Automatic task extraction and calendar entry
Automatically detected and identified tasks and calendar items from electronic communications may be populated into one or more tasks applications and calendaring applications. Text content retrieved from one or more electronic communications may be extracted and parsed for determining whether keywords or terms contained in the parsed text may lead to a classification of the text content or part of the text content as a task. Identified tasks may be automatically populated into a tasks application. Similarly, text content from such sources may be parsed for keywords and terms that may be identified as indicating calendar items, for example, meeting requests. Identified calendar items may be automatically populated into a calendar application as a calendar entry.
1. A method of automatically extracting a task item or a calendar item from an electronic communication, comprising:
receiving an electronic communication item;
processing the electronic communication item to identify text components and to identify metadata comprising the electronic communication item;
extracting a plurality of features from one or both of the text components and metadata that are usable to classify the electronic communication item as a task or calendar item;
identifying at least one of the plurality of features as being associated with a project workspace of which multiple users are members;
obtaining one or both of data and metadata contained in the project workspace;
assessing, by a machine-learning classifier application, the plurality of features against one or both of the data and metadata obtained from the project workspace;
based on the assessment, assigning a probability that the electronic communication item is a task item or a calendar item;
based on the assigned probability, generating a corresponding proposed task item or a proposed calendar item; and
displaying the proposed task item or proposed calendar item.
2. The method of claim 1 , wherein the machine-learning classifier application has been trained on pre-defined patterns of text that have been previously identified as text associated with at least one of a task item, a non-task item, a calendar item and a non-calendar item.
3. The method of claim 2 , wherein the pre-defined patterns of text are represented as feature vectors.
4. The method of claim 3 , wherein the machine-learning classifier application comprises a linear support vector application.
5. The method of claim 1 , wherein the extracted features include one or more of: a name, a date, a time, and subject line text.
6. The method of claim 1 , wherein displaying the proposed task item or proposed calendar item includes displaying a user-selectable option to accept or reject the proposed task item or proposed calendar item.
7. The method of claim 6 , the method further comprising displaying a replacement field that is user-accessible to enter a replacement task item or replacement calendar item for the proposed task item or proposed calendar item.
8. The method of claim 1 , wherein the project workspace is associated with a sender or a recipient of the electronic communication item.
9. A computing device for automatically extracting a task item or a calendar item from an electronic communication, comprising:
a processing unit; and
a memory including computer executable instructions which when executed by the processing unit causes the processing unit to:
receive an electronic communication item;
process the electronic communication item to identify text components and to identify metadata comprising the electronic communication item;
extract a plurality of features from one or both of the text components and metadata that are usable to classify the electronic communication item as a task or calendar item;
identify at least one of the plurality of features as being associated with a project workspace of which multiple users are members;
obtain one or both of data and metadata contained in the project workspace;
assess, by a machine-learning classifier application, the plurality of features against one or both of the data and metadata obtained from the project workspace;
based on the assessment, assign a probability that the electronic communication item is a task item or a calendar item;
based on the assigned probability, generate a corresponding proposed task item or proposed calendar item; and
display the proposed task item or proposed calendar item.
10. The computing device of claim 9 , wherein the machine-learning classifier application has been trained on pre-defined patterns of text that have been previously identified as text associated with at least one of a task item, a non-task item, a calendar item and a non-calendar item.
11. The computing device of claim 10 , wherein the pre-defined patterns of text are represented as feature vectors.
12. The computing device of claim 11 , wherein the machine-learning classifier application comprises a linear support vector application.
13. The computing device of claim 9 , wherein the extracted features include one or more of: a name, a date, a time, and subject line text.
14. The computing device of claim 9 , wherein displaying the proposed task item or proposed calendar item includes displaying a user-selectable option to accept or reject the proposed task item or proposed calendar item.
15. The computing device of claim 14 , wherein the processing unit is further caused to display a replacement field that is user-accessible to enter a replacement task item or replacement calendar item for the proposed task item or proposed calendar item.
16. The computing device of claim 9 , wherein the project workspace is associated with a sender or a recipient of the electronic communication item.
17. A computer readable storage device containing computer executable instructions which when executed by a computer perform a method of automatically extracting a task item or a calendar item from an electronic communication, comprising:
receiving an electronic communication item;
processing the electronic communication item to identify text components and to identify metadata comprising the electronic communication item;
extracting a plurality of features from one or both of the text components and meta data that are usable to classify the electronic communication item as a task or calendar item;
identifying at least one of the plurality of features as being associated with a project workspace of which multiple users are members;
obtaining one or both of data and metadata contained in the project workspace;
assessing, by a machine-learning classifier application, the plurality of features against one or both of the data and metadata obtained from the project workspace;
based on the assessment, assigning a probability that the electronic communication item is a task item or a calendar item;
based on the assigned probability, generating a corresponding proposed task item or proposed calendar item; and
displaying the proposed task item or the proposed calendar item.
18. The computer readable storage device of claim 17 , wherein the machine-learning classifier application has been trained on pre-defined patterns of text that have been previously identified as text associated with at least one of a task item, a non-task item, a calendar item and a non-calendar item.
19. The computer readable storage device of claim 18 , wherein the pre-defined patterns of text are represented as feature vectors.
20. The computer readable storage device of claim 17 , wherein the project workspace is associated with a sender or a recipient of the electronic communication item.