Systems and methods for automatically identifying unmet technical needs and/or technical problems

A computer implemented method of identifying documents disclosing a serious issue or problem, comprising:

• accessing, over a network, a plurality of documents, the plurality of documents having textual elements;
• analyzing with a processor textual elements of a document of the plurality of documents to identify one or more problem kernels, wherein a problem kernel comprises at least one phrase expressing a technical problem or unmet technical need;
• scoring at least one portion of the document, the scoring comprising at least calculating with the processor a problem kernel likelihood score based on:
• (a) a number of serious issue words in the at least one portion of the document, wherein the serious issue words indicate a serious issue or problem, and
• (b) proximity between the number of serious issue words and characteristic words in the at least one portion of the document, wherein the characteristic words indicate a generic characteristic of a thing;
• one of automatically calculating with the processor based at least on the on the text of the at least one portion of the document a monetary valuation number indicating a relative or absolute monetary value associated with the identified problem kernel likelihood score and storing to a data storage device the monetary valuation number for the at least one portion of the document;
• and
• automatically calculating with the processor based at least on the text of the at least one portion of the document a relative or absolute problem intensity number based on at least the identified problem kernel likelihood score and a trend associated with a serious issue or problem;
• and,
• providing a user interface with which a user can display information about a plurality of documents that have been sorted or filtered taking into account at least their problem kernel likelihood score and one of their monetary valuation number and their problem intensity number.

A computer implemented method of identifying documents disclosing a serious issue or problem, comprising:

• reading a serious issue identifier database having words indicating a serious issue or problem;
• accessing, over a network, a plurality of documents, the plurality of documents having textual elements;
• analyzing textual elements of a document of the plurality of documents to identify one or more problem kernels, wherein a problem kernel comprises at least one phrase expressing a technical problem or unmet technical need and scoring the at least one portion of the document, the scoring comprising at least calculating a problem kernel likelihood based on:
• a number of serious issue words in the at least one portion of the document, wherein the serious issue words indicate a serious issue or problem, and
• proximity between the number of serious issue words and characteristic words in the at least one portion of the document, wherein the characteristic words indicate a generic characteristic of a thing;
• automatically calculating a relative or absolute problem intensity number for at least the text of the at least one portion of the document, wherein the problem intensity number is based on at least the identified problem kernel likelihood score and a trend associated with a serious issue or problem;
• ranking the at least one portion of the document against other documents or portions thereof based on the problem kernel likelihood score of the at least one portion of the document;
• generating a visual interface identifying documents disclosing a likely problem kernel based on the ranking.

A computer implemented method of generating an image on an electronic display, comprising:

• accepting user query input;
• querying a database to identify documents that meet the user query input, including synonyms from a synonym database, if applicable;
• reading a serious issue identifier database having words indicating a serious issue or problem;
• accessing, over a network, a plurality of documents, the plurality of documents having textual elements;
• analyzing textual elements of documents to identify one or more problem kernels, wherein a problem kernel comprises at least one phrase expressing a technical problem or unmet technical need and scoring at least one portion of the documents, the scoring comprising at least calculating a problem kernel likelihood based on:
• a number of serious issue words in the at least one portion of the documents wherein the serious issue words indicate a serious issue or problem, and;
• proximity between the number of serious issue words and characteristic words in the at least one portion of the documents, wherein the characteristic words indicate a generic characteristic of a thing;
• automatically calculating with a processor a relative or absolute problem intensity number for at least the text of the at least one portion of the document, wherein the problem intensity number is based on at least the identified problem kernel likelihood score and a trend associated with a serious issue or problem;
• identifying and ranking candidate documents based at least on the problem kernel likelihood score of the at least one portion of the documents;
• providing a user interface for user to view the ranked candidate documents;
• and,
• displaying at least one portion of a ranked candidate document on a computer display in which serious issue words are shown in one set of display characteristics and other words are shown in a different set of display characteristics.