Tools and methods for determining semantic relationship indexes

Abstract

Systems, apparatuses, and methods for determining an individual's sentimental baseline, based on a plurality of data items and characteristics. The data items may include objective and quantitative data, as well as subjective and qualitative data. The system, apparatus, or method may obtain a number of relationships between information atoms, identify sentiments associated with the relationships, and calculate sentimental baselines for those relationships. Differences from any baseline may also be calculated, to determine true changes in sentiment. Relationships between those differences and other data or relationships may also be calculated, to determine how a change in sentiment is related to other changes in behavior. For example, relationships between a particular difference and changes in any metric, sub-metric, group of characteristics, data item, data source, characteristic, sentiment, or groups thereof may be determined. These relationships may also be used to predict future behavior or sentiment.

What is claimed is: 
     
         1 . A method of identifying baselines for relationships, comprising:
 obtaining, at a computer, a first set of relationships between information atoms;   identifying baselines for the first set of relationships;   obtaining a second set of relationships between the information atoms;   determining differences between the baselines and the second set of relationships; and   identifying how the differences relate to at least one information atom;   determining a result based on how the differences relate to at least one information atom; and   outputting the result.   
     
     
         2 . The method of  claim 1 , wherein the baselines comprise first baselines and the differences comprise first differences, the method comprising:
 identifying first sentiments for the first set of relationships;   identifying second baselines for the first sentiments;   identifying second sentiments for the second set of relationships; and   determining second differences between the baselines and second sentiments.   
     
     
         3 . The method of  claim 1 , comprising:
 storing the baselines;   recognizing patterns in the differences;   identifying new baselines based on the patterns; and   updating the stored baselines with the new baselines.   
     
     
         4 . The method of  claim 1 , wherein at least one information atom comprises a metric pertaining to an organization's goals, the method comprising;
 determining a third set of relationships between the metrics and the other information atoms;   identifying the differences related to the metrics, based on the third relationships;   determining a second result based on the differences related to the metrics; and   outputting the second result.   
     
     
         5 . The method of  claim 2 , wherein the information atoms comprise descriptors of individuals, statements made by individuals, or topics to which the statements pertain. 
     
     
         6 . The method of  claim 5 , comprising;
 identifying a fourth set of relationships between the differences and the information atoms;   associating the differences with specific ones of the individuals, based on the fourth set of relationships;   calculating scores for the individuals, based on the third and fourth relationships; and   outputting a score related to at least one individual.   
     
     
         7 . The method of  claim 5 , comprising;
 identifying a fourth set of relationships between the differences and the information atoms;   associating the differences with specific ones of the individuals, based on the fourth set of relationships;   calculating scores for the individuals, based on the third and fourth relationships; and   outputting the differences.   
     
     
         8 . The method of  claim 4 , wherein the information atoms comprise descriptors of individuals, further comprising;
 identifying a fourth set of relationships between the differences and the information atoms; and   associating the differences with specific ones of the individuals, based on the fourth set of relationships.   
     
     
         9 . The method of  claim 1 , wherein at least one relationship in the first or second set of relationships comprises a magnitude. 
     
     
         10 . The method of  claim 1 , wherein at least one relationship in the first or second set of relationships comprises a direction. 
     
     
         11 . The method of  claim 1 , comprising:
 recognizing patterns in the differences; and   adjusting the second relationships based on the patterns and the baselines.   
     
     
         12 . The method of  claim 1 , comprising:
 recognizing patterns in the differences; and   adjusting the information atoms based on the patterns and baselines.   
     
     
         13 . A method of identifying sentimental baselines for relationships, comprising:
 obtaining, at a computer, a first set of relationships between information atoms;   identifying first sentiments associated with the first set of relationships;   identifying baselines for the sentiments;   obtaining a second set of relationships between the information atoms;   identifying second sentiments, associated with the second set of relationships;   determining differences between the baselines and second set of sentiments;   identifying how the differences relate to at least one information atom;   determining a result based on how the differences relate to at least one information atom; and   outputting the result.   
     
     
         14 . The method of  claim 13 , comprising:
 storing the baselines;   recognizing patterns in the differences;   identifying new baselines based on the patterns; and   updating the stored baselines with the new baselines.   
     
     
         15 . The method of  claim 13 , wherein the information atoms comprise a first set of information atoms, the method comprising:
 computing a third set of relationships between the differences and the first set of information atoms;   for specific ones of the differences, identifying a second set of information atoms, based on the differences and third relationships; and   outputting at least one of the second set of information atoms.   
     
     
         16 . The method of  claim 13 , wherein the information atoms comprise a first set of information atoms, the method comprising:
 identifying a second set of information atoms related to the specific ones of the first set of information atoms;   obtaining a third set of information atoms;   computing a fourth set of relationships between the second and third sets of information atoms;   identifying second differences, based on the fourth set of relationships; and   outputting at least one of the second differences.   
     
     
         17 . The method of  claim 16 , comprising:
 computing a fifth set of relationships between the second differences and the second and third sets of information atoms;   for specific ones of the second differences, identifying a fourth set of information atoms, based on the second differences and fifth relationships; and   outputting at least one of the third set of information atoms.   
     
     
         18 . A non-transitory computer-readable storage medium encoded with instructions that, when executed on a processor, perform a method of identifying baselines for relationships, the method comprising:
 obtaining, at a computer, a first set of relationships between information atoms;   identifying baselines for the first set of relationships;   obtaining a second set of relationships between the information atoms;   determining differences between the baselines and second set of relationships;   identifying how the differences relate to at least one information atom;   determining a result based on how the differences relate to at least one information atom; and   outputting the result.   
     
     
         19 . The storage medium of  claim 18 , wherein the baselines comprise sentiments, and the method comprises:
 identifying first sentiments for the first set of relationships;   identifying baselines for the first sentiments;   identifying second sentiments for the second set of relationships; and   determining differences between the baselines and second sentiments.   
     
     
         20 . The storage medium of  claim 18 , wherein the method comprises:
 storing the baselines;   recognizing patterns in the differences;   identifying new baselines based on the patterns; and   updating the stored baselines with the new baselines.   
     
     
         21 . The storage medium of  claim 18 , wherein at least one information atom comprises a metric, and the method comprises:
 identifying how the differences relate to the metrics;   determining an overall score for specific ones of the metrics, based on the differences; and   outputting the score.   
     
     
         22 . A characteristic-based server to identify baselines for relationships, the server comprising;
 a relationship module to identify relationships between information atoms;   a storage module to store baselines; and   a calculation module to determine differences between the relationships and baselines.   
     
     
         23 . The server of  claim 22 , comprising:
 a sentiment analysis module to identify sentiments associated with the relationships.   
     
     
         24 . The server of  claim 23 , comprising:
 a pattern recognition module to identify patterns in the differences.   
     
     
         25 . The server of  claim 24 , wherein the relationship module is further operative to determine second relationships between information atoms and metrics, and third relationships between differences and the metrics.