Determining digital personas using data-driven analysis

Abstract

Embodiments of the present disclosure relate to determining digital personas using data-driven analysis. The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a digital-driven approach to organize a user's user activity data into a hierarchy of digital actions, digital tasks, and digital workflows, and to categorize vectors representing frequent activities from the hierarchy into a persona group for the user. With this vector representation, the disclosed system is able to categorize vector representations from other vector representations' distribution from other users into the persona group for a particular user. Based on at least one of the determined persona group or vector representation, the disclosed system is able to use a node graph to determine digital recommendations for the particular user to collaborate with other users or on a particular project.

Claims

1. A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor, cause a computing device to: Identify the set of digital actions performed by the user from the digital action log corresponding to the user; A subset of digital actions performed by the user is categorized into a set of digital tasks, and a subset of digital tasks performed by the user is categorized into a set of digital workflows; Generate user activity vectors, which represent frequent digital actions from the set of digital actions, frequent digital tasks from the set of digital tasks, and frequent digital workflows from the set of digital workflows; The user's role group is determined by clustering the user's activity vector with the additional user activity vectors of the additional users using a clustering model. Digital recommendations for user collaboration between the user and additional users are generated using the following method: Generate a node graph, which includes nodes representing users and edges that link one or more nodes together to represent relationships between users; The node graph is modified by utilizing a classification model and the role groups corresponding to the user activity vector and the additional user activity vector to generate predicted connections between the user and the additional users regarding specific item nodes. as well as For a specific project corresponding to the specific project node, generate user collaboration recommendations between the user and additional users; as well as The digital recommendation is sent to the client device corresponding to the user and the additional user, so that the client device provides the user collaboration recommendation between the user and the additional user for display within the graphical user interface.

2. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to: send the digital recommendation to one of the client devices, such that the user's client device provides an optional option for initiating shared items with additional users from the user's collaborative recommendations, for display within a graphical user interface.

3. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to modify the node graph by utilizing a logistic regression model and the role group corresponding to the user activity vector and the additional user activity vector.

4. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to: generate the digital recommendation by determining a suggested user team based on the role group and the modified node graph.

5. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to: generate the digital recommendation by generating at least one of a suggested digital template, a digital notification, or a graphical dashboard having one or more suggested users.

6. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to: generate another digital recommendation for the suggested item by utilizing the classification model to determine another predicted edge between a user node associated with the user and another item node.

7. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to: The subset of digital actions is categorized into the set of digital tasks by classifying the frequent digital actions into the set of digital tasks; and The subset of digital tasks is categorized into the set of digital workflows by classifying the frequent digital tasks into the set of digital workflows.

8. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the user activity vector by: Using cross-user session data mining capabilities, the frequent digital actions from the digital action set, the frequent digital tasks from the digital task set, and the frequent digital workflows from the digital workflow set are identified from the digital action logs; and Generate the user activity vectors to represent the occurrence of the frequent digital actions, frequent digital tasks, and frequent digital workflows within the user session.

9. The non-transient computer-readable storage medium of claim 1, further comprising instructions that, when executed by the at least one processor, cause the computing device to: determine the user's role group by using the clustering model to map the user activity vectors to the role group based on the distribution of the user activity vector set.

10. A system comprising: One or more storage devices, including clustering models and digital action logs corresponding to users; as well as One or more processors are configured to cause the system to: The set of digital actions is identified from the digital action log corresponding to the user, the set of digital actions being performed by the user during the user session corresponding to the set of digital actions; Using data mining capabilities, the following steps are taken to generate a multi-level hierarchical structure of session co-occurrence: The set of frequent digital actions performed by the user is categorized into a set of digital tasks; as well as The set of frequent digital tasks performed by the user is categorized into a set of digital workflows; Using the data mining function, determine the set of frequent digital workflows from the set of digital workflows; Generate the user activity vector of the user, wherein the user activity vector represents the occurrence of the set of frequent digital actions, the set of frequent digital tasks, and the set of frequent digital workflows within the user session; The clustering model is used to map the user activity vectors of a user set to role groups based on the distribution of the user activity vectors, thereby determining the role group of the user. Digital recommendations for user collaboration between the user and additional users are generated using the following method: Generate a node graph, which includes nodes representing users and edges that link one or more nodes together to represent relationships between users; The node graph is modified by utilizing a classification model and the role group corresponding to the user activity vector and the additional user activity vector from the user activity vector to generate predicted connections between the user and the additional users regarding specific item nodes. as well as For a specific project corresponding to the specific project node, generate user collaboration recommendations between the user and additional users; as well as The digital recommendation is sent to the client device corresponding to the user and the additional user, so that the client device provides the user collaboration recommendation between the user and the additional user for display within the graphical user interface.

11. The system of claim 10, wherein the one or more processors are further configured to cause the system to: The frequent digital action set is identified by determining that a subset of digital actions from the set of digital actions satisfies one or more frequency thresholds; and The frequent digital task set is identified by determining that a subset of digital tasks from the set of digital tasks satisfies one or more frequency thresholds.

12. The system of claim 10, wherein the one or more processors are further configured to cause the system to: generate the digital recommendations by generating graphical visualizations, the graphical visualizations including frequency plots of the frequent digital action sets across role groups or heatmaps of multiple shared items among the role groups.

13. The system of claim 10, wherein the one or more processors are further configured to cause the system to: Generate one or more classification probabilities that the user will collaborate with the additional user on the specific project; and The digital recommendation is generated based on the one or more classification probabilities.

14. The system of claim 10, wherein the one or more processors are further configured to cause the system to: send the digital recommendation to one of the client devices to cause the client device corresponding to the user to provide a selectable list of suggested users for the specific item for display within a graphical user interface, wherein the selectable list includes the additional users.

15. The system of claim 10, wherein the one or more processors are further configured to cause the system to generate the digital recommendation by determining a suggested user team based on the role group and the modified node graph.

16. The system of claim 10, wherein the one or more processors are further configured to cause the system to generate the digital recommendations by: Based on the modified node graph, a proposed inter-role group collaboration is generated between the user and a second additional user outside the user's role group.

17. The system of claim 10, wherein the one or more processors are further configured to cause the system to: The frequent digital actions are categorized into the digital task set by classifying the set of frequently co-occurring digital actions performed by the user during a specific user session; and The frequent digital task set is categorized into the digital workflow set by classifying the set of frequently co-occurring digital tasks performed by the user during the specific user session.

18. The system of claim 10, wherein the one or more processors are further configured to cause the system to: send the digital recommendation to one of the client devices to cause the client device corresponding to the user to provide suggestions from one or more additional users granting editing, copying, or viewing permissions for the specific item for display within a graphical user interface.

19. A computer-implemented method, comprising: Digital action logs that identify and correspond to a set of users within an organization; Perform steps for determining frequent digital actions, frequent digital tasks, and frequent digital workflows performed by corresponding users from the user set based on the digital action log; Generate user activity vectors for the user set, wherein the user activity vectors for the user set represent the frequent digital actions, frequent digital tasks, and frequent digital workflows performed by the corresponding users; The role groups of the user set are determined by clustering specific user activity vectors into role groups using a clustering model; Digital recommendations for user collaboration between the user and additional users are generated using the following method: Generate a node graph, which includes nodes representing users and edges that link one or more nodes together to represent relationships between users; as well as The node graph is modified by utilizing a classification model and the role group corresponding to the specific user activity vector to generate predicted connections between the user and additional users regarding specific item nodes. as well as The digital recommendation is sent to the client device corresponding to the user and the additional user, so that the client device provides the user collaboration recommendation between the user and the additional user for display within the graphical user interface.

20. The computer-implemented method according to claim 19, further comprising: The digital recommendation is sent to one of the client devices to enable the user's client device to provide an option to initiate shared items with additional users recommended by the user for display within a graphical user interface.

Images