Product baseline information extraction
In an approach for automatically extracting product baseline information from a request for proposal document, a processor receives the document. A processor detects a table in the document. A processor identifies a table header on the table. The table header is associated with a name and an associated volume of the product. A processor extracts context based on the table header from the table. The context includes the name and the associated volume of the product. A processor maps the extracted context with the name of the product in the table to an associated name of the product based on a pre-defined product ontology.
1. A computer-implemented method comprising:
receiving, by one or more processors, a document;
detecting, by one or more processors, a table in the document;
identifying, by one or more processors, a table header on the table, the table header being associated with a name and a volume of a product, wherein identifying the table header includes:
filtering information which is unrelated to the name and the volume of the product in the document by using natural language processing that analyzes and understands text, languages and information in the document,
identifying temporal context associated with the product, the temporal context being used to aggregate the volume of the product, and
identifying spatial context associated with the product, the spatial context being used to aggregate the volume of the product;
extracting, by one or more processors, context based on the table header from the table, the context including the name and the volume of the product, wherein extracting the context includes linking the context to the name of the product;
mapping, by one or more processors, the extracted context with the name of the product in the table to an associated name of the product based on a pre-defined product ontology, wherein the pre-defined product ontology encompasses representation, formal naming and definition of categories, properties and relations of products, wherein the pre-defined product ontology has a hierarchical structure indicating which product is part of another product;
summarizing, by one or more processors, the volume of the product with the associated name of the product based on the pre-defined product ontology; and
outputting, by one or more processors, the associated name and summarized volume of the product.
2. The computer-implemented method of claim 1 , wherein detecting the table in the document includes:
identifying a column having the name of the product, and
identifying a row having the volume associated with the name based on the column.
3. A computer program product comprising:
one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to receive a document;
program instructions to detect a table in the document;
program instructions to identify a table header on the table, the table header being associated with a name and a volume of a product, wherein program instructions to identify the table header include:
program instructions to filter information which is unrelated to the name and the volume of the product in the document by using natural language processing that analyzes and understands text, languages and information in the document,
program instructions to identify temporal context associated with the product, the temporal context being used to aggregate the volume of the product, and
program instructions to identify spatial context associated with the product, the spatial context being used to aggregate the volume of the product;
program instructions to extract context based on the table header from the table, the context including the name and the volume of the product, wherein program instructions to extract the context include program instructions to link the context to the name of the product;
program instructions to map the extracted context with the name of the product in the table to an associated name of the product based on a pre-defined product ontology, wherein the pre-defined product ontology encompasses representation, formal naming and definition of categories, properties and relations of products, wherein the pre-defined product ontology has a hierarchical structure indicating which product is part of another product;
program instructions to summarize the volume of the product with the associated name of the product based on the pre-defined product ontology; and
program instructions to output the associated name and summarized volume of the product.
4. The computer program product of claim 3 , wherein program instructions to detect the table in the document include:
program instructions, stored on the one or more computer-readable storage media, to identify a column having the name of the product, and
program instructions, stored on the one or more computer-readable storage media, to identify a row having the volume associated with the name based on the column.
5. A computer system comprising:
one or more computer processors, one or more computer readable storage media, and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to receive a document;
program instructions to detect a table in the document;
program instructions to identify a table header on the table, the table header being associated with a name and a volume of a product, wherein program instructions to identify the table header include:
program instructions to filter information which is unrelated to the name and the volume of the product in the document by using natural language processing that analyzes and understands text, languages and information in the document,
program instructions to identify temporal context associated with the product, the temporal context being used to aggregate the volume of the product, and
program instructions to identify spatial context associated with the product, the spatial context being used to aggregate the volume of the product;
program instructions to extract context based on the table header from the table, the context including the name and the volume of the product, wherein program instructions to extract the context include program instructions to link the context to the name of the product;
program instructions to map the extracted context with the name of the product in the table to an associated name of the product based on a pre-defined product ontology, wherein the pre-defined product ontology encompasses representation, formal naming and definition of categories, properties and relations of products, wherein the pre-defined product ontology has a hierarchical structure indicating which product is part of another product;
program instructions to summarize the volume of the product with the associated name of the product based on the pre-defined product ontology; and
program instructions to output the associated name and summarized volume of the product.
6. The computer system of claim 5 , wherein program instructions to detect the table in the document include:
program instructions, stored on the one or more computer-readable storage media, to identify a column having the name of the product, and
program instructions, stored on the one or more computer-readable storage media, to identify a row having the volume associated with the name based on the column.