Summary of a resource
AssigneeInternational Business Machines Corporation
InventorsAshleigh Shona Denholm, Emma Jane Dawson, Jack Peter Wadsted, Eunjin Lee
Life of this patent
Estimating the term…
Abstract
Concepts for automatically generating a summary of a resource are presented. One example comprises analyzing at least a portion of electronic content comprising a reference to a resource to determine a context identifier for the electronic content, the context identifier describing subject-matter of the electronic content. Content of the resource is also analyzed to determine one or more content identifiers for the resource, the one or more content identifiers describing subject-matter of the resource. A summary of the resource is then generated based on the context identifier and the one or more content identifiers.
Claims20
A computer-implemented method for automatically generating a summary of a resource, the method comprising:
- scraping electronic content from a current conversation within which is provided a referenced resource, wherein the conversation is scraped beginning from a defined starting point (in time or in number of words);
- scraping a web page HTML content data, wherein the web page HTML content data is the referenced resource;
- analyzing at least a portion of the scraped electronic content to determine a context identifier for the electronic content, the context identifier describing subject-matter of the electronic content;
- analyzing content of the referenced resource to determine one or more content identifiers for the resource, the one or more content identifiers describing subject-matter of the referenced resource;
- and
- in response to the context identifier significantly matching one or more of the content identifiers, generating a summary of the portion of the referenced resource that matches the context identifier.
A computer program product for automatically generating a summary of a resource, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing unit to cause the processing unit to perform a method comprising:
- scraping electronic content from a current conversation within which is provided a referenced resource, wherein the conversation is scraped beginning from a defined starting point (in time or in number of words);
- scraping a web page HTML content data, wherein the web page HTML content data is the referenced resource;
- analyzing at least a portion of the scraped electronic content to determine a context identifier for the electronic content, the context identifier describing subject-matter of the electronic content;
- analyzing content of the referenced resource to determine one or more content identifiers for the resource, the one or more content identifiers describing subject-matter of the referenced resource;
- and
- in response to the context identifier significantly matching one or more of the content identifiers, generating a summary of the portion of the referenced resource that matches the context identifier.
A system for automatically generating a summary of a resource, the system comprising:
- one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
- scraping electronic content from a current conversation within which is provided a referenced resource, wherein the conversation is scraped beginning from a defined starting point (in time or in number of words);
- scraping a web page HTML content data, wherein the web page HTML content data is the referenced resource;
- performing a first analysis of at least a portion of the scraped electronic content to determine a context identifier for the electronic content, the context identifier describing subject-matter of the electronic content;
- performing a second analysis of a content of the referenced resource to determine one or more content identifiers for the resource, the one or more content identifiers describing subject-matter of the referenced resource;
- and
- in response to the context identifier significantly matching one or more of the content identifiers, generating a summary of the portion of the referenced resource that matches the context identifier.
Dependencies are inferred from the claim text.