Bulletin board data mapping and presentation
A computer-implemented method performed at a server system having one or more processors and memory, the method comprising receiving a set of curated documents comprising one or more documents identified as being relevant to a sector, analyzing the set of curated documents to determine one or more words and a count of each of the one or more words for all documents of the curated set of documents, further analyzing the set of curated documents, by analyzing one or more n-grams based on the one or more words, determining a first score based on a term frequency and a global document frequency of each of the one or more words of each of the one or more n-grams, determining a document vector based on averages of the first score, where the document vector comprises a perfect document for the sector, and storing the document vector in the data store.
1. A computer system for file analysis, the system comprising:
a memory comprising instructions executable by one or more processors, wherein the one or more processors are operable to execute the instructions to:
control a hardware engine, comprising an entity extractor and a similarity engine, operatively coupled via a graphics bus to accelerate identification and analysis of large datasets in real-time, wherein the hardware engine is configured to:
identify one or more relevant files according to one or more semantic concepts;
identify one or more words for each of the one or more relevant files;
identify one or more n-grams according to the one or more words identified in the one or more relevant files, wherein an n-gram is one or more combinations of the one or more words;
generate a plurality of first scores, wherein each first score of the plurality of first scores is generated according to a term frequency and a global document frequency for each of the one or more words of each of the one or more n-grams of each of the one or more relevant files;
perform vector analysis on the one or more relevant files to generate a model document that improves file classification accuracy and reduces computational complexity by efficiently identifying unknown files according to similarities to relevant files, in order to assign each unknown files a relevant score;
generate a document vector according to averages of the plurality of first scores, wherein the document vector represents a reduced-dimensional representation of the file that increases the speed and accuracy of comparison between files and comprises a final value that illustrates how valuable the one or more words are in the one or more unknown files;
compare the unknown file with the model document according to the term frequency and the global document frequency; and
assign the relevant score to the unknown file according to the comparison, wherein the relevant score is used in a practical application comprising one or more of a technical space, a conceptual field, a geographic location and an industry sector, thereby enhancing the speed and efficiency of file retrieval and classification in such environments.
2. The computer system of claim 1 , wherein the one or more relevant files comprise the one or more files.
3. The computer system of claim 1 , wherein the one or more processors are operable to execute the instructions to:
display to the user, a list of the one or more relevant files having the highest second score that are most relevant to the one or more semantic concepts.
4. The computer system of claim 1 , wherein the one or more semantic concepts comprises at least one of mergers and acquisitions, financial updates, regulatory changes, legal issues, executive turnover, natural disasters, healthcare, education, schools, bankruptcy, and Hollywood news.
5. The computer system of claim 1 , wherein the one or more n-grams comprises at least four words of the one or more words.
6. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
control a hardware engine, comprising an entity extractor and a similarity engine, operatively coupled via a graphics bus to accelerate identification and analysis of large datasets in real-time, wherein the hardware engine is configured to:
identify one or more relevant files according to one or more semantic concepts;
identify one or more words in the one or more relevant files;
identify one or more n-grams according to the one or more words identified in the one or more files, wherein an n-gram is one or more combinations of the one or more words;
generate a plurality of first scores, wherein each first score of the plurality of first scores is generated according to a term frequency and a global document frequency for each of the one or more words of each of the one or more n-grams of each of the one or more relevant files;
perform vector analysis on the one or more relevant files to generate a model document that improves file classification accuracy and reduces computational complexity by efficiently identifying unknown files according to similarities to relevant files, in order to assign each unknown files a relevant score;
generate a document vector according to averages of the plurality of first scores, wherein the document vector represents a reduced-dimensional representation of the file that increases the speed and accuracy of comparison between files and comprises a final value that illustrates how valuable the one or more words are in the one or more unknown files;
compare the unknown file with the model document according to the term frequency and the global document frequency; and
assign the relevant score to the unknown file according to the comparison, wherein the relevant score is used in a practical application comprising one or more of a technical space, a conceptual field, a geographic location and an industry sector, thereby enhancing the speed and efficiency of file retrieval and classification in such environments.
7. The one or more computer-readable non-transitory storage media of claim 6 , wherein:
the one or more processors are operable to execute the instructions to:
receive a search query from a user;
identify one or more files according to the search query;
determine the one or more semantic concepts according to the one or more files; and
the one or more relevant files comprise the one or more files.
8. The one or more computer-readable non-transitory storage media of claim 6 , wherein the one or more processors are operable to execute the instructions to:
compare each of the one or more relevant files to the document vector to determine a second score for each of the one or more relevant files; and
display to the user, a list of the one or more relevant files having the highest second score that are most relevant to the one or more semantic concepts.
9. The one or more computer-readable non-transitory storage media of claim 6 , wherein the one or more semantic concepts comprises at least one of mergers and acquisitions, financial updates, regulatory changes, legal issues, executive turnover, natural disasters, healthcare, education, schools, bankruptcy, and Hollywood news.
10. The one or more computer-readable non-transitory storage media of claim 6 , wherein the one or more n-grams comprises at least four words of the one or more words.