unless additional user input is received to perform the action and suggesting a corrective action to the dataset.