Information processing device, information processing method, and program

Claims

1. A means of complementing ontology data using a graph machine learning model that has learned the relationships between the information contained in ontology data, A means for generating a natural language processing model that generates a natural language processing model based on complementary ontology data, An information processing device equipped with the following features.

2. The system includes a learning means for training the aforementioned graph machine learning model, The ontology data includes multiple nodes and directed links that indicate the relationships between the nodes. The information processing apparatus according to claim 1, wherein the learning means trains the graph machine learning model to predict the relationships between unlinked nodes in the ontology data, using a plurality of nodes included in the ontology data and known relationships between the nodes.

3. The graph machine learning model takes data with one missing element from the three elements of the source node, the destination node, and the relationship between the nodes as a query, and outputs candidate elements for the missing element and their predicted scores. The information processing apparatus according to claim 2, wherein the complementary means reflects candidate elements whose predicted scores are above a predetermined threshold into the ontology data.

4. It includes means for acquiring ontology data and natural language documents. The information processing apparatus according to claim 1, wherein the natural language processing model generation means generates a natural language processing model based on the complemented ontology data and the natural language document.

5. An information processing method performed by a computer, We use a graph machine learning model that has learned the relationships between pieces of information contained in ontology data to perform ontology data completion. An information processing method that generates a natural language processing model based on complementary ontology data.

6. We use a graph machine learning model that has learned the relationships between pieces of information contained in ontology data to perform ontology data completion. A program that causes a computer to perform a process of generating a natural language processing model based on supplemented ontology data.