Techniques for improving project data storage by generating standardized data storage templates

A computer-implemented method for improving project data storage by generating standardized data storage templates comprising:

• aggregating, by one or more processors, project data from one or more sets of project data stored in a project database, the project data corresponding to at least two projects of a plurality of projects, and the project data being in a non-standardized format;
• extracting, by the one or more processors, text data from the project data;
• inputting, by the one or more processors, the text data and an input prompt into a first machine learning (ML) model configured to extract one or more services indicated by the text data;
• generating, by the one or more processors, a text embedding for each service of the one or more services;
• and
• applying, by the one or more processors, a second ML model to (i) the one or more services and (ii) the text embeddings, wherein applying the second ML model includes:
• clustering the one or more services and the text embeddings into a set of clusters based on similarity values indicating similarities between (i) one or more of the one or more services and (ii) one or more of the text embeddings,
• generating, based on the set of clusters, a plurality of data storage templates indicating a standardized set of services in a standardized format for projects with associated project data included in one or more clusters of the set of clusters, and
• determining a primary data storage template based on a cluster size of a first cluster of the set of clusters.

A tangible machine-readable medium comprising instructions that, when executed, cause a machine to at least:

• aggregate project data from one or more sets of project data corresponding to at least two projects of a plurality of projects, the project data being in a non-standardized format;
• extract text data from the project data;
• input the text data and an input prompt into a first machine learning (ML) model configured to extract one or more services indicated by the text data;
• generate a text embedding for each service of the one or more services;
• and
• apply a second ML model to (i) the one or more services and (ii) the text embeddings, wherein applying the second ML model includes:
• clustering the one or more services and the text embeddings into a set of clusters based on similarity values indicating similarities between (i) one or more of the one or more services and (ii) one or more of the text embeddings,
• generating, based on the set of clusters, a plurality of data storage templates indicating a standardized set of services in a standardized format for projects with associated project data included in one or more clusters of the set of clusters, and
• determining a primary data storage template based on a cluster size of a first cluster of the set of clusters.