CONTEXT SEARCH SYSTEM
A computer based media, method and system for developing at least one context frame that summarizes a measure performance situation for one or more levels of one or more organizations, providing applications for managing the measure performance that adapt to the performance situation by using a context frame and a database that automatically captures and incorporates any changes in the measure performance situation.
1 . (canceled)
2 . A computer-implemented performance management method, comprising:
obtaining information from an external database to evaluate performance;
identifying elements of the performance;
creating quantitative mission measures using the information;
assigning weights to the quantitative mission measures;
identifying key performance indicators via a predictive model by determining a relative contribution of each of the elements of the performance to each of the weighted quantitative mission measures; and
producing a report that compares a result of the identification.
3 . The method of claim 2 , wherein the information comprises text information, geospatial data, video or audio information, or event risk data.
4 . The method of claim 2 , wherein the weights are assigned to the quantitative mission measures based, at least in part, on user input or a relative level defined by historic data.
5 . The method of claim 2 , wherein the predictive model is selected from a group comprising: a neural network; CART; GARCH; projection pursuit regression; a generalized additive model (GAM); a redundant regression network; rough-set analysis; boosted Naive Bayes Regression; MARS; linear regression; support vector method; and stepwise regression.
6 . The method of claim 2 , further comprising:
segmenting the elements of the performance into clusters that share similar characteristics;
evaluating the predictive model using the segmented elements of the performance; and
applying the segmented elements of the performance to the predictive model if the accuracy of the predictive model is improved.
7 . The method of claim 2 , further comprising:
identifying keywords, from the information, that are relevant to the quantitative mission measures; and
applying the keywords to the predictive model.
8 . The method of claim 2 , further comprising:
identifying patterns from the information for each element of the performance;
determining a frequency and a type of each of the identified patterns; and
applying the identified patterns to the predictive model.
9 . The method of claim 8 , wherein the patterns for each element of the performance are identified using the Apriori algorithm.
10 . The method of claim 2 , further comprising:
identifying geo-coded data from the information;
converting the geo-coded data in accordance with a geo-coding standard; and
calculating pre-defined attributes for the converted geo-coded data.
11 . The method of claim 10 , wherein the calculated pre-defined attributes include one or more of summary data, trends, comparisons to a baseline value, and time lagged values.
12 . A performance management system, comprising:
memory; and
one or more processors configured to:
obtain information from an external database to evaluate performance;
identify elements of the performance;
create quantitative mission measures using the information;
identify key performance indicators via a predictive model by determining a relative contribution of each of the elements of the performance to each of the quantitative mission measures; and
produce a report that compares a result of the identification.
13 . The system of claim 12 , wherein the one or more processors are further configured to assign weights to the quantitative mission measures and determine the relative contribution of each of the elements of the performance to each of the weighted quantitative mission measures.
14 . The system of claim 12 , wherein the information comprises text information, geospatial data, video or audio information, or event risk data.
15 . The system of claim 13 , wherein the weights are assigned to the quantitative mission measures based, at least in part, on user input or a relative level defined by historic data.
16 . The system of claim 12 , wherein the predictive model is selected from a group comprising: a neural network; CART; GARCH; projection pursuit regression; a generalized additive model (GAM); a redundant regression network; rough-set analysis; boosted Naive Bayes Regression; MARS; linear regression; support vector method; and stepwise regression.
17 . The system of claim 12 , wherein the one or more processors are further configured to:
segment the elements of the performance into clusters that share similar characteristics;
evaluate the predictive model using the segmented elements of the performance; and
apply the segmented elements of the performance to the predictive model if accuracy of the predictive model is improved
18 . The system of claim 12 , wherein the one or more processors are further configured to:
identify keywords, from the information, that are relevant to the quantitative mission measures; and
apply the keywords to the predictive model.
19 . The system of claim 12 , wherein the one or more processors are further configured to:
identify patterns from the information for each element of the performance;
determine a frequency and a type of each of the identified patterns; and
apply the identified patterns to the predictive model.
20 . The system of claim 19 , wherein the patterns for each element of the performance are identified using the Apriori algorithm.
21 . The system of claim 12 , wherein the one or more processors are further configured to:
identify geo-coded data from the information;
convert the geo-coded data in accordance with a geo-coding standard; and
calculate pre-defined attributes for the converted geo-coded data.
22 . The system of claim 21 , wherein the calculated pre-defined attributes include one or more of summary data, trends, comparisons to a baseline value, and time lagged values.