Systems and methods for automatically identifying unmet technical needs and/or technical problems
Systems and methods are provided for automatically identifying and displaying unmet technical needs and/or technical problems, such as identifying and displaying serious technical issues in specific areas of technology. In some exemplary embodiments, the text of technical documents is automatically analyzed to determine whether the text of any document identifies or potentially identifies a technical problem. In exemplary embodiments, portions of a documents called “problem kernels” and their associated features are automatically identified, automatically scored, and automatically ranked, and a subset of the problem kernels and/or features of problem kernels are displayed to a user on a computer display.
1. A computing system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
obtaining one or more documents from at least one document database;
analyzing the one or more documents using deficiency recognizer logic to identify at least one problem kernel, wherein the at least one problem kernel comprises a subset of the one or more documents that is indicative of a technical problem or unmet technical need;
analyzing the at least one problem kernel using summarization logic, wherein the summarization logic comprises an attentional encoder-decoder component;
generating, by the summarization logic, a summarized problem kernel based upon at least a portion of the at least one problem kernel; and
storing the summarized problem kernel.
2. The computing system of claim 1 , wherein the summarized problem kernel comprises fewer words than the at least one problem kernel.
3. The computing system of claim 1 , wherein the summarized problem kernel is indicative of one or more problem elements from the at least one problem kernel.
4. The computing system of claim 3 , further comprising:
identifying a subset of the one or more problem elements that are substantially identical.
5. The computing system of claim 4 , further comprising:
linking substantially identical problem elements of the subset of the one or more problem elements; and
generating one or more problem element clusters based upon the linked substantially identical problem elements.
6. The computing system of claim 1 , wherein the portion of the at least one problem kernel used to generate the summarized problem kernel is selected based upon at least one problem intensity metric.
7. The computing system of claim 1 , wherein the summarized problem kernel is additionally based upon external data obtained via a search engine query.
8. The computing system of claim 1 , wherein the summarized problem kernel is additionally based upon at least one problem intensity metric.
9. The computing system of claim 8 , wherein the at least one problem intensity metric is based upon at least one of a problem severity, publication date, problem persistency, problem recency, problem growth, or commercial relevance.
10. The computing system of claim 1 , wherein the summarized problem kernel is additionally based upon at least one of data related to previously identified technical problems or unmet technical needs or a relationship between technology elements.
11. The computing system of claim 1 , further comprising:
causing the summarized problem kernel to be displayed to a user at a user computing device.
12. The computing system of claim 1 , further comprising:
generating data corresponding to the at least one problem kernel, wherein the data comprises at least a problem intensity score based upon a problem kernel magnitude associated with the at least one problem kernel.
13. The computing system of claim 12 , wherein the summarized problem kernel is additionally based upon the data corresponding to the at least one problem kernel.
14. A method comprising:
obtaining one or more documents from at least one document database;
analyzing the one or more documents using deficiency recognizer logic to identify at least one problem kernel, wherein the at least one problem kernel comprises a subset of the one or more documents that is indicative of a technical problem or unmet technical need;
analyzing the at least one problem kernel using summarization logic, wherein the summarization logic comprises an attentional encoder-decoder component;
generating, by the summarization logic, a summarized problem kernel based upon at least a portion of the at least one problem kernel; and
storing the summarized problem kernel.
15. The method of claim 14 , wherein the summarized problem kernel comprises fewer words than the at least one problem kernel.
16. The method of claim 14 , wherein the summarized problem kernel is indicative of one or more problem elements from the at least one problem kernel.
17. The method of claim 16 , further comprising:
identifying a subset of the one or more problem elements that are substantially identical;
linking substantially identical problem elements of the subset of the one or more problem elements; and
generating one or more problem element clusters based upon the linked substantially identical problem elements.
18. A computing system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
receiving a first input set forth by a user of a user computing device;
obtaining one or more documents from at least one document database based upon the first input;
analyzing the one or more documents using deficiency recognizer logic to identify at least one problem kernel, wherein the at least one problem kernel comprises a subset of the one or more documents that is indicative of a technical problem or unmet technical need associated with the first input;
generating data corresponding to the at, least one problem kernel, wherein the data comprises at least a problem intensity score based upon a problem kernel magnitude associated with the at least one problem kernel;
analyzing the at least one problem kernel using summarization logic, wherein the summarization logic comprises an attentional encoder-decoder component;
generating, by the summarization logic, a summarized problem kernel based upon at least a portion of the at least one problem kernel and the data corresponding to the at least one problem kernel; and
causing the summarized problem kernel to be presented to the user at the user computing device.
19. The computing device of claim 18 , further comprising:
receiving a second input set forth by the user of the user computing device, the second input comprising one or more filter parameters;
responsive to receiving the second input, selecting the portion of the at least one problem kernel used to generate the summarized problem kernel, wherein the selecting is based upon the second input.
20. The computing device of claim 19 , wherein the one or more filter parameters comprise at least one of: a keyword, a problem element, one of more entity names, one or more industry names, or one or more geographic regions.