Digital processing systems and methods for improving dataset state determinations

1 . A non-transitory computer-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations for improving dataset state determinations using Artificial Intelligence (AI), the operations comprising:

accessing a data structure including a plurality of differing datasets stored across multiple data sources distributed over a network, wherein each of the plurality of datasets is associated with a user-determined dataset status, the user-determined dataset status is selected from a plurality of dataset statuses, and wherein accessing the data structure includes dynamically aggregating the plurality of differing datasets onto a unified data structure;

for each of the plurality of datasets:

inputting the dataset into an AI agent, including a machine learning algorithm, wherein the AI agent is configured to preprocess the dataset to detect and resolve inconsistencies, and analyze the dataset to automatically and dynamically determine an associated AI-determined dataset status by leveraging relationships between the plurality of datasets;

comparing the user-determined dataset status with the AI-determined dataset status; and

when the comparing results in a determination of a difference between the user-determined dataset status and the AI-determined dataset status, instituting a remedial action including automatically choosing between the user-determined dataset status and the AI-determined dataset status based on a predefined rule, and when resulting from the predefined rule, the user-determined dataset status is preferred over the AI-determined dataset status:

generating a feedback entry comprising the dataset, the user-provided dataset status, and information indicative of the user-determined dataset status being preferred over the AI-determined dataset status;

updating an AI agent training dataset stored in a memory accessible to the AI agent by incorporating the feedback entry into the AI agent training dataset;

updating one or more parameters of the machine learning algorithm based on the updated AI agent training dataset; and

configuring the AI agent to utilize the updated AI agent training dataset when automatically and dynamically determining, for a subsequent dataset, an associated AI-determined dataset status.

2 . The non-transitory computer-readable medium of claim 1 , wherein the AI-determined dataset status is selected from the plurality of dataset statuses.

3 . The non-transitory computer-readable medium of claim 1 , wherein the remedial action further includes outputting an indicator signaling a discrepancy.

4 . The non-transitory computer-readable medium of claim 3 , wherein outputting the indicator signaling the identified discrepancy includes presenting a visual indicator signaling the discrepancy on a display.

5 . The non-transitory computer-readable medium of claim 4 , wherein the AI agent is further configured to provide textual justifications for the determination of the associated dataset status and wherein the operations further comprise in response to a user interaction with the visual indicator, outputting a justification indicator, wherein the justification indicator is configured to provide a textual justification for the discrepancy.

6 . The non-transitory computer-readable medium of claim 5 , wherein outputting the justification indicator includes presenting on the display a pop-up window configured to display the textual justification for the discrepancy and to display a GUI element for ignoring the AI-determined dataset status.

7 . The non-transitory computer-readable medium of claim 6 , wherein the operations further comprise in response to a user interaction with the GUI element causing the pop-up window and the visual indicator to disappear from the display.

8 . The non-transitory computer-readable medium of claim 1 , wherein the plurality of datasets corresponds to a plurality of projects, each project being associated with project-related data, and the project-related data includes at least one of a plurality of tasks, a task completion rate, a timeline, or an associated project manager.

9 . The non-transitory computer-readable medium of claim 1 , wherein the operations further comprise presenting on a display the plurality of datasets with the associated user-determined dataset statuses.

10 . The non-transitory computer-readable medium of claim 9 , wherein the operations further comprise presenting on the display the plurality of datasets with the associated AI-determined dataset statuses.

11 . The non-transitory computer-readable medium of claim 9 , wherein the operations further comprise enabling, on the display, a modification of the associated user-determined dataset status.

12 . The non-transitory computer-readable medium of claim 1 , wherein the operations further comprise when the comparing results in a determination of a correspondence between the user-determined dataset status and the AI-determined dataset status, outputting an indicator signaling a correspondence.

13 . The non-transitory computer-readable medium of claim 1 , wherein the AI agent is further configured to provide insights for each of the plurality of datasets.

14 . A method for improving dataset state determinations using Artificial Intelligence (AI), the method comprising:

accessing a data structure including a plurality of differing datasets stored across multiple data sources distributed over a network, wherein each of the plurality of datasets is associated with a user-determined dataset status, the user-determined dataset status is selected from a plurality of dataset statuses, and wherein accessing the data structure includes dynamically aggregating the plurality of differing datasets onto a unified data structure;

for each of the plurality of datasets:

inputting the dataset into an AI agent, including a machine learning algorithm, wherein the AI agent is configured to preprocess the dataset to detect and resolve inconsistencies, and analyze the dataset to automatically and dynamically determine an associated AI-determined dataset status by leveraging relationships between the plurality of datasets;

comparing the user-determined dataset status with the AI-determined dataset status; and

when the comparing results in a determination of a difference between the user-determined dataset status and the AI-determined dataset status, instituting a remedial action including automatically choosing between the user-determined dataset status and the AI-determined dataset status based on a predefined rule, and when resulting from the predefined rule, the user-determined dataset status is preferred over the AI-determined dataset status:

generating a feedback entry comprising the dataset, the user-provided dataset status, and information indicative of the user-determined dataset status being preferred over the AI-determined dataset status;

updating an AI agent training dataset stored in a memory accessible to the AI agent by incorporating the feedback entry into the AI agent training dataset;

updating one or more parameters of the machine learning algorithm based on the updated AI agent training dataset; and

configuring the AI agent to utilize the updated AI agent training dataset when automatically and dynamically determining, for a subsequent dataset, an associated AI-determined dataset status.

15 . The method of claim 14 , wherein the remedial action further includes outputting an indicator signaling a discrepancy.

16 . The method of claim 15 , wherein outputting the indicator signaling the identified discrepancy includes presenting a visual indicator signaling the discrepancy on a display.

17 . A system for improving dataset state determinations using Artificial Intelligence (AI), the system comprising:

at least one processor configured to:

access a data structure including a plurality of differing datasets stored across multiple data sources distributed over a network, wherein each of the plurality of datasets is associated with a user-determined dataset status, the user-determined dataset status is selected from a plurality of dataset statuses, and wherein accessing the data structure includes dynamically aggregating the plurality of differing datasets onto a unified data structure;

for each of the plurality of datasets:

input the dataset into an AI agent, including a machine learning algorithm, wherein the AI agent is configured to preprocess the dataset to detect and resolve inconsistencies, and analyze the dataset to automatically and dynamically determine an associated AI-determined dataset status by leveraging relationships between the plurality of datasets;

compare the user-determined dataset status with the AI-determined dataset status; and

when the comparing results in a determination of a difference between the user-determined dataset status and the Al-determined dataset status, institute a remedial action including automatically choosing between the user-determined dataset status and the AI-determined dataset status based on a predefined rule, and when resulting from the predefined rule, the user-determined dataset status is preferred over the AI-determined dataset status:

generate a feedback entry comprising the dataset, the user-provided dataset status, and information indicative of the user-determined dataset status being preferred over the AI-determined dataset status;

update an AI agent training dataset stored in a memory accessible to the AI agent by incorporating the feedback entry into the AI agent training dataset;

update one or more parameters of the machine learning algorithm based on the updated AI agent training dataset; and

configure the AI agent to utilize the updated AI agent training dataset when automatically and dynamically determining, for a subsequent dataset, an associated AI-determined dataset status.

18 . The system of claim 17 , wherein the remedial action further includes outputting an indicator signaling a discrepancy.

19 . The system of claim 18 , wherein outputting the indicator signaling the identified discrepancy includes presenting a visual indicator signaling the discrepancy on a display.

20 . The non-transitory computer-readable medium of claim 1 , wherein the machine learning comprises one of: a support vector machine, a random forest, a nearest neighbors algorithm, a deep learning algorithm, an artificial neural network algorithm, a convolutional neural network algorithm, or a recursive neural network algorithm.

21 . The non-transitory computer-readable medium of claim 1 , wherein generating the feedback entry includes generating and incorporating into the feedback entry a difference log identifying the determined difference between the user-determined dataset status and the AI-determined dataset status.

22 . The non-transitory computer-readable medium of claim 1 , wherein the one or more machine learning algorithm parameters include at least one of: one or more formulas, one or more functions, one or more rules, or one or more procedures.