Metadata-based recommendations of workflows for data files
A computing platform is configured to: (i) receive, from a first client station, a data file; (ii) obtain metadata associated with the data file; (iii) determine, based on the obtained metadata, at least one recommended workflow for assignment to the data file, wherein the workflow defines a set of one or more actions that are to be taken in connection with the data file; and (iv) transmit, to a second client station, a communication identifying the at least one recommended workflow and thereby cause an indication of the at least one recommended workflow for the data file to be presented at a user interface of the second client station.
1. A computing platform comprising:
a network interface;
at least one processor;
at least one non-transitory computer-readable medium; and
program instructions stored on the at least one non-transitory computer-readable medium that are executable by the at least one processor such that the computing platform is configured to:
provide a common data environment (CDE) for electronic data files that serves as a source of truth for electronic data files associated with a construction project;
receive, from a first client station, a data file;
based on determined categories of metadata that have more influence compared to other categories with respect to determining workflows to be carried out with respect to data files, obtain, from a set of metadata associated with the data file, a subset of metadata associated with the data file;
input the obtained subset of metadata into one or more machine-learning models, wherein the one or more machine-learning models are trained based on historical data regarding workflow assignments for construction projects;
use the one or more machine-learning models to output, for each respective workflow in a universe of workflows that are available for assignment to data files, a predicted likelihood that the respective workflow is appropriate for the data file;
determine, based on the predicted likelihoods and a predefined threshold value, at least one recommended workflow for assignment to the data file, wherein each workflow of the at least one recommended workflow (i) defines a set of one or more actions that are to be taken in connection with the data file and (ii) is associated with a respective predicted likelihood that exceeds the predefined threshold value;
display, via a second client station, a graphical user interface (GUI) including a user-selectable button presented to a user to select a given recommended workflow for assignment to the data file, wherein the user-selectable button presented to the user includes an element to select an indicator that allows the user to dismiss the given recommended workflow as an option for assignment to the data file;
prior to promoting the data file to the CDE, assign a selected workflow from the at least one recommended workflow as an associated workflow for the data file;
in response to assigning the selected workflow from the at least one recommended workflow as an associated workflow for the data file, automatically initiate the selected workflow by generating a communication regarding the selected workflow and sending, to a third client station that is associated with an individual responsible for performing a first action of the selected workflow, the communication regarding the selected workflow, wherein the communication regarding the selected workflow includes information about the data file, an action required, and a due date of the action; and
after the selected workflow is completed, promote the data file to the CDE.
2. The computing platform of claim 1 , wherein the obtained subset of metadata comprises at least one of: metadata generated by the computing platform or metadata that has been received from one or more client stations.
3. The computing platform of claim 1 , wherein the obtained subset of metadata comprises metadata from a plurality of categories of metadata, wherein the plurality of categories are less than all available categories of metadata associated with the metadata currently stored for the data file.
4. The computing platform of claim 1 , further comprising program instructions stored on the at least one non-transitory computer-readable medium that are executable by the at least one processor such that the computing platform is configured to:
obtain updated metadata associated with the data file; and
determine, based at least in part on the updated metadata, an updated workflow for assignment to the data file.
5. The computing platform of claim 4 , further comprising program instructions stored on the at least one non-transitory computer-readable medium that are executable by the at least one processor such that the computing platform is configured to:
assign the updated workflow as an associated workflow for the data file; and
in response to assigning the updated workflow, automatically initiate the updated workflow assigned to the data file.
6. The computing platform of claim 1 , wherein the first client station and the second client station are the same client station.
7. The computing platform of claim 1 , wherein the third client station is different than the first client station and the second client station.
8. A non-transitory computer-readable medium, wherein the non-transitory computer-readable medium is provisioned with program instructions that, when executed by at least one processor, cause a computing platform to:
provide a common data environment (CDE) for electronic data files that serves as a source of truth for electronic data files associated with a construction project;
receive, from a first client station, a data file;
based on determined categories of metadata that have more influence compared to other categories with respect to determining workflows to be carried out with respect to data files, obtain, from a set of metadata associated with the data file, a subset of metadata associated with the data file;
input the obtained subset of metadata into one or more machine-learning models, wherein the one or more machine-learning models are trained based on historical data regarding workflow assignments for construction projects;
use the one or more machine-learning models to output, for each respective workflow in a universe of workflows that are available for assignment to data files, a predicted likelihood that the respective workflow is appropriate for the data file;
determine, based on the predicted likelihoods and a predefined threshold value, at least one recommended workflow for assignment to the data file, wherein each workflow of the at least one recommended workflow (i) defines a set of one or more actions that are to be taken in connection with the data file and (ii) is associated with a respective predicted likelihood that exceeds the predefined threshold value;
display, via a second client station, a graphical user interface (GUI) including a user-selectable button presented to a user to select a given recommended workflow for assignment to the data file, wherein the user-selectable button presented to the user includes an element to select an indicator that allows the user to dismiss the given recommended workflow as an option for assignment to the data file;
prior to promoting the data file to the CDE, assign a selected workflow from the at least one recommended workflow as an associated workflow for the data file;
in response to assigning the selected workflow from the at least one recommended workflow as an associated workflow for the data file, automatically initiate the selected workflow by generating a communication regarding the selected workflow and sending, to a third client station that is associated with an individual responsible for performing a first action of the selected workflow, the communication regarding the selected workflow, wherein the communication regarding the selected workflow includes information about the data file, an action required, and a due date of the action; and
after the selected workflow is completed, promote the data file to the CDE.
9. The non-transitory computer-readable medium of claim 8 , wherein the obtained subset of metadata comprises at least one of: metadata generated by the computing platform or metadata that has been received from one or more client stations.
10. The non-transitory computer-readable medium of claim 8 , wherein the obtained subset of metadata comprises metadata from a plurality of categories of metadata, wherein the plurality of categories are less than all available categories of metadata associated with the metadata currently stored for the data file.
11. The non-transitory computer-readable medium of claim 8 , further comprising program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor such that the computing platform is configured to:
obtain updated metadata associated with the data file; and
determine, based at least in part on the updated metadata, an updated workflow for assignment to the data file.
12. The non-transitory computer-readable medium of claim 11 , wherein the non-transitory computer-readable medium is also provisioned with program instructions that, when executed by at least one processor, cause a computing platform to:
assign the updated workflow as an associated workflow for the data file; and
in response to assigning the updated workflow, automatically initiate the updated workflow assigned to the data file.
13. The non-transitory computer-readable medium of claim 8 , wherein the first client station and the second client station are the same client station.
14. The non-transitory computer-readable medium of claim 8 , wherein the third client station is different than the first client station and the second client station.
15. A method carried out by a computing platform, the method comprising:
providing a common data environment (CDE) for electronic data files that serves as a source of truth for electronic data files associated with a construction project;
receiving, from a first client station, a data file;
based on determined categories of metadata that have more influence compared to other categories with respect to determining workflows to be carried out with respect to data files, obtaining, from a set of metadata associated with the data file, a subset of metadata associated with the data file;
inputting the obtained subset of metadata into one or more machine-learning models, wherein the one or more machine-learning models are trained based on historical data regarding workflow assignments for construction projects;
using the one or more machine-learning models to output, for each respective workflow in a universe of workflows that are available for assignment to data files, a predicted likelihood that the respective workflow is appropriate for the data file;
determining, based on the predicted likelihoods and a predefined threshold value, at least one recommended workflow for assignment to the data file, wherein each workflow of the at least one recommended workflow (i) defines a set of one or more actions that are to be taken in connection with the data file and (ii) is associated with a respective predicted likelihood that exceeds the predefined threshold value;
displaying, via a second client station, a graphical user interface (GUI) including a user-selectable button presented to a user to select a given recommended workflow for assignment to the data file, wherein the user-selectable button presented to the user includes an element to select an indicator that allows the user to dismiss the given recommended workflow as an option for assignment to the data file;
prior to promoting the data file to the CDE, assigning a selected workflow from the at least one recommended workflow as an associated workflow for the data file;
in response to assigning the selected workflow from the at least one recommended workflow as an associated workflow for the data file, automatically initiating the selected workflow by generating a communication regarding the selected workflow and sending, to a third client station that is associated with an individual responsible for performing a first action of the selected workflow, the communication regarding the selected workflow, wherein the communication regarding the selected workflow includes information about the data file, an action required, and a due date of the action; and
after the selected workflow is completed, promoting the data file to the CDE.
16. The method of claim 15 , wherein the obtained subset of metadata comprises at least one of: metadata generated by the computing platform or metadata that has been received from one or more client stations.
17. The method of claim 15 , wherein the obtained subset of metadata comprises metadata from a plurality of categories of metadata, wherein the plurality of categories are less than all available categories of metadata associated with the metadata currently stored for the data file.