Abstract: A device may receive, in near-real time, unstructured data associated with an application or a system, and may extract textual data from the unstructured data. The device may parse the textual data to generate parsed textual data, and may perform natural language processing on the parsed textual data to generate processed textual data. The device may process the processed textual data, with a clustering model, to identify topical data associated with the processed textual data, and may process the topical data, with a classification model, to group the topical data into categories. The device may generate a knowledge graph based on the categories, and may store the knowledge graph in a data structure. The knowledge graph may enable the device to provide answers to questions associated with the application or the system.

Abstract: A device may receive, in near-real time, unstructured data associated with an application or a system, and may extract textual data from the unstructured data. The device may parse the textual data to generate parsed textual data, and may perform natural language processing on the parsed textual data to generate processed textual data. The device may process the processed textual data, with a clustering model, to identify topical data associated with the processed textual data, and may process the topical data, with a classification model, to group the topical data into categories. The device may generate a knowledge graph based on the categories, and may store the knowledge graph in a data structure. The knowledge graph may enable the device to provide answers to questions associated with the application or the system.

Abstract: In some examples, artificial intelligence and machine learning based project management assistance may include ascertaining an inquiry by a user. The inquiry may be related to a project. An attribute associated with the user and an attribute associated with the project may be ascertained. The inquiry may be analyzed based on the ascertained attributes associated with the user and the project. A predictor category may be identified, based on the analyzed inquiry, from a plurality of predictor categories that include a performance predictor category, a quality predictor category, a retrospect predictor category, and a planning predictor category. A predictor from a plurality of predictors may be identified based on the identified predictor category. A response to the inquiry may be generated based on execution of the identified predictor. Further, a display responsive to the inquiry may be generated based on the generated response.

Abstract: A device receives a command to identify an automation evaluation for a role, determines tasks of the role based on data relating to the role, and determines activities for the tasks based on the data relating to the role. The device determines one or more automation scores, which correspond to a suitability for automation of the activities, based on a set of characteristics of the activities and based on the data relating to the role. The automation scores are determined using a machine learning model to parse natural language descriptions of the activities and score parsed portions of the natural language descriptions. The device generates, for the role, an aggregate automation score based on the automation scores, determines the automation evaluation for the role based on the aggregate automation score and characteristics of an entity associated with the role, and performs an action relating to the automation evaluation.

Abstract: A device may predict, based on historical data relating to a plurality of past projects, a trigger to perform a project health check for a project. The device may process project data relating to the project to determine a health check status of the project based on predicting the trigger to perform the project health check for the project. The device may generate a recommendation relating to altering completion of the project based on the health check status of the project. The device may communicate with one or more devices to provide information identifying the recommendation. The device may receive, from the one or more devices, response information relating to the recommendation. The device may perform a response action relating to the recommendation based on receiving the response information.

Abstract: A device receives a command to identify an automation evaluation for a role, determines tasks of the role based on data relating to the role, and determines activities for the tasks based on the data relating to the role. The device determines one or more automation scores, which correspond to a suitability for automation of the activities, based on a set of characteristics of the activities and based on the data relating to the role. The automation scores are determined using a machine learning model to parse natural language descriptions of the activities and score parsed portions of the natural language descriptions. The device generates, for the role, an aggregate automation score based on the automation scores, determines the automation evaluation for the role based on the aggregate automation score and characteristics of an entity associated with the role, and performs an action relating to the automation evaluation.

Abstract: A device may predict, based on historical data relating to a plurality of past projects, a trigger to perform a project health check for a project. The device may process project data relating to the project to determine a health check status of the project based on predicting the trigger to perform the project health check for the project. The device may generate a recommendation relating to altering completion of the project based on the health check status of the project. The device may communicate with one or more devices to provide information identifying the recommendation. The device may receive, from the one or more devices, response information relating to the recommendation. The device may perform a response action relating to the recommendation based on receiving the response information.

Abstract: In some examples, artificial intelligence and machine learning based project management assistance may include ascertaining an inquiry by a user. The inquiry may be related to a project. An attribute associated with the user and an attribute associated with the project may be ascertained. The inquiry may be analyzed based on the ascertained attributes associated with the user and the project. A predictor category may be identified, based on the analyzed inquiry, from a plurality of predictor categories that include a performance predictor category, a quality predictor category, a retrospect predictor category, and a planning predictor category. A predictor from a plurality of predictors may be identified based on the identified predictor category. A response to the inquiry may be generated based on execution of the identified predictor. Further, a display responsive to the inquiry may be generated based on the generated response.