Systems and methods for automatically determining a performance index
A computer-implemented method for analyzing electronic documents includes defining at least one search criterion for a plurality of index items relating to a subject; applying the at least one search criterion to a plurality of documents; determining, for each index item in the plurality of index items, a category index reflecting a degree to which the plurality of documents relates to the index item; and generating, with reference to the category index for each index item in the plurality of index items, a performance index reflecting a degree to which the plurality of documents relates to the subject.
1. A computer-implemented method comprising:
defining a first search criterion for locating references to a first entity of a plurality of entities referenced in a plurality of publicly-available news sources in connection with a first performance category in a plurality of performance categories, the plurality of publicly-available news sources comprising one or more of news reports, press releases, industry surveys, award announcements, trade publications, or regulatory filings;
defining a second search criterion, different from the first search criterion, for locating references to the first entity in the plurality of publicly-available news sources in connection with a second performance category in the plurality of performance categories;
applying the first search criterion to the plurality of publicly-available news sources, to obtain a first search result based on one or more matches of the first search criterion in a first subset of the plurality of publicly available news sources;
applying the second search criterion to the plurality of publicly-available news sources, to obtain a second search result based on one or more matches of the second search criterion in a second subset of the plurality of publicly available news sources;
determining, as a function of at least the first search result, a first category metric reflecting performance of the first entity in the first performance category as indicated by the plurality of publicly-available news sources;
determining, as a function of at least the second search result, a second category metric reflecting performance of the first entity in the second performance category as indicated by the plurality of publicly-available news sources; and
generating, as a function of at least the first category metric and the second category metric, a first performance index reflecting overall performance of the first entity across the plurality of performance categories as indicated by the plurality of publicly-available news sources.
2. The method of claim 1 , wherein generating the first performance index comprises aggregating the first category metric and the second category metric.
3. The method of claim 2 , wherein generating the first performance index further comprises applying a weighing factor to one or more of the first category metric and the second category metric.
4. The method of claim 1 , wherein the first performance index represents an evaluation of the first entity with respect to a characteristic of the first entity.
5. The method of claim 1 , further comprising:
defining a third search criterion for locating references to a second entity of the plurality of entities referenced in the plurality of publicly-available news sources in connection with the first performance category;
defining a fourth search criterion, different from the third search criterion, for locating references to the second entity in the plurality of publicly-available news sources in connection with the second performance category;
applying the third search criterion to the plurality of publicly-available news sources, to obtain a third search result based on one or more matches of the third search criterion in a third subset of the plurality of publicly available news sources;
applying the fourth search criterion to the plurality of publicly-available news sources, to obtain a fourth search result based on one or more matches of the fourth search criterion in a fourth subset of the plurality of publicly-available news sources;
determining, as a function of at least the third search result, a third category metric reflecting performance of the second entity in the first performance category as indicated by the plurality of publicly-available news sources;
determining, as a function of at least the fourth search result, a fourth category metric reflecting performance of the second entity in the second performance category as indicated by the plurality of publicly-available news sources; and
generating, as a function of at least the third category metric and the fourth category metric, a second performance index reflecting overall performance of the second entity across the plurality of performance categories as indicated by the plurality of publicly-available news sources.
6. The method of claim 5 , further comprising generating a graphical display comprising the first performance index and the second performance index.
7. The method of claim 6 , wherein the graphical display is one of a bar chart and a radar chart.
8. The method of claim 1 , wherein the first category metric comprises at least one of a count of documents in the plurality of publicly-available news sources satisfying the first search criterion, a count of hits within documents in the plurality of publicly-available news sources satisfying the first search criterion, and a depth of coverage of the first subject in relation to the first performance category in the plurality of publicly-available news sources.
9. The method of claim 1 , wherein applying the first search criterion to the plurality of publicly-available news sources comprises determining that at least one document in the plurality of publicly-available news sources contains a syntactic structure.
10. The method of claim 1 , wherein the first search criterion comprises a search string, and wherein applying the first search criterion to the plurality of publicly-available news sources comprises determining that at least one document in the plurality of publicly-available news sources satisfies the first search criterion by matching the search string in at least one location.
11. The method of claim 10 , wherein the search string comprises at least one of a keyword search, a phrase search, a proximity search, and a Boolean expression.
12. The method of claim 1 , further comprising:
generating, for at least one document of the plurality of publicly-available news sources, a search summary of the at least one document; and
presenting the search summary via a user interface.
13. The method of claim 1 , wherein the first search criterion comprises at least one term disambiguating the first performance category from a separate concept having similar terminology.
14. The method of claim 1 , wherein at least one news source in the plurality of publicly-available news sources is in both the first subset and the second subset of the plurality of publicly-available news sources.
15. An index generation system comprising:
at least one device including one or more hardware processors; and
one or more computer-readable media storing instructions that, when executed by the one or more processors, cause performance of operations comprising:
defining a first search criterion for locating references to a first entity of a plurality of entities referenced in a plurality of publicly-available news sources in connection with a first performance category in a plurality of performance categories, the plurality of publicly-available news sources comprising one or more of news reports, press releases, industry surveys, award announcements, trade publications, or regulatory filings;
defining a second search criterion, different from the first search criterion, for locating references to the first entity in the plurality of publicly-available news sources in connection with a second performance category in the plurality of performance categories;
applying the first search criterion to the plurality of publicly-available news sources, to obtain a first search result based on one or more matches of the first search criterion in a first subset of the plurality of publicly available news sources;
applying the second search criterion to the plurality of publicly-available news sources, to obtain a second search result based on one or more matches of the second search criterion in a second subset of the plurality of publicly available news sources;
determining, as a function of at least the first search result, a first category metric reflecting performance of the first entity in the first performance category as indicated by the plurality of publicly-available news sources;
determining, as a function of at least the second search result, a second category metric reflecting performance of the first entity in the second performance category as indicated by the plurality of publicly-available news sources; and
generating, as a function of at least the first category metric and the second category metric, a first performance index reflecting overall performance of the first entity across the plurality of performance categories as indicated by the plurality of publicly-available news sources.
16. The system of claim 15 , further comprising a document database configured to store a plurality of documents from the plurality of publicly-available news sources and metadata about the plurality of documents.
17. The system of claim 15 , the operations further comprising:
generating a graphical display comprising at least one of (a) the first performance index and (b) a second performance index reflecting overall performance of the second entity across the plurality of performance categories as indicated by the plurality of publicly-available news sources, the system further comprising a user interface configured to display the graphical display.
18. The system of claim 15 , wherein the first search criterion comprises a search string, and wherein applying the first search criterion to the plurality of publicly-available news sources comprises determining that at least one document in the plurality of publicly-available news sources satisfies the first search criterion by matching the search string in at least one location.
19. The system of claim 18 , wherein the search string comprises at least one of a keyword search, a phrase search, a proximity search, and a Boolean expression.
20. The system of claim 15 , further comprising a graphical user interface configured to receive at least one of the first search criterion and the second search criterion.