Digital employee experience improvement based on de-identified productivity data signals

1 . One or more non-transitory computer-readable storage media storing one or more sequences of instructions which, when executed using one or more processors of a computer, cause the one or more processors to execute:

monitoring, using one or more extractor application programming interfaces (APIs), a plurality of streams of digital data associated with user interactions with one or more different applications or platforms of the computer, each of the plurality of streams including data representing one or more events or activities associated with the user interactions;

extracting contents and contexts from the plurality of streams using the one or more extractor APIs;

determining one or more workflows represented in the user interactions, the one or more workflows including the extracted contents and contexts, the workflows indicating the user interactions with the computer during a time series comprising a plurality of timestamps associated with times at which the user interactions with the computer occurred;

storing the one or more workflows at a user computer;

determining, from the one or more workflows, one or more chunks of the one or more workflows, based on the plurality of timestamps, each chunk corresponding to a subpart of one of the one or more workflows and corresponding to a set of the plurality of timestamps associated with the subpart, each chunk including the content and contexts of the one or more workflows associated with the set of the plurality of timestamps;

evaluating the one or more chunks to infer, by the computer, one or more inferred actions using the content and contexts of the one or more workflows associated with the set of the plurality of timestamps; and

automating one or more subsequent workflows associated with a user based on the one or more inferred actions.

2 . The one or more non-transitory computer-readable storage media of claim 1 , wherein the user interactions with the computer include user engagement and attendance associated with calendar events, meetings, email conversations, reviewing, presentations, uniform resource locators (URL) links, conferences, video streams, studying materials, blogs, work applications, non-work applications, active interactions, inactive interactions, or application programs.

3 . The one or more non-transitory computer-readable storage media of claim 1 , wherein the one or more extractor APIs comprise one or more Ally-tree-based extractors, OAuth-based extractors, and extractors based on optical character recognition (OCR), or extractors based on automatic speech recognition (ASR).

4 . The one or more non-transitory computer-readable storage media of claim 1 , further comprising sequences of instructions which, when executed using the one or more processors of a computer, cause the one or more processors to execute:

receiving one or more queries specifying a particular chunk;

retrieving content and context associated with the particular chunk; and

evaluating the particular chunk using the retrieved content and context associated with the particular chunk, the evaluating creating one or more inferred actions associated with the particular chunk.

5 . The one or more non-transitory computer-readable storage media of claim 1 , further comprising sequences of instructions which, when executed using the one or more processors of a computer, cause the one or more processors to execute determining an order by which the one or more inferred actions are displayed on a display device of the computer.

6 . The one or more non-transitory computer-readable storage media of claim 5 , further comprising sequences of instructions which, when executed using the one or more processors of a computer, cause the one or more processors to execute displaying the inferred actions on a display device of the computer according to the determined order.

7 . The one or more non-transitory computer-readable storage media of claim 1 , wherein the one or more inferred actions include a coaching instruction of message.

8 . The one or more non-transitory computer-readable storage media of claim 1 , further comprising sequences of instructions which, when executed using the one or more processors of a computer, cause the one or more processors to execute the automating of the one or more subsequent workflows by automatically triggering one or more applications coupled over accessibility APIs based on the one or more inferred actions.

9 . The one or more non-transitory computer-readable storage media of claim 1 , further comprising sequences of instructions which, when executed using the one or more processors of a computer, cause the one or more processors to execute predicting one or more new workflows based on the one or more of the inferred actions.

10 . The one or more non-transitory computer-readable storage media of claim 1 , further comprising sequences of instructions which, when executed using the one or more processors of a computer, cause the one or more processors to execute the automating of the one or more subsequent workflows associated with the user based on the one or more inferred actions by automatic management of the one or more subsequent workflows such that an application of the one or more subsequent workflows interacted with by the user provides functionality in accordance with the one or more inferred actions.

11 . A computer-implemented method, executed using a computer comprising one or more processors and one or more non-transitory computer-readable storage media storing one or more sequences of instructions, the method comprising:

monitoring, using one or more extractor application programming interfaces (APIs), a plurality of streams of digital data associated with user interactions with one or more different applications or platforms of the computer, each of the plurality of streams including data representing one or more events or activities associated with the user interactions;

extracting contents and contexts from the plurality of streams using the one or more extractor APIs;

determining one or more workflows represented in the user interactions, the one or more workflows including the extracted contents and contexts, the workflows indicating the user interactions with the computer during a time series comprising a plurality of timestamps associated with times at which the user interactions with the computer occurred;

storing the one or more workflows at a user computer;

determining one or more chunks of the one or more workflows, each chunk corresponding to a subpart of one of the one or more workflows and corresponding to a set of the plurality of timestamps associated with the subpart, each chunk including the content and contexts of the one or more workflows associated with the set of the plurality of timestamps;

evaluating the one or more chunks, the evaluating creating one or more inferred actions using the content and contexts of the one or more workflows associated with the set of the plurality of timestamps; and

automating one or more subsequent workflows associated with a user based on the one or more inferred actions.

12 . The computer-implemented method of claim 11 , wherein the user interactions with the computer include user engagement and attendance associated with calendar events, meetings, email conversations, reviewing, presentations, uniform resource locators (URL) links, conferences, video streams, studying materials, blogs, work applications, non-work applications, active interactions, inactive interactions, or application programs.

13 . The computer-implemented method of claim 11 , wherein the one or more extractor APIs comprise one or more Ally-tree-based extractors, OAuth-based extractors, and extractors based on optical character recognition (OCR), or extractors based on automatic speech recognition (ASR).

14 . The computer-implemented method of claim 11 , further comprising:

receiving one or more queries specifying a particular chunk;

retrieving content and context associated with the particular chunk; and

evaluating the particular chunk using the retrieved content and context associated with the particular chunk, the evaluating creating one or more inferred actions associated with the particular chunk.

15 . The computer-implemented method of claim 11 , further comprising determining an order by which the one or more inferred actions are displayed on a display device of the computer.

16 . The computer-implemented method of claim 15 , further comprising displaying the inferred actions on a display device of the computer according to the determined order.

17 . The computer-implemented method of claim 11 , wherein the one or more inferred actions include a coaching instruction of message.

18 . The computer-implemented method of claim 11 , wherein the automating of the one or more subsequent workflows includes automatically triggering one or more applications coupled over accessibility APIs based on the one or more inferred actions.

19 . The computer-implemented method of claim 11 , further comprising predicting one or more new workflows based on the one or more of the inferred actions.

20 . The computer-implemented method of claim 11 , wherein the automating of the one or more subsequent workflows associated with the user based on the one or more inferred actions includes automatic management of the one or more subsequent workflows such that an application of the one or more subsequent workflows interacted with by the user provides functionality in accordance with the one or more inferred actions.